![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "w1eJGgplR2ca"
},
"source": [
"# Import libraries and install packages"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "ztWmkFD0EPES",
"outputId": "b8a8ab30-c985-4273-8798-1d1baeefc66b"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting geemap\n",
" Downloading geemap-0.20.6-py2.py3-none-any.whl (2.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m30.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting bqplot (from geemap)\n",
" Downloading bqplot-0.12.39-py2.py3-none-any.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m81.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting colour (from geemap)\n",
" Downloading colour-0.1.5-py2.py3-none-any.whl (23 kB)\n",
"Requirement already satisfied: earthengine-api>=0.1.347 in /usr/local/lib/python3.10/dist-packages (from geemap) (0.1.350)\n",
"Collecting eerepr>=0.0.4 (from geemap)\n",
" Downloading eerepr-0.0.4-py3-none-any.whl (9.7 kB)\n",
"Requirement already satisfied: folium>=0.13.0 in /usr/local/lib/python3.10/dist-packages (from geemap) (0.14.0)\n",
"Collecting geocoder (from geemap)\n",
" Downloading geocoder-1.38.1-py2.py3-none-any.whl (98 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.6/98.6 kB\u001b[0m \u001b[31m13.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting ipyevents (from geemap)\n",
" Downloading ipyevents-2.0.1-py2.py3-none-any.whl (130 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.5/130.5 kB\u001b[0m \u001b[31m19.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting ipyfilechooser>=0.6.0 (from geemap)\n",
" Downloading ipyfilechooser-0.6.0-py3-none-any.whl (11 kB)\n",
"Collecting ipyleaflet>=0.17.0 (from geemap)\n",
" Downloading ipyleaflet-0.17.2-py3-none-any.whl (3.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.7/3.7 MB\u001b[0m \u001b[31m97.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting ipytree (from geemap)\n",
" Downloading ipytree-0.2.2-py2.py3-none-any.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m80.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from geemap) (3.7.1)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from geemap) (1.22.4)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from geemap) (1.5.3)\n",
"Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (from geemap) (5.13.1)\n",
"Collecting pyperclip (from geemap)\n",
" Downloading pyperclip-1.8.2.tar.gz (20 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting python-box (from geemap)\n",
" Downloading python_box-7.0.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (3.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.2/3.2 MB\u001b[0m \u001b[31m105.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting scooby (from geemap)\n",
" Downloading scooby-0.7.2-py3-none-any.whl (16 kB)\n",
"Requirement already satisfied: google-cloud-storage in /usr/local/lib/python3.10/dist-packages (from earthengine-api>=0.1.347->geemap) (2.8.0)\n",
"Requirement already satisfied: google-api-python-client>=1.12.1 in /usr/local/lib/python3.10/dist-packages (from earthengine-api>=0.1.347->geemap) (2.84.0)\n",
"Requirement already satisfied: google-auth>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from earthengine-api>=0.1.347->geemap) (2.17.3)\n",
"Requirement already satisfied: google-auth-httplib2>=0.0.3 in /usr/local/lib/python3.10/dist-packages (from earthengine-api>=0.1.347->geemap) (0.1.0)\n",
"Requirement already satisfied: httplib2<1dev,>=0.9.2 in /usr/local/lib/python3.10/dist-packages (from earthengine-api>=0.1.347->geemap) (0.21.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from earthengine-api>=0.1.347->geemap) (2.27.1)\n",
"Requirement already satisfied: branca>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from folium>=0.13.0->geemap) (0.6.0)\n",
"Requirement already satisfied: jinja2>=2.9 in /usr/local/lib/python3.10/dist-packages (from folium>=0.13.0->geemap) (3.1.2)\n",
"Requirement already satisfied: ipywidgets in /usr/local/lib/python3.10/dist-packages (from ipyfilechooser>=0.6.0->geemap) (7.7.1)\n",
"Collecting traittypes<3,>=0.2.1 (from ipyleaflet>=0.17.0->geemap)\n",
" Downloading traittypes-0.2.1-py2.py3-none-any.whl (8.6 kB)\n",
"Collecting xyzservices>=2021.8.1 (from ipyleaflet>=0.17.0->geemap)\n",
" Downloading xyzservices-2023.2.0-py3-none-any.whl (55 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m55.4/55.4 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: traitlets>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from bqplot->geemap) (5.7.1)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->geemap) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->geemap) (2022.7.1)\n",
"Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from geocoder->geemap) (8.1.3)\n",
"Requirement already satisfied: future in /usr/local/lib/python3.10/dist-packages (from geocoder->geemap) (0.18.3)\n",
"Collecting ratelim (from geocoder->geemap)\n",
" Downloading ratelim-0.1.6-py2.py3-none-any.whl (4.0 kB)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from geocoder->geemap) (1.16.0)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (1.0.7)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (0.11.0)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (4.39.3)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (1.4.4)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (23.1)\n",
"Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (8.4.0)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->geemap) (3.0.9)\n",
"Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly->geemap) (8.2.2)\n",
"Requirement already satisfied: google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5 in /usr/local/lib/python3.10/dist-packages (from google-api-python-client>=1.12.1->earthengine-api>=0.1.347->geemap) (2.11.0)\n",
"Requirement already satisfied: uritemplate<5,>=3.0.1 in /usr/local/lib/python3.10/dist-packages (from google-api-python-client>=1.12.1->earthengine-api>=0.1.347->geemap) (4.1.1)\n",
"Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.4.1->earthengine-api>=0.1.347->geemap) (5.3.0)\n",
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.4.1->earthengine-api>=0.1.347->geemap) (0.3.0)\n",
"Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.4.1->earthengine-api>=0.1.347->geemap) (4.9)\n",
"Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.10/dist-packages (from ipywidgets->ipyfilechooser>=0.6.0->geemap) (5.5.6)\n",
"Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.2.0)\n",
"Requirement already satisfied: widgetsnbextension~=3.6.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets->ipyfilechooser>=0.6.0->geemap) (3.6.4)\n",
"Requirement already satisfied: ipython>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets->ipyfilechooser>=0.6.0->geemap) (7.34.0)\n",
"Requirement already satisfied: jupyterlab-widgets>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets->ipyfilechooser>=0.6.0->geemap) (3.0.7)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2>=2.9->folium>=0.13.0->geemap) (2.1.2)\n",
"Requirement already satisfied: google-cloud-core<3.0dev,>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from google-cloud-storage->earthengine-api>=0.1.347->geemap) (2.3.2)\n",
"Requirement already satisfied: google-resumable-media>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from google-cloud-storage->earthengine-api>=0.1.347->geemap) (2.5.0)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->earthengine-api>=0.1.347->geemap) (1.26.15)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->earthengine-api>=0.1.347->geemap) (2022.12.7)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->earthengine-api>=0.1.347->geemap) (2.0.12)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->earthengine-api>=0.1.347->geemap) (3.4)\n",
"Requirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from ratelim->geocoder->geemap) (4.4.2)\n",
"Requirement already satisfied: googleapis-common-protos<2.0dev,>=1.56.2 in /usr/local/lib/python3.10/dist-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-api-python-client>=1.12.1->earthengine-api>=0.1.347->geemap) (1.59.0)\n",
"Requirement already satisfied: protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5 in /usr/local/lib/python3.10/dist-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-api-python-client>=1.12.1->earthengine-api>=0.1.347->geemap) (3.20.3)\n",
"Requirement already satisfied: google-crc32c<2.0dev,>=1.0 in /usr/local/lib/python3.10/dist-packages (from google-resumable-media>=2.3.2->google-cloud-storage->earthengine-api>=0.1.347->geemap) (1.5.0)\n",
"Requirement already satisfied: jupyter-client in /usr/local/lib/python3.10/dist-packages (from ipykernel>=4.5.1->ipywidgets->ipyfilechooser>=0.6.0->geemap) (6.1.12)\n",
"Requirement already satisfied: tornado>=4.2 in /usr/local/lib/python3.10/dist-packages (from ipykernel>=4.5.1->ipywidgets->ipyfilechooser>=0.6.0->geemap) (6.2)\n",
"Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (67.7.2)\n",
"Collecting jedi>=0.16 (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap)\n",
" Downloading jedi-0.18.2-py2.py3-none-any.whl (1.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m87.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: pickleshare in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.7.5)\n",
"Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (3.0.38)\n",
"Requirement already satisfied: pygments in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (2.14.0)\n",
"Requirement already satisfied: backcall in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.2.0)\n",
"Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.1.6)\n",
"Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (4.8.0)\n",
"Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth>=1.4.1->earthengine-api>=0.1.347->geemap) (0.5.0)\n",
"Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.10/dist-packages (from widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (6.4.8)\n",
"Requirement already satisfied: parso<0.9.0,>=0.8.0 in /usr/local/lib/python3.10/dist-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.8.3)\n",
"Requirement already satisfied: pyzmq>=17 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (23.2.1)\n",
"Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (21.3.0)\n",
"Requirement already satisfied: jupyter-core>=4.6.1 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (5.3.0)\n",
"Requirement already satisfied: nbformat in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (5.8.0)\n",
"Requirement already satisfied: nbconvert in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (6.5.4)\n",
"Requirement already satisfied: nest-asyncio>=1.5 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (1.5.6)\n",
"Requirement already satisfied: Send2Trash>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (1.8.0)\n",
"Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.17.1)\n",
"Requirement already satisfied: prometheus-client in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.16.0)\n",
"Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.10/dist-packages (from pexpect>4.3->ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.7.0)\n",
"Requirement already satisfied: wcwidth in /usr/local/lib/python3.10/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.2.6)\n",
"Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.10/dist-packages (from jupyter-core>=4.6.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (3.3.0)\n",
"Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.10/dist-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (21.2.0)\n",
"Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (4.9.2)\n",
"Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (4.11.2)\n",
"Requirement already satisfied: bleach in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (6.0.0)\n",
"Requirement already satisfied: defusedxml in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.7.1)\n",
"Requirement already satisfied: entrypoints>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.4)\n",
"Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.2.2)\n",
"Requirement already satisfied: mistune<2,>=0.8.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.8.4)\n",
"Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.7.4)\n",
"Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (1.5.0)\n",
"Requirement already satisfied: tinycss2 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (1.2.1)\n",
"Requirement already satisfied: fastjsonschema in /usr/local/lib/python3.10/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (2.16.3)\n",
"Requirement already satisfied: jsonschema>=2.6 in /usr/local/lib/python3.10/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (4.3.3)\n",
"Requirement already satisfied: attrs>=17.4.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (23.1.0)\n",
"Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.19.3)\n",
"Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (1.15.1)\n",
"Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (2.4.1)\n",
"Requirement already satisfied: webencodings in /usr/local/lib/python3.10/dist-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (0.5.1)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->ipyfilechooser>=0.6.0->geemap) (2.21)\n",
"Building wheels for collected packages: pyperclip\n",
" Building wheel for pyperclip (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for pyperclip: filename=pyperclip-1.8.2-py3-none-any.whl size=11124 sha256=0eba7cac19c544c6c9f2d0de85e9feaa201cd6219c75d94d0a7100f4871a33c7\n",
" Stored in directory: /root/.cache/pip/wheels/04/24/fe/140a94a7f1036003ede94579e6b4227fe96c840c6f4dcbe307\n",
"Successfully built pyperclip\n",
"Installing collected packages: pyperclip, colour, xyzservices, traittypes, scooby, ratelim, python-box, jedi, geocoder, eerepr, ipytree, ipyleaflet, ipyfilechooser, ipyevents, bqplot, geemap\n",
"Successfully installed bqplot-0.12.39 colour-0.1.5 eerepr-0.0.4 geemap-0.20.6 geocoder-1.38.1 ipyevents-2.0.1 ipyfilechooser-0.6.0 ipyleaflet-0.17.2 ipytree-0.2.2 jedi-0.18.2 pyperclip-1.8.2 python-box-7.0.1 ratelim-0.1.6 scooby-0.7.2 traittypes-0.2.1 xyzservices-2023.2.0\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting geopandas\n",
" Downloading geopandas-0.13.0-py3-none-any.whl (1.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting fiona>=1.8.19 (from geopandas)\n",
" Downloading Fiona-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m16.0/16.0 MB\u001b[0m \u001b[31m57.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from geopandas) (23.1)\n",
"Requirement already satisfied: pandas>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from geopandas) (1.5.3)\n",
"Collecting pyproj>=3.0.1 (from geopandas)\n",
" Downloading pyproj-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.7/7.7 MB\u001b[0m \u001b[31m74.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: shapely>=1.7.1 in /usr/local/lib/python3.10/dist-packages (from geopandas) (2.0.1)\n",
"Requirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8.19->geopandas) (23.1.0)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8.19->geopandas) (2022.12.7)\n",
"Requirement already satisfied: click~=8.0 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8.19->geopandas) (8.1.3)\n",
"Collecting click-plugins>=1.0 (from fiona>=1.8.19->geopandas)\n",
" Downloading click_plugins-1.1.1-py2.py3-none-any.whl (7.5 kB)\n",
"Collecting cligj>=0.5 (from fiona>=1.8.19->geopandas)\n",
" Downloading cligj-0.7.2-py3-none-any.whl (7.1 kB)\n",
"Collecting munch>=2.3.2 (from fiona>=1.8.19->geopandas)\n",
" Downloading munch-2.5.0-py2.py3-none-any.whl (10 kB)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.0->geopandas) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.0->geopandas) (2022.7.1)\n",
"Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.0->geopandas) (1.22.4)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from munch>=2.3.2->fiona>=1.8.19->geopandas) (1.16.0)\n",
"Installing collected packages: pyproj, munch, cligj, click-plugins, fiona, geopandas\n",
"Successfully installed click-plugins-1.1.1 cligj-0.7.2 fiona-1.9.3 geopandas-0.13.0 munch-2.5.0 pyproj-3.5.0\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (1.2.2)\n",
"Requirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.22.4)\n",
"Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.10.1)\n",
"Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.2.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (3.1.0)\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting pyshp\n",
" Downloading pyshp-2.3.1-py2.py3-none-any.whl (46 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.5/46.5 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: pyshp\n",
"Successfully installed pyshp-2.3.1\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting pycrs\n",
" Downloading PyCRS-1.0.2.tar.gz (36 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Building wheels for collected packages: pycrs\n",
" Building wheel for pycrs (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for pycrs: filename=PyCRS-1.0.2-py3-none-any.whl size=32686 sha256=b273a59e8d8dba1a7de3d0fcd5665ac2e2cbfcf5644632d7d0b69b99ddebe1d1\n",
" Stored in directory: /root/.cache/pip/wheels/47/1d/70/7a5bdf33347e7c75e95b06b1fa38f076a59a9506653cc24aff\n",
"Successfully built pycrs\n",
"Installing collected packages: pycrs\n",
"Successfully installed pycrs-1.0.2\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting shap\n",
" Downloading shap-0.41.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (572 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m572.6/572.6 kB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from shap) (1.22.4)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from shap) (1.10.1)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from shap) (1.2.2)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from shap) (1.5.3)\n",
"Requirement already satisfied: tqdm>4.25.0 in /usr/local/lib/python3.10/dist-packages (from shap) (4.65.0)\n",
"Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.10/dist-packages (from shap) (23.1)\n",
"Collecting slicer==0.0.7 (from shap)\n",
" Downloading slicer-0.0.7-py3-none-any.whl (14 kB)\n",
"Requirement already satisfied: numba in /usr/local/lib/python3.10/dist-packages (from shap) (0.56.4)\n",
"Requirement already satisfied: cloudpickle in /usr/local/lib/python3.10/dist-packages (from shap) (2.2.1)\n",
"Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba->shap) (0.39.1)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from numba->shap) (67.7.2)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2022.7.1)\n",
"Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (1.2.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (3.1.0)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->shap) (1.16.0)\n",
"Installing collected packages: slicer, shap\n",
"Successfully installed shap-0.41.0 slicer-0.0.7\n"
]
}
],
"source": [
"!pip install geemap # --> Google Earth Engine (GEE)\n",
"!pip install geopandas #--> Geospatial data \n",
"%pip install scikit-learn #--> Machine learning \n",
"!pip install pyshp #--> Working with shapefiles\n",
"!pip install pycrs #--> Python GIS package\n",
"!pip install shap\n",
"\n",
"# Talking with local terminal on your computer\n",
"import os\n",
"\n",
"# GEE\n",
"import ee\n",
"from geemap.conversion import js_snippet_to_py\n",
"import geemap\n",
"from geemap import ml\n",
"\n",
"# Geospatial data manipulation and analysis tools\n",
"import geopandas as gpd\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.image import imread\n",
"import tensorflow as tf\n",
"import seaborn as sns\n",
"import time\n",
"import math\n",
"\n",
"# Machine learning with sci-kit learn\n",
"from sklearn import ensemble, metrics\n",
"from sklearn.model_selection import train_test_split, learning_curve, validation_curve, GridSearchCV\n",
"from sklearn.metrics import confusion_matrix, classification_report, accuracy_score\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.datasets import (make_blobs,\n",
" make_circles,\n",
" make_moons)\n",
"from sklearn.cluster import KMeans, SpectralClustering, DBSCAN\n",
"from sklearn.metrics import silhouette_score, f1_score\n",
"\n",
"import scipy.stats as stats\n",
"\n",
"# Statistical tests\n",
"import statsmodels.api as sm\n",
"from scipy.stats import shapiro \n",
"import scipy.stats as stat\n",
"from math import sqrt\n",
"import shap\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 36
},
"id": "Zbnu0bKfEhcY",
"outputId": "be27131b-60d0-4aa8-ba19-f2d27f4d76ba"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'/device:GPU:0'"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
}
},
"metadata": {},
"execution_count": 2
}
],
"source": [
"# Check which prorcessor unit we are using\n",
"tf.test.gpu_device_name()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "L2l-hgCCEjOD",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 182
},
"outputId": "54a2c3d7-7299-4c4f-c112-e7c5c2a183a6"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"To authorize access needed by Earth Engine, open the following URL in a web browser and follow the instructions. If the web browser does not start automatically, please manually browse the URL below.\n",
"\n",
" https://code.earthengine.google.com/client-auth?scopes=https%3A//www.googleapis.com/auth/earthengine%20https%3A//www.googleapis.com/auth/devstorage.full_control&request_id=9zxjkZY6Kuhwr4v92_SEc0fQzi666JcsmldzAZBAfxk&tc=RoLUng-fhEY8uBUxRuIEhdNX9tHvWq68yShbMU1mxdo&cc=xGVrHj1LefYW8D0WJhrv5be1hIJTb7M-YN5QyS_2Oh4\n",
"\n",
"The authorization workflow will generate a code, which you should paste in the box below.\n",
"Enter verification code: 4/1AbUR2VOjFoQtQ2EGa_UpsSGhHOXzSz3xm1dPjhyECbKHQAhFRR0yA24jJEA\n",
"\n",
"Successfully saved authorization token.\n"
]
}
],
"source": [
"# Initialize access to GEE\n",
"Map = geemap.Map()\n",
"\n",
"# 0) Follow external link \n",
"# 1) Choose project name\n",
"# 2) \"Generate token\"\n",
"# 3) Choose account\n",
"# 4) Give access (check of both boxes)\n",
"# 5) Copy authorization code\n",
"# 6) Add authorization code below"
]
},
{
"cell_type": "markdown",
"source": [
"# Functions\n",
"- Deglint\n",
"- Remove duplicates\n",
"- Tau\n",
"- Variance\n",
"- Confusion matrix\n",
"- CM maker"
],
"metadata": {
"id": "clFCidMpADYY"
}
},
{
"cell_type": "markdown",
"source": [
"Deglint"
],
"metadata": {
"id": "WTC1Y901GT5R"
}
},
{
"cell_type": "code",
"source": [
"\n",
"# Deglint function\n",
"def deglint(img, glint):\n",
" '''\n",
" Sun-glint correction of image\n",
" '''\n",
" # Blue (B2) and NIR (B8) \n",
" # linearfitB gets linear relationship (slope) and offset between the Blue and NIR bands\n",
" linearfitB = img.select(['B8','B2']).reduceRegion(\n",
" **{\n",
" 'reducer': ee.Reducer.linearFit(), \n",
" 'geometry': glint,\n",
" 'scale':10,\n",
" 'maxPixels':1e9\n",
" }) \n",
"\n",
" # Green (B3) and NIR (B8)\n",
" # linearfitG gets linear relationship (slope) and offset between the Green and NIR bands \n",
" linearfitG = img.select(['B8','B3']).reduceRegion(\n",
" **{\n",
" 'reducer': ee.Reducer.linearFit(),\n",
" 'geometry': glint,\n",
" 'scale':10,\n",
" 'maxPixels':1e9\n",
" }) \n",
" # Red (B4) and NIR\n",
" # linearfitR gets linear relationship (slope) and offset between the Red and NIR bands\n",
" linearfitR = img.select(['B8','B4']).reduceRegion(\n",
" **{\n",
" 'reducer': ee.Reducer.linearFit(),\n",
" 'geometry': glint,\n",
" 'scale':10,\n",
" 'maxPixels':1e9\n",
" })\n",
" \n",
" \n",
" slopeImage = ee.Dictionary( # Collects the slopes in a dictionary \n",
" {\n",
" 'Blue': linearfitB.get('scale'),\n",
" 'Green': linearfitG.get('scale'),\n",
" 'Red': linearfitR.get('scale')\n",
" }).toImage() # Converts dicitonary to image\n",
" \n",
" # Define minimum NIR value.\n",
" # Source code: https://gis.stackexchange.com/questions/331890/wgs84-projection-is-invalid-for-aggregations . Accessed 02.03.23 \n",
" minNIR = img.select('B8').reduceRegion(ee.Reducer.min(), glint, 10).toImage()\n",
" # Deglint formula\n",
" return img.select(['B2','B3', 'B4']).subtract(slopeImage.multiply(img.select('B8').subtract(minNIR)))\n",
"\n",
"\n"
],
"metadata": {
"id": "tHcDtCAObksO"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Removing duplicates"
],
"metadata": {
"id": "NzjYyUmzGRkT"
}
},
{
"cell_type": "code",
"source": [
"# Function to remove duplicates from a dataset\n",
" def remove_duplicates(data):\n",
"\n",
" # Get the class column name\n",
" label = data.columns[-1]\n",
"\n",
" # remove all duplicates\n",
" data_ndup = data.drop_duplicates()\n",
"\n",
" # Check for imbalance in dataset\n",
" minimum = min(data_ndup[label].value_counts())\n",
"\n",
" # Correct for imbalance in dataset\n",
" # source code: https://stackoverflow.com/questions/52935324/make-dataframe-balanced-with-respect-to-a-specific-column. Accessed 13.03.23\n",
" data_ndup = (data_ndup.groupby(label, as_index=False)\n",
" .apply(lambda x: x.sample(n=minimum))\n",
" .reset_index(drop=True))\n",
" return data_ndup"
],
"metadata": {
"id": "neaKnxYzGQwp"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
" Confusion matrix"
],
"metadata": {
"id": "v7QnYbl7F4QG"
}
},
{
"cell_type": "code",
"source": [
"def cm_datsets(cm1, cm2, cm3, cm4, cm5, title):\n",
" '''\n",
" Insert two different confusion matrices (cms) created with sci-kit learns:\n",
" cm = confusion_matrix(y_true,y_pred)\n",
" '''\n",
"\n",
" # Plot confusion matrices next to each other \n",
" # Source code: https://stackoverflow.com/questions/61016110/plot-multiple-confusion-matrices-with-plot-confusion-matrix. Accessed 21.03.23\n",
" font_dict = {'fontsize': 15,\n",
" 'fontweight':15}\n",
"\n",
" font = {\n",
" 'weight' : 'bold',\n",
" 'size' : 15}\n",
"\n",
" fig, ax = plt.subplots(1, 5, figsize=(25,8), sharex = True, sharey = True)\n",
" fig.suptitle(str(title), fontsize=20)\n",
" ax[0].set_title(\"Dataset 1\")\n",
" ax[1].set_title(\"Dataset 2\")\n",
" ax[2].set_title(\"Dataset 3\")\n",
" ax[3].set_title(\"Dataset 4\")\n",
" ax[4].set_title(\"Dataset 5\")\n",
" names=['water', 'seaweed', 'seagrass']\n",
"\n",
" metrics.ConfusionMatrixDisplay(\n",
" confusion_matrix = cm1/cm1.astype(float).sum(axis=0), display_labels=names).plot(ax=ax[0], cmap='Blues') # values_format= '2g'\n",
"\n",
" metrics.ConfusionMatrixDisplay(\n",
" confusion_matrix =cm2/cm2.astype(float).sum(axis=0), display_labels=names).plot(ax=ax[1], cmap='Blues')\n",
"\n",
" metrics.ConfusionMatrixDisplay(\n",
" confusion_matrix =cm3/cm3.astype(float).sum(axis=0), display_labels=names).plot(ax=ax[2], cmap='Blues')\n",
"\n",
" metrics.ConfusionMatrixDisplay(\n",
" confusion_matrix =cm4/cm4.astype(float).sum(axis=0), display_labels=names).plot(ax=ax[3], cmap='Blues')\n",
"\n",
" metrics.ConfusionMatrixDisplay(\n",
" confusion_matrix =cm5/cm5.astype(float).sum(axis=0), display_labels=names).plot(ax=ax[4], cmap='Blues')\n",
"\n",
" #values_formatstr\n",
" plt.rc('font', **font)\n",
" plt.tight_layout() \n",
" return plt.show()"
],
"metadata": {
"id": "FXMKLIN5F2_n"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Tau and variance functions"
],
"metadata": {
"id": "Dmew4Eu7BtUr"
}
},
{
"cell_type": "code",
"source": [
"def tau(pra_x):\n",
" pre = 0.33333 #chance from three classes are 0.3333 \n",
" return (pra_x - pre)/(1-pre)\n",
"\n",
"def variance(data, accuracy):\n",
" pre = 0.33333 \n",
" return accuracy*(1-accuracy)/(len(data)*((1-pre)**2))"
],
"metadata": {
"id": "41yqCf00BsrZ"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"CM maker"
],
"metadata": {
"id": "qZYpA446GIW4"
}
},
{
"cell_type": "code",
"source": [
"#from sklearn.metrics import confusion_matrix\n",
"# Source code: https://stackoverflow.com/a/59839952. Accessed: 03.05.2023\n",
"\n",
"def cm_maker(cmx, title):\n",
" cm = cmx/cmx.astype(float).sum(axis=0)\n",
"\n",
" # figure(figsize=(WIDTH_SIZE,HEIGHT_SIZE))\n",
" plt.figure(figsize=(5,4))\n",
" ax = plt.subplot()\n",
" sns.set(font_scale=1.2) # Adjust to fit\n",
" sns.heatmap(cm, annot=True, ax=ax, cmap=\"Blues\", fmt=\".2g\"); \n",
"\n",
" # Labels, title and ticks\n",
" label_font = {'size':'18'} # Adjust to fit\n",
" ax.set_xlabel('Predicted labels', fontdict=label_font);\n",
" ax.set_ylabel('Tru labels', fontdict=label_font);\n",
"\n",
" title_font = {'size':'21'} # Adjust to fit\n",
" ax.set_title(title, fontdict=title_font);\n",
"\n",
" ax.tick_params(axis='both', which='major', labelsize=13) # Adjust to fit\n",
" ax.xaxis.set_ticklabels(['Water', 'Seaweed', 'Seagrass']);\n",
" ax.yaxis.set_ticklabels(['Water', 'Seaweed', 'Seagrass']);\n",
" return plt.show()"
],
"metadata": {
"id": "CIqoPgKpGG86"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "c_KJzjYG2Kwt"
},
"source": [
"# Collecting training data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "r0z8ris6ErPY",
"outputId": "89c682a2-3e57-4b12-fe4b-b1874957d26d"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Number of images fulfilling the cloud-coverage critera that will be used to make a composite image: 4\n",
"The least cloudy image was taken (YYYY-MM-DD): 2019-07-19\n",
"Cloud percentage: 3.15% of the least cloudy image\n",
"features available: ['B2', 'B3', 'B4', 'B8']\n"
]
}
],
"source": [
"# Source code: https://developers.google.com/earth-engine/guides/ic_info. Accessed: 16.02.2023\n",
"point = ee.Geometry.Point([-69.740859, 43.544235]) # Center around a specified point\n",
"\n",
"# Criteria for maximum cloudiness\n",
"MAX_CLOUD_PROBABILITY = 5\n",
"CLOUD_THRES = 5\n",
"\n",
"# Get the least cloudy image\n",
"image_train = (\n",
" ee.ImageCollection('COPERNICUS/S2_SR') # Dataset from GEE\n",
" .filterBounds(point) # Filter satellite-images around our region of interest (ROI)\n",
" .filterDate('2019-06-02','2019-10-01') # Filter time\n",
" .sort('CLOUDY_PIXEL_PERCENTAGE') # fiter for cloud percentage\n",
" .first() # Take the image with least cloud coverage\n",
" .select('B[2-4]','B[8]') # Select bands B2, B3, B4, and B8 as features\n",
")\n",
"\n",
"# Create a collection of images over a time-periode for training data\n",
"s2_coll_train = (ee.ImageCollection('COPERNICUS/S2_SR')\n",
" .filterBounds(point) # Filter satellite-images around our region of interest (ROI)\n",
" .filterDate('2019-06-02','2019-10-01')\n",
" .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', CLOUD_THRES))\n",
" )\n",
"\n",
"# Create a composite training image using min-value\n",
"s2_composite_min=s2_coll_train.select(['B[2-4]','B[8]']).min()\n",
"# Create a composite training image using the median-value\n",
"s2_composite_median = s2_coll_train.select(['B[2-4]','B[8]']).median()\n",
" \n",
"print('Number of images fulfilling the cloud-coverage critera that will be used to make a composite image:', s2_coll_train.size().getInfo())\n",
"print('The least cloudy image was taken (YYYY-MM-DD):', ee.Date(image_train.get('system:time_start')).format('YYYY-MM-dd').getInfo())\n",
"cloud_perc = image_train.get('CLOUDY_PIXEL_PERCENTAGE').getInfo()*100\n",
"print(f'Cloud percentage: {cloud_perc:,.2f}% of the least cloudy image')\n",
"print('features available:', s2_composite_min.bandNames().getInfo())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"e72457788c1b4494b43f0ad2f67266a9",
"a5b7b0fb76ee44d99cfc297dfcfd645a",
"738055902d5349f8bf055a7deaae82e8",
"c315634c5d6e4b219ef43c955ba523ee",
"8b67043bc069428e9d62dbedb1aeaf46",
"04903c876c874ff4a04bc97bf650c6f3",
"255a8b1bfdb243939b329b4fc9f7be34",
"0e5bcbfcc1fd4647bc49dd698a47b04f",
"79ea9824542f4b28994e88c4959d92eb",
"ecef97aec5be4769a358e2a0839329f9",
"f552a8f456c646e5ba552c3f25ea2851",
"a332fd2cd3e04a24ad2eabe6def61c49",
"62775bccba86442abef0cd26818c0789",
"1ff139e4d3bf4facb58b709875de3b49",
"bc17a853edf44644b1a7864ebc152066",
"c53b4a84cb80490e95fc35b39db5fc24",
"ad173935f3bc4968af1b72dfbfa4563d",
"8947e9a86bd6410091d82b792fca475f",
"e8759997e1054b8d91a8e3608d8f62f4",
"b3c2b951576242d998e523c0cdf3ee5d",
"138fbfc914ee46599d0aafd741b0923b",
"0c82f7be08604b648ffc990698e22063",
"1f54852b3ab54c9197f1d1749f19e6b4",
"ecb6e0ca71cd4bb58bd8902ea3843c34",
"e4314390d1a44b178dbb1fe232f47827",
"cb096552bfa24e19a9ec683127989841",
"0f251bfdc821402d9e42647f68c71a3c",
"418fcc0266b944f0ad1d3330c0bf1942"
]
},
"id": "BsXzzAid72Gc",
"outputId": "376a0970-6def-47fc-da70-2c31b8a99687"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(center=[43.544235, -69.740859], controls=(WidgetControl(options=['position', 'transparent_bg'], widget=HBo…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "e72457788c1b4494b43f0ad2f67266a9"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"# Instantiate a new map\n",
"Map = geemap.Map()\n",
"Map.set_center(-69.740859, 43.544235, zoom=10)\n",
"\n",
"# Visually inspect the least cloudy image and composite images given median and minimum values \n",
"vis_params = {\"bands\": [ 'B2', 'B3', 'B4'], \"min\": 0, \"max\": 1500, \"gamma\": 3.5}\n",
"Map.addLayer(image_train, vis_params, 'Least cloudy sent-2 image')\n",
"Map.addLayer(s2_composite_median, vis_params, 'Sent-2 median')\n",
"Map.addLayer(s2_composite_min, vis_params, 'Sent-2 min')\n",
"\n",
"# Use toolbar on the left side, e.g., \" Draw a rectangle\" over an area \n",
"# to extract NIR values (min and random) from two pixels. \n",
"# Areas of deep waters are recommended.\n",
"Map"
]
},
{
"cell_type": "markdown",
"source": [
"# Sunglint correcting Casco Bay image"
],
"metadata": {
"id": "XOWp8zemV7Kv"
}
},
{
"cell_type": "code",
"source": [
"##Sun-glint correction\n",
"# Adaptation from https://www.youtube.com/watch?v=_V0X1LdSta4. Accessed 10.02.2023.\n",
"shp_path_glint_train = '/content/glint_train.shp'\n",
"glint = geemap.shp_to_ee(shp_path_glint_train) # Stores the rectangle(s) geometry to extract NIR-values from\n",
"\n",
"# Store glint_train locally for reproducability \n",
"#Map.draw_features # Collects the drawn rectangle(s)\n",
"#glint = ee.FeatureCollection(Map.draw_features) # Stores the rectangle(s) geometry to extract NIR-values from\n",
"#geemap.ee_to_shp(glint, filename='/content/glint_train.shp') \n",
"\n",
"\n",
"# Deglinted image\n",
"S2_deglint = deglint(s2_composite_min, glint) "
],
"metadata": {
"id": "_M4uiPMfuK4Q"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Creating land/water mask of sun-glint corrected Casco Bay image "
],
"metadata": {
"id": "IRsDSsFHWJ4-"
}
},
{
"cell_type": "code",
"source": [
"mask = S2_deglint.gt(0) # Using threshold 0 to distinguish land from ocean.\n",
"s2_deglint_masked = S2_deglint.updateMask(mask) # Ocean mask \n",
"\n",
"NIR_thres = 500\n",
"b8 =s2_composite_min.select('B8')\n",
"\n",
"# Source code: \n",
"p. Accessed: 23.03.23\n",
"threshold = b8.where(b8.gt(NIR_thres),1).where(b8.lt(NIR_thres),0)\n",
"\n",
"# Source code: https://www.youtube.com/watch?v=qO3Te5pfOHc. Accesssed: 23.03.23\n",
"S2_masked = threshold.updateMask(threshold) # Land mask\n",
"\n",
"# Display layers\n",
"vis_params_deglint = {\"bands\": [ 'B2', 'B3','B4'], \"min\": 0, \"max\": 1500, 'gamma':3.5} # Visible parameters \n",
"\n",
"Map.addLayer(S2_deglint, vis_params_deglint, 'sun-glint corrected Sent-2') # Deglinter image \n",
"Map.addLayer(s2_deglint_masked, vis_params_deglint, 'masked Sent-2 deglinted image') # Ocean layer without land\n",
"Map.addLayer(S2_masked, {'palette': ['black']} , 'S2 Land Mask') # Land mask with black color\n",
"Map"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"6efafbf5b992427d9ae957fb5b005167",
"d7dc369311864540882ccf6c773a2a6a",
"ef514b9dd0b848f29d8df414d8f0e661",
"b0febbe8dc58487992aefe19ab51af27",
"1232e1ef4e8544b49642393cc4d9fc5c",
"40b53fee18cd422f9922037554da587f",
"dc12207b883946babb9b3cee7dba56df",
"2903bf7af622464e81c9fda6d26a559b",
"974b83414b914e7bbbdcc0a08642307c",
"5fdee656c2e44413aaeedd1d047bd76a",
"ed6fdeeb41ec4770ae4ff2cb67f41a21",
"ac80f51374244b3492e3799aebc4d01d",
"2cdf48b5ca5d482dba952cfb14e747c7",
"3e06d254d7ec4356b4485175861ac769",
"002ce5f644a9465793fc408e52190035",
"8ca095c753394a64a11cc12691a30527",
"c790e07a7f4048b9b11cfc7363c85c88",
"aaf3901894154288847fd8550c6ea65c",
"3fc3d6a773a548c5b71647388fcdb497",
"4a14eb71df854ad19acd25fb2f2edabe",
"cf56b2c2974e4773aab8777c81ed65e3",
"4fd570e6b8044c41af9e5aa5d2a930f7",
"b8a572bc17ad41f3b429998923884c02",
"bb3e8892d9b34a63b5bfcc57c3b89af2",
"8c177bc5be68411a8b01057cbc44f57b",
"388eaaae653941f9b5826f49f70d15c9",
"3cb79ad442dd47468344718ca45cd806",
"3587fd8d2ac443a9bd5d0d8acaf7fbeb",
"a5c5d2d7617549b382c546a44e01e60d",
"b0947fac13b647d1885dd43e54d86c64",
"1567886b20a4492787efa5fb1442f703",
"8bb84616161647b1a78c27c0bcdc7b71",
"d032663d2f154bd3a691b1c3ad2dde82",
"6f3c1d5282954f1bae4b9156baf9f3a1"
]
},
"id": "sTngsE8hWIyC",
"outputId": "7815c6d2-dff2-491d-b9e5-cf83176cfcb6"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(bottom=96080.0, center=[43.544235, -69.740859], controls=(WidgetControl(options=['position', 'transparent_…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "6efafbf5b992427d9ae957fb5b005167"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"6efafbf5b992427d9ae957fb5b005167",
"d7dc369311864540882ccf6c773a2a6a",
"ef514b9dd0b848f29d8df414d8f0e661",
"b0febbe8dc58487992aefe19ab51af27",
"1232e1ef4e8544b49642393cc4d9fc5c",
"40b53fee18cd422f9922037554da587f",
"dc12207b883946babb9b3cee7dba56df",
"2903bf7af622464e81c9fda6d26a559b",
"974b83414b914e7bbbdcc0a08642307c",
"5fdee656c2e44413aaeedd1d047bd76a",
"ed6fdeeb41ec4770ae4ff2cb67f41a21",
"ac80f51374244b3492e3799aebc4d01d",
"2cdf48b5ca5d482dba952cfb14e747c7",
"3e06d254d7ec4356b4485175861ac769",
"002ce5f644a9465793fc408e52190035",
"8ca095c753394a64a11cc12691a30527",
"c790e07a7f4048b9b11cfc7363c85c88",
"aaf3901894154288847fd8550c6ea65c",
"3fc3d6a773a548c5b71647388fcdb497",
"4a14eb71df854ad19acd25fb2f2edabe",
"cf56b2c2974e4773aab8777c81ed65e3",
"4fd570e6b8044c41af9e5aa5d2a930f7",
"b8a572bc17ad41f3b429998923884c02",
"bb3e8892d9b34a63b5bfcc57c3b89af2",
"8c177bc5be68411a8b01057cbc44f57b",
"388eaaae653941f9b5826f49f70d15c9",
"3cb79ad442dd47468344718ca45cd806",
"3587fd8d2ac443a9bd5d0d8acaf7fbeb",
"a5c5d2d7617549b382c546a44e01e60d",
"b0947fac13b647d1885dd43e54d86c64",
"1567886b20a4492787efa5fb1442f703",
"8bb84616161647b1a78c27c0bcdc7b71",
"d032663d2f154bd3a691b1c3ad2dde82",
"6f3c1d5282954f1bae4b9156baf9f3a1"
]
},
"id": "9qYNZr7XCckE",
"outputId": "ba4d62bf-94d2-47af-d4fa-2103e3dde6b4"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(bottom=96080.0, center=[43.544235, -69.740859], controls=(WidgetControl(options=['position', 'transparent_…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "6efafbf5b992427d9ae957fb5b005167"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"# Calculating NDVI\n",
"nir = s2_composite_min.select('B8')\n",
"red = s2_composite_min.select('B4')\n",
"ndvi_image = nir.subtract(red).divide(nir.add(red)).rename('NDVI')\n",
"\n",
"# Add NIR-band to deglinted image\n",
"s2_deglint_masked = s2_deglint_masked.addBands(nir)\n",
"\n",
"# Add NDVI to RGB-image and deglinted image\n",
"s2_deglint_masked = s2_deglint_masked.addBands(ndvi_image)\n",
"Map"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"6efafbf5b992427d9ae957fb5b005167",
"d7dc369311864540882ccf6c773a2a6a",
"ef514b9dd0b848f29d8df414d8f0e661",
"b0febbe8dc58487992aefe19ab51af27",
"1232e1ef4e8544b49642393cc4d9fc5c",
"40b53fee18cd422f9922037554da587f",
"dc12207b883946babb9b3cee7dba56df",
"2903bf7af622464e81c9fda6d26a559b",
"974b83414b914e7bbbdcc0a08642307c",
"5fdee656c2e44413aaeedd1d047bd76a",
"ed6fdeeb41ec4770ae4ff2cb67f41a21",
"ac80f51374244b3492e3799aebc4d01d",
"2cdf48b5ca5d482dba952cfb14e747c7",
"3e06d254d7ec4356b4485175861ac769",
"002ce5f644a9465793fc408e52190035",
"8ca095c753394a64a11cc12691a30527",
"c790e07a7f4048b9b11cfc7363c85c88",
"aaf3901894154288847fd8550c6ea65c",
"3fc3d6a773a548c5b71647388fcdb497",
"8bb84616161647b1a78c27c0bcdc7b71",
"d032663d2f154bd3a691b1c3ad2dde82",
"6f3c1d5282954f1bae4b9156baf9f3a1",
"4a14eb71df854ad19acd25fb2f2edabe",
"cf56b2c2974e4773aab8777c81ed65e3",
"4fd570e6b8044c41af9e5aa5d2a930f7",
"b8a572bc17ad41f3b429998923884c02",
"bb3e8892d9b34a63b5bfcc57c3b89af2",
"8c177bc5be68411a8b01057cbc44f57b",
"388eaaae653941f9b5826f49f70d15c9",
"3cb79ad442dd47468344718ca45cd806",
"3587fd8d2ac443a9bd5d0d8acaf7fbeb",
"a5c5d2d7617549b382c546a44e01e60d",
"b0947fac13b647d1885dd43e54d86c64",
"1567886b20a4492787efa5fb1442f703"
]
},
"id": "dGlyoVSGClEQ",
"outputId": "6eb2251a-d6f5-4cd2-9ae4-9c4065a0c6a1"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(bottom=96080.0, center=[43.544235, -69.740859], controls=(WidgetControl(options=['position', 'transparent_…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "6efafbf5b992427d9ae957fb5b005167"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"# Store region of interst (training) locally for reproducability \n",
"# roi_train = ee.FeatureCollection(Map.draw_last_feature)\n",
"#geemap.ee_to_shp(roi_train, filename='/content/roi_train.shp') \n",
"\n",
"shp_path_roi_train = '/content/roi_train.shp'\n",
"roi_train = geemap.shp_to_ee(shp_path_roi_train)\n",
"\n",
"#Citations:\n",
"# Amante, C. and B. W. Eakins, ETOPO1 1 Arc-Minute Global Relief Model: Procedures, Data Sources and Analysis. \n",
"# NOAA Technical Memorandum NESDIS NGDC-24, 19 pp, March 2009.\n",
"\n",
"# Import elevation dataset from GEE\n",
"dataset = ee.Image('NOAA/NGDC/ETOPO1')\n",
"bathymetry_clipped = dataset.clip(roi_train)\n",
"\n",
"# Extract band 'bedrock' and rename it bathymetry for convenience\n",
"bathymetry = bathymetry_clipped.select('bedrock').rename('bathymetry')\n",
"\n",
"# Add bathymetry band to deglinted and raw image\n",
"s2_deglint_masked = s2_deglint_masked.addBands(bathymetry)\n",
"\n",
"# Add NDVI-image to map\n",
"ndviParams = {min: -1, max: 1, 'palette': ['blue', 'white', 'green']}\n",
"Map.addLayer(ndvi_image, ndviParams, 'NDVI image')\n",
"Map.addLayer(roi_train, {}, 'training site')\n",
"\n",
"# Add bathymetry data on the map\n",
"bathymetryVis = {\n",
" 'min': -7000.0,\n",
" 'max': 3000.0,\n",
" 'palette': ['011de2', 'afafaf', '3603ff', 'fff477', 'b42109'],\n",
"}\n",
"Map.addLayer(bathymetry, bathymetryVis, 'bathymetry')\n",
"Map"
]
},
{
"cell_type": "code",
"source": [
"# Add ground truth data geometry of seagrass, seaweed, and water\n",
"shp_path_SW = '/content/Coastal_Marine_Geology.shp'\n",
"seaweed_shp = geemap.shp_to_ee(shp_path_SW)\n",
"\n",
"shp_path_SG = '/content/MaineDEP_-_Eelgrass_2018_(Casco_Bay_Only).shp'\n",
"seagrass_shp = geemap.shp_to_ee(shp_path_SG)\n",
"\n",
"# Drew rectangles to represent water, than downloaded them locally\n",
"# geemap.ee_to_shp(water, filename='/content/water.shp')\n",
"shp_path_water = '/content/water.shp'\n",
"water_shp = geemap.shp_to_ee(shp_path_water)"
],
"metadata": {
"id": "OCzY5ymer1CP"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "wCR53MxcaLgS",
"outputId": "ad27fa77-5de1-4ea3-a00e-61c7f5551bb5"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"We have: \n",
" 4874 samples from the seagrass polygons \n",
" 939 samples from the seaweed polygons \n",
" 4992 samples from the water polygons \n",
"10805\n"
]
}
],
"source": [
"# increase sample size of seaweed\n",
"sample_sw = s2_deglint_masked.sample(**{\n",
" 'region': seaweed_shp.geometry(),\n",
" 'numPixels':5000, # Collect only a 100 datapoints from the geometries to as there as so few polygons of seagrass in the area\n",
" 'geometries': True,\n",
" 'seed' :3,\n",
" 'scale': 10, # Set to 10 as our resolution is 10-meters\n",
"})\n",
"\n",
"sample_sg = s2_deglint_masked.sample(**{\n",
" 'region': seagrass_shp.geometry(),\n",
" 'numPixels':5000, \n",
" 'geometries': True,\n",
" 'seed' :3,\n",
" 'scale': 10,\n",
"})\n",
"\n",
"sample_water = s2_deglint_masked.sample(**{\n",
" 'region': water_shp.geometry(),\n",
" 'numPixels':5000,\n",
" 'geometries': True,\n",
" 'seed' :3,\n",
" 'scale': 10,\n",
"})\n",
"\n",
"# Convert samples from ee-objects to geodataframes\n",
"gdf_sw = geemap.ee_to_geopandas(sample_sw)\n",
"gdf_sg = geemap.ee_to_geopandas(sample_sg)\n",
"gdf_water = geemap.ee_to_geopandas(sample_water)\n",
"\n",
"# Get number of samples fetched for each class\n",
"length_sg = len(gdf_sg)\n",
"length_sw = len(gdf_sw)\n",
"length_water = len(gdf_water)\n",
"print(f'We have: \\n {length_sg} samples from the seagrass polygons \\n {length_sw} samples from the seaweed polygons \\n {length_water} samples from the water polygons ')\n",
"\n",
" # Crete Class column 'Cover'\n",
"gdf_water['Cover'] = int(1) # class water\n",
"gdf_sw['Cover'] = int(2) # class seaweed\n",
"gdf_sg['Cover'] = int(3) # class seagrass\n",
"\n",
"\n",
"# Merge the three dataframes and create a single dataset\n",
"# Source code: https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html. Accessed 08.02.23\n",
"frames = [gdf_water, gdf_sw, gdf_sg]\n",
"\n",
"data = pd.concat(frames, ignore_index=True)\n",
"print(len(data))"
]
},
{
"cell_type": "markdown",
"source": [
"# Visually compare the sample points to the ground truth polygons. "
],
"metadata": {
"id": "Z1GJJkXKAzWT"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "rNJh0yE2b62_",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"51b6742b33024e2c8340f9bf44eea952",
"9b9daf62fe724466bd1551280ccc16a5",
"439b3e801d0140b68741f23b94edb4f3",
"7ac37d672bdf420eb81a706b6eb22318",
"dd5757764e9743dfb844fbbb70f779ea",
"181f5a481d03428fb68e4f6a910f49ce",
"da7ec3591598445988f9ca88dac6c872",
"b2ab18570bb84b58ac2a9456452acbd7",
"900d6b0cdbcc425da6f7b7e7b1f11e56",
"49c2724c99d24c548f63ed3942fe959c",
"95f96e1110934a2ab5a00fd0b05c7b31",
"99c8bd298bab4c17b3b8d5ff268fd64f",
"53eca3e3e5ea4dafa9ae57ba7625acd8",
"854cdcbfc51a47479a2ebb598f0d5d93",
"45823ef7f755453783c644ea67220df2",
"5c2c915685374099a305b6cece513244",
"33ecf86fa09b4336991f708afc5f6896",
"2e7dc0ecf3934f63be925141fda4e306",
"2c20d6b165404856912693ed73a7b40f",
"466dffe81d2f46c1941f6b4544938821",
"383a5615019c453093dfec0607db9e47",
"b3779b2b62f047738f58a099a9d7c32b",
"a825560c3bcd480987174c3be15ef0df",
"35347ca422fd4224aa50d6d7bed32ff5",
"e8a7cf8625d04812a4d811644f3da0cf",
"544bbe482655450b842943a83df793f4",
"053ed8c6b9194a8f9c3a3a0816cfb362",
"1141ea938ecc438cb8f97ad12d2d6aef",
"8fff55d216c14080b524585c3007da91",
"bb3db6c28f4740fc802974c0d0a0fb50",
"1247c2543e644f478a4828031e6ae22c",
"94e007ad31a04c55bd7591b4e43d2030"
]
},
"outputId": "2ef07095-7722-49a9-9ed6-d880b4527d99"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(center=[43.544235, -69.740859], controls=(WidgetControl(options=['position', 'transparent_bg'], widget=HBo…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "51b6742b33024e2c8340f9bf44eea952"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"Map = geemap.Map()\n",
"Map.set_center(-69.740859, 43.544235, zoom=10)\n",
"\n",
"vis_params = {\"bands\": [ 'B2', 'B3', 'B4'], \"min\": 0, \"max\": 1500, \"gamma\": 1.5}\n",
"Map.addLayer(image_train, vis_params, 'Sent-2 image')\n",
"Map.addLayer(s2_composite_min, vis_params, 'Sent-2 min')\n",
"\n",
"vis_params_deglint = {\"bands\": [ 'B2', 'B3','B4'], \"min\": 0, \"max\": 1500, 'gamma':1.5}\n",
"\n",
"Map.addLayer(S2_deglint, vis_params_deglint, 'sun-glint corrected Sent-2')\n",
"Map.addLayer(s2_deglint_masked, vis_params_deglint, 'masked Sent-2 deglinted image')\n",
"\n",
"vis_params_sw = {'color':'#7b3e00'}\n",
"vis_params_sg = {'color':'1c5f2c'} \n",
"vis_params_water = {'color':'#0d98ba'} \n",
"\n",
"# Ground truth polygons \n",
"Map.addLayer(seagrass_shp, vis_params_sg, 'seagrass')\n",
"Map.addLayer(seaweed_shp, vis_params_sw, 'seaweed')\n",
"Map.addLayer(water_shp, vis_params_water, 'water')\n",
"\n",
"# Sample points\n",
"#Map.addLayer(sample_sg, vis_params_sg, 'seagrass samples')\n",
"#Map.addLayer(sample_sw, vis_params_sw, 'seaweed samples')\n",
"#Map.addLayer(sample_water, vis_params_water, 'water samples')\n",
"Map"
]
},
{
"cell_type": "markdown",
"source": [
"# OBIA-method at the training site"
],
"metadata": {
"id": "iEh5bUN2A3x_"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "qGu0xgW2Bfyu",
"outputId": "f684b0a6-3777-4794-efd2-837ce579972c"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['clusters',\n",
" 'B2_mean',\n",
" 'B3_mean',\n",
" 'B4_mean',\n",
" 'B8_mean',\n",
" 'NDVI_mean',\n",
" 'bathymetry_mean']"
]
},
"metadata": {},
"execution_count": 88
}
],
"source": [
"# Select seed-pixels for clustering, spaced at least 36 pixels apart. Clipped to region of interest. \n",
"seeds = ee.Algorithms.Image.Segmentation.seedGrid(36).clip(roi_train)\n",
"\n",
"# Run SNIC --> create super-pixels\n",
"snic = ee.Algorithms.Image.Segmentation.SNIC(**{\n",
" 'image': s2_deglint_masked, # Image to create superpixels \n",
" 'size': 32, # Spacing between each seed in pixels. Each seed are 32 pixels away from each other \n",
" 'compactness': 5, # How compact the super-pixels should be. Larger values creates squares, small more organic patterns\n",
" 'connectivity': 8, # Number of pixels that can be connected to one pixel. 4 means the pixels around one that shares a side, 8 means also those pixels who touches the corners of a pixel. \n",
" 'neighborhoodSize':256, # \n",
" 'seeds': seeds # Square grid of seeds. Each seed with a spacing of 36 pixels inbetween them. \n",
"})\n",
"\n",
"# Outputs average values for the super-pixels \n",
"snic.bandNames().getInfo()"
]
},
{
"cell_type": "code",
"source": [
"#Display the clusters.\n",
"Map.addLayer(snic.randomVisualizer(), None, 'Clusters')\n",
"# Display the RGB cluster means.\n",
"visParams = {\n",
" 'bands': ['B4_mean', 'B3_mean', 'B2_mean'],\n",
" 'min': 0,\n",
" 'max': 255\n",
"}\n",
"\n",
"vis_params_sw = {'color':'#7b3e00'}\n",
"vis_params_sg = {'color':'1c5f2c'} \n",
"\n",
"Map.addLayer(snic, visParams, 'RGB cluster means')\n",
"#Map.addLayer(S2_masked, {'palette': ['black']} , 'S2 Land Mask')\n",
"#Map.addLayer(seagrass_shp, vis_params_sg, 'seagrass')\n",
"#Map.addLayer(seaweed_shp, vis_params_sw, 'seaweed')\n",
"Map"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"014a11b26dfb49c6b0a491a0ebaa914c",
"70f619c71bb041d18cb491f033a0ad69",
"8776ae2337ba471abf799b5a169d4646",
"be3ec1bf814e475d8d768c0d4b08bfeb",
"740cd8aaa8fb45fea859386e2a242cd0",
"8acc479bceb24e2f8fb1347017513f50",
"525def0abc574281906a0126835f2d44",
"82ba4a76ff2649dda62aafead62becce",
"2e8699f93ab344bc9d05aa36fa4e04fd",
"21a5de1fe83c40ad92c8201a210be0ee",
"55fb7212219a488eadbc6f8f0bb1742e",
"a9baaa1c79cc499fb9b1cd6238fc52a3",
"2cdf48b5ca5d482dba952cfb14e747c7",
"9f475813be5b46bda6bb888e28e9e5ad",
"0a1a74dc273148669492d513d562f7ec",
"9aaf09b24aed4f1ba714c77f4de6560e",
"b7db8182d16d44f5bf17dac7e8d8e08d",
"b4cf5078a30743b08c840d1e0300cce6",
"80fc19ac6ea043e4a39243552e708074",
"04c233230e834d7daeb0af22ad41bff2",
"7a1695e01efb4ab8bee2ff4bd36b3204",
"243325fe24644cb5becf8919a473f567",
"99c35096efa64d60b5994569ff8788f4",
"8d5dd99acd7143bc807bf554cc6b068d",
"7e013697bca24e3b9512b54aeef865d9",
"1528935753574f98a16b9f3bec36219e",
"d469db5a3a3f4ab3b1122e010ac747c6",
"5801ae53063a462db8ebe894e5e02311",
"f66de992ab3941279dd548ad4040b404",
"dba3d72a47144cf9b76da246602d6cee",
"a8a8f395c07b4d67ac605aac9ce5f75a",
"8caf2c53ab0e4522a6b6f2cb135ca79f",
"ddfeaf5dab694ad7b4570c909c34a616",
"552f193a1a764c95a6c39a4e290598a8",
"88a3c40a5cff44c99f5eef522c6173b1",
"3e10538710de44ae9dcdc1397a9da2f7",
"60709f00ec5f40ec821af19a341319dd",
"7447d33baa794f2599a43722574b4131",
"edee0efa58db47568ad441ac268d59b8",
"e418530a345e4949ada5edd0c629b8db",
"315bfbb501674c8984a76b13669adfb5",
"8b0f0296c25f44ef98422e4bfcff28b1",
"fcd71c3f41e54f5b9d0d11a36b9d533c",
"571fbf60d58648e0952b9aa3a7d0e5db",
"c90908bb32c645139d2e7680015ec396",
"0d8a7932123048cba3d323f653574652",
"37220239ec1c46a698f2bda9d756f9df",
"65a9dc973fc74fc0ba6b1fb1f09d2a78",
"323cd63ffba7485388112433c89323fb",
"07fcafa586ff47289214018639974cef",
"e3f78c7694324bb49d5a477faf322f96",
"b6ff8955109543a1a7da26b840768c58",
"a395ac8c991144d6a49fa5b543334748",
"d4664425d9684e399e269de92807a154",
"4f4b9de5bd65428cbafd5778cd18f72b",
"e591c09333c14135a1ed77ebd9bd2324",
"5065c4db3a9b4e148c92a1c5559ca08e",
"1123357a905d4d95abca983a979aa510",
"dd993e9553274611a4ebb5465db2b286",
"10ac3896b8b740ee95382daee5d84162",
"cb00dace8a0144e18a2e7cd93738ca4d",
"8b2e8f28ca5649e58a7961da0c5b38b5",
"fc6d6084f2804ac08196b836df78456d",
"449e3c61fde6490b892dffe35e676fd3",
"a9a87b33923b48dc94ae1a7f72a7d436",
"89e3b0b177ce4fbaad217d99bec44054",
"fb0d6bcbc8d440efbdc07b62d3d14dac",
"93794847aa364ec6b84c745d7d891e30",
"8fd9dee4efe045ad9c6c91576588e0a3",
"7fc1a329c9ed4f9e8bed2029db8cc8ed",
"0d7a4b0795ea44409a58aec45d74434e",
"cdd2b87d1db648e28d3577f740c9474d",
"0a3efe6f402c46de89bc570d70708812",
"df970abbcf6a4cc79868dfe66cf1e4f3",
"17d64e3ded274a5c90ceccdd7e753508",
"d8883bfabff4411db37a2cd29563a58f",
"a19768dd083b4b13aba34793b7150db1",
"5075a9c03fb84da9aa733f0adb8e3070",
"3e146471734b46ea8e8896526b676908",
"12febb91b15e411d995faa09a55c922e",
"e0b9832237ed4d58a2fc4bf9a56a7cb3",
"640083966a674b24b24f3d7df4fc9eff",
"c7dd029220ad4fdbaf9801eed6fb5404",
"dfc2538c6bed46afb7e2db5bddbf7dd4",
"12f4d8edf8314ea78abb45fc4c9b9916",
"fa2bf179f83a4c27bba38c2db15bb014",
"55b018ece54a4ad382116e2fba28a92d",
"9c185c065f9b4d118882b709b601d0fc",
"42de45f4226c4f03a833cc96cd976767",
"2c49d6a2fe1444ff8af9a312697d1a10",
"c9fb635fb3e94d93a545681ee0b7c003",
"b24e328414d647f49c3017894a35c9d7",
"8f231715325d4d2b92754349cced5139",
"7552200719694e328b47fce0d4e4c55e",
"5714fb6c8f704600922bb10d4ee9f8a6",
"4446f30cd66b407cbd209d9bc2e3bee0",
"f4d8b82ce786440ca864a3da9de2041c",
"26029118754d4ded87ffa3bd07dc5464",
"7132116f2f5b4679abc5a511847a5eec",
"4594f220ea0345499bec12a58b68dfcb",
"f432633c5fa544c68a0cbe14fe5dd843",
"74e412e73f24488b8af4f9228e305bfe",
"0eac3758d9cd44838ffffb69b2008494",
"2eaeccfca18a4a199867792031b6d754",
"994ed370844341b6a4aa80852ca76487",
"8804458e27404039acfefecd43454905",
"8faffd3551c8465fa3c2929a11728595",
"88f65aca67644956b460a543861a4f0b",
"4299dbe116464660b86c50f82b8cd43d",
"3227574ba3b94bd0bdcc2ab7f2d5eeeb",
"a9124d50217848bfb7269e2dd244b3f6",
"4e4e3e04d1af40c6984144d459e9c721",
"e867648ada6c4a1bb9102598e7c31cd5",
"9f495408ed314d76b50b4ba2fae9a4a8",
"9ca69df3bc9e44259404d8cec0ac32ca",
"f2db84a536ed43f686ff6666e8c76630",
"ec10ab12be9342b2bb9b2121a8362931",
"83dd63a7bfb14bfe8aabab6fdd233fad",
"3529e1161abb4e04815969bdcdf20714",
"f40c749432de47499527b4fc69875342",
"95a9bccb469d45259421f32d9306faeb",
"767db1ffadf7400fa27a664e721466e7",
"01ee0a0f2c524e5c8a515119a446b9af",
"d79703cccce347c9a0c5b9e932a8a4c5",
"7315ae5e25d84babae92019bf788fb75",
"e234f05e117e407c9249ed14f1cc774f",
"ad6ae144fa1046b09c1997d45fcf0432",
"2ec8aa42f7294067a8241e1908f8628b",
"f6f4c66213714cdaabeb1b17ea2d74b6",
"704b27149b5a4b44ba9701024ee4b9dc",
"8d482588c33543a0bd591f85205ac830",
"e1f1ad2b37bb486c93f68dbab1a93c32",
"e8d86a0d7b8440549447e9a56416662d",
"1bb8f314bd804aeca8d7b1e6c8a53961",
"5a1396eacec244f8a8f6e98f6403b8b8",
"85374e830b59413e8c62439eef024059",
"0dffe092a48748df9a4887df58dc2bb6",
"25edf524684b4e01ae47a25c9513a78c",
"995aef9ea6ca4e3792733bf7f505b9f6",
"68e0bbe408204d8cbc626f62dc52e4b5",
"046f8042d10b441eb2c3ddcc1a716df5",
"1324e57487ce4643b6c1b89d9d8e5a27",
"c00c7409aca244c4b55d79aafc82a45b"
]
},
"id": "Suujwx3yI0Pl",
"outputId": "9c44ffc3-1ee5-44e1-9192-aafaf91359fc"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(bottom=765082.7388728482, center=[43.72561622035781, -69.9768711867684], controls=(WidgetControl(options=[…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "014a11b26dfb49c6b0a491a0ebaa914c"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7keLMtfhLg0P",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "00cb9328-cadd-4833-cdc9-cad9c1862180"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['clusters',\n",
" 'B2',\n",
" 'B3',\n",
" 'B4',\n",
" 'B8',\n",
" 'NDVI',\n",
" 'bathymetry',\n",
" 'area',\n",
" 'perimeter',\n",
" 'width',\n",
" 'height']"
]
},
"metadata": {},
"execution_count": 90
}
],
"source": [
"'''\n",
"# In order to try to still the image (avoid the super-pixels to change with scale), code commented out here is used. Did not work...\n",
"# source code: https://gis.stackexchange.com/questions/333413/is-google-earth-engine-snic-segmentation-algorithm-inconsistent. Accessed 10.02.23\n",
"snic.reproject(**{\n",
" 'crs': 'EPSG:4326',\n",
" 'scale': 10\n",
"})\n",
"\n",
"# Source code: https://developers.google.com/earth-engine/apidocs/ee-algorithms-image-segmentation-snic. 10.02.23\n",
"# Lock map zoom to maintain the desired scale of the segmentation computation.\n",
"'''\n",
"# Using super-pixels to get object-based features: \n",
"clusters = snic.select('clusters') \n",
"\n",
"#Area\n",
"area = ee.Image.pixelArea().addBands(clusters).reduceConnectedComponents(ee.Reducer.sum(), 'clusters', 256)\n",
"#Map.addLayer(area, {min:50000, max: 500000}, 'Cluster Area', False)\n",
"\n",
"minMax = clusters.reduceNeighborhood(ee.Reducer.minMax(), ee.Kernel.square(1))\n",
"perimeterPixels = minMax.select(0).neq(minMax.select(1)).rename('perimeter')\n",
"\n",
"# Perimeter\n",
"perimeter = perimeterPixels.addBands(clusters).reduceConnectedComponents(ee.Reducer.sum(), 'clusters', 256);\n",
"\n",
"# Width and Height\n",
"sizes = ee.Image.pixelLonLat().addBands(clusters).reduceConnectedComponents(ee.Reducer.minMax(), 'clusters', 256)\n",
"width = sizes.select('longitude_max').subtract(sizes.select('longitude_min')).rename('width')\n",
"height = sizes.select('latitude_max').subtract(sizes.select('latitude_min')).rename('height')\n",
"\n",
"bands = ['B2_mean', 'B3_mean', 'B4_mean', 'B8_mean','clusters', 'bathymetry_mean','NDVI_mean']\n",
"\n",
"# objectPropertiesImage is now an image containing 11 feautres. \n",
"objectPropertiesImage = ee.Image.cat([\n",
" snic.select(bands).rename(['clusters', 'B2', 'B3', 'B4', 'B8', 'NDVI', 'bathymetry']),\n",
" area,\n",
" perimeter,\n",
" width,\n",
" height\n",
"]).float()\n",
"\n",
"# Image with now 11 features and super-pixels\n",
"objectPropertiesImage.bandNames().getInfo()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "0jT4TRIj8BVU",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "5c2c1712-e7c7-4270-874a-30e777894b38"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"We have: \n",
" 4999 samples from the seagrass polygons \n",
" 952 samples from the seaweed polygons \n",
" 4815 samples from the water polygons \n",
"10766\n"
]
}
],
"source": [
"# Use functions below if data to get sample data fro training, validaiton and test. \n",
"# To save time, these sets have already been created and stored locally.\n",
"# The files used her ecan be found with the rest on git-hub for reproducable results.\n",
"\n",
"# increase sample size of seaweed\n",
"sample_sw = objectPropertiesImage.sample(**{\n",
" 'region': seaweed_shp,\n",
" 'numPixels':5000, # Collect only a 100 datapoints from the geometries to as there as so few polygons of seagrass in the area\n",
" 'geometries': True,\n",
" 'seed' :5,\n",
" 'scale': 10, # Set to 10 as our resolution is 10-meters\n",
"})\n",
"\n",
"sample_sg = objectPropertiesImage.sample(**{\n",
" 'region': seagrass_shp,\n",
" 'numPixels':5000, \n",
" 'geometries': True,\n",
" 'seed' :5,\n",
" 'scale': 10,\n",
"})\n",
"\n",
"sample_water = objectPropertiesImage.sample(**{\n",
" 'region': water_shp.geometry(),\n",
" 'numPixels':5000,\n",
" 'geometries': True,\n",
" 'seed' :5,\n",
" 'scale': 10,\n",
"})\n",
"\n",
"# Convert samples from ee-objects to geodataframes\n",
"gdf_sw = geemap.ee_to_geopandas(sample_sw)\n",
"gdf_sg = geemap.ee_to_geopandas(sample_sg)\n",
"gdf_water = geemap.ee_to_geopandas(sample_water)\n",
"\n",
"# Get number of samples fetched for each class\n",
"length_sg = len(gdf_sg)\n",
"length_sw = len(gdf_sw)\n",
"length_water = len(gdf_water)\n",
"print(f'We have: \\n {length_sg} samples from the seagrass polygons \\n {length_sw} samples from the seaweed polygons \\n {length_water} samples from the water polygons ')\n",
"\n",
" # Crete Class column 'Cover'\n",
"gdf_water['Cover'] = int(1) # class water\n",
"gdf_sw['Cover'] = int(2) # class seaweed\n",
"gdf_sg['Cover'] = int(3) # class seagrass\n",
"\n",
"\n",
"# Merge the three dataframes and create a single dataset\n",
"# Source code: https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html. Accessed 08.02.23\n",
"frames = [gdf_water, gdf_sw, gdf_sg]\n",
"\n",
"data = pd.concat(frames, ignore_index=True)\n",
"print(len(data))\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "edS9PvgzeQzM"
},
"outputs": [],
"source": [
"# Visually inspect that the samples are drawn from the training site \n",
"Map = geemap.Map()\n",
"Map.set_center(-69.740859, 43.544235, zoom=10)\n",
"\n",
"# Visually inspect the image and composite iamges created \n",
"vis_params = {\"bands\": [ 'B2', 'B3', 'B4'], \"min\": 0, \"max\": 1500, \"gamma\": 1.5}\n",
"Map.addLayer(image_train, vis_params, 'Sent-2 image')\n",
"\n",
"vis_params_sw = {'color':'#7b3e00'}\n",
"vis_params_sg = {'color':'1c5f2c'} \n",
"vis_params_water = {'color':'#0d98ba'} \n",
"\n",
"Map.addLayer(seagrass_shp, vis_params_sg, 'seagrass')\n",
"Map.addLayer(seaweed_shp, vis_params_sw, 'seaweed')\n",
"Map.addLayer(water_shp, vis_params_water, 'water')\n",
"\n",
"Map.addLayer(sample_sg, vis_params_sg, 'seagrass samples')\n",
"Map.addLayer(sample_sw, vis_params_sw, 'seaweed samples')\n",
"Map.addLayer(sample_water, vis_params_water, 'water samples')\n",
"Map"
]
},
{
"cell_type": "markdown",
"source": [
"# Storing data locally"
],
"metadata": {
"id": "PRGn4g6sBKvY"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "DPJmp4pmZKEL"
},
"outputs": [],
"source": [
"# Store the training data locally for reproducability and faster \n",
"# data = data11_ndup\n",
"# All data: \n",
"# 1) data.head() # Check how the data looks \n",
"# 2) data.describe()\n",
"# 2) data.isnull().sum().sum() # Check for null-values \n",
"# 3) data.columns # Found mix-up mistake of columns\n",
"# 4) data = data.drop(['geometry'], axis=1) # Remove duplicates created \n",
"# 5) data.head() # Verify that our fix worked\n",
"# 6) data = data.sample(frac=1) # Randomize the data\n",
"# 8) data.to_csv(r'/content/OBIA_train11.csv', index=False) "
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "x3RZTSA61h1L"
},
"source": [
"# Collecting test-data\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "zpQbB6JF1nFV",
"outputId": "ea868ff7-f71e-4285-be63-9c73dd90c0ca"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Number of Sentinel 2 images in creating the training composite with: 5\n",
"The least cloudy image was taken (YYYY-MM-DD): 2021-10-24\n",
"Cloud percentage: 30.48% of the least cloudy image\n",
"features available: ['B2', 'B3', 'B4', 'B8']\n"
]
}
],
"source": [
"# Source code: https://developers.google.com/earth-engine/guides/ic_info. Accessed: 16.02.2023\n",
"point_test = ee.Geometry.Point([-70.269, 43.680]) # Center around a specified point\n",
"\n",
"# Criteria for maximum cloudiness\n",
"MAX_CLOUD_PROBABILITY = 5\n",
"CLOUD_THRES = 5\n",
"\n",
"######################################################################################################################\n",
"######################################################################################################################\n",
"# Get the least cloudy image\n",
"image_test = (\n",
" ee.ImageCollection('COPERNICUS/S2_SR') # Dataset from GEE\n",
" .filterBounds(point_test) # Filter satellite-images around our region of interest (ROI)\n",
" .filterDate('2021-06-02','2021-11-01') # Filter time\n",
" .sort('CLOUDY_PIXEL_PERCENTAGE') # fiter for cloud percentage\n",
" .first() # Take the image with least cloud coverage\n",
" .select('B[2-4]','B[8]') # Select bands B2, B3, B4, and B8 as features\n",
")\n",
"######################################################################################################################\n",
"######################################################################################################################\n",
"# Create a collection of images over a time-periode for training data\n",
"s2_coll_test = (ee.ImageCollection('COPERNICUS/S2_SR')\n",
" .filterBounds(point_test) # Filter satellite-images around our region of interest (ROI)\n",
" .filterDate('2021-06-02','2021-10-01')\n",
" .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', CLOUD_THRES))\n",
" )\n",
"\n",
"# Create a composite training image using min-value\n",
"s2_composite_min=s2_coll_test.select(['B[2-4]','B[8]']).min()\n",
"# Create a composite training image using the median-value\n",
"s2_composite_median = s2_coll_test.select(['B[2-4]','B[8]']).median()\n",
"\n",
"# Number of images fulfilling the cloud-coverage critera that will be used to make a composite image \n",
"print('Number of Sentinel 2 images in creating the training composite with:', s2_coll_test.size().getInfo())\n",
" # Print date and cloud percentage (in decimal)\n",
"print('The least cloudy image was taken (YYYY-MM-DD):', ee.Date(image_test.get('system:time_start')).format('YYYY-MM-dd').getInfo())\n",
"cloud_perc = image_test.get('CLOUDY_PIXEL_PERCENTAGE').getInfo()*100\n",
"print(f'Cloud percentage: {cloud_perc:,.2f}% of the least cloudy image')\n",
"print('features available:', s2_composite_min.bandNames().getInfo())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"2b37c8d0b9b04506a71f1cab938d2348",
"95d76359729e4d9cbb5e46a3c12e028b",
"64f8886adcfb4c4fbf2f6b9ebe4eb2fc",
"308fb62ae06a4f2db0d65ef4e4a28e3c",
"44c8e6344f3d471985e651e72dd9d668",
"62cf87a9f1da45f38a9f73ed76c5e46e",
"6543ecaf4b7747dc8f280c15d2d17150",
"7eb7af01d25c4aba8f2932b6ae8f9f43",
"457acd593bbe473cbdf1729c3f712032",
"b4519fad5d1742978fd3b28de7c738c7",
"298dbac52ba346d9a601ec9b11552a17",
"aecc5746b278466c9b6c2cd7e4be185a",
"1106d02a682042a18aa617cced4460fa",
"837457f322f344e59601438383011344",
"55ea244a98b24a969c73c8d301645586",
"61f7107c8ff04e6cb16d77ea024f8dae",
"32796e5d222e4be2a3113cc71a8db973",
"45dca9f9370a4e5c8f6cc645715e6527",
"0c77be2d06324a1297a3b25497e728ef",
"8e8775cc91bc46d1aec106e5372caf9f",
"7f07f649ff7f47059c30ff731203b748",
"8ec543d5d37e489098030c401be7ecd8",
"2b1836617a634db9a348e140d1043fda",
"c4d76896ab1c486298cdf242be15f1b0",
"29c5e2d917a6428db2b3ea8212ee583e",
"9dce60248e8e4eb5a56d2aa32b030244",
"51a5f4d2de9e49caaeef792ff85e5b1d",
"169226077aba4a819bf3286e6b7fce7b",
"69e21ce283b444d08620a3a109cba633",
"7cfdb9b89abd4eac82f98fd5da6755fb",
"3bb43f6e296841e59da84e82b2396bf5",
"1fa0f5614b4143b9a77ecc4a96e016e6",
"61f4a4f60714476b8dd32223c13f1812"
]
},
"id": "s4NubZDRi0TV",
"outputId": "8210ad3f-65b3-4cea-e222-f13693d55047"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(center=[43.544235, -69.740859], controls=(WidgetControl(options=['position', 'transparent_bg'], widget=HBo…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "2b37c8d0b9b04506a71f1cab938d2348"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"# Instantiate a new map\n",
"Map = geemap.Map()\n",
"Map.set_center(-69.740859, 43.544235, zoom=10)\n",
"\n",
"# Visually inspect the image and composite iamges created \n",
"vis_params = {\"bands\": [ 'B2', 'B3', 'B4'], \"min\": 0, \"max\": 1500, \"gamma\": 1.5}\n",
"Map.addLayer(image_test, vis_params, 'Sent-2 image test')\n",
"Map.addLayer(s2_composite_median, vis_params, 'Sent-2 median')\n",
"Map.addLayer(s2_composite_min, vis_params, 'Sent-2 min')\n",
"# Use toolbar on the left side, e.g., \" Draw a rectangle\" over a sight \n",
"# to extract NIR values (min and random) from two pixels. \n",
"# Areas of deep waters are recommended.\n",
"Map\n",
"# Draw a rectangle in an area of deep water! "
]
},
{
"cell_type": "code",
"source": [
"# Store glint_test locally for reproducability \n",
"#Map.draw_features # Collects the drawn rectangle(s)\n",
"#glint = ee.FeatureCollection(Map.draw_features) # Stores the rectangle(s) geometry to extract NIR-values from\n",
"\n",
"#geemap.ee_to_shp(glint, filename='/content/glint_test.shp') "
],
"metadata": {
"id": "wAsGTbG0PNoV"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"e02a65c8ee324a7b975ecc92c4ab15e6",
"26ebb03e7c954c63ab29e73d467a8d52",
"3b40c7079a8e4727b58b11f42bcba0a5",
"e9da94d8bcb241a6ac34b0a8a90613aa",
"9c3e474baaf840e7bc9c4d8f1b8a08c8",
"ac6f9d3441d747a6930c610f5d772ebe",
"20cd9ab11cf94c2e88a5cc2bff61a8d2",
"a8885888761e4e37a1c73e3ef31eec34",
"2685b51ce7a0407c95ed79de2cad156d",
"1aaef91a8be749c489239fceacae08f5",
"581d62df6ef64589b0454f1dafee1c67",
"174b4511f33542a49b19ca0ad7c57c57",
"2cdf48b5ca5d482dba952cfb14e747c7",
"d10ee13bc778486e9ecfec5181eeceb1",
"f0a2b407ced04cfb91669529e1b0b9a3",
"e1a09c25407c48bbb01445b14a8bc379",
"e0ff43e13c0948ef83cf3fcbefd5c513",
"3161792ce84f45419346c40f51cdfee9",
"a65db715d6634b5ea519b18f07fe92aa",
"40bcba1f10444233af0e5ebea08f0e13",
"ea75002a1f9544758e2d6a3ce5ccd3bc",
"5d60208fd468492f89f7e3c476c15f04",
"fb58b950c9224809b70f47f77089cd66",
"4c8c6fbf6e6f40f59c600b711392ca92",
"f5d3e5bc31394474a2ca505a828e930d",
"3541999f98c74890b90e63851dea0807",
"a21fe412f0314902aa5a9145d6e92378",
"92422524aa614d2a850df2d2b5024ea4",
"0ebb3418e6c9472fbce105ce0705c4e8",
"1d6e81acda5d4a56b5485ec75d0030f6",
"0ccd0ea1d3734e208680fc1226d87279",
"2e00dcf7a277425d9ed4b58a535d1c38",
"02c1145b8dfb4d0599c047af84cbc4b5",
"d7e26a7de23940a0b2113874578ee772",
"689f353aa9464b909473a1aba39eafb8",
"dfe7028d1be240d1a58e132d62a074dd",
"179b102ac9e844d7ba24b0d7d625fd03",
"9cd71ea7aedf4bdf802c12f37703ec21",
"cec01783518948aeb24acf3bcddb02bf",
"9fda0e6cc0134496bcdb5ee7527f32ac",
"7e9791e9bb4042dc873b14933c2b89d1",
"c4d8970c87fe4255ad77ead5e8fc5e9d",
"e76dc569984c40edbc34ab37f3ac608f",
"cba7e24392b44d9e975532bbec6a586d",
"b1e54225362d4694be4b22925f4fa661",
"28eff78fc21347a29e9419162fdc3963",
"2ae56cc1b7764c1191fca1ef076fcc3f",
"1ce2d17640724ae5abd5d82ec131c2e1",
"63e193d980964dc283bfe832aad458ab",
"1c666d24db334b94b9585f5fd519714d",
"e0ab30fe821a4ff3b71c797fd1946518",
"e78fdcd624324472b0f8daf7aa609cd7",
"fbeb6c8f4fcf48f4a0895d4bf9240f3b",
"22d8875017bc49868d47b6e0b6ff7aba",
"dd4a0e15ab574f63806a3fdf6b0caec3",
"78dafb3a0a99468b909b807d117292cf",
"b5db91947ace4a52ba5ee566c77089cc",
"1b604c286eda4f2e8fada7dffe3a30d5",
"52b80a2a8dea4cf89c01bf4794762ab4",
"0efe55d3112c4216867913ae53a5d4ff",
"a6317ac08e8d4c82a733da2e0be67852",
"fa5829cece6042aabeb5730db9f11feb",
"5baadb39514e4835aea9c2b4c0fc3dd3",
"4cb0c2c9b1664fb7b5d68b3136626883",
"9e2c02620b7c4bcc863674020c3dc1aa",
"136d798962db41d2b6453177effd345c",
"6e4320984bee495e862eca24f9da0c6e",
"e894ce7234a84324b0debd8e003348bb",
"3d2b60d827364088b8bd1eba0ee0d3cc",
"0f8e20c677ad4e238530573560b36172",
"3ca453dd0e0340908a1fb7d0e0ce5f2a",
"67f4072e8a8d43d691e0d3f1dfdb0851",
"3567d9a5773c4706aa4aa709155e67b0",
"417e03faf797428db79081404091bb5c",
"de27817c659c4d2db278d56ac8e7bab2",
"0dbc91ebdae14fcdbae18e19e9aae312",
"c36a9c6bdb5749c9b7152a134d6d1887",
"2856c2d014fa4989ac5add5533a24475",
"12b2de0cd35b4412bf8c3037e15fcf46",
"b4688753f4eb4552bd7cd74b4a7c9307",
"efa5e15903fe4de9b90fe64c880c945e",
"e11307d97d63452fbde12c3a30c3ea23",
"aac14b7ac64c4d1287b71689108a23a9",
"1275c37f1e334e10b1f59b35ab280f19",
"978ab1babcfc4e8fab9fd226b2cf6070",
"dd95bb9769c040dba86a17fa4925fdaa",
"9c871beed0c447e78d750ec8bf953c56",
"e3c481c095e544f28872d121b30c7e2d",
"e2fdbb5529324718a4dc05b2a947ed81",
"29be0fe528f74660b0e76cc645934423",
"8e91f4e4b7c4449b9c11a6dd97993605",
"9c123b0e1a70431f9591be85d7558c94",
"ad3ee7ad6dd74cb58bd56e1922ae4222",
"84b0129b27884b9ab3e2adb546e187be",
"3bca5dfbd30245e3bcb1679029e43ee1",
"306b444132cc468d97c9790239b1d575",
"131608806e1b4961b00b3466a8e5cfb6",
"34addc150cb34c4eb12cfdfda306d02e",
"c52f256812564e9c86103992ef58b7d6",
"e620c4205f1a4b6f864b04dc8ed5537f",
"435a7242c2f94623b02248a5a62233d1",
"b5f60bc339674d7aa7acfdfe67383b80",
"d098a67e44f9457bb272cfdf414e261a",
"f85c7036c48742d596c46975d110a29c",
"6d9683c5491b41b1860ad247d4ae71c6",
"009a3fd297ed40ada71cb8ab1fe003a4",
"2fc2fcad7f404120aa7c2848ee89ff80",
"da2b1a3d06ec4b4faa43331f2be8de89",
"3c6aa7e310734e7c8b23a9b78249a9ff"
]
},
"id": "qBwq-LMbjVA5",
"outputId": "bf06d4a8-19d2-437b-8e79-8c335b2ca0ff"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(bottom=765105.6301778263, center=[43.72277642944339, -69.97642829655824], controls=(WidgetControl(options=…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "e02a65c8ee324a7b975ecc92c4ab15e6"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"# Apply deglint function\n",
"path_glint_test = '/content/glint_test.shp'\n",
"glint = geemap.shp_to_ee(path_glint_test)\n",
"\n",
"S2_deglint = deglint(s2_composite_min, glint) \n",
"\n",
"mask = S2_deglint.gt(0)\n",
"s2_deglint_masked = S2_deglint.updateMask(mask)\n",
"\n",
"\n",
"NIR_thres = 500\n",
"b8 =s2_composite_min.select('B8')\n",
"\n",
"# Source code: https://code.earthengine.google.com/?accept_repo=users%2Fstcarp%2FCME_MappingWorkshop. Accessed: 23.03.23\n",
"threshold = b8.where(b8.gt(NIR_thres),1).where(b8.lt(NIR_thres),0)\n",
"#Map.addLayer(landmask, {'bands': ['B8'], 'gamma': 1, 'max': 1, 'opacity': 1},'S2 Land Mask')\n",
"\n",
"# Source code: https://www.youtube.com/watch?v=qO3Te5pfOHc. Accesssed: 23.03.23\n",
"# Land mask\n",
"S2_masked = threshold.updateMask(threshold)\n",
"vis_params_deglint = {\"bands\": [ 'B2', 'B3','B4'], \"min\": 0, \"max\": 1500, 'gamma':1.5}\n",
"\n",
"Map.addLayer(s2_deglint_masked, vis_params_deglint, 'masked Sent-2 deglinted image')\n",
"Map.addLayer(S2_masked, {'palette': ['black']} , 'S2 Land Mask')\n",
"\n",
"\n",
"# Show deglinted image in map\n",
"vis_params_deglint = {\"bands\": [ 'B2', 'B3','B4'], \"min\": 0, \"max\": 1500, 'gamma':1.5}\n",
"\n",
"Map.addLayer(S2_deglint, vis_params_deglint, 'sun-glint corrected Sent-2')\n",
"Map"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "xqgLjRAckL3t"
},
"outputs": [],
"source": [
"# Add feature: NDVI \n",
"\n",
"# Calculating NDVI\n",
"nir = s2_composite_min.select('B8')\n",
"red = s2_composite_min.select('B4')\n",
"ndvi_image = nir.subtract(red).divide(nir.add(red)).rename('NDVI')\n",
"\n",
"# Add NIR-band to deglinted image\n",
"s2_deglint_masked = s2_deglint_masked.addBands(nir)\n",
"\n",
"# Add NDVI to RGB-image and deglinted image\n",
"s2_deglint_masked = s2_deglint_masked.addBands(ndvi_image)\n",
"\n",
"# sent2019 = ee.Image('COPERNICUS/S2/20190719T153601_20190719T153707_T19TDJ')\n",
"# Visualize the added features to show that they are actually added "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kLWBgalymHT3",
"outputId": "8ed20a7d-d79f-4477-f5cb-4bb664568446"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Generating URL ...\n",
"Downloading data from https://earthengine.googleapis.com/v1alpha/projects/earthengine-legacy/tables/73a8937772fb333d5db68ea2af92edf5-bdcd11f9849bc2fa72db0fbbf15f216e:getFeatures\n",
"Please wait ...\n",
"Data downloaded to /content/roi_test.shp\n"
]
}
],
"source": [
"# Store region of interst (test) locally for reproducability \n",
"#roi_test = ee.FeatureCollection(Map.draw_last_feature)\n",
"#geemap.ee_to_shp(roi_test, filename='/content/roi_test.shp') \n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "UbA5tVP00X6N"
},
"outputs": [],
"source": [
"# Add ground truth data geometry of seagrass, seaweed, and water\n",
"# Must upload to google colabs for each new runtime...\n",
"shp_path_SW = '/content/Coastal_Marine_Geology.shp'\n",
"seaweed_shp = geemap.shp_to_ee(shp_path_SW)\n",
"\n",
"shp_path_SG = '/content/MaineDEP_Seagrass_2021_(South_Coast_-_Elliot_to_Cape_Elizabeth).shp'\n",
"seagrass_shp = geemap.shp_to_ee(shp_path_SG)\n",
"\n",
"# Drew rectangles to represent water, than downloaded them locally\n",
"# geemap.ee_to_shp(water, filename='/content/water.shp')\n",
"shp_path_water_test = '/content/water_test.shp'\n",
"water_test_shp = geemap.shp_to_ee(shp_path_water_test)\n",
"\n",
"shp_path_roi_test = '/content/roi_test.shp'\n",
"roi_test = geemap.shp_to_ee(shp_path_roi_test)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 621,
"referenced_widgets": [
"e02a65c8ee324a7b975ecc92c4ab15e6",
"26ebb03e7c954c63ab29e73d467a8d52",
"3b40c7079a8e4727b58b11f42bcba0a5",
"e9da94d8bcb241a6ac34b0a8a90613aa",
"9c3e474baaf840e7bc9c4d8f1b8a08c8",
"ac6f9d3441d747a6930c610f5d772ebe",
"20cd9ab11cf94c2e88a5cc2bff61a8d2",
"a8885888761e4e37a1c73e3ef31eec34",
"2685b51ce7a0407c95ed79de2cad156d",
"1aaef91a8be749c489239fceacae08f5",
"581d62df6ef64589b0454f1dafee1c67",
"174b4511f33542a49b19ca0ad7c57c57",
"2cdf48b5ca5d482dba952cfb14e747c7",
"d10ee13bc778486e9ecfec5181eeceb1",
"f0a2b407ced04cfb91669529e1b0b9a3",
"e1a09c25407c48bbb01445b14a8bc379",
"e0ff43e13c0948ef83cf3fcbefd5c513",
"3161792ce84f45419346c40f51cdfee9",
"a65db715d6634b5ea519b18f07fe92aa",
"40bcba1f10444233af0e5ebea08f0e13",
"da2b1a3d06ec4b4faa43331f2be8de89",
"3c6aa7e310734e7c8b23a9b78249a9ff",
"ea75002a1f9544758e2d6a3ce5ccd3bc",
"5d60208fd468492f89f7e3c476c15f04",
"fb58b950c9224809b70f47f77089cd66",
"4c8c6fbf6e6f40f59c600b711392ca92",
"f5d3e5bc31394474a2ca505a828e930d",
"3541999f98c74890b90e63851dea0807",
"a21fe412f0314902aa5a9145d6e92378",
"92422524aa614d2a850df2d2b5024ea4",
"0ebb3418e6c9472fbce105ce0705c4e8",
"1d6e81acda5d4a56b5485ec75d0030f6",
"0ccd0ea1d3734e208680fc1226d87279",
"2e00dcf7a277425d9ed4b58a535d1c38",
"02c1145b8dfb4d0599c047af84cbc4b5",
"d7e26a7de23940a0b2113874578ee772",
"689f353aa9464b909473a1aba39eafb8",
"dfe7028d1be240d1a58e132d62a074dd",
"179b102ac9e844d7ba24b0d7d625fd03",
"9cd71ea7aedf4bdf802c12f37703ec21",
"cec01783518948aeb24acf3bcddb02bf",
"9fda0e6cc0134496bcdb5ee7527f32ac",
"7e9791e9bb4042dc873b14933c2b89d1",
"c4d8970c87fe4255ad77ead5e8fc5e9d",
"e76dc569984c40edbc34ab37f3ac608f",
"cba7e24392b44d9e975532bbec6a586d",
"b1e54225362d4694be4b22925f4fa661",
"28eff78fc21347a29e9419162fdc3963",
"2ae56cc1b7764c1191fca1ef076fcc3f",
"1ce2d17640724ae5abd5d82ec131c2e1",
"63e193d980964dc283bfe832aad458ab",
"1c666d24db334b94b9585f5fd519714d",
"e0ab30fe821a4ff3b71c797fd1946518",
"e78fdcd624324472b0f8daf7aa609cd7",
"fbeb6c8f4fcf48f4a0895d4bf9240f3b",
"22d8875017bc49868d47b6e0b6ff7aba",
"dd4a0e15ab574f63806a3fdf6b0caec3",
"78dafb3a0a99468b909b807d117292cf",
"b5db91947ace4a52ba5ee566c77089cc",
"1b604c286eda4f2e8fada7dffe3a30d5",
"52b80a2a8dea4cf89c01bf4794762ab4",
"0efe55d3112c4216867913ae53a5d4ff",
"a6317ac08e8d4c82a733da2e0be67852",
"fa5829cece6042aabeb5730db9f11feb",
"5baadb39514e4835aea9c2b4c0fc3dd3",
"4cb0c2c9b1664fb7b5d68b3136626883",
"9e2c02620b7c4bcc863674020c3dc1aa",
"136d798962db41d2b6453177effd345c",
"6e4320984bee495e862eca24f9da0c6e",
"e894ce7234a84324b0debd8e003348bb",
"3d2b60d827364088b8bd1eba0ee0d3cc",
"0f8e20c677ad4e238530573560b36172",
"3ca453dd0e0340908a1fb7d0e0ce5f2a",
"67f4072e8a8d43d691e0d3f1dfdb0851",
"3567d9a5773c4706aa4aa709155e67b0",
"417e03faf797428db79081404091bb5c",
"de27817c659c4d2db278d56ac8e7bab2",
"0dbc91ebdae14fcdbae18e19e9aae312",
"c36a9c6bdb5749c9b7152a134d6d1887",
"2856c2d014fa4989ac5add5533a24475",
"12b2de0cd35b4412bf8c3037e15fcf46",
"b4688753f4eb4552bd7cd74b4a7c9307",
"efa5e15903fe4de9b90fe64c880c945e",
"e11307d97d63452fbde12c3a30c3ea23",
"aac14b7ac64c4d1287b71689108a23a9",
"1275c37f1e334e10b1f59b35ab280f19",
"978ab1babcfc4e8fab9fd226b2cf6070",
"dd95bb9769c040dba86a17fa4925fdaa",
"9c871beed0c447e78d750ec8bf953c56",
"e3c481c095e544f28872d121b30c7e2d",
"e2fdbb5529324718a4dc05b2a947ed81",
"29be0fe528f74660b0e76cc645934423",
"8e91f4e4b7c4449b9c11a6dd97993605",
"9c123b0e1a70431f9591be85d7558c94",
"ad3ee7ad6dd74cb58bd56e1922ae4222",
"84b0129b27884b9ab3e2adb546e187be",
"3bca5dfbd30245e3bcb1679029e43ee1",
"306b444132cc468d97c9790239b1d575",
"131608806e1b4961b00b3466a8e5cfb6",
"34addc150cb34c4eb12cfdfda306d02e",
"c52f256812564e9c86103992ef58b7d6",
"e620c4205f1a4b6f864b04dc8ed5537f",
"435a7242c2f94623b02248a5a62233d1",
"b5f60bc339674d7aa7acfdfe67383b80",
"d098a67e44f9457bb272cfdf414e261a",
"f85c7036c48742d596c46975d110a29c",
"6d9683c5491b41b1860ad247d4ae71c6",
"009a3fd297ed40ada71cb8ab1fe003a4",
"2fc2fcad7f404120aa7c2848ee89ff80"
]
},
"id": "NhRoSf5WkZA8",
"outputId": "3833d69b-621a-4acd-89f3-0936be56b964"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Map(bottom=191647.0, center=[43.65049011666604, -69.82255300591171], controls=(WidgetControl(options=['positio…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "e02a65c8ee324a7b975ecc92c4ab15e6"
}
},
"metadata": {
"application/vnd.jupyter.widget-view+json": {
"colab": {
"custom_widget_manager": {
"url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/b3e629b1971e1542/manager.min.js"
}
}
}
}
}
],
"source": [
"#Citations:\n",
"# Amante, C. and B. W. Eakins, ETOPO1 1 Arc-Minute Global Relief Model: Procedures, Data Sources and Analysis. \n",
"# NOAA Technical Memorandum NESDIS NGDC-24, 19 pp, March 2009.\n",
"\n",
"# Import elevation dataset from GEE\n",
"dataset = ee.Image('NOAA/NGDC/ETOPO1')\n",
"bathymetry_clipped = dataset.clip(roi_test)\n",
"# Extract band 'bedrock' and rename it bathymetry for convenience\n",
"bathymetry = bathymetry_clipped.select('bedrock').rename('bathymetry')\n",
"# Add bathymetry band to deglinted and raw image\n",
"s2_deglint_masked = s2_deglint_masked.addBands(bathymetry)\n",
"\n",
"# Add NDVI-image to map\n",
"ndviParams = {min: -1, max: 1, 'palette': ['blue', 'white', 'green']}\n",
"Map.addLayer(ndvi_image, ndviParams, 'NDVI image')\n",
"\n",
"# Add bathymetry data on the map\n",
"bathymetryVis = {\n",
" 'min': -7000.0,\n",
" 'max': 3000.0,\n",
" 'palette': ['011de2', 'afafaf', '3603ff', 'fff477', 'b42109'],\n",
"}\n",
"Map.addLayer(bathymetry, bathymetryVis, 'bathymetry')\n",
"\n",
"\n",
"Map"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 67
},
"id": "FH3GBVaNpbop",
"outputId": "47864993-adbc-4630-8875-0e466ab3459e"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"| \n", " | B2 | \n", "B3 | \n", "B4 | \n", "B8 | \n", "NDVI | \n", "area | \n", "bathymetry | \n", "clusters | \n", "height | \n", "perimeter | \n", "width | \n", "Cover | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| min | \n", "4.648089 | \n", "19.761433 | \n", "7.502752 | \n", "14.029513 | \n", "-0.643138 | \n", "2.910087e+02 | \n", "-95.000000 | \n", "-2.143270e+09 | \n", "0.000090 | \n", "4.000000 | \n", "0.000269 | \n", "1.0 | \n", "
| max | \n", "424.446869 | \n", "586.466736 | \n", "314.722870 | \n", "1680.623169 | \n", "0.530570 | \n", "1.337740e+06 | \n", "9.000000 | \n", "2.141246e+09 | \n", "0.022638 | \n", "3303.000000 | \n", "0.022278 | \n", "3.0 | \n", "
| mean | \n", "151.851839 | \n", "172.319574 | \n", "65.210750 | \n", "128.288379 | \n", "-0.251607 | \n", "2.524283e+05 | \n", "-20.576017 | \n", "1.701418e+07 | \n", "0.006816 | \n", "741.305081 | \n", "0.008285 | \n", "2.0 | \n", "
| median | \n", "149.610626 | \n", "160.370346 | \n", "61.359627 | \n", "48.347687 | \n", "-0.247572 | \n", "1.489008e+05 | \n", "-8.000000 | \n", "8.095993e+07 | \n", "0.005929 | \n", "551.000000 | \n", "0.006648 | \n", "2.0 | \n", "
| \n", " | B2 | \n", "B3 | \n", "B4 | \n", "B8 | \n", "NDVI | \n", "area | \n", "bathymetry | \n", "clusters | \n", "height | \n", "perimeter | \n", "width | \n", "Cover | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| min | \n", "3.081182 | \n", "3.407706 | \n", "3.775116 | \n", "0.855829 | \n", "-0.943325 | \n", "4.326251e+02 | \n", "-169.000000 | \n", "-2.136294e+09 | \n", "0.000090 | \n", "6.000000 | \n", "0.000180 | \n", "1.0 | \n", "
| max | \n", "938.488831 | \n", "519.432922 | \n", "497.195038 | \n", "1134.019531 | \n", "0.817706 | \n", "1.508511e+06 | \n", "18.814028 | \n", "2.132384e+09 | \n", "0.020482 | \n", "3160.000000 | \n", "0.021829 | \n", "3.0 | \n", "
| mean | \n", "84.307340 | \n", "42.195296 | \n", "34.037155 | \n", "98.461466 | \n", "-0.413507 | \n", "2.217561e+05 | \n", "-47.036060 | \n", "2.356907e+07 | \n", "0.006413 | \n", "660.636856 | \n", "0.007403 | \n", "2.0 | \n", "
| median | \n", "13.884672 | \n", "11.637926 | \n", "7.754019 | \n", "8.075504 | \n", "-0.451971 | \n", "1.490917e+05 | \n", "-13.560373 | \n", "-4.968477e+07 | \n", "0.005839 | \n", "561.000000 | \n", "0.006692 | \n", "2.0 | \n", "
| \n", " | B2 | \n", "B3 | \n", "B4 | \n", "B8 | \n", "NDVI | \n", "bathymetry | \n", "Cover | \n", "
|---|---|---|---|---|---|---|---|
| min | \n", "11.445064 | \n", "72.611548 | \n", "7.959170 | \n", "4.000000 | \n", "-0.887324 | \n", "-95.00000 | \n", "1.0 | \n", "
| max | \n", "414.216802 | \n", "580.094922 | \n", "508.628516 | \n", "1204.000000 | \n", "0.275949 | \n", "9.00000 | \n", "3.0 | \n", "
| mean | \n", "157.683654 | \n", "176.932218 | \n", "65.909692 | \n", "53.607829 | \n", "-0.288229 | \n", "-20.99976 | \n", "2.0 | \n", "
| median | \n", "155.026305 | \n", "166.274654 | \n", "61.596720 | \n", "45.000000 | \n", "-0.283951 | \n", "-8.00000 | \n", "2.0 | \n", "
| \n", " | B2 | \n", "B3 | \n", "B4 | \n", "B8 | \n", "NDVI | \n", "bathymetry | \n", "Cover | \n", "
|---|---|---|---|---|---|---|---|
| min | \n", "11.445064 | \n", "72.611548 | \n", "7.959170 | \n", "4.000000 | \n", "-0.887324 | \n", "-95.00000 | \n", "1.0 | \n", "
| max | \n", "414.216802 | \n", "580.094922 | \n", "508.628516 | \n", "1204.000000 | \n", "0.275949 | \n", "9.00000 | \n", "3.0 | \n", "
| mean | \n", "157.683654 | \n", "176.932218 | \n", "65.909692 | \n", "53.607829 | \n", "-0.288229 | \n", "-20.99976 | \n", "2.0 | \n", "
| median | \n", "155.026305 | \n", "166.274654 | \n", "61.596720 | \n", "45.000000 | \n", "-0.283951 | \n", "-8.00000 | \n", "2.0 | \n", "
| \n", " | geometry | \n", "B2 | \n", "B3 | \n", "B4 | \n", "B8 | \n", "NDVI | \n", "bathymetry | \n", "Cover | \n", "
|---|---|---|---|---|---|---|---|---|
| 2127 | \n", "POINT (-69.84626 43.74277) | \n", "107.487388 | \n", "185.113466 | \n", "57.134909 | \n", "50 | \n", "-0.212598 | \n", "-1 | \n", "3 | \n", "
| 2163 | \n", "POINT (-70.12650 43.71369) | \n", "62.087794 | \n", "127.566923 | \n", "17.486048 | \n", "96 | \n", "0.263158 | \n", "-9 | \n", "3 | \n", "
| 1729 | \n", "POINT (-69.70015 43.87059) | \n", "210.095864 | \n", "305.280065 | \n", "88.270159 | \n", "25 | \n", "-0.593496 | \n", "-8 | \n", "2 | \n", "
| 2361 | \n", "POINT (-70.11682 43.71576) | \n", "141.756813 | \n", "208.260089 | \n", "63.621469 | \n", "34 | \n", "-0.387387 | \n", "-6 | \n", "3 | \n", "
| 542 | \n", "POINT (-69.07918 43.41019) | \n", "89.547932 | \n", "90.640032 | \n", "13.135080 | \n", "13 | \n", "-0.161290 | \n", "-156 | \n", "1 | \n", "
| \n", " | B2 | \n", "B3 | \n", "B4 | \n", "B8 | \n", "NDVI | \n", "area | \n", "bathymetry | \n", "clusters | \n", "height | \n", "perimeter | \n", "width | \n", "Cover | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "12.124972 | \n", "6.152216 | \n", "4.841733 | \n", "4.536298 | \n", "-0.608847 | \n", "78542.734375 | \n", "-152.421432 | \n", "-555143296 | \n", "0.004941 | \n", "416 | \n", "0.004222 | \n", "water | \n", "
| 1 | \n", "12.751205 | \n", "8.429532 | \n", "6.886879 | \n", "5.985725 | \n", "-0.587517 | \n", "898464.625000 | \n", "-163.301193 | \n", "-823210496 | \n", "0.014912 | \n", "2043 | \n", "0.016349 | \n", "water | \n", "
| 2 | \n", "310.981720 | \n", "382.838623 | \n", "463.150146 | \n", "688.335815 | \n", "0.012179 | \n", "20180.642578 | \n", "-3.000000 | \n", "-136047600 | \n", "0.003144 | \n", "68 | \n", "0.001168 | \n", "seagrass | \n", "
| 3 | \n", "13.633481 | \n", "9.480711 | \n", "7.263058 | \n", "7.786502 | \n", "-0.324886 | \n", "225692.234375 | \n", "-10.922240 | \n", "167464896 | \n", "0.005929 | \n", "772 | \n", "0.009522 | \n", "seaweed | \n", "
| 4 | \n", "16.298777 | \n", "13.743753 | \n", "9.256524 | \n", "15.451407 | \n", "-0.833239 | \n", "215768.625000 | \n", "-21.996683 | \n", "1505098368 | \n", "0.008714 | \n", "413 | \n", "0.006737 | \n", "seaweed | \n", "
| \n", " | Accuracy | \n", "Model | \n", "Dataset | \n", "
|---|---|---|---|
| 0 | \n", "0.57 | \n", "SML | \n", "1 | \n", "
| 1 | \n", "0.74 | \n", "SML | \n", "2 | \n", "
| 2 | \n", "0.75 | \n", "SML | \n", "3 | \n", "
| 3 | \n", "0.72 | \n", "SML | \n", "4 | \n", "
| 4 | \n", "0.73 | \n", "SML | \n", "5 | \n", "
| \n", " | SML | \n", "SSL | \n", "UML | \n", "
|---|---|---|---|
| Dataset | \n", "\n", " | \n", " | \n", " |
| 1 | \n", "0.57 | \n", "0.59 | \n", "0.12 | \n", "
| 2 | \n", "0.74 | \n", "0.76 | \n", "0.25 | \n", "
| 3 | \n", "0.75 | \n", "0.68 | \n", "0.19 | \n", "
| 4 | \n", "0.72 | \n", "0.74 | \n", "0.22 | \n", "
| 5 | \n", "0.73 | \n", "0.71 | \n", "0.07 | \n", "
| \n", " | PB | \n", "PB | \n", "GEOBIA | \n", "PB | \n", "GEOBIA | \n", "
|---|---|---|---|---|---|
| 0 | \n", "0.57 | \n", "0.74 | \n", "0.74 | \n", "0.71 | \n", "0.72 | \n", "
| 1 | \n", "0.59 | \n", "0.76 | \n", "0.68 | \n", "0.74 | \n", "0.71 | \n", "
| 2 | \n", "0.12 | \n", "0.25 | \n", "0.19 | \n", "0.22 | \n", "0.07 | \n", "
| \n", " | drop_SML | \n", "drop_SSL | \n", "
|---|---|---|
| Dataset | \n", "\n", " | \n", " |
| 1 | \n", "-0.10 | \n", "0.10 | \n", "
| 2 | \n", "-0.13 | \n", "-0.05 | \n", "
| 3 | \n", "-0.11 | \n", "-0.01 | \n", "
| 4 | \n", "-0.19 | \n", "-0.08 | \n", "
| 5 | \n", "-0.08 | \n", "0.02 | \n", "