This repository contains code and data for a geospatial intelligence workshop covering unsupervised land cover classification with Sentinel-2 data.
Make sure you have the following installed on your local machine:
Docker: Install Docker on your machine by following the instructions provided here.
-
Clone the repository:
git clone https://github.com/Romanian-Space-Initiative/Geospatial-Intelligence-Workshop.git cd Geospatial-Intelligence-Workshop/webapp -
Build the Docker container:
docker-compose build
-
Run the Docker container:
docker-compose up
-
Open your web browser and go to http://localhost:5001 to access the web application.
For the first part of the workshop, we will use a Google Colab notebook. Follow these steps:
-
Open a new notebook using your Google account(and if you do not have one, please create it): Google Colab.
-
Download the following files locally(This is already done if you cloned the repository on you computer):
- All .tif images from the "S2_data" folder
- All files from the "ValidationData" folder
- The notebook "Sentinel2_unsupervised_classification.ipynb"
-
In Google Colab, click on File -> Upload notebook and upload the "Sentinel2_unsupervised_classification.ipynb" notebook.
-
In the Files tab on the left, create a new folder named "S2_data." Upload the .tif images to this folder using the three dots menu.
-
Upload each file from the "ValidationData" folder separately.
Note: Allow all files to fully upload before proceeding.
-
Run the cells in the notebook to perform the unsupervised land cover classification with Sentinel-2 data.
webapp/: Contains the Flask web application code.satellite_data/: Contains Jupyter notebook for unsupervised land cover classification with Sentinel-2 data.validation_data/: Contains files for validation data points.
Feel free to reach out if you have any issues or questions!