LULC Automation using Machine Learning

• Tech Stack: Python, Github, Rasterio, Geopandas, Matplotlib, JupyterNotebook, Colab, GEE, Microsoft Azure, Streamlit, Flask, Tensorlow, QGIS
• Project Duration: 8 Weeks
• Github URL: Project Link
• Certificate URL: My Project Certificate

Mapping the extent of land use and land cover categories over time is essential for better environmental monitoring, urban planning, nature protection, conflict prevention, disaster reduction, rescue planning as well as long-term climate adaptation efforts.

This initiative was aimed at building a machine learning model that can accurately classify Land Use and Land Cover Changes (LULC) in satellite imagery. The trained model automatically generates the LULC map for a given region of interest. The map is visualized in a streamlit application.

Members: Joseph Moturi, .

More information available on Github.