This project demonstrates how to use ChatGPT-generated prompts and the Google Earth Engine JavaScript API to build a series of practical geospatial analyses. It follows exercises from the course "Introduction to Geospatial Data Analysis with ChatGPT and Google Earth Engine", applying real-world use cases like vegetation monitoring, air quality assessment, drought mapping, flood detection, and urban planning.
- Urban and Vegetation Dynamics in Vietnam
- Air Quality Assessment over New Delhi
- Spatiotemporal Drought Monitoring in Indonesia
- Flood Monitoring and Damage Assessment
- Urban Green Space Analysis in Indonesian Cities
- Landsat 8 TOA:
LANDSAT/LC08/C02/T1_TOA - MODIS NDVI:
MODIS/061/MOD13A2 - MODIS LST:
MODIS/061/MOD11A1 - MODIS ET & PET:
MODIS/061/MOD16A2 - Sentinel-5P NO2:
COPERNICUS/S5P/NRTI/L3_NO2 - Sentinel-1 SAR GRD:
COPERNICUS/S1_GRD - GHS Population:
JRC/GHSL/P2023A/GHS_POP - Country boundaries:
USDOS/LSIB_SIMPLE/2017,CGAZ_ADM1 - Sentinel-2 Surface Reflectance data:
COPERNICUS/S2_SR_HARMONIZED - Global Administrative Unit Layers:
FAO/GAUL/2015/level2 - Open Buildings V3 – global building footprint dataset:
GOOGLE/Research/open-buildings/v3/polygons
- Course: Introduction to Geospatial Data Analysis with ChatGPT and Google Earth Engine
- Platform: United Nations University
- Prompt-based Analysis: Powered by ChatGPT + GEE JavaScript API
This project is a hands-on effort to blend AI tools with geospatial science. All results were derived using AI-generated coding prompts and GEE best practices.