satellite-imagery

You can calculate NDVI time series directly in the cloud using Google Earth Engine and geemap, processing Sentinel-2 or Landsat datasets at planetary scale without downloading raw files. The Skill generates NDVI, EVI, and other indices for your defined region and time window.

Supervised land use land cover classification is best performed using Random Forest algorithms via Google Earth Engine and geemap. This Skill applies Random Forest to your training labels over satellite imagery to classify land cover types and export the results as GeoTIFF.

Bitemporal change detection compares satellite imagery from two distinct time windows to quantify and classify change intensity. This Skill uses Google Earth Engine to process bitemporal images, identifying where vegetation or land cover changed between periods like 2018 and 2023.

Yes, you need the earthengine-api and geemap Python dependencies to run this workflow and export GeoTIFF raster files. The Skill relies on Earth Engine batch tasks to export classified land cover and change detection products for GIS workflows.

Yes, you can use Sentinel-2 and Landsat-style band sets for vegetation monitoring in Google Earth Engine. This Skill processes these datasets to generate vegetation indices like NDVI and EVI, enabling time series analysis over your selected area of interest.