Source codes for groundwater pumping prediction using integrated remote sensing datasets and machine learning

Official code: "Integrating Segment Anything Model derived boundary prior and high-level semantics for cropland extraction from high-resolution remote sensing images

Public repository of our work in the search for an optimal multi-view crop classifier (considering encoder architectures and fusion strategies)

Current available solutions eg #WorldCover apply inconsistent "cropland" definitions from #FAOSATA’s and are rarely up to date. This work focused on building cost effective classification for cropland mapping for #Sudan, #Iran & #Afghanistan regions. For Afghanistan we focused on temporal classification while for the rest year-long classification

Exploring and detecting farm plots in KAZA in collaboration with WWF Germany's Space+Science Team