TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders

Tanjim Bin Faruk, Abdul Matin, Shrideep Pallickara +1

Hyperspectral satellite imagery offers sub-30 m views of Earth in hundreds of contiguous spectral bands, enabling fine-grained mapping of soils, crops, and land cover. While self-s…