TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916890145718272 |
|---|---|
| author | Faruk, Tanjim Bin Matin, Abdul Pallickara, Shrideep Pallickara, Sangmi Lee |
| author_facet | Faruk, Tanjim Bin Matin, Abdul Pallickara, Shrideep Pallickara, Sangmi Lee |
| contents | 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-supervised Masked Autoencoders excel on RGB and low-band multispectral data, they struggle to exploit the intricate spatial-spectral correlations in 200+ band hyperspectral images. We introduce TerraMAE, a novel HSI encoding framework specifically designed to learn highly representative spatial-spectral embeddings for diverse geospatial analyses. TerraMAE features an adaptive channel grouping strategy, based on statistical reflectance properties to capture spectral similarities, and an enhanced reconstruction loss function that incorporates spatial and spectral quality metrics. We demonstrate TerraMAE's effectiveness through superior spatial-spectral information preservation in high-fidelity image reconstruction. Furthermore, we validate its practical utility and the quality of its learned representations through strong performance on three key downstream geospatial tasks: crop identification, land cover classification, and soil texture prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07020 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders Faruk, Tanjim Bin Matin, Abdul Pallickara, Shrideep Pallickara, Sangmi Lee Computer Vision and Pattern Recognition Machine Learning 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-supervised Masked Autoencoders excel on RGB and low-band multispectral data, they struggle to exploit the intricate spatial-spectral correlations in 200+ band hyperspectral images. We introduce TerraMAE, a novel HSI encoding framework specifically designed to learn highly representative spatial-spectral embeddings for diverse geospatial analyses. TerraMAE features an adaptive channel grouping strategy, based on statistical reflectance properties to capture spectral similarities, and an enhanced reconstruction loss function that incorporates spatial and spectral quality metrics. We demonstrate TerraMAE's effectiveness through superior spatial-spectral information preservation in high-fidelity image reconstruction. Furthermore, we validate its practical utility and the quality of its learned representations through strong performance on three key downstream geospatial tasks: crop identification, land cover classification, and soil texture prediction. |
| title | TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.07020 |