Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.15666 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913131999002624 |
|---|---|
| author | Si, Haozhe Wan, Yuxuan Wang, Yuqing Do, Minh Zhao, Han |
| author_facet | Si, Haozhe Wan, Yuxuan Wang, Yuqing Do, Minh Zhao, Han |
| contents | Hyperspectral imaging (HSI) provides dense spectral information for the Earth's surface, enabling material-level understanding of land cover and ecosystem dynamics. Despite recent progress in hyperspectral self-supervised learning (SSL), existing datasets remain temporally shallow, limiting the development of long-horizon spatiotemporal modeling. To address this gap, we introduce ChronoEarth-492K, the first large-scale, temporally calibrated hyperspectral SSL dataset built upon NASA's EO-1 Hyperion mission, the world's longest continuous hyperspectral archive up to date (2001-2017). ChronoEarth-492K comprises 492,354 radiometrically harmonized patches across 185,398 global locations over 17 years, with 28,786 sites containing multi-temporal sequences ($\geq 3$ observations) that enable both short- and long-horizon temporal analysis. Building on this foundation, we establish the ChronoEarth-Benchmark, a unified evaluation suite spanning static, short-horizon, and long-horizon temporal tasks, constructed from six open-source geospatial products covering land cover, crop type, forest dynamics, and soil properties. We further introduce a standardized evaluation protocol and report extensive baseline results across state-of-the-art hyperspectral foundation models. Together, ChronoEarth and benchmark provide the first large-scale, temporally grounded platform for systematic spatiotemporal hyperspectral representation learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15666 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ChronoEarth-492K: A Large Scale and Long Horizon Spatiotemporal Hyperspectral Earth Observation Dataset and Benchmark Si, Haozhe Wan, Yuxuan Wang, Yuqing Do, Minh Zhao, Han Computer Vision and Pattern Recognition Hyperspectral imaging (HSI) provides dense spectral information for the Earth's surface, enabling material-level understanding of land cover and ecosystem dynamics. Despite recent progress in hyperspectral self-supervised learning (SSL), existing datasets remain temporally shallow, limiting the development of long-horizon spatiotemporal modeling. To address this gap, we introduce ChronoEarth-492K, the first large-scale, temporally calibrated hyperspectral SSL dataset built upon NASA's EO-1 Hyperion mission, the world's longest continuous hyperspectral archive up to date (2001-2017). ChronoEarth-492K comprises 492,354 radiometrically harmonized patches across 185,398 global locations over 17 years, with 28,786 sites containing multi-temporal sequences ($\geq 3$ observations) that enable both short- and long-horizon temporal analysis. Building on this foundation, we establish the ChronoEarth-Benchmark, a unified evaluation suite spanning static, short-horizon, and long-horizon temporal tasks, constructed from six open-source geospatial products covering land cover, crop type, forest dynamics, and soil properties. We further introduce a standardized evaluation protocol and report extensive baseline results across state-of-the-art hyperspectral foundation models. Together, ChronoEarth and benchmark provide the first large-scale, temporally grounded platform for systematic spatiotemporal hyperspectral representation learning. |
| title | ChronoEarth-492K: A Large Scale and Long Horizon Spatiotemporal Hyperspectral Earth Observation Dataset and Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.15666 |