首个覆盖17年的大规模高光谱地球观测数据集，支持长期时空建模。
ChronoEarth-492K: A Large Scale and Long Horizon Spatiotemporal Hyperspectral Earth Observation Dataset and Benchmark
- 基于NASA EO-1任务构建492,354个辐射定标影像块，覆盖全球18.5万点位
- 包含28,786个站点的多时相序列，支持短/长时序分析，最长跨度达17年
- 配套统一评测基准，适用于地表覆盖、作物类型等多类遥感任务
高光谱成像（HSI）为地表提供密集光谱信息，有助于实现地表覆盖与生态系统动态的材料级理解。尽管高光谱自监督学习（SSL）取得进展，现有数据集仍存在时间深度不足的问题，制约了长时序时空建模的发展。为此，我们提出ChronoEarth-492K，首个基于NASA EO-1 Hyperion任务的大规模、时间校准的高光谱自监督学习数据集，该任务是迄今持续时间最长的全球高光谱档案（2001–2017）。ChronoEarth-492K包含492,354个辐射定标图像块，覆盖185,398个全球位置，历时17年，其中28,786个站点具有≥3次观测的多时相序列，可支持短时序与长时序分析。在此基础上，我们建立ChronoEarth-Benchmark，一个涵盖静态、短时序和长时序任务的统一评估体系，基于六个开源地理空间产品构建，覆盖土地覆盖、作物类型、森林动态与土壤属性。我们还提出标准化评估协议，并报告多种先进高光谱基础模型的基线结果。整体而言，ChronoEarth及其基准为系统性时空高光谱表征学习提供了首个大规模、时间对齐的平台。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。