构建跨大陆水体变化数据集，提升长期水动态预测能力
HydroChronos: Forecasting Decades of Surface Water Change
- 融合遥感、气候与地形数据，构建三十年多模态时空数据集
- 新模型比基准模型在变化检测上提升14%的F1值
- 揭示关键气候变量影响，助力未来水文建模优化
表面水体动态预测对水资源管理和气候变化适应至关重要，但领域内缺乏全面的数据集和标准化基准。本文提出HydroChronos，一个大规模、多模态时空数据集，用于表面水体动态预测，填补该空白。数据集涵盖欧洲、北美和南美多样湖泊与河流超过三十年的对齐Landsat 5与Sentinel-2影像、气候数据及数字高程模型。我们还提出了AquaClimaTempo UNet，一种具有专用气候数据分支的新型时空架构，作为强基准。该模型在变化检测与变化方向分类任务中分别比持续性基准提升14%和11%的F1值，在变化幅度回归任务中降低0.1 MAE。最后，通过可解释AI分析，识别出影响水体变化的关键气候变量与输入通道，为未来建模提供指导。
原文摘要 · Abstract (English)
Forecasting surface water dynamics is crucial for water resource management and climate change adaptation. However, the field lacks comprehensive datasets and standardized benchmarks. In this paper, we introduce HydroChronos, a large-scale, multi-modal spatiotemporal dataset for surface water dynamics forecasting designed to address this gap. We couple the dataset with three forecasting tasks. The dataset includes over three decades of aligned Landsat 5 and Sentinel-2 imagery, climate data, and Digital Elevation Models for diverse lakes and rivers across Europe, North America, and South America. We also propose AquaClimaTempo UNet, a novel spatiotemporal architecture with a dedicated climate data branch, as a strong benchmark baseline. Our model significantly outperforms a Persistence baseline for forecasting future water dynamics by +14% and +11% F1 across change detection and direction of change classification tasks, and by +0.1 MAE on the magnitude of change regression. Finally, we conduct an Explainable AI analysis to identify the key climate variables and input channels that influence surface water change, providing insights to inform and guide future modeling efforts.
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。