arXiv cs.AI· Pengfei Qu, Lei Ye, Wenyu Ouyang, Chi Zhang, Yikai Chai, Shuolong Xu, Yongri Piao, Miao Zhang, Huchuan Lu·· 4 小时前AI 评分23
利用 AlphaEarth 地球基础模型嵌入提升水文模型的径流模拟性能
Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings
AI 导读
一项发表于 arXiv 的研究评估了 64 维 AlphaEarth Foundations（AEF）嵌入作为新的静态流域表征，在 CAMELS 数据集上检验其对径流预测的价值。结果显示，AEF 嵌入在样本外设置下比 CAMELS 属性更稳健，样本内性能则几乎相同；在 100 个目标流域的非观测流域预测中，AEF 静态输入总体提升了性能。研究认为地球基础模型嵌入为非观测流域预测提供了可迁移的表征。
正文 · 原文
Abstract:Accurate prediction in ungauged basins (PUB) requires effective transfer across hydrologically diverse regions. While deep learning has advanced large-sample hydrological modeling, its cross-regional generalization depends in part on the static basin descriptors used to guide model behavior. Earth Foundation Models (EFMs) provide a promising alternative by learning environmental representations from multi-modal satellite data. In this study, we evaluate the 64-dimensional AlphaEarth Foundations (AEF) embeddings as a new form of static basin representation and assess their value for streamflow prediction under both in-sample (IS) and out-of-sample (OOS) settings using the CAMELS dataset. Results show that AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance. Mutual-information analysis reveals statistical associations between AEF embeddings and conventional catchment attributes related to terrain, vegetation, and rooting characteristics. We further investigate similarity-based donor-basin selection for PUB using CAMELS attributes and AEF embeddings. Across 100 target basins, AEF static inputs generally improved PUB performance. With AEF inputs, similarity-based donor selection outperformed random selection for smaller donor pools, but its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance. Leave-one-cluster-out experiments showed AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training. Overall, this study demonstrates that Earth Foundation Model embeddings provide a transferable representation for PUB prediction and underscores the importance of basin representation quality and donor pool design, motivating future research toward unified hydrological foundation models.
| Comments: | 26 pages, 10 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2601.01558 [cs.LG] |
| (or arXiv:2601.01558v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2601.01558 arXiv-issued DOI via DataCite |
Submission history
From: Wenyu Ouyang [view email]
[v1]
Sun, 4 Jan 2026 15:14:16 UTC (7,997 KB)
[v2]
Wed, 1 Jul 2026 07:18:11 UTC (8,369 KB)
[v3]
Wed, 4 Nov 2026 11:43:31 UTC (6,636 KB)
来源：arXiv cs.AI · arxiv.org