Observation-Constrained Physical Snow Water Equivalent Simulations Using a Physics-Guided Machine Learning Approach
文献类型：期刊论文
| 作者 | Zhao, Wenli5; Fang, Jianing5; Yang, Tao4; Lian, Xu3; Winkler, Alexander J.1,2; Sun, Fubao4; Gentine, Pierre5 |
| 刊名 | WATER RESOURCES RESEARCH
 |
| 出版日期 | 2026-03-20 |
| 卷号 | 62期号:3页码:e2025WR041406 |
| 关键词 | snow water equivalent land surface model bias corrections machine learning hybrid model physics guided |
| ISSN号 | 0043-1397 |
| DOI | 10.1029/2025WR041406 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Estimating daily snow water equivalent (SWE) is critical for hydrological and climate applications, yet physical models often struggle to represent SWE, especially its interannual anomalies. In this study, we developed a hybrid physics-guided machine learning (ML) model (hybrid model), by augmenting the Community Land Model 4.0 SWE simulations with a long short-term memory (LSTM) network. The model is trained using the GlobSnow v3.0 data set and forced with meteorological data to estimate daily SWE at 0.5 degrees over the Northern Hemisphere (NH). Our results demonstrate that the hybrid model significantly outperforms both the standalone physical and pure ML models in predicting SWE magnitude, timing, and anomalies, especially in complex mountainous regions. Explainable ML analyses suggest that the hybrid approach leverages the snow-related physics while effectively utilizing observational data to enhance predictive accuracy. Moreover, we identify a widespread climate memory effect influencing SWE predictions across the NH, with memory-dominant extreme events leading to greater SWE losses or gains relative to the average impacts of all extreme events, including those without strong memory effects. These findings underscore the hybrid model's ability to correct memory-related biases that are not fully captured in current land surface models. Overall, our study highlights the value of hybrid modeling for improving SWE simulations and its potential as an alternative snow emulator within existing land surface models. |
| URL标识 | 查看原文 |
| WOS关键词 | MICROWAVE RADIOMETER DATA ; TIBETAN PLATEAU ; MODELS ; CLIMATE ; PRODUCTS ; COVER ; ERROR ; SPACE ; UNCERTAINTIES ; PERFORMANCE |
| WOS研究方向 | Environmental Sciences & Ecology ; Marine & Freshwater Biology ; Water Resources |
| 语种 | 英语 |
| WOS记录号 | WOS:001720397800001 |
| 出版者 | AMER GEOPHYSICAL UNION |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221188]  |
| 专题 | 陆地水循环及地表过程院重点实验室_外文论文 |
| 通讯作者 | Zhao, Wenli |
| 作者单位 | 1.ELLIS Jena Unit, Jena, Germany 2.Max Planck Inst Biogeochem, Jena, Germany; 3.Peking Univ, Coll Urban & Environm Sci, Beijing, Peoples R China; 4.Chinese Acad Sci, Key Lab Water Cycle & Related Land Surface Proc, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China; 5.Columbia Univ, Dept Earth & Environm Engn, New York, NY 10027 USA; |
| 推荐引用方式 GB/T 7714 | Zhao, Wenli,Fang, Jianing,Yang, Tao,et al. Observation-Constrained Physical Snow Water Equivalent Simulations Using a Physics-Guided Machine Learning Approach[J]. WATER RESOURCES RESEARCH,2026,62(3):e2025WR041406. |
| APA | Zhao, Wenli.,Fang, Jianing.,Yang, Tao.,Lian, Xu.,Winkler, Alexander J..,...&Gentine, Pierre.(2026).Observation-Constrained Physical Snow Water Equivalent Simulations Using a Physics-Guided Machine Learning Approach.WATER RESOURCES RESEARCH,62(3),e2025WR041406. |
| MLA | Zhao, Wenli,et al."Observation-Constrained Physical Snow Water Equivalent Simulations Using a Physics-Guided Machine Learning Approach".WATER RESOURCES RESEARCH 62.3(2026):e2025WR041406. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。