数据有限流域的可微物理水文模型及其评价

IF 5.9 1区 地球科学 Q1 ENGINEERING, CIVIL Journal of Hydrology Pub Date : 2024-12-02 DOI:10.1016/j.jhydrol.2024.132471
Wenyu Ouyang, Lei Ye, Yikai Chai, Haoran Ma, Jinggang Chu, Yong Peng, Chi Zhang
{"title":"数据有限流域的可微物理水文模型及其评价","authors":"Wenyu Ouyang, Lei Ye, Yikai Chai, Haoran Ma, Jinggang Chu, Yong Peng, Chi Zhang","doi":"10.1016/j.jhydrol.2024.132471","DOIUrl":null,"url":null,"abstract":"Recent advancements in deep learning (DL) have significantly improved hydrological modeling by extracting generalities from large-sample datasets and enhancing predictive accuracy. However, DL models often rely heavily on large volumes of data, which are often unavailable or insufficient in many real-world hydrological applications. This challenge has prompted interest in integrating DL with physically based hydrological models (PBHMs). This study explores such integration using differentiable programming with the Xin’anjiang model. We introduce two advanced model variants: the differentiable Xin’anjiang model (dXAJ), which retains the Xin’anjiang model’s structure while incorporating Long Short-Term Memory (LSTM) networks for parameter learning, and the dXAJ<ce:inf loc=\"post\">nn</ce:inf> model, which replaces the traditional evapotranspiration module of dXAJ model with a neural network. Both models were evaluated against the evolutionary algorithm-calibrated XAJ model (eXAJ) across five basins in the Three Gorge region of China and eight basins from the CAMELS dataset under varying data-limited conditions. Our results showed that both dXAJ and dXAJ<ce:inf loc=\"post\">nn</ce:inf> models outperformed the eXAJ model in streamflow prediction accuracy as they have different optimization mechanism, demonstrating that the local optimization mechanism in differentiable models (DMs) tends to generalize better during validation than global optimization approaches in data-limited contexts. The DMs also provided reliable evapotranspiration estimates, even without using evapotranspiration data for calibration. Although the dXAJ<ce:inf loc=\"post\">nn</ce:inf> model offered greater flexibility, it did not consistently yield better results and exhibited a tendency toward overfitting in certain basins. The study also found that both models require a minimum of three years of training data (including a one-year warm-up period) to achieve acceptable predictive performance, with longer data records further preventing overfitting. These findings underscore the ability of DMs to effectively balance data-driven techniques and physical mechanisms, highlighting the importance of sufficient training data.","PeriodicalId":362,"journal":{"name":"Journal of Hydrology","volume":"24 1","pages":""},"PeriodicalIF":5.9000,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A differentiable, physics-based hydrological model and its evaluation for data-limited basins\",\"authors\":\"Wenyu Ouyang, Lei Ye, Yikai Chai, Haoran Ma, Jinggang Chu, Yong Peng, Chi Zhang\",\"doi\":\"10.1016/j.jhydrol.2024.132471\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent advancements in deep learning (DL) have significantly improved hydrological modeling by extracting generalities from large-sample datasets and enhancing predictive accuracy. However, DL models often rely heavily on large volumes of data, which are often unavailable or insufficient in many real-world hydrological applications. This challenge has prompted interest in integrating DL with physically based hydrological models (PBHMs). This study explores such integration using differentiable programming with the Xin’anjiang model. We introduce two advanced model variants: the differentiable Xin’anjiang model (dXAJ), which retains the Xin’anjiang model’s structure while incorporating Long Short-Term Memory (LSTM) networks for parameter learning, and the dXAJ<ce:inf loc=\\\"post\\\">nn</ce:inf> model, which replaces the traditional evapotranspiration module of dXAJ model with a neural network. Both models were evaluated against the evolutionary algorithm-calibrated XAJ model (eXAJ) across five basins in the Three Gorge region of China and eight basins from the CAMELS dataset under varying data-limited conditions. Our results showed that both dXAJ and dXAJ<ce:inf loc=\\\"post\\\">nn</ce:inf> models outperformed the eXAJ model in streamflow prediction accuracy as they have different optimization mechanism, demonstrating that the local optimization mechanism in differentiable models (DMs) tends to generalize better during validation than global optimization approaches in data-limited contexts. The DMs also provided reliable evapotranspiration estimates, even without using evapotranspiration data for calibration. Although the dXAJ<ce:inf loc=\\\"post\\\">nn</ce:inf> model offered greater flexibility, it did not consistently yield better results and exhibited a tendency toward overfitting in certain basins. The study also found that both models require a minimum of three years of training data (including a one-year warm-up period) to achieve acceptable predictive performance, with longer data records further preventing overfitting. These findings underscore the ability of DMs to effectively balance data-driven techniques and physical mechanisms, highlighting the importance of sufficient training data.\",\"PeriodicalId\":362,\"journal\":{\"name\":\"Journal of Hydrology\",\"volume\":\"24 1\",\"pages\":\"\"},\"PeriodicalIF\":5.9000,\"publicationDate\":\"2024-12-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Hydrology\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1016/j.jhydrol.2024.132471\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hydrology","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1016/j.jhydrol.2024.132471","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

摘要

深度学习(DL)的最新进展通过从大样本数据集中提取一般性并提高预测准确性,显著改善了水文建模。然而,深度学习模型通常严重依赖于大量数据,而这些数据在许多现实世界的水文应用中往往不可用或不足。这一挑战激发了人们将深度学习与基于物理的水文模型(phhm)相结合的兴趣。本研究利用可微规划与新安江模型探讨这种整合。我们引入了两种先进的模型变体:可微新安江模型(dXAJ),它保留了新安江模型的结构,同时结合了长短期记忆(LSTM)网络进行参数学习;以及dXAJnn模型,它用神经网络取代了dXAJ模型的传统蒸散发模块。在不同的数据限制条件下,利用演化算法校准的XAJ模型(eXAJ)对中国三峡地区5个流域和骆驼数据集8个流域进行了评估。结果表明,由于具有不同的优化机制,dXAJ和dXAJnn模型在流量预测精度上都优于eXAJ模型,这表明在数据有限的情况下,可微模型中的局部优化机制往往比全局优化方法在验证过程中具有更好的泛化能力。即使没有使用蒸散发数据进行校准,DMs也提供了可靠的蒸散发估计。尽管dXAJnn模型提供了更大的灵活性,但它并不能始终得到更好的结果,并且在某些盆地中表现出过拟合的趋势。研究还发现,这两种模型都需要至少三年的训练数据(包括一年的预热期)才能达到可接受的预测性能,更长的数据记录进一步防止过拟合。这些发现强调了dm有效平衡数据驱动技术和物理机制的能力,强调了足够的训练数据的重要性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A differentiable, physics-based hydrological model and its evaluation for data-limited basins
Recent advancements in deep learning (DL) have significantly improved hydrological modeling by extracting generalities from large-sample datasets and enhancing predictive accuracy. However, DL models often rely heavily on large volumes of data, which are often unavailable or insufficient in many real-world hydrological applications. This challenge has prompted interest in integrating DL with physically based hydrological models (PBHMs). This study explores such integration using differentiable programming with the Xin’anjiang model. We introduce two advanced model variants: the differentiable Xin’anjiang model (dXAJ), which retains the Xin’anjiang model’s structure while incorporating Long Short-Term Memory (LSTM) networks for parameter learning, and the dXAJnn model, which replaces the traditional evapotranspiration module of dXAJ model with a neural network. Both models were evaluated against the evolutionary algorithm-calibrated XAJ model (eXAJ) across five basins in the Three Gorge region of China and eight basins from the CAMELS dataset under varying data-limited conditions. Our results showed that both dXAJ and dXAJnn models outperformed the eXAJ model in streamflow prediction accuracy as they have different optimization mechanism, demonstrating that the local optimization mechanism in differentiable models (DMs) tends to generalize better during validation than global optimization approaches in data-limited contexts. The DMs also provided reliable evapotranspiration estimates, even without using evapotranspiration data for calibration. Although the dXAJnn model offered greater flexibility, it did not consistently yield better results and exhibited a tendency toward overfitting in certain basins. The study also found that both models require a minimum of three years of training data (including a one-year warm-up period) to achieve acceptable predictive performance, with longer data records further preventing overfitting. These findings underscore the ability of DMs to effectively balance data-driven techniques and physical mechanisms, highlighting the importance of sufficient training data.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Hydrology
Journal of Hydrology 地学-地球科学综合
CiteScore
11.00
自引率
12.50%
发文量
1309
审稿时长
7.5 months
期刊介绍: The Journal of Hydrology publishes original research papers and comprehensive reviews in all the subfields of the hydrological sciences including water based management and policy issues that impact on economics and society. These comprise, but are not limited to the physical, chemical, biogeochemical, stochastic and systems aspects of surface and groundwater hydrology, hydrometeorology and hydrogeology. Relevant topics incorporating the insights and methodologies of disciplines such as climatology, water resource systems, hydraulics, agrohydrology, geomorphology, soil science, instrumentation and remote sensing, civil and environmental engineering are included. Social science perspectives on hydrological problems such as resource and ecological economics, environmental sociology, psychology and behavioural science, management and policy analysis are also invited. Multi-and interdisciplinary analyses of hydrological problems are within scope. The science published in the Journal of Hydrology is relevant to catchment scales rather than exclusively to a local scale or site.
期刊最新文献
Evolution patterns, driving mechanisms, and ecological indicative effects of 730 lakes water color in the Yangtze River Basin (1984–2023) Hydrological connectivity and biogeochemical dynamics in the function and management of the lower Oder floodplain Urban real-time rainfall-runoff prediction using adaptive SSA-decomposition with dual attention Geochemical behavior of high-level radium contamination in representative coastal saltworks LSTM-FKAN coupled with feature extraction technique for Precipitation–Runoff modeling
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1