基于领域对抗神经网络的机器学习蒸散模型的可外推性改进

IF 4.8 2区 环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Haiyang Shi, Ximing Cai
{"title":"基于领域对抗神经网络的机器学习蒸散模型的可外推性改进","authors":"Haiyang Shi,&nbsp;Ximing Cai","doi":"10.1016/j.envsoft.2025.106383","DOIUrl":null,"url":null,"abstract":"<div><div>Machine learning-based evapotranspiration (ET) models capture complex nonlinear relationships but struggle with global extrapolation due to unbalanced data distribution, limiting accurate ET assessments crucial for understanding water and energy cycles. This study used Domain-Adversarial Neural Networks (DANN) to improve the geographical adaptability of ET models by mitigating site-level distributional discrepancies. DANN significantly enhanced ET prediction accuracy, with a median Kling-Gupta Efficiency (KGE) increase of 0.27 (p &lt; 0.001) and with a range from 0.06 to 0.58 for the middle 90% values compared to the traditional Leave-One-Out (LOO) method. DANN proves particularly effective for isolated sites and biome transition zones, reducing errors and avoiding low-accuracy predictions. By leveraging data from resource-rich areas, DANN strengthens the reliability of global-scale ET products, especially in ungauged regions. Future evaluations and improvements are necessary, such as using additional accuracy metrics beyond KGE and focusing on sites located at the intersection of several climate types and sites with unique soil-vegetation-atmosphere processes. This study demonstrates the potential of domain adaptation techniques to enhance the generalization and extrapolation capabilities of machine learning in hydrological predictions.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"187 ","pages":"Article 106383"},"PeriodicalIF":4.8000,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Extrapolability improvement of machine learning-based evapotranspiration models via domain-adversarial neural networks\",\"authors\":\"Haiyang Shi,&nbsp;Ximing Cai\",\"doi\":\"10.1016/j.envsoft.2025.106383\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Machine learning-based evapotranspiration (ET) models capture complex nonlinear relationships but struggle with global extrapolation due to unbalanced data distribution, limiting accurate ET assessments crucial for understanding water and energy cycles. This study used Domain-Adversarial Neural Networks (DANN) to improve the geographical adaptability of ET models by mitigating site-level distributional discrepancies. DANN significantly enhanced ET prediction accuracy, with a median Kling-Gupta Efficiency (KGE) increase of 0.27 (p &lt; 0.001) and with a range from 0.06 to 0.58 for the middle 90% values compared to the traditional Leave-One-Out (LOO) method. DANN proves particularly effective for isolated sites and biome transition zones, reducing errors and avoiding low-accuracy predictions. By leveraging data from resource-rich areas, DANN strengthens the reliability of global-scale ET products, especially in ungauged regions. Future evaluations and improvements are necessary, such as using additional accuracy metrics beyond KGE and focusing on sites located at the intersection of several climate types and sites with unique soil-vegetation-atmosphere processes. This study demonstrates the potential of domain adaptation techniques to enhance the generalization and extrapolation capabilities of machine learning in hydrological predictions.</div></div>\",\"PeriodicalId\":310,\"journal\":{\"name\":\"Environmental Modelling & Software\",\"volume\":\"187 \",\"pages\":\"Article 106383\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2025-02-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Modelling & Software\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1364815225000672\",\"RegionNum\":2,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Modelling & Software","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1364815225000672","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

基于机器学习的蒸散发(ET)模型捕捉复杂的非线性关系,但由于数据分布不平衡,难以进行全球外推,限制了准确的蒸散发评估,这对理解水和能源循环至关重要。本研究利用域对抗神经网络(DANN),通过减轻站点级分布差异来提高ET模型的地理适应性。DANN显著提高了ET的预测精度,KGE中位数提高了0.27 (p <;0.001),与传统的Leave-One-Out (LOO)方法相比,中间90%值的范围为0.06至0.58。事实证明,DANN对孤立的站点和生物群落过渡区特别有效,可以减少错误并避免低准确性的预测。通过利用来自资源丰富地区的数据,DANN加强了全球尺度ET产品的可靠性,特别是在未测量的地区。未来的评估和改进是必要的,例如使用KGE以外的额外精度指标,并关注位于几种气候类型交叉点和具有独特土壤-植被-大气过程的站点。本研究展示了领域适应技术在增强水文预测中机器学习的泛化和外推能力方面的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Extrapolability improvement of machine learning-based evapotranspiration models via domain-adversarial neural networks
Machine learning-based evapotranspiration (ET) models capture complex nonlinear relationships but struggle with global extrapolation due to unbalanced data distribution, limiting accurate ET assessments crucial for understanding water and energy cycles. This study used Domain-Adversarial Neural Networks (DANN) to improve the geographical adaptability of ET models by mitigating site-level distributional discrepancies. DANN significantly enhanced ET prediction accuracy, with a median Kling-Gupta Efficiency (KGE) increase of 0.27 (p < 0.001) and with a range from 0.06 to 0.58 for the middle 90% values compared to the traditional Leave-One-Out (LOO) method. DANN proves particularly effective for isolated sites and biome transition zones, reducing errors and avoiding low-accuracy predictions. By leveraging data from resource-rich areas, DANN strengthens the reliability of global-scale ET products, especially in ungauged regions. Future evaluations and improvements are necessary, such as using additional accuracy metrics beyond KGE and focusing on sites located at the intersection of several climate types and sites with unique soil-vegetation-atmosphere processes. This study demonstrates the potential of domain adaptation techniques to enhance the generalization and extrapolation capabilities of machine learning in hydrological predictions.
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
Environmental Modelling & Software
Environmental Modelling & Software 工程技术-工程:环境
CiteScore
9.30
自引率
8.20%
发文量
241
审稿时长
60 days
期刊介绍: Environmental Modelling & Software publishes contributions, in the form of research articles, reviews and short communications, on recent advances in environmental modelling and/or software. The aim is to improve our capacity to represent, understand, predict or manage the behaviour of environmental systems at all practical scales, and to communicate those improvements to a wide scientific and professional audience.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信