基于物理和人工智能的降雨-径流-泥沙过程建模混合模型

IF 2.8 3区 环境科学与生态学 Q2 WATER RESOURCES Hydrological Sciences Journal-Journal Des Sciences Hydrologiques Pub Date : 2023-07-27 DOI:10.1080/02626667.2023.2241850
G. Gelete, Vahid Nourani, H. Gokçekuş, Tagesse Gichamo
{"title":"基于物理和人工智能的降雨-径流-泥沙过程建模混合模型","authors":"G. Gelete, Vahid Nourani, H. Gokçekuş, Tagesse Gichamo","doi":"10.1080/02626667.2023.2241850","DOIUrl":null,"url":null,"abstract":"ABSTRACT This study evaluates the performance of the Hydrologic Engineering Center-Hydrologic Modelling System (HEC-HMS), Hydrologiska Byråns Vattenbalansavdelning (HBV), Soil and Water Assessment Tool (SWAT), feedforward neural network (FFNN), adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR) and multilinear regression (MLR) for modelling the rainfall–runoff–sediment process in Katar catchment, Ethiopia. Afterward, neural network ensemble (NE), weighted average ensemble (WE) and simple average ensemble (SE) techniques were developed to improve the performance of single models. The performance of the models was evaluated using Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE) and mean absolute error (MAE). The results show that the ANFIS model outperformed the other single models for rainfall–runoff–sediment modelling. Moreover, the integration of artificial intelligence and physically-based models resulted in improved performance, with the NE technique demonstrating better accuracy by improving individual models by 5.8–27.6% for rainfall–runoff and 3.59–37.9% for suspended sediment load modelling in the validation phase.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Physical and artificial intelligence-based hybrid models for rainfall–runoff–sediment process modelling\",\"authors\":\"G. Gelete, Vahid Nourani, H. Gokçekuş, Tagesse Gichamo\",\"doi\":\"10.1080/02626667.2023.2241850\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT This study evaluates the performance of the Hydrologic Engineering Center-Hydrologic Modelling System (HEC-HMS), Hydrologiska Byråns Vattenbalansavdelning (HBV), Soil and Water Assessment Tool (SWAT), feedforward neural network (FFNN), adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR) and multilinear regression (MLR) for modelling the rainfall–runoff–sediment process in Katar catchment, Ethiopia. Afterward, neural network ensemble (NE), weighted average ensemble (WE) and simple average ensemble (SE) techniques were developed to improve the performance of single models. The performance of the models was evaluated using Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE) and mean absolute error (MAE). The results show that the ANFIS model outperformed the other single models for rainfall–runoff–sediment modelling. Moreover, the integration of artificial intelligence and physically-based models resulted in improved performance, with the NE technique demonstrating better accuracy by improving individual models by 5.8–27.6% for rainfall–runoff and 3.59–37.9% for suspended sediment load modelling in the validation phase.\",\"PeriodicalId\":55042,\"journal\":{\"name\":\"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2023-07-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.1080/02626667.2023.2241850\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"WATER RESOURCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1080/02626667.2023.2241850","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"WATER RESOURCES","Score":null,"Total":0}
引用次数: 1

摘要

摘要:本研究评估了水文工程中心-水文建模系统(HEC-HMS)、Hydrologiska byr Vattenbalansavdelning (HBV)、水土评估工具(SWAT)、前馈神经网络(FFNN)、自适应神经模糊推理系统(ANFIS)、支持向量回归(SVR)和多元线性回归(MLR)对埃塞俄比亚Katar流域降雨-径流-泥沙过程的模拟效果。随后,提出了神经网络集成(NE)、加权平均集成(WE)和简单平均集成(SE)技术来提高单个模型的性能。采用Nash-Sutcliffe效率(NSE)、均方根误差(RMSE)和平均绝对误差(MAE)对模型的性能进行评价。结果表明,ANFIS模型对降雨-径流-泥沙的模拟效果优于其他单一模型。此外,人工智能和基于物理的模型的整合提高了性能,在验证阶段,NE技术显示出更好的准确性,降雨径流模型的准确性提高了5.8-27.6%,悬浮泥沙负荷模型的准确性提高了3.59-37.9%。
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
Physical and artificial intelligence-based hybrid models for rainfall–runoff–sediment process modelling
ABSTRACT This study evaluates the performance of the Hydrologic Engineering Center-Hydrologic Modelling System (HEC-HMS), Hydrologiska Byråns Vattenbalansavdelning (HBV), Soil and Water Assessment Tool (SWAT), feedforward neural network (FFNN), adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR) and multilinear regression (MLR) for modelling the rainfall–runoff–sediment process in Katar catchment, Ethiopia. Afterward, neural network ensemble (NE), weighted average ensemble (WE) and simple average ensemble (SE) techniques were developed to improve the performance of single models. The performance of the models was evaluated using Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE) and mean absolute error (MAE). The results show that the ANFIS model outperformed the other single models for rainfall–runoff–sediment modelling. Moreover, the integration of artificial intelligence and physically-based models resulted in improved performance, with the NE technique demonstrating better accuracy by improving individual models by 5.8–27.6% for rainfall–runoff and 3.59–37.9% for suspended sediment load modelling in the validation phase.
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
CiteScore
6.60
自引率
11.40%
发文量
144
审稿时长
9.8 months
期刊介绍: Hydrological Sciences Journal is an international journal focused on hydrology and the relationship of water to atmospheric processes and climate. Hydrological Sciences Journal is the official journal of the International Association of Hydrological Sciences (IAHS). Hydrological Sciences Journal aims to provide a forum for original papers and for the exchange of information and views on significant developments in hydrology worldwide on subjects including: Hydrological cycle and processes Surface water Groundwater Water resource systems and management Geographical factors Earth and atmospheric processes Hydrological extremes and their impact Hydrological Sciences Journal offers a variety of formats for paper submission, including original articles, scientific notes, discussions, and rapid communications.
期刊最新文献
Potential assessment of calibration approaches using the SWAT hydrological model for streamflow and sediment yield for a large-scale catchment Explaining the groundwater salinity of hard-rock aquifers in semi-arid hinterlands using a multidisciplinary approach An assessment of small island hydrological research activity conducted in the Oceania region Spatiotemporal river–aquifer interactions of a large tropical dryland river with high anthropic intervention A priori selection of hydrological model structures in modular modelling frameworks: application to Great Britain
×
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