arrow
返回

Generating interpretable rainfall-runoff models automatically from data

delete2024-11-01
delete1
delete
OA
AI
T
Travis Adrian Dantzer *
B
Branko Kerkez
DOI:10.1016/j.advwatres.2024.104796delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
A sudden surge of data has created new challenges in water management, spanning quality control, assimilation, and analysis. Few approaches are available to integrate growing volumes of data into interpretable results. Process-based hydrologic models have not been designed to consume large amounts of data. Alternatively, new machine learning tools can automate data analysis and forecasting, but their lack of interpretability and reliance on very large data sets limits the discovery of insights and may impact trust. To address this gap, we present a new approach, which seeks to strike a middle ground between process-, and data-based modeling. The contribution of this work is an automated and scalable methodology that discovers differential equations and latent state estimations within hydrologic systems using only rainfall and runoff measurements. We show how this enables automated tools to learn interpretable models of 6 to 18 parameters solely from measurements. We apply this approach to nearly 400 stream gaging sites across the US, showing how complex catchment dynamics can be reconstructed solely from rainfall and runoff measurements. We also show how the approach discovers surrogate models that can replicate the dynamics of a much more complex process-based model, but at a fraction of the computational complexity. We discuss how the resulting representation of watershed dynamics provides insight and computational efficiency to enable automated predictions across large sensor networks.
Keyword:
Model discovery
Rainfall-Runoff
Dynamical systems
Explainable AI
Surrogate modeling
Data-driven
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Advances in Water Resources 封面图
Advances in Water Resources
IF:
4.2
论文数:
4.7K
被引数:
2.0W

机构

U
university of michigan system
学者数:
593
论文数: 1.5K
被引数: 6.3W
引用论文

引用论文

Skeletal infections in children
err1994-02-01
err0
PREAI
errLaurie O. Hughes; James Aronson
err分享
err收藏
Candida glabrata’s Genome Plasticity Confers a Unique Pattern of Expressed Cell Wall Proteins
err2018-06-05
err0
errOAAI
errEunice López-Fuentes; Guadalupe Gutiérrez-Escobedo; Bea Timmermans; Patrick Van Dijck; Alejandro De Las Peñas; Irene Castaño
err分享
err收藏
Benchmarking of a Physically Based Hydrologic Model
err2017-08-04
err101
errOAAI
errNewman, Andrew J.; Mizukami, Naoki; Clark, Martyn P.; Wood, Andrew W.; Nijssen, Bart; Nearing, Grey
err分享
err收藏
err分享
err收藏
Hydrologically informed machine learning for rainfall-runoff modelling: towards distributed modelling
err2021-08-11
err91
errOAAI
errHerath, Herath Mudiyanselage Viraj Vidura; Chadalawada, Jayashree; Babovic, Vladan
err分享
err收藏
err分享
err收藏
学者 查看更多内容