{"title":"在机器学习溪流模型中将可解释人工智能与土壤水分动态联系起来","authors":"Alexander Ley, Helge Bormann, Markus Casper","doi":"10.2166/nh.2024.003","DOIUrl":null,"url":null,"abstract":"\n \n Machine learning algorithms are increasingly applied in hydrological studies with promising results. However, these algorithms generally lack the ability for easy interpretability of the results by users. In this study, we compare six different explainable artificial intelligence (XAI) algorithms that help understand the effect of input data on the simulation results. The methods are explored on two distinct approaches for streamflow modeling using the long short-term memory (LSTM) model: a single model approach using only meteorological forcing data and a regional approach including also static catchment attributes. To gain further insight into the internal dynamics of the LSTM models, the relationship between cell states and soil moisture is investigated. A strong correlation suggests that the LSTM models inherently capture the concept of soil moisture as a catchment-scale storage mechanism. The XAI methods are applied to derive a timestep of influence, revealing how many days of input data are relevant for the model output. All XAI methods result in similar seasonal patterns in the timestep of influence, suggesting that the methods are comparable. Setting soil moisture dynamics in context to seasonal development of the timestep of influence suggests resetting LSTM as soon as soil moisture saturation occurs.","PeriodicalId":55040,"journal":{"name":"Hydrology Research","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Linking explainable artificial intelligence and soil moisture dynamics in a machine learning streamflow model\",\"authors\":\"Alexander Ley, Helge Bormann, Markus Casper\",\"doi\":\"10.2166/nh.2024.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n \\n Machine learning algorithms are increasingly applied in hydrological studies with promising results. However, these algorithms generally lack the ability for easy interpretability of the results by users. In this study, we compare six different explainable artificial intelligence (XAI) algorithms that help understand the effect of input data on the simulation results. The methods are explored on two distinct approaches for streamflow modeling using the long short-term memory (LSTM) model: a single model approach using only meteorological forcing data and a regional approach including also static catchment attributes. To gain further insight into the internal dynamics of the LSTM models, the relationship between cell states and soil moisture is investigated. A strong correlation suggests that the LSTM models inherently capture the concept of soil moisture as a catchment-scale storage mechanism. The XAI methods are applied to derive a timestep of influence, revealing how many days of input data are relevant for the model output. All XAI methods result in similar seasonal patterns in the timestep of influence, suggesting that the methods are comparable. Setting soil moisture dynamics in context to seasonal development of the timestep of influence suggests resetting LSTM as soon as soil moisture saturation occurs.\",\"PeriodicalId\":55040,\"journal\":{\"name\":\"Hydrology Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-05-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Hydrology Research\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.2166/nh.2024.003\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Environmental Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hydrology Research","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.2166/nh.2024.003","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Environmental Science","Score":null,"Total":0}
Linking explainable artificial intelligence and soil moisture dynamics in a machine learning streamflow model
Machine learning algorithms are increasingly applied in hydrological studies with promising results. However, these algorithms generally lack the ability for easy interpretability of the results by users. In this study, we compare six different explainable artificial intelligence (XAI) algorithms that help understand the effect of input data on the simulation results. The methods are explored on two distinct approaches for streamflow modeling using the long short-term memory (LSTM) model: a single model approach using only meteorological forcing data and a regional approach including also static catchment attributes. To gain further insight into the internal dynamics of the LSTM models, the relationship between cell states and soil moisture is investigated. A strong correlation suggests that the LSTM models inherently capture the concept of soil moisture as a catchment-scale storage mechanism. The XAI methods are applied to derive a timestep of influence, revealing how many days of input data are relevant for the model output. All XAI methods result in similar seasonal patterns in the timestep of influence, suggesting that the methods are comparable. Setting soil moisture dynamics in context to seasonal development of the timestep of influence suggests resetting LSTM as soon as soil moisture saturation occurs.
期刊介绍:
Hydrology Research provides international coverage on all aspects of hydrology in its widest sense, and welcomes the submission of papers from across the subject. While emphasis is placed on studies of the hydrological cycle, the Journal also covers the physics and chemistry of water. Hydrology Research is intended to be a link between basic hydrological research and the practical application of scientific results within the broad field of water management.