Ali El Bilali, Youssef Brouziyne, Oumaima Attar, Houda Lamane, Abdessamad Hadri, Abdeslam Taleb
{"title":"预测沉积物产量的物理信息机器学习算法:物理一致性、敏感性和可解释性分析。","authors":"Ali El Bilali, Youssef Brouziyne, Oumaima Attar, Houda Lamane, Abdessamad Hadri, Abdeslam Taleb","doi":"10.1007/s11356-024-34245-2","DOIUrl":null,"url":null,"abstract":"<p><p>The sediment transport, involving the movement of the bedload and suspended sediment in the basins, is a critical environmental concern that worsens water scarcity and leads to degradation of land and its ecosystems. Machine learning (ML) algorithms have emerged as powerful tools for predicting sediment yield. However, their use by decision-makers can be attributed to concerns regarding their consistency with the involved physical processes. In light of this issue, this study aims to develop a physics-informed ML approach for predicting sediment yield. To achieve this objective, Gaussian, Center, Regular, and Direct Copulas were employed to generate virtual combinations of physical of the sub-basins and hydrological datasets. These datasets were then utilized to train deep neural network (DNN), conventional neural network (CNN), Extra Tree, and XGBoost (XGB) models. The performance of these models was compared with the modified universal soil loss equation (MUSLE), which serves as a process-based model. The results demonstrated that the ML models outperformed the MUSLE model, exhibiting improvements in Nash-Sutcliffe efficiency (NSE) of approximately 10%, 18%, 32%, and 41% for the DNN, CNN, Extra Tree, and XGB models, respectively. Furthermore, through Sobol sensitivity and Shapley additive explanation-based interpretability analyses, it was revealed that the Extra Tree model displayed greater consistency with the physical processes underlying sediment transport as modeled by MUSLE. The proposed framework provides new insights into enhancing the accuracy and applicability of ML models in forecasting sediment yield while maintaining consistency with natural processes. Consequently, it can prove valuable in simulating process-related strategies aimed at mitigating sediment transport at watershed scales, such as the implementation of best management practices.</p>","PeriodicalId":545,"journal":{"name":"Environmental Science and Pollution Research","volume":null,"pages":null},"PeriodicalIF":5.8000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Physics-informed machine learning algorithms for forecasting sediment yield: an analysis of physical consistency, sensitivity, and interpretability.\",\"authors\":\"Ali El Bilali, Youssef Brouziyne, Oumaima Attar, Houda Lamane, Abdessamad Hadri, Abdeslam Taleb\",\"doi\":\"10.1007/s11356-024-34245-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The sediment transport, involving the movement of the bedload and suspended sediment in the basins, is a critical environmental concern that worsens water scarcity and leads to degradation of land and its ecosystems. Machine learning (ML) algorithms have emerged as powerful tools for predicting sediment yield. However, their use by decision-makers can be attributed to concerns regarding their consistency with the involved physical processes. In light of this issue, this study aims to develop a physics-informed ML approach for predicting sediment yield. To achieve this objective, Gaussian, Center, Regular, and Direct Copulas were employed to generate virtual combinations of physical of the sub-basins and hydrological datasets. These datasets were then utilized to train deep neural network (DNN), conventional neural network (CNN), Extra Tree, and XGBoost (XGB) models. The performance of these models was compared with the modified universal soil loss equation (MUSLE), which serves as a process-based model. The results demonstrated that the ML models outperformed the MUSLE model, exhibiting improvements in Nash-Sutcliffe efficiency (NSE) of approximately 10%, 18%, 32%, and 41% for the DNN, CNN, Extra Tree, and XGB models, respectively. Furthermore, through Sobol sensitivity and Shapley additive explanation-based interpretability analyses, it was revealed that the Extra Tree model displayed greater consistency with the physical processes underlying sediment transport as modeled by MUSLE. The proposed framework provides new insights into enhancing the accuracy and applicability of ML models in forecasting sediment yield while maintaining consistency with natural processes. Consequently, it can prove valuable in simulating process-related strategies aimed at mitigating sediment transport at watershed scales, such as the implementation of best management practices.</p>\",\"PeriodicalId\":545,\"journal\":{\"name\":\"Environmental Science and Pollution Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.8000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Science and Pollution Research\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.1007/s11356-024-34245-2\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/7/11 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"N/A\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Science and Pollution Research","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1007/s11356-024-34245-2","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/11 0:00:00","PubModel":"Epub","JCR":"N/A","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
摘要
沉积物输运涉及流域中床载荷和悬浮沉积物的移动,是一个重要的环境问题,它加剧了水资源短缺,并导致土地及其生态系统退化。机器学习(ML)算法已成为预测泥沙产量的强大工具。然而,决策者在使用这些算法时可能会担心它们与相关物理过程是否一致。有鉴于此,本研究旨在开发一种基于物理信息的 ML 方法,用于预测泥沙产量。为实现这一目标,我们采用了高斯、中心、常规和直接 Copulas 来生成子流域和水文数据集的物理虚拟组合。然后利用这些数据集训练深度神经网络 (DNN)、传统神经网络 (CNN)、额外树和 XGBoost (XGB) 模型。这些模型的性能与作为基于过程的模型的改良通用土壤流失方程(MUSLE)进行了比较。结果表明,ML 模型的性能优于 MUSLE 模型,DNN、CNN、Extra Tree 和 XGB 模型的纳什-苏特克利夫效率(NSE)分别提高了约 10%、18%、32% 和 41%。此外,通过基于 Sobol 敏感性和 Shapley 加法解释的可解释性分析发现,Extra Tree 模型与 MUSLE 所模拟的沉积物输运的基本物理过程具有更高的一致性。所提出的框架为提高 ML 模型预测泥沙产量的准确性和适用性,同时保持与自然过程的一致性提供了新的见解。因此,该框架在模拟旨在减缓流域范围内沉积物迁移的过程相关策略(如实施最佳管理实践)方面具有重要价值。
Physics-informed machine learning algorithms for forecasting sediment yield: an analysis of physical consistency, sensitivity, and interpretability.
The sediment transport, involving the movement of the bedload and suspended sediment in the basins, is a critical environmental concern that worsens water scarcity and leads to degradation of land and its ecosystems. Machine learning (ML) algorithms have emerged as powerful tools for predicting sediment yield. However, their use by decision-makers can be attributed to concerns regarding their consistency with the involved physical processes. In light of this issue, this study aims to develop a physics-informed ML approach for predicting sediment yield. To achieve this objective, Gaussian, Center, Regular, and Direct Copulas were employed to generate virtual combinations of physical of the sub-basins and hydrological datasets. These datasets were then utilized to train deep neural network (DNN), conventional neural network (CNN), Extra Tree, and XGBoost (XGB) models. The performance of these models was compared with the modified universal soil loss equation (MUSLE), which serves as a process-based model. The results demonstrated that the ML models outperformed the MUSLE model, exhibiting improvements in Nash-Sutcliffe efficiency (NSE) of approximately 10%, 18%, 32%, and 41% for the DNN, CNN, Extra Tree, and XGB models, respectively. Furthermore, through Sobol sensitivity and Shapley additive explanation-based interpretability analyses, it was revealed that the Extra Tree model displayed greater consistency with the physical processes underlying sediment transport as modeled by MUSLE. The proposed framework provides new insights into enhancing the accuracy and applicability of ML models in forecasting sediment yield while maintaining consistency with natural processes. Consequently, it can prove valuable in simulating process-related strategies aimed at mitigating sediment transport at watershed scales, such as the implementation of best management practices.
期刊介绍:
Environmental Science and Pollution Research (ESPR) serves the international community in all areas of Environmental Science and related subjects with emphasis on chemical compounds. This includes:
- Terrestrial Biology and Ecology
- Aquatic Biology and Ecology
- Atmospheric Chemistry
- Environmental Microbiology/Biobased Energy Sources
- Phytoremediation and Ecosystem Restoration
- Environmental Analyses and Monitoring
- Assessment of Risks and Interactions of Pollutants in the Environment
- Conservation Biology and Sustainable Agriculture
- Impact of Chemicals/Pollutants on Human and Animal Health
It reports from a broad interdisciplinary outlook.