Subsidence vulnerability assessment due to groundwater over-abstraction using AI-based multiple cluster analysis

IF 4.6 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software Pub Date : 2025-09-03 DOI:10.1016/j.envsoft.2025.106679

Sina Sadeghfam , Soroush Mohammadi , Ata Allah Nadiri , Ali Ehsanitabar , Senapathi Venkatramanan , Abu Reza Md Towfiqul Islam , Yong Xiao , Mehdi Rahmati

{"title":"Subsidence vulnerability assessment due to groundwater over-abstraction using AI-based multiple cluster analysis","authors":"Sina Sadeghfam , Soroush Mohammadi , Ata Allah Nadiri , Ali Ehsanitabar , Senapathi Venkatramanan , Abu Reza Md Towfiqul Islam , Yong Xiao , Mehdi Rahmati","doi":"10.1016/j.envsoft.2025.106679","DOIUrl":null,"url":null,"abstract":"<div><div>Land subsidence triggered by excessive groundwater extraction is a topical research activity, and the ALPRIFT framework calculates the Subsidence Vulnerability Index (SVI). In this study, we employed Artificial Intelligence (AI) to reduce the inherent subjectivity in the ALPRIFT framework using Inclusive Multiple Modeling (IMM). IMM incorporates Random Forest (RF) and Support Vector Machine (SVM) to conduct cluster analysis at Level 1 and identify clusters fed into another RF model at Level 2. We applied this formulation to an unconfined aquifer, which was affected by water table decline. The study identified vulnerable areas in the central part of the aquifer, representing a maximum of 14 cm of subsidence detected by InSAR. The ratio of vulnerable areas to total areas are 5.5, 8.8 and 5.4 % for RF, SVM and IMM, respectively. Compared to the basic ALPRIFT framework, the AI models at both levels considerably improved the modeling performance from 0.7 to 96.5.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"194 ","pages":"Article 106679"},"PeriodicalIF":4.6000,"publicationDate":"2025-09-03","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/S1364815225003639","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

Abstract

Land subsidence triggered by excessive groundwater extraction is a topical research activity, and the ALPRIFT framework calculates the Subsidence Vulnerability Index (SVI). In this study, we employed Artificial Intelligence (AI) to reduce the inherent subjectivity in the ALPRIFT framework using Inclusive Multiple Modeling (IMM). IMM incorporates Random Forest (RF) and Support Vector Machine (SVM) to conduct cluster analysis at Level 1 and identify clusters fed into another RF model at Level 2. We applied this formulation to an unconfined aquifer, which was affected by water table decline. The study identified vulnerable areas in the central part of the aquifer, representing a maximum of 14 cm of subsidence detected by InSAR. The ratio of vulnerable areas to total areas are 5.5, 8.8 and 5.4 % for RF, SVM and IMM, respectively. Compared to the basic ALPRIFT framework, the AI models at both levels considerably improved the modeling performance from 0.7 to 96.5.

查看原文本刊更多论文

基于人工智能多聚类分析的地下水超采沉降脆弱性评价

地下水过度开采引发的地面沉降是一个研究热点，ALPRIFT框架计算了地面沉降脆弱性指数（SVI）。在本研究中，我们利用人工智能（AI）利用包容性多重建模（IMM）来降低ALPRIFT框架中的固有主观性。IMM结合随机森林（RF）和支持向量机（SVM）在第1层进行聚类分析，并识别在第2层输入另一个RF模型的聚类。我们将此公式应用于受地下水位下降影响的无承压含水层。该研究确定了含水层中部的脆弱区域，代表了InSAR探测到的最大14厘米的下沉。脆弱区占总面积的比例分别为5.5%、8.8%和5.4%。与基本的ALPRIFT框架相比，这两个级别的人工智能模型的建模性能从0.7提高到96.5。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

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.