Tunnelling-induced ground surface settlement: A comprehensive review with particular attention to artificial intelligence technologies

Natural Hazards Research Pub Date : 2024-03-01 DOI:10.1016/j.nhres.2023.11.002

Gang Niu, Xuzhen He, Haoding Xu, Shaoheng Dai

{"title":"Tunnelling-induced ground surface settlement: A comprehensive review with particular attention to artificial intelligence technologies","authors":"Gang Niu, Xuzhen He, Haoding Xu, Shaoheng Dai","doi":"10.1016/j.nhres.2023.11.002","DOIUrl":null,"url":null,"abstract":"<div><p>Shallow tunnels in urban areas are close to adjacent buildings and municipal pipelines. Ground surface settlement (GSS) due to tunnelling can cause damage to those infrastructures surrounded. Many methods have been proposed for evaluating ground settlement induced by tunnelling, including empirical, analytical, numerical and artificial intelligence methods. This paper reviews the proposed methods in detail based on published 677 articles within past ten years. The principles, assumptions and application scope of those methods are summarized and the advantages and limitations of each method are discussed. Since artificial intelligence (AI) become popular in recent few years, the application of AI in the aspect of tunnelling-induced ground deformation is introduced emphatically. Finally, the challenges of ground displacement prediction by machine learning (ML) are clarified and future research directions are suggested.</p></div>","PeriodicalId":100943,"journal":{"name":"Natural Hazards Research","volume":"4 1","pages":"Pages 148-168"},"PeriodicalIF":0.0000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666592123001129/pdfft?md5=769b5ced330f65fc3b86cc419108fee9&pid=1-s2.0-S2666592123001129-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Natural Hazards Research","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666592123001129","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Shallow tunnels in urban areas are close to adjacent buildings and municipal pipelines. Ground surface settlement (GSS) due to tunnelling can cause damage to those infrastructures surrounded. Many methods have been proposed for evaluating ground settlement induced by tunnelling, including empirical, analytical, numerical and artificial intelligence methods. This paper reviews the proposed methods in detail based on published 677 articles within past ten years. The principles, assumptions and application scope of those methods are summarized and the advantages and limitations of each method are discussed. Since artificial intelligence (AI) become popular in recent few years, the application of AI in the aspect of tunnelling-induced ground deformation is introduced emphatically. Finally, the challenges of ground displacement prediction by machine learning (ML) are clarified and future research directions are suggested.

查看原文本刊更多论文

隧洞引起的地表沉降：全面综述，特别关注人工智能技术

城市地区的浅层隧道毗邻建筑物和市政管道。隧道开挖引起的地表沉降（GSS）会对周围的基础设施造成破坏。目前已提出了许多方法来评估由隧道挖掘引起的地面沉降，包括经验法、分析法、数值法和人工智能法。本文根据过去十年间发表的 677 篇文章，对所提出的方法进行了详细评述。本文总结了这些方法的原理、假设和应用范围，并讨论了每种方法的优势和局限性。鉴于近年来人工智能（AI）的流行，重点介绍了人工智能在隧道诱发地表变形方面的应用。最后，阐明了机器学习（ML）预测地表位移所面临的挑战，并提出了未来的研究方向。

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

Natural Hazards Research

CiteScore

4.10

自引率

0.00%

发文量