Skip to main navigation Skip to search Skip to main content

Artificial intelligence for classification of railway earth retaining structures

  • Western Sydney University
  • Transport for New South Wales

Research output: Chapter in Book / Conference PaperChapterpeer-review

1 Citation (Scopus)

Abstract

Earth retaining structures (ERS) play a crucial role in the infrastructure of railway networks. It supports and protects railway networks from soil and rock erosion. However, different types of defects can form on ERS that can cause slope failure, soil erosion, and degradation of its structural integrity. Timely repair of these defects is essential. However, before detecting defects, it is important to classify ERS, as the occurrence and nature of defects often depend on the specific type of ERS. This study proposes the use of artificial intelligence (AI), specifically improved ConvNeXt V2, for automatically classifying three common types of railway ERS captured with GPS metadata from Transport for New South Wales (TfNSW) railway networks as a proof of concept. Classifying ERS is a necessary step prior to defect detection because defects of ERS are dependent on its type. The study also extracts the GPS coordinates of the classified ERS from the captured data to enable the inspector to locate and conduct further inspection of that ERS.

Original languageEnglish
Title of host publication3rd International Conference on Geomechanics and Geoenvironmental Engineering: Proceedings of iCGMGE 2025
EditorsPan Hu, Giang Nguyen, Chin Leo, Henry Wong, Samanthika Liyanapathirana
Place of PublicationSwitzerland
PublisherSpringer
Pages79-86
Number of pages8
ISBN (Electronic)9783032208859
ISBN (Print)9783032208842
DOIs
Publication statusPublished - 2026
Event3rd International Conference on Geomechanics and Geoenvironmental Engineering, iCGMGE 2025 - Sydney, Australia
Duration: 26 Nov 202528 Nov 2025

Publication series

NameLecture Notes in Civil Engineering
Volume842 LNCE
ISSN (Print)2366-2557
ISSN (Electronic)2366-2565

Conference

Conference3rd International Conference on Geomechanics and Geoenvironmental Engineering, iCGMGE 2025
Country/TerritoryAustralia
CitySydney
Period26/11/2528/11/25

Keywords

  • Classification
  • ConvNeXt V2
  • Earth Retaining Structures (ERS)
  • GPS metadata
  • Railway

Fingerprint

Dive into the research topics of 'Artificial intelligence for classification of railway earth retaining structures'. Together they form a unique fingerprint.

Cite this