Hazard assessment framework for statistical analysis of cut slopes using track inspection videos and geospatial information

Abstract
Transportation corridors constructed using through- and side-cuts are susceptible to hazardous slope failures, potentially causing infrastructure damage, operational suspensions and loss of life. To monitor the stability of known geohazards at the local scale, geotechnical investigation of each slope is typically performed to calculate a factor of safety. In many corridors, however, this method is labour-intensive due to the quantity of geohazards and statistical methods are instead used to identify hazardous sections. This paper introduces a new slope failure hazard assessment technique, utilising susceptibility mapping of geospatial information and computer vision-based analysis of right-of-way videos recorded by railroad track inspection vehicles, applied to a section of railroad track near Harrisburg, Pennsylvania. Combining these results, an enhanced relative hazard assessment algorithm was formulated. Using the developed framework, geohazards of primary concern were determined which should be prioritised for future geotechnical investigation and remediation efforts.
Description
This is an Accepted Manuscript of an article published by Taylor & Francis in Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards on 6/12/2023, available at: https://doi.org/10.1080/17499518.2023.2222369. © 2023 Informa UK Limited, trading as Taylor & Francis Group. This article will be embargoed until 06/12/2024.
Keywords
slope stability analysis, object detection, landslide susceptibility mapping, hazard analysis, cut slopes
Citation
Palese, Michael, Te Pei, Tong Qiu, Allan M. Zarembski, Chaopeng Shen, and Joseph W. Palese. “Hazard Assessment Framework for Statistical Analysis of Cut Slopes Using Track Inspection Videos and Geospatial Information.” Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, June 12, 2023, 1–16. https://doi.org/10.1080/17499518.2023.2222369.