United States Department of Transportation
i
Landslide Risk Assessment in Cut Locations Using Artificial Intelligence Based on Right-of-Way Videos and Geophysical Data
-
2022-06-30
-
[PDF-9.77 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report 07/01/2020 – 06/30/2022
-
Corporate Publisher:
-
Abstract:Sidehill and through cuts are often used in the construction of new railroad rights-of-way to limit the length, curvature, and grade of the route. However, rights-of-way that utilize cuts are susceptible to damage from falling debris driven by slope failure events such as shallow landslides and rockfalls. At-risk slopes, or geohazards, are traditionally analyzed using intensive field investigations and historical failure events to determine their likelihood of failure and the potential consequences of failure. Anticipating slope failures that may occur due to everyday weather events and other catalysts in the region helps protect railroad assets and employees, ensuring safe operations. Many rights-of-way have a large density of geohazards; thus, performing in-situ measurements to determine their failure likelihood requires extensive resources. In addition, installing infrastructure to detect or inhibit debris flow is expensive and often unrealistic for all geohazards. This study aimed to create a new slope stability risk framework for railroad cut sections by processing digital images of railroad rights-of-way recorded by inspection vehicles and related geophysical data. A geohazard-affected track section along the Harrisburg Line was used as the study area. Computer vision techniques were used to identify and quantify geohazard features that indicated slope instability. An object detection model based on deep learning (DL) was trained to detect these slope instability indicators and generate risk scores from rights-of-way inspection videos. Moreover, a landslide inventory was compiled, and a landslide susceptibility model was developed for the study area based on available geophysical data. The object detection model and the landslide susceptibility model were combined using a relative risk assessment framework to determine which sections were most at-risk of landslide, and results were compared with the railroad identified geohazard sections across the study area.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
