Document Type : Review Article
Authors
1
Department of Civil Engineering, Southern Illinois University Edwardsville (SIUE), Edwardsville, IL, USA
2
Department of Data Science, Maryville University, St. Louis, MO, USA
10.48309/jeires.2026.569173.1337
Abstract
The increasing frequency and severity of natural disasters in the United States pose major challenges to national security, economic stability, and the resilience of critical infrastructure systems. A substantial share of disaster-related infrastructure damage results from geotechnical failures such as landslides, soil liquefaction, and erosion. Effective post-disaster recovery, therefore, depends on rapid and accurate ground damage assessment; yet conventional field-based inspection methods remain time-intensive, costly, and limited in spatial coverage. This review examines recent advances in artificial intelligence and deep learning techniques for post-disaster geotechnical damage assessment. It synthesizes state-of-the-art approaches, particularly convolutional neural networks, for automated detection and classification of ground damage using high-resolution satellite imagery, unmanned aerial vehicle data, and interferometric synthetic aperture radar. The reviewed studies indicate that AI-assisted frameworks enable near-real-time damage mapping at regional and national scales. From an operational perspective, AI-based damage assessment supports faster prioritization of inspections, improved resource allocation, and reduced recovery times for federal and state agencies, including the Federal Emergency Management Agency and State Departments of Transportation. The review also identifies key challenges related to data standardization, model generalization, and scalability, and outlines future directions to support nationwide implementation and long-term infrastructure resilience. Unlike existing reviews, this study provides a nationally focused synthesis that explicitly links AI-driven geotechnical damage detection methodologies with post-disaster decision-making, emergency response prioritization, and long-term critical infrastructure resilience at regional and national scales.
Graphical Abstract
Keywords
Subjects
OPEN ACCESS
©2026 The author(s). This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/
