Advanced Geospatial and Computational Analytics for Predicting Subsidence and Slope Failure in the U.S.A Mining Regions

Authors: Abass Aliu, Kipkorir Yano Yator

DOI: https://doi.org/10.37082/IJIRMPS.v14.i1.232891

Short DOI: https://doi.org/hbk6sd

Country: United States

Full-text Research PDF File:   View   |   Download

Abstract: Mining-induced subsidence and slope failure pose significant hazards to infrastructure, environmental sustainability, and public safety across major mining regions in the United States. Recent advances in geospatial technologies, including Interferometric Synthetic Aperture Radar (InSAR), LiDAR, and unmanned aerial systems, combined with sophisticated computational analytics and machine learning algorithms, have substantially enhanced the capability to monitor, predict, and manage these geohazards. This systematic review synthesizes findings from 33 key studies employing advanced geospatial data and computational methods for subsidence and slope failure prediction in U.S. mining contexts. We outline methods integrating satellite remote sensing, geotechnical databases, and multidisciplinary spatial datasets to extract relevant deformation features, which are then analyzed using hybrid machine learning models such as STL-XGBoost, adaptive dynamic models, and optimized backpropagation neural networks. These models exhibit improved accuracy over traditional empirical approaches, reducing prediction errors by 30-60% and achieving strong correlations (>0.9) with observed subsidence. The spatial risk maps generated reveal heterogeneity in subsidence susceptibility linked closely to mining activity, groundwater extraction, and geologic structures, facilitating targeted mitigation. Feature importance analyses identify primary influences, including slope gradient, soil characteristics, climatic factors, and mining parameters, guiding monitoring priorities. Case studies validate model applicability for real-time monitoring and risk reduction, supporting sustainable mining and environmental resilience. Our comprehensive synthesis confirms that deploying integrated advanced geospatial and computational analytics delivers robust, scalable tools essential for effective hazard management and land stewardship in U.S. mining regions facing increasing environmental pressures. These insights inform future research and operational frameworks, advancing geohazard prediction accuracy and reliability in mining-impacted landscapes globally.

Keywords:

Paper Id: 232891

Published On: 2026-01-18

Published In: Volume 14, Issue 1, January-February 2026

Share this