Submission Deadline: 31 May 2027 View: 262 Submit to Special Issue
Prof. Dr. Haijia Wen
Email: jhw@cqu.edu.cn
Affiliation: School of Civil Engineering, Chongqing University, Chongqing, China
Research Interests: geotechnical risks, geological disasters, natural hazards
Prof. Dr. Zhongqiang Liu
Email: zhongqiang.liu@ngi.no
Affiliation: Department of Natural Hazards, Norwegian Geotechnical Institute (NGI), Oslo, Norway
Research Interests: artificial intelligence, machine learning, AI-driven modeling
Prof. Dr. Yu Wang
Email: wang.yu@ust.hk
Affiliation: Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, China
Research Interests: machine learning, data‑driven modeling, hazard prediction and risk assessment
Prof. Dr. Peng Xie
Email: peng_xie@hainanu.edu.cn
Affiliation: College of Civil Engineering and Architecture, Hainan University, Haikou, China
Research Interests: geotechnical risks, geological disasters, natural hazards
Dr. Zizheng Guo
Email: zizheng.guo@hebut.edu.cn
Affiliation: School of Civil and Transportation Engineering, Hebei University of Technology, Tianjin, China
Research Interests: geohazard, monitoring and early warning, spatial modelling, risk assessment, land use and land cover, climate change
Rapid urbanization, climate change, and intensified human activities have led to increasingly frequent and severe geotechnical risks and natural hazards, including landslides, debris flows, ground subsidence, earthquakes, and other geological disasters. These events are governed by highly nonlinear processes, multi-source uncertainties, and complex multi-scale interactions among geological materials, environmental drivers, and engineering activities. Traditional physics-based modeling alone is often insufficient to capture such complexity with high accuracy and efficiency.
With the rapid development of computational intelligence, artificial intelligence, and data-driven modeling, new opportunities have emerged to advance hazard prediction, early warning systems, and risk-informed engineering decision-making. Techniques such as machine learning, deep learning, physics-informed neural networks, hybrid data–physics models, and multi-source data fusion have demonstrated strong potential in improving the understanding, simulation, and forecasting of geotechnical and geological hazards. However, challenges remain in model interpretability, generalization, uncertainty quantification, and the integration of physical laws with data-driven approaches.
This Special Issue aims to provide a high-level academic platform for researchers and practitioners to exchange advances in AI-driven geotechnical hazard modeling, identify emerging challenges, and outline future research directions. It welcomes innovative theories, computational methods, and practical applications that enhance the reliability, transparency, and scientific rigor of hazard assessment and risk mitigation. Potential topics include, but are not limited to:
· AI-enhanced geotechnical hazard prediction — machine learning and deep learning models for landslides, debris flows, ground subsidence, and rockfall forecasting.
· Physics-informed machine learning — hybrid data–physics modeling for soil–rock mechanics, slope stability, and multi-field coupling.
· Data-driven early warning systems — real-time monitoring, multi-sensor fusion, and anomaly detection for natural hazards.
· Uncertainty quantification in geotechnical modeling — probabilistic, interval, and fuzzy approaches for hazard assessment.
· Remote sensing and UAV-based hazard mapping — deep learning for segmentation, detection, and change analysis of geological disasters.
· Surrogate and reduced order modeling — meta models, multifidelity learning, and efficient simulation of complex geotechnical processes.
· AI-driven risk assessment and decision support — intelligent frameworks for hazard zoning, emergency response, and resilience planning.
· Computational intelligence for soil and rock behavior — constitutive modeling, parameter inversion, and nonlinear material characterization.
· Big data analytics for natural hazards — spatiotemporal pattern mining, clustering, and predictive analytics.
· Physics-guided generative models — generative AI for synthetic hazard data, scenario simulation, and rare event modeling.
· Digital twins for geotechnical systems — real-time simulation, monitoring integration, and adaptive hazard forecasting.
· Computational modeling of cascading hazards — earthquake-induced landslides, rainfall-triggered failures, and multi-hazard interactions.
· AI-assisted geotechnical design optimization — intelligent optimization for slopes, foundations, tunnels, and underground structures.
· Explainable and trustworthy AI — interpretability, robustness, and reliability of AI models in safety-critical geotechnical applications.
Login
Register
Submit a Paper
Propose a Special lssue