Special Issue on Intelligent Rock Mechanics for Major Engineering Projects: Theory, Methods, and Applications

Rock mechanics is central to the planning, design, construction, and operation of major infrastructure and resource-development projects in transportation, hydropower, energy development, underground space utilization, and extraterrestrial resource exploration. As these projects extend into increasingly challenging geological environments, the reliable assessment of nonlinear and anisotropic rock-mass behavior, together with timely mitigation of engineering risks, is of utmost importance. Addressing these challenges increasingly depends on the effective use of data from drilling and geophysical investigations, surveying and remote sensing, field monitoring, and connected sensing systems. Together, these sources generate large volumes of heterogeneous, multiscale data that can provide critical insights into rock-mass behavior and evolving engineering risks.

Artificial intelligence (AI) offers new approaches to integrating multisource observations with rock mechanics knowledge, constitutive models, and governing physical laws. Its engineering value, however, depends on whether the methods are interpretable, transferable across sites and scales, and supported by credible validation.

This special issue aims to bring together and present state-of-the-art theoretical, methodological, and applied advances at the intersection of AI and rock mechanics that address practical needs in major engineering projects. In doing so, it seeks to advance intelligent rock mechanics, deepen scientific understanding of complex rock engineering systems, and strengthen capabilities for prediction, early warning, and risk management.

Particular emphasis is placed on i studies that establish effective links among multisource observations, mechanical models, uncertainty assessment, and engineering decision-making and that are validated through laboratory experiments, field testing, real-time monitoring, or well-documented engineering applications.

Topics of interest include, but are not limited to:

• Theories and methods for applying established and emerging AI techniques in geotechnical and rock engineering, including machine learning, deep learning, computer vision, multimodal and physics-informed learning, generative AI, large language models, reinforcement learning, intelligent optimization, and related approaches;
• AI-enabled acquisition, processing, integration, governance, and quality control of heterogeneous, multisource geotechnical and rock engineering data for major engineering projects;
• Knowledge-guided and physics-informed AI methods based on laboratory and field observations for geotechnical and rock-mass characterization, including the testing, identification, and inverse analysis of geotechnical and rock-mass parameters, uncertainty quantification, and rock-mass quality classification;
• Intelligent sensing, detection, identification, prediction, and early warning of hazards in geotechnical and rock engineering, including decision-support systems based on real-time monitoring and dynamic risk assessment;
• AI-enabled technologies and integrated systems for site investigation, design, construction, operation, and maintenance throughout the life cycle of major engineering projects.

Submissions should state (1) the domain-specific knowledge and physical principles incorporated into the study; (2) the contributions of the work to safety, risk management, or hazard mitigation in major engineering projects; and (3) the evidence supporting the generalizability, interpretability, and reliability of the proposed models or methods.

Submission deadline: 30 December 2026

Guest Editors:

• Dong Wang, China Railway Eryuan Engineering Group Co., Ltd.; Email: wangdong13@crecg.com
• Xuhai Tang, Wuhan University; Email: xuhaitang@whu.edu.cn
• Li Ren, Sichuan University; Email: renli@scu.edu.cn
• Jiangmei Qiao, Wuhan University; Email: jiangmei_qiao@whu.edu.cn
• Fei Wang, China Railway Eryuan Engineering Group Co., Ltd.; Email: sirbuer@163.com