Special Issue on Knowledge-guided AI for Geotechnical Engineering: Robust Inference under Data Scarcity

Introduction:

Geotechnical engineering often involves making high-stakes decisions using scarce, heterogeneous, and site-specific data in addition to multiple other sources of uncertainty (e.g., measurement error, inherent variability, and model inadequacy). In this setting, while purely data-driven machine learning may fit historical patterns well, it may extrapolate poorly, violate basic mechanics or design rules, and produce overconfident predictions.

This Special Issue invites contributions on knowledge-guided AI-methods that explicitly embed domain knowledge (e.g., mechanics, constitutive behaviour, conservation laws, design codes/standards, expert judgement, causal structure) to achieve robust inference under data scarcity across geotechnical applications.

Topics of interest include, but are not limited to:

• Bayesian hierarchical modelling for site characterization;
• Hybrid FEM+ML constitutive surrogates honoring critical-state/plasticity principles; 
• Physics-informed neural networks/neural operators for coupled flow–deformation problems;
• Multi-fidelity Gaussian processes linking empirical/design models and sparse data;
• Reliability/risk analysis with physics-guided surrogates;
• Transfer learning, Bayesian information borrowing, and data assimilation for data augmentation.

Submissions should state the knowledge encoded, how it is integrated (priors, constraints, structures), and why it improves model performance versus purely data-driven baselines. The overarching goal of the Special Issue is to advance practical, transparent AI that respects geomechanical principles, generalizes across geotechnical sites/projects, and meaningfully reduces decision risk when data are limited.

Submission Instructions: 

Please read the Guide for Authors before submitting. All articles should be submitted online.

Submission deadline: December 31, 2026

Guest Editors:

• Zhongqiang Liu, Norwegian Geotechnical Institute, Norway; Oslo Metropolitan University, Norway; email: zhongqiang.liu@ngi.no
• Yu Feng, Sun Yat-sen University, China; email: fengy253@mail.sysu.edu.cn
• Wengang Zhang, Chongqing University, China; email: cheungwg@126.com
• Wenping Gong, China University of Geosciences (Wuhan), China; email: wenpinggong@cug.edu.cn
• Dongming Zhang, Tongji University, China; email: 09zhang@tongji.edu.cn
• Songfeng Guo, Institute of Geology and Geophysics, Chinese Academy of Sciences, China; email: guosongfeng@mail.iggcas.ac.cn