Advances in Machine Learning Applications for Underground Space

The Editorial Board of Machine Learning and Data Science in Geotechnics is inviting new papers on Data-centric modelling and analysis of sustainable geotechnical systems. 

The aim of this special issue is to transform the construction  and operation and maintenance of underground space using machine learning (ML)-based digital techniques. This has included the use of ML algorithms, physics-informed neural networks, underground digital twins, fundamental soil-structure mechanics-informed ML, and artificial intelligence (AI)-powered live construction monitoring. Applications include, but are not limited to, tunnelling, pipelines, deep excavations, deep foundations, basement construction, mining, and shafts. By gathering cutting-edge research, case studies, and technical reviews, this issue seeks to highlight how ML algorithms and ML-based digital techniques can improve the design, monitoring, and maintenance of geo-structures.

Examples of topics of papers may include, but are not limited to:

• site investigations
• predicting soil-structure interaction
• assessing structural health
• and optimizing construction processes.

Contributions will include both theoretical developments and practical implementations, ensuring a comprehensive overview of the state-of-the-art in this rapidly evolving field.

To pursue these aims, this Special Issue will welcome State-of-the-Art, theoretical contributions as well as illustrations of best-practice case-study applications of a wide range of data-centric approaches relying on machine learning and artificial intelligence techniques.

Submitted papers will be anonymously commented upon by other members of the civil engineering profession (peer review) – a process which maintains the high technical quality of the journal. Not all submitted papers are accepted. 

• Submit your Paper by 25th April 2025.

For queries or late submissions, please e-mail. You can also read our Guidelines for Authors.