Practical Machine Learning for Sustainable Geotechnical Engineering

Submit your manuscript here!

Introduction

The rapid evolution of machine learning (ML) and data science is transforming the landscape of geotechnical engineering, offering new opportunities to enhance prediction accuracy, optimise design processes, and improve infrastructure resilience. With increasing availability of large and diverse datasets—from laboratory testing and field monitoring to remote sensing and digital twins—data-driven approaches are becoming integral to understanding complex soil behaviour and geotechnical systems. ML techniques have demonstrated significant potential in applications such as slope stability analysis, settlement prediction, soil classification, and geohazard monitoring. Despite this progress, the application of machine learning in geotechnics remains largely focused on model development and predictive performance, with comparatively limited emphasis on real-world implementation and engineering integration.

Challenges such as data quality, uncertainty, interpretability, and transferability continue to hinder the wider adoption of ML in practice. In many cases, models perform well under controlled conditions but lack robustness when applied to diverse field scenarios, highlighting the need for approaches that prioritise reliability, scalability, and practical applicability. This special issue aims to address these challenges by advancing the role of machine learning and data science in geotechnical engineering with a focus on practical impact and implementation. It seeks to bring together contributions that demonstrate not only methodological innovation but also tangible benefits in engineering decision-making, design optimisation, monitoring, and risk management. Contributions may include applied case studies, integration frameworks, hybrid physics-informed approaches, and the use of emerging technologies such as generative AI and advanced sensing systems.

By fostering collaboration between academia and industry, this special issue aims to bridge the gap between research and practice, supporting the development of more reliable, sustainable, and data-informed geotechnical engineering solutions in response to increasing environmental and societal demands.

List of topic areas

1. Real-world ML applications and case studies in geotechnical design, monitoring, and asset management with measurable outcomes
2. Decision-support and risk-informed frameworks integrating ML into engineering workflows to improve reliability, safety, and sustainability
3. Generative AI in geotechnics, including synthetic data, scenario simulation, design augmentation, and AI-assisted workflows
4. Integration with advanced data sources, including EO, satellite monitoring, GIS, remote sensing, and digital twins for infrastructure and geohazards
5. Methodological advances with practical relevance, including interpretable and physics-informed ML addressing scalability, robustness, and uncertainty

Submissions Information

Submissions are made using ScholarOne Manuscripts. Registration and access are available at: https://mc.manuscriptcentral.com/mlag

Author guidelines must be strictly followed. Please see: https://www.emeraldgrouppublishing.com/journal/mlag

Authors should select (from the drop-down menu) the special issue title at the appropriate step in the submission process, i.e. in response to "Please select the issue you are submitting to."

Submitted articles must not have been previously published, nor should they be under consideration for publication anywhere else, while under review for this journal.

Open access vouchers

As an author, if you are affiliated with one of our partner organisations you may be eligible for a prepaid open access publishing voucher. Click here to learn more.

Key deadlines

Opening date for manuscripts submissions: 25/05/2026 
Closing date for manuscripts submission: 25/02/2027