Geoengineering and geomechanics deals with geomaterials that, by their inherent nature, exhibit varied and uncertain behavior due to the complicated geological processes. Modeling the behavior of geomaterials in geotechnical engineering applications is complex and to a greater extent currently still beyond the ability of most physics-based engineering methods.

Since its inception in the mid-1950s, artificial intelligence (AI) has become a disruptive and pervasive technique. Machine learning (ML) is a sub-branch of AI and is mainly the study of computer algorithms that automatically improve their performance through experience. In recent years, with the rapid development of machine learning (ML) and, more recently, deep learning (DL) as a Data Science branch, and its implementation in many engineering fields, geotechnical researchers and practitioners have started looking into disciplinary or thematic applications of ML methods in geotechnical engineering. The greater and ever-growing interest in ML facilitated the foundation of the ISSMGE technical committee (TC) of TC309 “Machine Learning and Big Data” in 2018.

To discuss the challenges, opportunities, and trends related to the adoption of machine learning in geotechnical research and industrial workflows, the TC309 is organizing a Mini-symposium on “Machine Learning in Geotechnics” at the 4th International Conference on Information Technology in Geo-Engineering (ICITG) on August 4–5, 2022, in Singapore. The Mini-symposium is intended to be a small-scale, but high-quality and single-track event focussing on the promotion, dissemination and exchange of knowledge and ideas through discussions. The organising committee of this Mini-symposium decided to publish a special issue of Acta Geotechnica on “Machine Learning in Geotechnics.” We assemble some 30 papers in this thematic issue, which provide insights into the latest developments and challenges in applying machine learning to geoscience and geoengineering. Focal points of the issue include, but are not limited to, innovative applications of: (1) conventional machine learning (ML) methods, such as artificial neural networks (ANNs), support vector machines (SVMs), random forest (RF) and multivariate adaptive regression splines (MARS); (2) deep learning methods, such as convolutional neural network (CNN) and gated recurrent unit (GRU); (3) hybrid ML methods, such as combination of the modified version of the equilibrium optimizer (EO), i.e., MEO, and two conventional machine learning algorithms, namely extreme learning machine (ELM) and artificial neural network (ANN). ML is an inspiration for the geotechnical community for developing and implementing innovative data-driven methods for a variety of new applications, also beyond those shared in this special issue.

We would like to thank all the authors for contributing their papers, and all the reviewers for reviewing the manuscripts, and the editors of Acta Geotechnica and the editorial office staff for their great supports. Without their trusts and efforts, this special issue would not be possible. All papers in this special issue will be presented in Mini-symposium “Machine Learning in Geotechnics.” Our gratitude goes to Professor Jian Chu, the 4ICITG conference chair, for this kind arrangement.