A gold open-access journal from ICE Publishing. The journal’s Article publication charge (£1,250) will be waived for submissions made before 1st May 2025.

Aims and scope

Machine Learning and Data Science in Geotechnics (MLaG) aims to disseminate original contributions in the emerging fields of machine learning, artificial intelligence, big data analysis, and statistical approaches, with a focus on addressing various geotechnical engineering challenges.

Submitted papers should explicitly or implicitly utilise and/or develop these themes to tackle specific geotechnical engineering scenarios or applications. The journal encourages contributions that leverage these advanced methods to achieve more sustainable geotechnical solutions. As such, submissions addressing improved resilience of infrastructure, minimizing resource use, enhancing efficiency, and promoting long-term sustainability in geotechnical practices are particularly welcomed.

The scope of the journal encompasses geotechnical problems ranging from micro-scale concerns, such as coupled effects in soils as multiphase materials, to large-scale challenges, including different infrastructure or geostructures like tunnels, slopes, embankments, bridges, foundations, railways, mines and geoenvironmental systems.