Deep learning, automation, and big data analysis to reduce uncertainty in geotechnical practice

Guest editor(s)

Maria Ferentinou, Liverpool John Moores University, UK; Charles John MacRobert, Stellenbosch University, South Africa; Michael Sakellariou, National Technical University of Athens, Greece; and Siau Chen Chian (Darren), National University of Singapore


Machine learning in geotechnics

The Editorial Board of Machine Learning and Data Science in Geotechnics warmly invites authors to submit Papers on projects related to Deep learning, automation, and big data analysis to reduce uncertainty in geotechnical practice.  

The aim of the special issue is to centre the agenda for machine learning in geotechnics on big data, and data analysis, the use of models, such as deep learning, computer vision, 3D models, to investigate large and complex datasets, (i.e. real time data), to apply data mining techniques, in order  to produce novel applications, with an aim to reduce uncertainty and  optimise design.  


Computer based models such as artificial neural networks have grown and applied broadly to a range of geotechnical engineering problems, since the first publications in the sector in the 90s.

In recent years, ANN modelling appears to be significantly successful with the rapid development and spread of machine learning, with many applications in areas such as site characterisation, ground / geomaterial behaviour, liquefaction, slope, tunnelling and underground excavation, retaining structures and deep foundations. Cilliers, (1999), in his book Complexity & postmodernism refers to the importance of these methods ‘..

"...because they have the ability to conserve the complexity of the systems they model as they  they have complex structures themselves. They also encode information about their environment in a distributed form and are capable to self-organize their internal structure’.

Therefore, they are suitable and relevant for geotechnical engineering dominated by the variability of soils and rock sparse data, and inherent high degree of uncertainty.

Suggested topics for authors to submit Papers on:

  • Soil and rock properties and behavior
  • Subsurface characterizations uncertainty and risk modelling
  • Advances in sensing, monitoring and modelling
  • Multi-scale processes
  • Digital twin ground infrastructure representation
  • Data science, data-driven geotechnics, Big-data integration
  • Data quality  and data governance
  • Geotechnics informatics
  • Cognitive decision biases of the computer
  • Data mining, inferential statistics
  • Features extraction;  high-dimensional data, transfer learning
  • Physics-informed deep learning
  • Bayesian inference methods
  • Open science.

Deadline for Paper submission: 29 November 2024

Interested authors are recommended to first read the journal homepage Author guidelines.  

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

ICE Publishing journals are committed to act as champions of the UN SDGs and to further the knowledge needed for them to be achieved in the civil engineering industry. You can find out more about them and our work towards meeting them in our UN SDG Resource Centre.

If you have a question about the journal, writing, peer review or any of the above, please contact the Commissioning Editor Benjamin Ramster.

Machine Learning and Data Science in Geotechnics Call for Papers