Machine Learning for Data-Centric Geotechnics

Machine learning and other digital technologies fed with large datasets offer a major set of tools for practical geotechnical design. Large language models and other generative AIs can perform cognitive tasks currently undertaken by humans -- and might even predict the next event based on some time series. This depends on a balance of data centricity, fit-for (and transform) practice, and geotechnical context, and can be achieved by the integration of information, data, techniques, tools, perspectives, concepts, theories, along with experience from both geotechnical engineering and machine learning in computer science. And yet good engineering and research outcomes are still dependent on how practice (which includes the workforce) is improved or even transformed in the longer term to better serve end-users. This collection of focused chapters from a group of specialists presents principles and broad up to date practice of machine learning, along with a number of example areas of site characterization, design and construction in geotechnics.

This book is essential for sophisticated practitioners as well as graduate students.

Kok-Kwang Phoon is President designate of Singapore University of Technology and Design. He has edited or written several books with CRC Press, including Model Uncertainties in Foundation Design. He was awarded the ASCE Norman Medal twice in 2005 and 2020, and is the Founding Editor of Georisk.

Chong Tang is a Professor of Dalian University of Technology in China. He was awarded ASCE's Norman Medal in 2020.

Zi-Jun Cao is Professor at Southwest Jiaotong University, China. He received the GEOSNet Young Researcher Award in 2022 and ISSMGE Bright Spark Lecture Award in 2019.