Applications of Artificial Intelligence in Geotechnical Engineering

Since artificial intelligence (AI) was first applied to geotechnical engineering in the early-1990s, in the form of artificial neural networks (ANNs), it has shown great promise in providing superior estimates of a wide range of geotechnical behaviors and applications, when compared against traditional techniques. This paper examines two artificial intelligence techniques, namely ANNs and genetic programming (GP), that have been applied successfully by the author and his co-workers to the settlement of shallow and pile foundations and predicting the performance of rolling dynamic compaction. The paper also examines the benefits and limitations of AI in the context of geotechnical engineering, and the process for developing optimal models.

Keywords: Machine learning, artificial neural networks, genetic programming, shallow foundations, pile foundations, ground improvement.