Development of neural network-based surrogate models in geotechnics: a state-of- the-art review

Purpose This state-of-the-art paper provides an overview of surrogate modelling methods suitable for geotechnical engineering, covering the entire cycle of model development. Design/methodology/approach The paper discusses neural network-based surrogate modelling and its applicability in geotechnical engineering, including its limitations. It addresses techniques for data set generation, sampling, tuning, selecting activation functions and assessing accuracy. Findings Each step during the development of surrogate models offers various options and therefore requires a systematic approach. Besides standardised benchmarking and richer data sets key areas for future research include advanced or hybrid architectures, such as physics-informed long short-term memory networks and transformers to improve generalisability, efficiency and physical consistency. Originality/value This paper reviews and highlights the most promising methods for surrogate model development in geotechnical engineering, considering the most critical aspects for building high-performing predictive models and lays an outlook for future research.