Advancing geotechnical engineering education: Proposing an AI/ML-integrated curriculum for enhanced soft soil-structure interaction analysis

¹ Head of Engineering, TDAC Geotechnical Solutions (P), Ltd, Ernakulam, Kerala, India
² Department of Civil Engineering, Govt. Engineering College, Thrissur, Kerala, India

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Soft marine clay deposits along coastal regions present significant challenges in geotechnical engineering due to their high compressibility and long-term consolidation behaviour. Regions such as Kerala in India are vulnerable to settlement and subsidence issues arising from infrastructure development on under-consolidated marine deposits. While classical soil mechanics provides the theoretical basis for analysing such behaviour, modern geotechnical projects increasingly generate monitoring datasets requiring systematic interpretation beyond conventional analytical approaches. This paper proposes a data-driven geotechnical education framework aimed at bridging the gap between traditional soil mechanics training and emerging data-centric engineering practices. A review of undergraduate and postgraduate geotechnical curricula highlights limited emphasis on interpretation of field monitoring data and large geotechnical datasets. The study identifies key educational gaps and proposes a specialised postgraduate course focused on interpretation of monitoring data related to soft soil behaviour and long-term settlement. The proposed curriculum integrates geotechnical instrumentation, monitoring data interpretation, and data-driven modelling concepts to enable students to evaluate soil–structure interaction in soft clay environments. The framework is relevant for coastal regions characterised by extensive soft deposits and long-term ground deformation. The study highlights the importance of evolving geotechnical education to prepare engineers capable of integrating field observations with analytical and data-driven approaches.