Digital twin applications in geotechnical engineering: a systematic review

Purpose Digital twins (DTs) offer promising advances in geotechnical engineering by improving prediction accuracy, operational efficiency and risk management. However, their adoption in the field remains limited compared to other industries such as manufacturing and civil engineering. This study reviews current DT applications in geotechnical engineering, examining research trends, enabling technologies and key challenges. By identifying gaps and future directions, this study aims to facilitate DT integration into underexplored areas and advance technological capabilities for more data-driven decision-making. Design/methodology/approach A systematic review of DT applications in geotechnical engineering was conducted, analysing publication trends, key research areas and enabling technologies. The study examines the integration of DT with machine learning, real-time data acquisition and interoperability challenges. Findings highlight research gaps and propose strategies for overcoming barriers to adoption, ensuring DTs’ effective application in diverse geotechnical contexts. Findings DT research in geotechnical engineering is fragmented, with most studies focused on tunnelling and slopes, while areas such as soil mechanics remain underexplored. The increasing integration of DT with machine learning is improving predictive capabilities, but challenges such as interoperability, scalable platforms and real-time data acquisition are hindering widespread adoption. Addressing these issues is critical to advancing DT applications and improving geotechnical project outcomes. Originality/value This study provides a structured assessment of DT adoption in geotechnical engineering, identifying key gaps and opportunities. By highlighting the need for interoperable platforms, broader applications and technological advances, it provides insights for researchers and practitioners. Addressing these challenges will help position DTs as transformative tools, enabling more efficient and data-driven geotechnical engineering.