Special Session on
AI Applications in Computational Geomechanics
Aim and Scope
Recent advances in artificial intelligence (AI), machine learning (ML), and data-driven modelling are transforming the way complex geomechanical and geomechanical problems are analysed and solved. Traditional geomechanics often relies on empirical correlations, simplified constitutive models, and computationally intensive numerical simulations. While these approaches have served the field well, they can struggle to capture the highly nonlinear, heterogeneous, and multiscale nature of geomaterials such as soils and rocks. This special session aims to bring together researchers, engineers, and practitioners working at the intersection of computational geomechanics and artificial intelligence. The goal is to explore how modern AI techniques can enhance predictive capabilities, improve simulation efficiency, and enable new approaches to understanding geomechanical systems.
AI-driven techniques such as deep learning, physics-informed neural networks, surrogate modelling, and hybrid data–physics approaches are increasingly being used to complement classical numerical methods, including finite element methods (FEM), discrete element methods (DEM), and multiphysics simulations. The session will particularly focus on emerging applications where AI assists in solving complex geomechanical challenges related to infrastructure resilience, energy systems, environmental protection, and hazard mitigation. It will also highlight interdisciplinary research connecting geomechanical engineering with computational intelligence, data science, and advanced sensing technologies.
Topics of Interest
- The special session invites original research papers and case studies on topics including, but not limited to:
- Machine learning approaches for geomechanical parameter prediction and constitutive modelling
- Data-driven modelling in computational geomechanics (FEM, DEM, CFD–DEM, multiphysics models)
- Physics-informed neural networks for geomechanical simulations
- AI applications in slope stability, landslides, and disaster risk assessment
- AI-based interpretation of geospatial and field monitoring data for climate science
- Applications in AI in construction, mining and renewable energy
This session will provide a platform for interdisciplinary discussion and collaboration between experts in geomechanical engineering, computational mechanics, and artificial intelligence. The session aims to showcase emerging research trends, encourage knowledge exchange, and identify future research directions in AI-enabled geomechanics for sustainable and resilient infrastructure systems.
Paper Submission :
Potential authors may submit their manuscripts for presentation consideration through ICETCI 2026 submission system electronically at https://edas.info/N34670, following the conference guidelines. All submissions will go through peer review process. To submit your paper to this special session, you have to choose our special session title on the submission page.
Important Dates
| Last Date for Paper Submission | Apr 05, 2026 |
| Final Notification of Review Outcomes | Jun 15, 2026 |
| Submission of Final Paper | Jun 30, 2025 |
Organizers :
Dr. Soukat Kumar Das is presently working as an Assistant Professor in the Department of Civil Engineering at the National Institute of Technology (NIT) Rourkela, India. He received his PhD in Civil Engineering from IIT Kanpur in 2021, an MTech from IIT Roorkee, and a B.E. from Jadavpur University. Prior to joining NIT Rourkela, he worked as a Postdoctoral Researcher at King Abdullah University of Science and Technology (KAUST), Saudi Arabia. Dr. Das leads the Renewable Energy & Geomechanics Applications Laboratory (REGAL-Lab) at NIT Rourkela. His research focuses on granular mechanics, renewable energy systems, computational geomechanics, DEM–FEM coupling, constitutive modelling of geomaterials, and AI/ML-enabled modelling for energy and sustainability applications. His current work spans carbon sequestration, geothermal energy systems, granular dampers, bioinspired granular barriers for coastal protection, and rover wheel–soil interaction using data-driven modelling. He has published extensively in leading international journals and serves as a reviewer for several top-tier journals in geomechanical and computational mechanics. Dr. Das actively supervises PhD, MTech, and undergraduate students and is involved in multiple nationally and internationally funded research projects aligned with sustainability, disaster resilience, and advanced infrastructure systems.
Lab Website: https://regal-lilac.vercel.app/; Email: dassoukat@nitrkl.ac.in; Phone:+91-7881104501
Dr. Panthadeep Bhattacharjee received his Ph.D. in Computer Science and Engineering from the Indian Institute of Technology Guwahati (IITG). His broad research interests include data mining, machine learning, pattern recognition, and incremental algorithms. He obtained his M.Tech in Computer Science and Engineering from the National Institute of Technology Durgapur (NITD). During his master’s program, he developed an optimal virtual keyboard in the Bengali language aimed at improving text entry speed. Dr. Bhattacharjee completed his B.Tech in Information Technology from Assam University, Silchar. He completed his higher secondary education from the prestigious Cotton University (formerly Cotton College), Guwahati. Prior to joining National Institute of Technology Rourkela, Dr. Bhattacharjee worked as an Assistant Professor in the Department of Computer Science and Engineering at Indian Institute of Information Technology Guwahati (IIITG). He also served as an Assistant Professor in the School of Computer Engineering at KIIT Deemed to be University, Bhubaneswar. Dr. Bhattacharjee has been a professional member of the Association for Computing Machinery (ACM) since 2016. He received the Best Thesis Award in the Ph.D. Research Symposium track at the International Conference on Distributed Computing and Internet Technology (ICDCIT) 2022. His research primarily focuses on developing incremental algorithms for handling dynamic data, particularly for mining clusters and detecting outliers. As part of his research, Dr. Bhattacharjee conducted one of the most comprehensive studies on density-based clustering algorithms proposed since 1996, covering developments over a span of 23 years. He was also offered a postdoctoral research position at the University of Porto, Portugal, for a project titled “Generating Artificial Data for ML Algorithms.”
Lab Website: https://madept-lab.vercel.app/; Email: bhattacharjeep@nitrkl.ac.in