Govinda Anantha Padmanabha
Govinda Anantha Padmanabha has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Thomas Seidl
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
1 shared publication - Konstantinos Karapiperis1 shared publication
- Michal Levin
Department of Materials Science and Engineering, Technion - Israel Institute of Technology, Haifa 3200003, Israel
1 shared publication Miriam Borshevsky
1 shared publication- Nikolaos Bouklas
Cornell University
1 shared publication - Noy Cohen
Department of Materials Science and Engineering Technion -Israel Institute of Technology 3200003 Haifa Israel
1 shared publication
Latest Publications
- Open Access
- 13 March 2026
- Published by Copernicus GmbH
Data-Driven Forecasting of Geophysical Mass Movements
Geophysical mass movements such as landslides and snow avalanches represent major natural hazards, particularly in mountainous regions like the European Alps. Their dynamics arise from heterogeneous material compositions interacting with complex topography, rendering reliable prediction extremely challenging. Although remote sensing techniques provide detailed measurements of terrain shape and ground motion, these observations alone cannot predict mass movements. High-fidelity numerical approaches, such as the Material Point Method (MPM), offer valuable mechanistic insight but are too computationally demanding for real-time or large-scale forecasting. This work introduces a three-dimensional geometric foundation model designed to efficiently learn and predict the spatiotemporal evolution of mass movement events. The framework is trained on high-fidelity MPM simulations validated against high-resolution remote sensing data to construct a dataset spanning diverse topographies and flow behaviours. Leveraging recent advances in operator-based neural networks and Transformer architectures, the model learns geometric and physical attributes directly on three-dimensional manifolds, enabling resolution-invariant prediction and generalization across heterogeneous terrains. The resulting surrogate model rapidly predicts the full evolution of topography, capturing key features such as flow trajectories, runout, and deposition patterns while significantly reducing computational cost compared to conventional high-fidelity numerical solvers. This efficiency allows extensive scenario exploration and broad spatial coverage, making the approach suitable for operational hazard-assessment pipelines and future digital-twin environments. In summary, the proposed framework offers a fast and robust tool for modeling geophysical mass movements, with the potential to significantly enhance large-scale hazard analysis and support next-generation monitoring systems.
- 13 March 2026
- Published by Copernicus GmbH
Open AccessData-Driven Forecasting of Geophysical Mass Movements
Geophysical mass movements such as landslides and snow avalanches represent major natural hazards, particularly in mountainous regions like the European Alps. Their dynamics arise from heterogeneous material compositions interacting with complex topography, rendering reliable prediction extremely challenging. Although remote sensing techniques provide detailed measurements of terrain shape and ground motion, these observations alone cannot predict mass movements. High-fidelity numerical approaches, such as the Material Point Method (MPM), offer valuable mechanistic insight but are too computationally demanding for real-time or large-scale forecasting. This work introduces a three-dimensional geometric foundation model designed to efficiently learn and predict the spatiotemporal evolution of mass movement events. The framework is trained on high-fidelity MPM simulations validated against high-resolution remote sensing data to construct a dataset spanning diverse topographies and flow behaviours. Leveraging recent advances in operator-based neural networks and Transformer architectures, the model learns geometric and physical attributes directly on three-dimensional manifolds, enabling resolution-invariant prediction and generalization across heterogeneous terrains. The resulting surrogate model rapidly predicts the full evolution of topography, capturing key features such as flow trajectories, runout, and deposition patterns while significantly reducing computational cost compared to conventional high-fidelity numerical solvers. This efficiency allows extensive scenario exploration and broad spatial coverage, making the approach suitable for operational hazard-assessment pipelines and future digital-twin environments. In summary, the proposed framework offers a fast and robust tool for modeling geophysical mass movements, with the potential to significantly enhance large-scale hazard analysis and support next-generation monitoring systems.
- 19 September 2025
- Published by Elsevier in International Journal of Engineering Science
- Vol. 217
Physics augmented machine learning discovery of composition-dependent constitutive laws for 3D printed digital materials
- 19 September 2025
- Published by Elsevier in International Journal of Engineering Science
- Vol. 217
Physics augmented machine learning discovery of composition-dependent constitutive laws for 3D printed digital materials