Rajdipn | IIT Delhi Abu Dhabi

Research Areas

Digital Twins and Physics AI Data-Physics Fusion and Bayesian State Estimation Scientific Machine Learning and Neural Operators Uncertainty Quantification and Reliability System Identification and Model-Form Error Learning Structural Health Monitoring and Life Prediction

Biosketch

Dr. Rajdip Nayek is an Assistant Professor in the Department of Applied Mechanics at the Indian Institute of Technology Delhi and is currently serving on faculty secondment at IIT Delhi - Abu Dhabi. He received his Ph.D. in Civil Engineering from the University of Waterloo, Canada, following an M.E. from the Indian Institute of Science, Bangalore, and a B. Tech. from the National Institute of Technology Durgapur. Prior to joining IIT Delhi, he was a Postdoctoral Research Associate with the Dynamics Research Group in Mechanical Engineering at the University of Sheffield, UK.

His research focuses on trustworthy physics AI and digital twins for engineering systems, with particular emphasis on data-physics fusion, uncertainty quantification, system identification, model-form error learning, and scientific machine learning. He develops probabilistic methods that combine physics-based models with sensor data to identify hidden states, unknown inputs, and modeling discrepancies, enabling reliable prediction and decision-making under uncertainty. His research spans structural health monitoring, infrastructure and marine systems, reliability and life prediction, and uncertainty-aware operator learning.

Awards and Recognitions
  • Teaching Excellence Award, IIT Delhi (2025) – for outstanding teaching feedback in a course with a class size above 150
  • University of Waterloo Graduate Scholarship for Academic Excellence (2018–2019)
  • Best Teaching Assistant Award, University of Waterloo, Canada (2017–2019)
  • All India Rank 2 in GATE Civil Engineering (2012), among 40,872 candidates
  • Department Gold Medal, NIT Durgapur (2012) – First position in Civil Engineering
Recent Publications
  • Lone, S. N., De, S., & Nayek, R. (2026). α-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification. Computer Methods in Applied Mechanics and Engineering, 449, 118552.
  • Kumar, S., Tripura, T., Nayek, R., & Chakraborty, S. (2026). From local interactions to global operators: Scalable Gaussian process operator for physical systems. Journal of Computational Physics, 114785.
  • Kumar, S., Nayek, R., & Chakraborty, S. (2025). Towards Gaussian Process for operator learning: An uncertainty-aware resolution-independent operator learning algorithm for computational mechanics. Computer Methods in Applied Mechanics and Engineering, 435, 117664.
  • Kashyap, S., Rogers, T. J., & Nayek, R. (2024). A Gaussian-process assisted model-form error estimation in multiple-degrees-of-freedom systems. Mechanical Systems and Signal Processing, 216, 111474.
  • Nayek, R., Chakraborty, S., & Narasimhan, S. (2019). A Gaussian process latent force model for joint input-state estimation in linear structural systems. Mechanical Systems and Signal Processing, 128, 497–530.