As a Ph.D. in Mechanical Engineering, my research focuses on the intersection of computational mechanics and machine learning. Within computational mechanics, I have developed extensive expertise in material modeling, non-linear finite element analysis (FEA), and fracture mechanics, encompassing brittle, ductile, and quasi-brittle materials, as well as rate-dependent viscoplasticity. Additionally, I have developed several machine learning algorithms for partial differential equations (PDEs) and bypass the computationally expensive numerical simulations, rigorously worked on physics-informed neural networks, operator learning techniques and uncertainty quantification methods. My overarching goal is to leverage machine learning techniques to accelerate computational simulations in fields such as mechanics, phase separation, and weather prediction.

Material characterization and phase field fracture modeling of 3D printed
thermoplastics, composites, and nanocomposites. Bayesian calibration and uncertainty quantification using numerical models and experiments. Developing data-driven methods for applications in computational fracture mechanics especially phase-field fracture. Physics informed neural networks to accelerate forward and inverse problems. Machine learning for PDE governed systems. Adaptive sampling methods for accelerating physics informed neural networks. Characterizing fracture in chemically strengthened glass using phase-field modelling. Numerical optimization, Numerical analysis of Partial differential equations (spectral methods, non-linear PDEs), Continuum mechanics and Fracture mechanics, Machine learning.