My interests lie in working on challenging theory and coding problems of predictions in physics and applied mathematics. Currently, I work on data assimilation problems using both deeplearning and physics-based techniques with interest in large dynamical systems such as the ocean. Another line of my work explores the possible application of covariant Lyapunov vectors( errors along these directions grow fastest) in the uncertainty quantification of model forecasts. As I come from a Physics background this gives me the edge to analyse the system from both its theoretical underpinning as well as a computational perspective. Broadly, I categorize my research interests in sequential state estimation, quantum computation, physics-inspired deep learning architectures, uncertainty quantification in deep learning, and climate data science.