Building interpretable machine learning force fields and explainable AI methods for molecular systems and space-critical operations.
Indian Association for the Cultivation of Science, Kolkata · M.Sc. 2nd Year (Integrated Ph.D.) · AIR 5
I research machine learning force fields (MLFFs) with a personal focus on their explainability — understanding not just what a model predicts, but why. My work under Dr. Avisek Das at IACS explores water–peptide dynamics using custom MD simulation pipelines built from scratch, where I develop information-theoretic approaches to evaluate chemical descriptors and build interpretable ML surrogates.
Across domains, my research is unified by a single question: how do we build AI systems that are not only accurate, but trustworthy and transparent? Whether the substrate is a hydrogen bonding network in a solvent mixture or a CubeSat telemetry stream, I pursue methods where every prediction can be interrogated, explained, and validated.
Highlights from 14+ research outputs. Preprints and full conference papers. Single-authored unless noted.
Open for doctoral research opportunities, collaborations, and discussions on computational chemistry and explainable AI.
Available upon request from 5 academic supervisors, including 3 Fellows of the Royal Society of Chemistry (FRSC).
Full referee details provided with applications.