Research Projects
Extrapolative ML models for Copolymers
Coarse Grained MD generated data of Adsorption Free Energy for Copolymer Chains has been tested for different ML algorithms extrapolative ability. We determined Neural Networks and XG boost are efficient for such tasks if trained on a sufficient data distributed in wide properties range.
Explainabale ML model for binary LJ fluids
The RDFs of a binary mixture with varying compositions and temperatures are collected from molecular dynamics (MD) simulations to establish and validate the ML model. In this ML pipeline, RDFs are discretized in order to reduce the output dimensions of the model. This, in turn, improves the efficacy and reduces the complexity of an ML RDF model.
Size and Shape driven phase behaviour of Polymer Nano-Composites
In this project we have addressed challenges in PNC's properties for different applications. We have employed MC MD in Kremer-Grest framework. Key innovation was to design such PNC's with a higher mechanical properties without losing electrical properties- Major challenge in industries.
Soon we are submitting this work in ACS- Macro Letters.
Machine Learning Models for Predicting Properties of Fiber Reinforced Polypropylenes
Government of India and HPCL -leading Oil Company sponsored industrial project. Objective was to implement ML tools in experimental data of different oil batches for properties prediction and employing inverse design framework to determine composition of batch from properties.
Non-solvent driven aggregation kinetics of Iron Oxide Nanoparticles through FNP
For a biomedical applications, IONPs encapsulation through PLGA is desired but due to aggregation timescale mismatch there is challenge to effective encapsulate IONP's. I have done mathematical modelling for total interparticle potentials through Extended DLVO theory for controlled and guided experiments. Research carried out in NTNU,Norway. In feb 2026 we are submitting our work in JCIS, Colloids and interfaces.
Embedding Driven Molecular Property Prediction and Novel Molecular Generation
Major Part of the work is carried out by U.G students of Patra Research Group. I have carried out feature engineering part in this revolutionary Gen-AI project.
