ML-DiCE
Developed a machine learning framework integrating random forest and neural networks to predict diffusion coefficients in alloys across multiple diffusion modes, achieving high accuracy (R² > 0.90).
Know More
CO2-RR Reduction Catalysts
Designed TiO2/MXene nanocomposite catalysts for electrochemical CO2 reduction, achieving ~99% Faradaic efficiency and revealing reaction mechanisms via density functional theory.
Know More
Thermal Conductivity under Irradiation
Investigated irradiation-induced changes in anisotropic thermal conductivity using combined experiments and Phonon-DFT simulations, showing significant reduction due to defect-driven phonon scattering.
Know More
Phonon Transport in SEI
Analyzed phonon-mediated thermal transport in SEI materials, highlighting the role of grain size and temperature in heat dissipation mechanisms at the atomic scale.
Know More
Data Analysis: biochar
Demonstrated that biochar reduces nanoplastic absorption in plants and mitigates toxicity, contributing to sustainable agricultural and environmental remediation strategies.
Know More
ML study: nanoplastic
Applied machine learning to uncover microbial interaction networks responsible for plastic degradation across environmental systems.
Know More
Mechanical Behavior in Alloys
Combined atomistic simulations and data-driven modeling to understand deformation mechanisms and slip resistance in advanced alloys.
Know More
hp-Adaptivity in MOOSE framework
Equipped LibMesh C++ library with smoothness based hp-adaptivity and added the same in MOOSE finite element framework as an intern at Idaho National Laboratory.
Know More
GNN-Dice
Graph Neural Network based modeling of Li-ion transport through Solid Electrolyte Interphase in Li-ion battery.