I work at the intersection of computational chemistry, catalysis, and data science, focusing on building physically interpretable models for reaction systems and materials design.
Research Profile
- 🧪 Research: Heterogeneous catalysis, reaction mechanisms, adsorption energetics
- 🧠 Focus: Machine learning for chemical systems & descriptor-based modeling
- 📊 Methods: Density Functional Theory (DFT), statistical learning, reaction networks
- 💻 Tools: Python, NumPy, pandas, scikit-learn, ASE, RDKit, VASP, LAMMPS
- Catalytic reaction energy landscapes
- Descriptor-based materials screening
- Data-driven reaction mechanism discovery
- Multi-scale modeling of catalytic systems
- Scientific visualization for high-impact publications
A computational framework for analyzing catalytic reaction pathways and energy profiles using DFT-derived datasets.
Machine learning workflow to predict catalytic performance from structural and electronic descriptors.
Publication-quality figure generation tools for heatmaps, volcano plots, and reaction networks.
DFT Calculations → Feature Engineering → ML Models → Reaction Prediction → Visualization → Publication
problem definition → mechanistic understanding → material/process design → validation → deployment + optimization.
Problem → EDL physics → Feature engineering → Dataset → ML/DL model → Physics-informed hybrid → Optimization → Experiment → Digital twiML