Selected Projects

Six quick cards—click a title to see the full page with What · Why · How · Results . Github (Implementation details)

2D Linear Elasticity via PINN

Physics-informed NN for fast, physics-consistent field predictions.

PINNFEM val loss 2.22

Melting-Point Prediction (2-Level Ensemble)

Stacked RF/XGB/LGBM/MLP with SHAP-guided features.

R² ≈ 0.83~3.041k samples 2 level Ensemble

Oxidation-State Assignment

Soft-voting ensemble on lean OQMD/ICSD data.

Proxy R² ≈ 0.91~7k OQMD Weighted soft voting

Semantic Band-Gap (LLM + KG)

RDF/SPARQL schema with LLM-assisted, explainable queries.

RDF/SPARQLLLM Explainable

Materials Database App

Auto-ETL + Flask UI to track datasets → features → results.

Auto-ETLFlask + SQLite CRUD

Formation-Energy Prediction

AutoML baseline with Matminer features and MAE-first selection.

R² 0.971–0.998Matminer PyCaret