bandgap-prediction

Multimodal Deep Learning pipeline for crystalline bandgap prediction. Combines 1D X-Ray Diffraction (XRD) patterns with engineered tabular features (Magpie & CrystalNN) using a dual-branch PyTorch ResNet architecture. Features high-throughput data extraction via Materials Project API and automated structural featurization.

Machine-learning screening of lead-free double perovskites with Monte Carlo techno-economic analysis. 3,280 candidates, XGBoost property models, 50,000-iteration TEA per candidate, offline tests and a runnable quickstart.

Website

System-conditioned reparameterization of the SCAN functional for accurate bandgaps: from analytical constraints to machine learning

Quantum-Inspired Hybrid Neural Network for accurate bandgap energy prediction using engineered material features and ensemble deep learning techniques.