The Battery Genome Project: AI for Energy Storage

To train participants to predict, screen, and validate next-gen battery materials using an end-to-end workflow: DFT (Quantum ESPRESSO) → ML ranking (Materials Project + Python) → ion-transport insights (LAMMPS MD).

• Understand where DFT, ML, and MD fit in battery materials discovery.
• Run and interpret DFT outputs (band/DOS) relevant to conductivity and stability proxies.
• Build a Materials Project → Python dataset pipeline for materials informatics.
• Engineer descriptors (pymatgen/matminer), train/evaluate ML models, and rank candidates.
• Simulate ion diffusion in LAMMPS and compute diffusion coefficients across conditions.
• Translate results into synthesis prioritization and performance-relevant insights.

📅 Day 1 — Atomic-Scale Modeling with DFT (Quantum ESPRESSO)

• Battery materials discovery workflow: where DFT fits and what it predicts
• DFT essentials for energy materials: electronic structure, band structure basics, DOS interpretation
• Practical setup: pseudopotentials, k-points, convergence, input file structure
• Hands-on: Configure and run a Quantum ESPRESSO calculation for a candidate anode crystal structure and extract electronic outputs
• Deliverable: A Density of States (DOS) plot with a short interpretation of conductivity relevance

📅 Day 2 — Machine Learning Screening at Scale (Materials Project + Python)

• Materials informatics pipeline: descriptors → model → ranking → validation strategy
• Data sourcing via Materials Project API and building a usable training dataset
• Property prediction: feature engineering with pymatgen/matminer, model selection, evaluation basics
• Hands-on: Mine a large materials dataset, build features, train a Random Forest model to predict a target proxy (e.g., voltage/capacity-related)
• Deliverable: Top 5 predicted candidate materials shortlist for synthesis prioritization

📅 Day 3 — Ion Transport & Charging-Speed Insights (LAMMPS Molecular Dynamics)

• Why ion diffusion governs rate performance: diffusion coefficient, transport physics basics
• MD setup fundamentals: force fields/potentials, temperature control, simulation workflow
• Turning trajectories into insight: diffusion coefficient estimation and temperature dependence
• Hands-on: Run a simple LAMMPS Li-ion diffusion simulation and compute diffusion coefficients across conditions
• Deliverable: An Arrhenius plot projecting diffusion-driven performance across temperatures

• UG/PG/PhD students, researchers, and professionals in Materials Science, Chemistry, Physics, Chemical Engineering, Energy, or related fields.
• Basic Python familiarity is helpful; no prior DFT/MD experience required (guided notebooks + templates provided).
• Interest in batteries, energy storage, computational materials, or materials informatics

• Set up and execute Quantum ESPRESSO calculations (pseudopotentials, k-points, convergence).
• Generate and interpret a DOS plot for conductivity relevance.
• Collect materials data via Materials Project API and create ML-ready datasets.
• Train a baseline model (e.g., Random Forest), evaluate it, and produce a ranked shortlist.
• Run a Li-ion diffusion MD workflow and compute diffusion coefficients + Arrhenius trends.
• Build a reusable workflow: DFT → ML screening → transport validation.