The Battery Genome Project: AI for Energy Storage

About This Course

This three-week, hands-on course is designed to equip learners with practical skills to perform atomic-scale simulations and data-driven screening for discovering next-generation battery materials. You will compute electronic properties using DFT, build an ML pipeline to rank candidate materials using Materials Project datasets, and simulate Li-ion diffusion with molecular dynamics to understand how transport behavior impacts charging-rate performance.

Each module includes a tangible output that you can showcase at the end of the course:

• Module 1: Generate a DOS plot
• Module 2: Create a top-5 candidate materials shortlist
• Module 3: Produce an Arrhenius diffusion plot

Aim

The course aims to train participants to predict, screen, and validate advanced battery materials through an end-to-end workflow: DFT (Quantum ESPRESSO) → ML ranking (Materials Project + Python) → Ion-transport insights (LAMMPS MD).

Course Objectives

By the end of this course, participants will be able to:

• Understand how DFT, ML, and MD contribute to battery materials discovery
• Run and interpret DFT outputs (band/DOS) for conductivity and stability
• Build a Materials Project → Python dataset pipeline for materials informatics
• Engineer descriptors using pymatgen/matminer, train ML models, and rank materials
• Simulate ion diffusion in LAMMPS and compute diffusion coefficients
• Translate computational results into actionable synthesis and performance insights

Course Structure

Module 1: Atomic-Scale Modeling with DFT (Quantum ESPRESSO)

• Understand where DFT fits in the battery materials discovery workflow
• Learn electronic structure basics, band structure, and DOS interpretation
• Set up practical calculations: pseudopotentials, k-points, convergence, and input files
• Hands-on: Run a Quantum ESPRESSO calculation for a candidate anode and extract electronic outputs

Deliverable: A DOS plot with a brief interpretation for conductivity relevance

Module 2: Machine Learning Screening at Scale (Materials Project + Python)

• Materials informatics pipeline: descriptors → model → ranking → validation
• Access data via Materials Project API and prepare datasets
• Feature engineering with pymatgen/matminer, model selection, and evaluation
• Hands-on: Train a Random Forest model to predict voltage/capacity proxies

Deliverable: Top 5 predicted candidate materials shortlist

Module 3: Ion Transport and Charging-Speed Insights (LAMMPS Molecular Dynamics)

• Understand diffusion coefficients and transport basics relevant for charging performance
• Set up MD simulations: force fields, temperature control, workflow
• Analyze trajectories to estimate diffusion and temperature dependence
• Hands-on: Run Li-ion diffusion simulations and compute coefficients

Deliverable: Arrhenius plot showing diffusion-based performance across temperatures

Who Should Enrol?

This course is ideal for:

• UG/PG/PhD students, researchers, and professionals in Materials Science, Chemistry, Physics, Chemical Engineering, Energy or related fields
• Learners interested in batteries, energy storage, computational materials, and materials informatics

Basic Python familiarity is helpful, but no prior DFT/MD experience is required. Guided notebooks and templates are provided.