🏆 A ranked list of awesome atomistic machine learning projects ⚛️🧬💎.

Python for Materials Machine Learning, Materials Descriptors, Machine Learning Force Fields, Deep Learning, etc.

An evaluation framework for machine learning models simulating high-throughput materials discovery.

Generate random alloys and compute various properties

The Wren sits on its Roost in the Aviary.

Representation Learning from Stoichiometry

LLM-powered agents for scientific research automation

A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces.

Vote on whether you think predicted crystal structures could be synthesised

Data-driven risk-conscious thermoelectric materials discovery

Quantum-inspired Cluster Expansion: formulating chemical space search as QUBOs and Ising models

Examples of using the Novel Materials Discovery (NOMAD) database, especially downloading all chemical formulas.

Additive Manufacturing Mapping of Compositional Spaces with Thermodynamic, Analytical, and Artificial Intelligence Models

Thermodynamics and phase stability of multicomponent alloys using conventional and enhanced sampling techniques applied to the Bragg–Williams Hamiltonian

Isomorphic TypeScript / JavaScript client to aggregate all the official Optimade providers

Using Bayesian optimization via Ax platform + SAASBO model to simultaneously optimize 23 hyperparameters in 100 iterations (set a new Matbench benchmark).

Evolutionary algorithm for development of glassy alloy materials

closed loop materials discovery using error correction learning

AI-Native Autonomous Materials Discovery Platform

Tool to search vast areas of chemical space for magnesium dissolution modulators.

MSc research project on application of Quality-Diversity algorithms for crystal structure prediction

Physics-guided ML system for discovering novel battery cathode materials without crystal structure data. Combines RAG, TRIZ, and evolutionary algorithms.

AI-driven virtual screening platform for molecular interaction prediction and compound prioritization.

Capstone project for my Master's degree. In it, I developed some machine learning models to predict the heat of formation for materials containing 1–3 components.

Project page for "Physics-informed graph neural networks accelerating microneedle simulations towards novelty of micro-nano scale materials discovery" as a part of Romrawin Chumpu's master thesis and publication.

Deep learning platform that predicts material properties and designs novel materials for electronics, energy storage, and manufacturing applications.

🧪 Accelerate materials discovery with MaterialGen, a deep learning platform for predicting properties and designing novel materials for advanced applications.

AI4Science Hackathon Submission: Cost-Effective Active Generative Discovery of MOFs for Carbon Capture