AI-Driven Expansion and Application of the Alexandria Database

TL;DR

This paper introduces a multi-stage AI workflow that significantly enhances materials discovery, expanding the Alexandria database with millions of structures and stable compounds, and providing tools for further research.

Contribution

The authors develop an integrated AI-driven pipeline combining generative models, machine learning potentials, and neural networks, resulting in a large, validated materials database and improved predictive models.

Findings

Achieved 99% success rate in identifying stable compounds within 100 meV/atom.

Expanded the Alexandria database to 5.8 million structures with 175,000 stable compounds.

Released a large dataset with structures, forces, and stresses for training universal force fields.

Abstract

We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches. By combining the Matra-Genoa generative model, Orb-v2 universal machine learning interatomic potential, and ALIGNN graph neural network for energy prediction, we generated 119 million candidate structures and added 1.3 million DFT-validated compounds to the ALEXANDRIA database, including 74 thousand new stable materials. The expanded ALEXANDRIA database now contains 5.8 million structures with 175 thousand compounds on the convex hull. Predicted structural disorder rates (37-43%) match experimental databases, unlike other recent AI-generated datasets. Analysis reveals fundamental patterns in space group distributions, coordination environments, and phase stability networks, including sub-linear scaling of convex hull connectivity. We release the complete dataset, including sAlex25 with 14 million out-of-equilibrium structures containing forces and stresses for training universal force fields. We demonstrate that fine-tuning a GRACE model on this data improves benchmark accuracy. All data, models, and workflows are freely available under Creative Commons licenses.