Accelerating Materials Science through AI

Accurate Prediction Models,Robust Software Frameworks,Curated Materials Datasets

Models

Web apps implementing pre-trained property prediction models.

Models

megnet.crystals.ai

MatErials Graph Network (MEGNet) models for formation energies, band gaps, elastic constants and other properties of crystals.

Materials Virtual Lab
May 14 2019
Models

dnn.crystals.ai

Deep neural networks for formation energy prediction of garnets and perovskites.

Materials Virtual Lab
May 14 2019

Tools

Software frameworks for robust AI in materials science.

MEGNet

Library for building graph networks for materials science developed by the Materials Virtual Lab.

Veidt

Library for machine learning for materials science developed by the Materials Virtual Lab.

Matminer

Data mining tool for materials science developed by the Hacking Materials group.

CGCNN

Implementation of the Crystal Graph Convolutional Neural Network (CGCNN) for prediction of crystal properties.

AENet

The Atomic Energy NETwork (AENet) package is a collection of tools for the construction and application of atomic interaction potentials based on artificial neural networks (ANN) developed by atomistic.net/.

Datasets

Curated datasets for reproducible AI in materials science.

MP 2019.4.1

Graphs and formation energies of ~133,000 Materials Project Crystals as of Apr 1 2019.

MP 2018.6.1

Graphs, formation energies, band gaps and elastic constants of ~60,000 Materials Project Crystals as of Jun 1 2018.

QM9 Molecules

Graphs of the QM9 set of ~134,000 molecules developed by Faber et al.

SNAP

Datasets for the development of Spectral Neighbor Analysis Potentials for various elements, alloys and compounds.

Get in Touch

This website is maintained by the Materials Virtual Lab at the University of California, San Diego. Please send us an email if you have any feedback on this site, especially on new models, tools or datasets that you would like included.