Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials

TL;DR

This paper introduces MatGAN, a GAN-based model that efficiently generates novel, chemically valid inorganic materials, significantly accelerating inverse design and screening processes in materials science.

Contribution

The study presents a GAN model trained on a large database that can generate chemically valid inorganic materials with high novelty without explicit chemical rule enforcement.

Findings

92.53% novelty in generated samples

84.5% chemically valid samples

Effective for inverse materials design

Abstract

A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties. One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database. Here, we propose a generative machine learning model (MatGAN) based on a generative adversarial network (GAN) for efficient generation of new hypothetical inorganic materials. Trained with materials from the ICSD database, our GAN model can generate hypothetical materials not existing in the training dataset, reaching a novelty of 92.53% when generating 2 million samples. The percentage of chemically valid (charge neutral and electronegativity balanced) samples out of all generated ones reaches 84.5% by our GAN when trained with materials from ICSD even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules. Our algorithm could be used to speed up inverse design or computational screening of inorganic materials.