Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials
This work addresses the problem of inverse design for materials scientists by providing an efficient sampling method, though it is incremental as it applies an existing GAN framework to a new domain.
The paper tackles the challenge of efficiently searching the chemical design space for inorganic materials by proposing MatGAN, a GAN-based model that generates hypothetical materials with 92.53% novelty and 84.5% chemical validity without explicit rules.
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.