Inverse Materials Design via Joint Generation of Crystal Structures and Local Electronic Descriptors

TL;DR

This paper introduces a diffusion-based generative model that jointly creates crystal structures and local electronic descriptors, improving inverse materials design by enhancing diversity, stability, and property targeting accuracy.

Contribution

The authors develop a novel joint denoising framework for crystal structures and electronic descriptors, demonstrating improved success rates and physical validity in generated materials.

Findings

Joint models outperform structure-only baselines in success rates.

Generated electronic descriptors closely match DFT references.

Descriptors enhance structural diversity and property targeting.

Abstract

Inverse design of inorganic crystals, in which structures are generated to satisfy a target property while preserving diversity and physical plausibility, remains more demanding than ab initio generation, as property conditioning can degrade the structural quality that current generative models otherwise achieve. We propose a diffusion framework that jointly denoises crystal-structure variables and site-resolved local electronic descriptors through a shared score network. As representative descriptors, we adopt Bader charge and atomic density of states (atomic DOS). Under both band-gap and formation energy conditioned generation, the joint models achieved higher success rates than the structure-only baseline in most target conditions, while simultaneously increasing the fraction of generated structures that satisfy uniqueness, novelty, thermodynamic stability, and physical validity (VSUN criteria). A dummy-variable control confirms that these gains originate from the electronic content of the descriptors rather than from auxiliary site-wise variables. The generated Bader charges agree with DFT references with an MAE of 5.5e-2 e on stable structures, and the generated atomic DOS captures the coarse spectral profile of the DFT reference around the modal accuracy range, although finer details and accuracy vary with elemental species. These results establish local electronic descriptors as effective generative variables that serve two complementary roles: broadening the explored materials space through increased structural diversity, and mitigating the trade-off between property targeting and structural quality by guiding the structural trajectory toward electronically plausible configurations during joint denoising.