Spectroscopy-Guided Discovery of Three-Dimensional Structures of Disordered Materials with Diffusion Models

TL;DR

This paper introduces a diffusion model-based framework that predicts and tailors 3D disordered material structures from spectral data, enabling scalable and property-specific materials design.

Contribution

The work presents a novel diffusion model approach for structure prediction from spectra, capable of generating large-scale structures from limited data, advancing materials discovery.

Findings

Successfully reproduces key structural features from XANES spectra

Guides atomic arrangements to match target spectra

Generates realistic large-scale structures from small datasets

Abstract

The ability to rapidly develop materials with desired properties has a transformative impact on a broad range of emerging technologies. In this work, we introduce a new framework based on the diffusion model, a recent generative machine learning method to predict 3D structures of disordered materials from a target property. For demonstration, we apply the model to identify the atomic structures of amorphous carbons ($a$-C) as a representative material system from the target X-ray absorption near edge structure (XANES) spectra--a common experimental technique to probe atomic structures of materials. We show that conditional generation guided by XANES spectra reproduces key features of the target structures. Furthermore, we show that our model can steer the generative process to tailor atomic arrangements for a specific XANES spectrum. Finally, our generative model exhibits a remarkable scale-agnostic property, thereby enabling generation of realistic, large-scale structures through learning from a small-scale dataset (i.e., with small unit cells). Our work represents a significant stride in bridging the gap between materials characterization and atomic structure determination; in addition, it can be leveraged for materials discovery in exploring various material properties as targeted.