Disentangle Structure-Spectrum Relationship with Physics-Informed Generative AI

The discovery of new materials relies on the interpretation of diverse measurements, such as spectral responses. The relationships between X-ray absorption near edge structure (XANES) line shape and material structures are often hidden in the complex data and challenging to explore beyond the first coordination shell. In this work, we overcome the challenge with a new machine learning framework: Rank-constrained Adversarial Autoencoders.

Adversarial autoencoders are generative models. For the XANES problem specifically, the model results in the mapping of a large database of spectra to a reduced dimensional latent space. However, the latent space variables themselves typically do not have any direct, physical meaning. To address the need for a physically interpretable latent space, we developed a novel constraint inspired by the rank correlation coefficient. Implementation of this constraint drives each dimension of the latent space to represent a target property, e.g. oxidation state or second shell coordination number in the transition metal oxide crystals considered in this study. The decoder was then utilized to reconstruct how the spectrum shape responds to the change of a structure descriptor, i.e., an individual dimension of the latent space. The algorithm not only reproduces known trends in the literature but also reveals unintuitive ones that are visually indiscernible in large datasets.