Learning from imperfections: constructing phase diagrams from atomic imaging of fluctuations

TL;DR

This paper introduces a novel approach using atomic-scale imaging and statistical physics to construct phase diagrams from imperfections, revealing insights into material behavior across composition and temperature ranges.

Contribution

It develops a framework combining atomic imaging, statistical physics, and machine learning to infer phase behavior and atomic interactions from imperfections in materials.

Findings

Atomic-scale studies can map finite regions of chemical space.

The framework reveals effective atomic interactions driving segregation.

A variational autoencoder identifies anomalous behaviors in phase diagrams.

Abstract

Materials characterization and property measurements are a cornerstone of material science, providing feedback from synthesis to applications. Traditionally, a single sample is used to derive information on a single point in composition space, and imperfections, impurities and stochastic details of material structure are deemed irrelevant or complicating factors in analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information on a finite area of chemical space. This information can be used to reconstruct the material properties in a finite composition and temperature range. We develop a statistical physics-based framework that incorporates chemical and structural data to infer effective atomic interactions driving segregation in a La5/8Ca3/8MnO3 thin-film. A variational autoencoder is used to determine anomalous behaviors in the composition phase diagram. This study provides a framework for creating generative models from diverse data and provides direct insight into the driving forces for cation segregation in manganites.