Combining Variational Autoencoders and Physical Bias for Improved Microscopy Data Analysis

TL;DR

This paper introduces a physics-augmented machine learning approach combining Variational Autoencoders with physics-based loss functions to improve the segmentation and analysis of microscopy data, effectively identifying physical regions in complex material images.

Contribution

It presents a novel unsupervised method that integrates physical priors into VAEs for enhanced interpretability and segmentation of microscopy data, applicable to various materials.

Findings

Effective in extracting meaningful features from microscopy images

Successfully applied to diverse materials like NiO-LSMO, BiFeO3, and graphene

Improves identification of physical regions and boundaries in data

Abstract

Electron and scanning probe microscopy produce vast amounts of data in the form of images or hyperspectral data, such as EELS or 4D STEM, that contain information on a wide range of structural, physical, and chemical properties of materials. To extract valuable insights from these data, it is crucial to identify physically separate regions in the data, such as phases, ferroic variants, and boundaries between them. In order to derive an easily interpretable feature analysis, combining with well-defined boundaries in a principled and unsupervised manner, here we present a physics augmented machine learning method which combines the capability of Variational Autoencoders to disentangle factors of variability within the data and the physics driven loss function that seeks to minimize the total length of the discontinuities in images corresponding to latent representations. Our method is applied to various materials, including NiO-LSMO, BiFeO3, and graphene. The results demonstrate the effectiveness of our approach in extracting meaningful information from large volumes of imaging data. The fully notebook containing implementation of the code and analysis workflow is available at https://github.com/arpanbiswas52/PaperNotebooks