Learning physical properties of liquid crystals with deep convolutional neural networks

Abstract

Machine learning algorithms have been available since the 1990s, but it is much more recently that they have come into use also in the physical sciences. While these algorithms have already proven to be useful in uncovering new properties of materials and in simplifying experimental protocols, their usage in liquid crystals research is still limited. This is surprising because optical imaging techniques are often applied in this line of research, and it is precisely with images that machine learning algorithms have achieved major breakthroughs in recent years. Here we use convolutional neural networks to probe several properties of liquid crystals directly from their optical images and without using manual feature engineering. By optimizing simple architectures, we find that convolutional neural networks can predict physical properties of liquid crystals with exceptional accuracy. We show that these deep neural networks identify liquid crystal phases and predict the order parameter of simulated nematic liquid crystals almost perfectly. We also show that convolutional neural networks identify the pitch length of simulated samples of cholesteric liquid crystals and the sample temperature of an experimental liquid crystal with very high precision.

arXiv comment11 pages, 4 figures, supplementary information; accepted for publication in Scientific Reports

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• scikit-image: Image processing in Python
• Machine learning and the physical sciences
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Insightful classification of crystal structures using deep learning
• History of art paintings through the lens of entropy and complexity
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
• Deep-Learning continuous gravitational waves
• Transient Classification in LIGO data using Difference Boosting Neural Network
• Estimating physical properties from liquid crystal textures via machine learning and complexity-entropy methods
• Deep Convolutional Neural Network Design Patterns

Cited by in corpus (8)

• Determining liquid crystal properties with ordinal networks and machine learning
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Characterizing unstructured data with the nearest neighbor permutation entropy
• Deep Learning Super-Diffusion in Multiplex Networks
• A genetic algorithm for the response of twisted nematic liquid crystals to an applied field
• Gradient dynamics in reinforcement learning
• Nonequilibrium thermodynamics of self-supervised learning
• Interpretable liquid crystal phase classification via two-by-two ordinal patterns