Inverse Design of Composite Metal Oxide Optical Materials based on Deep Transfer Learning

TL;DR

This paper introduces TLOpt, a transfer learning-based method combining neural networks and optimization algorithms to accurately inverse design composite metal oxide materials with desired optical properties, addressing small dataset challenges.

Contribution

The paper presents a novel transfer learning approach integrated with global optimization for inverse optical materials design, improving accuracy with limited data.

Findings

High accuracy in inverse design of material compositions.

Effective handling of small datasets through transfer learning.

Successful application to composite metal oxide materials.

Abstract

Optical materials with special optical properties are widely used in a broad span of technologies, from computer displays to solar energy utilization leading to large dataset accumulated from years of extensive materials synthesis and optical characterization. Previously, machine learning models have been developed to predict the optical absorption spectrum from a materials characterization image or vice versa. Herein we propose TLOpt, a transfer learning based inverse optical materials design algorithm for suggesting material compositions with a desired target light absorption spectrum. Our approach is based on the combination of a deep neural network model and global optimization algorithms including a genetic algorithm and Bayesian optimization. A transfer learning strategy is employed to solve the small dataset issue in training the neural network predictor of optical absorption spectrum using the Magpie materials composition descriptor. Our extensive experiments show that our algorithm can inverse design the materials composition with stoichiometry with high accuracy.