Tackling Data Scarcity with Transfer Learning: A Case Study of Thickness Characterization from Optical Spectra of Perovskite Thin Films

TL;DR

This paper presents thicknessML, a transfer learning-based machine learning model that accurately predicts thin film thickness from optical spectra, effectively addressing data scarcity in perovskite materials and enabling high-throughput characterization.

Contribution

The study introduces a transfer learning workflow and a novel model, thicknessML, for predicting film thickness from optical spectra with limited data, demonstrating significant accuracy improvements.

Findings

Achieved 92.2% accuracy in thickness prediction with transfer learning.

Validated the workflow with experimental data on six perovskite films.

Demonstrated extension to other material classes with minimal literature data.

Abstract

Transfer learning increasingly becomes an important tool in handling data scarcity often encountered in machine learning. In the application of high-throughput thickness as a downstream process of the high-throughput optimization of optoelectronic thin films with autonomous workflows, data scarcity occurs especially for new materials. To achieve high-throughput thickness characterization, we propose a machine learning model called thicknessML that predicts thickness from UV-Vis spectrophotometry input and an overarching transfer learning workflow. We demonstrate the transfer learning workflow from generic source domain of generic band-gapped materials to specific target domain of perovskite materials, where the target domain data only come from limited number (18) of refractive indices from literature. The target domain can be easily extended to other material classes with a few literature data. Defining thickness prediction accuracy to be within-10% deviation, thicknessML achieves 92.2% (with a deviation of 3.6%) accuracy with transfer learning compared to 81.8% (with a deviation of 3.6%) 11.7% without (lower mean and larger standard deviation). Experimental validation on six deposited perovskite films also corroborates the efficacy of the proposed workflow by yielding a 10.5% mean absolute percentage error (MAPE).