A self-driving lab for solution-processed electrochromic thin films

TL;DR

This paper presents a self-driving laboratory that uses automation and machine learning to rapidly optimize the processing parameters of solution-processed electrochromic thin films, improving development speed and material performance.

Contribution

It introduces an integrated system combining automation, image and spectral analysis, and Bayesian optimization for efficient electrochromic coating development.

Findings

Increased throughput in electrochromic film development.

Effective identification of optimal processing parameters.

Applicable to various solution-processed materials.

Abstract

Solution-processed electrochromic materials offer high potential for energy-efficient smart windows and displays. Their performance varies with material choice and processing conditions. Electrochromic thin film electrodes require a smooth, defect-free coating for optimal contrast between bleached and colored states. The complexity of optimizing the spin-coated electrochromic thin layer poses challenges for rapid development. This study demonstrates the use of self-driving laboratories to accelerate the development of electrochromic coatings by coupling automation with machine learning. Our system combines automated data acquisition, image processing, spectral analysis, and Bayesian optimization to explore processing parameters efficiently. This approach not only increases throughput but also enables a pointed search for optimal processing parameters. The approach can be applied to various solution-processed materials, highlighting the potential of self-driving labs in enhancing materials discovery and process optimization.