Machine-Learning-Optimized Perovskite Nanoplatelet Synthesis
This work addresses the need for efficient material optimization in renewable energy and devices, offering a method that reduces reliance on trial and error and is applicable to other nanocrystal syntheses, though it appears incremental as it builds on existing machine-learning approaches.
The researchers tackled the tedious process of optimizing perovskite nanoplatelet synthesis by merging three machine-learning models with Bayesian Optimization, achieving a dramatic improvement in quality using only about 200 syntheses and predicting PL emission maxima to obtain previously unobtainable 7 and 8 ML NPLs.
With the demand for renewable energy and efficient devices rapidly increasing, a need arises to find and optimize novel (nano)materials. This can be an extremely tedious process, often relying significantly on trial and error. Machine learning has emerged recently as a powerful alternative; however, most approaches require a substantial amount of data points, i.e., syntheses. Here, we merge three machine-learning models with Bayesian Optimization and are able to dramatically improve the quality of CsPbBr3 nanoplatelets (NPLs) using only approximately 200 total syntheses. The algorithm can predict the resulting PL emission maxima of the NPL dispersions based on the precursor ratios, which lead to previously unobtainable 7 and 8 ML NPLs. Aided by heuristic knowledge, the algorithm should be easily applicable to other nanocrystal syntheses and significantly help to identify interesting compositions and rapidly improve their quality.