Machine Learning-Directed Navigation of Synthetic Design Space: A Statistical Learning Approach to Controlling the Synthesis of Perovskite Halide Nanoplatelets in the Quantum-Confined Regime

The design of a chemical synthesis often relies on a combination of chemical intuition and Edisonian trial-and-error methods. Such methods are not just inefficient but inherently limited in their ability to quantitatively predict synthetic outcomes, easily defeated by complex interplays between variables, and oftentimes based on suppositions that are limited in validity. The synthesis of nanomaterials has been especially prone to empiricism given the combination of complex chemical reactivity as well as mesoscopic nucleation and growth phenomena spanning multiple temporal and spatial dimensions. Here, utilizing the synthesis of two-dimensional CsPbBr3 nanoplatelets as a model system, we demonstrate an efficient machine learning navigation of reaction space that allows for predictive control of layer thickness down to sub-monolayer dimensions. Support vector machine (SVM) classification and regression models are used to initially separate regions of the design space that yield quantum-confined nanoplatelets from regions yielding bulk particles and subsequently to predict the thickness of quantum-confined CsPbBr3 nanoplatelets that can be accessed under specific reaction conditions. The SVM models are not only just predictive and efficient in sampling the available design space but also provide fundamental insight into the influence of molecular ligands in constraining the dimensions of nanocrystals. The results illustrate a quantitative approach for efficient navigation of reaction design space and pave the way to navigation of more elaborate landscapes beyond dimensional control spanning polymorphs, compositional variants, and surface chemistry.