A new approach to synthesizing targeted particles of materials has been developed by researchers from PNNL. This method uses data science and machine learning (ML) techniques, which streamlines the process and makes it more efficient. The study, published in the Chemical Engineering Journal, details how the researchers addressed two main issues: identifying feasible experimental conditions and predicting potential particle characteristics for a given set of synthetic parameters.
The ML model they developed can accurately predict potential particle size and phase based on synthesis reaction parameters. By training the model on careful experimental characterization, the researchers were able to identify promising and feasible synthesis parameters to explore. Additionally, the search and ranking algorithm used revealed the previously overlooked importance of pressure applied during the synthesis on the resulting phase and particle size.
This innovative approach represents a paradigm shift for metal oxide particle synthesis and has the potential to significantly economize time and effort expended on ad hoc iterative synthesis approaches. For more information, Juejing Liu et al’s study can be found in the Chemical Engineering Journal with DOI: 10.1016/j.cej.2023.145216.