<br/>Organically templated metal oxides have been the focus of intense interest for several decades owing to a host of technologically intriguing properties that they can exhibit.  Most of these are produced through exploratory reactions. Unfortunately, most of these reactions are deemed ‘unsuccessful’ in that they do not result in the formation of a new unique phase.  In this work, machine-learning algorithms were trained on reaction data to predict reaction outcomes for the crystallization of templated vanadium selenites is demonstrated. Archived ‘dark’ reactions, both failed and successful attempts at hydrothermal syntheses, were used to create a database.  Physicochemical property descriptions to the raw notebook information using cheminformatics techniques, and the resulting data were used to train a machine-learning model to predict reaction ‘success.’ Inverting the machine-learning model reveals new hypotheses regarding the conditions for successful product formation.  Specifically, the role of amine structures on the in situ reduction of vanadium was probed using longitudinal reactions.  Additionally, the role of oxalic acid in charge density matching was investigated.<br/>

Probing formation mechanisms of templated vanadium selenites using reaction informatics

255th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.