Machine Learning-Based Analysis of Molar and Enantiomeric Ratios and Reaction Yields Using Images of Solid Mixtures

Visual observations are frequently used as a preliminary evaluation of the chemical contents of mixtures, but their accuracy largely depends on the observer’s experience and intuition, which are difficult to share. Here, we report component ratio pre-diction using image-based machine learning (ML), which is applicable to analysis of various solid mixtures, such as mix-tures of organics and inorganics, polymorphous crystals, and enantiomers. The trained model with 300 images could predict the sugar/dietary salt weight ratio from an image within 4% error. The ML prediction pipeline was shown to be broadly ap-plicable to polymorphic glycine, D/L-tartaric acid, and four-component systems. As an application demonstration, we also used our ML system to analyze yield of a solid-state decarboxylation reaction. These results demonstrated that accumulation of researchers’ experience derived from visual information can be shared as trained ML models and used as a quantitative analysis method.