Machine learning for predicting the viscosity of binary liquid mixtures

Viscosity is an important parameter in process engineering and is a key design objective for application areas including the coatings, lubricants, personal care, and pharmaceutical industries. The lack of reliable and general methods for predicting the viscosities of mixtures creates a barrier for modern process engineering and product design. In this work, we developed a graph-based neural network architecture and applied it to the problem of predicting the viscosity of binary liquid mixtures as a function of composition and temperature. To obtain a highquality training dataset, we also developed an automated curation pipeline and applied it to a large dataset collected from the literature by the National Institute of Standards and Technology (NIST) to be used as training data. The resulting model predicts viscosity with an MAE of 0.043 and an RMSE of 0.080 in log cP units (base 10). To improve the dependability of the model, we developed a classifier that evaluated the reliability of a prediction based on the variance between an ensemble of models. Using this approach, the model had an effective MAE of 0.029 and RMSE of 0.047 for predictions that were assessed as reliable (80% of the test set). Overall, this work provides 1) a large set of curated viscosity data that can be used for future machine learning efforts, 2) a new, graph-based deep learning approach for predicting the viscosity of binary mixtures, and 3) an illustrative case study for how deep learning can be used for accurate and reliable property prediction.

Automated summary

Viscosity is a crucial parameter in process engineering and various industries, such as coatings, lubricants, personal care, and pharmaceuticals. The lack of reliable methods for predicting mixture viscosities hampers process engineering and product design. This study developed a graph-based neural network architecture to predict the viscosity of binary liquid mixtures based on composition and temperature. A curated dataset was created using an automated curation pipeline and collected literature from NIST. The resulting model achieved high accuracy in viscosity prediction and a classifier was developed to assess prediction reliability.