Prediction of grade and recovery in flotation from physicochemical and operational aspects using machine learning models

[Display omitted] •Physicochemical and operational variables were considered for modeling.•Multivariable linear regression, k–nearest neighbors, decision tree, and random forests were used.•Random forests had the best performance in capturing the flotation behavior.•Contact angle and particle diameter were ultimately the most important for the prediction. Machine learning (ML) models for predicting flotation behavior focus on operational variables. Fundamental aspects, e.g., physicochemical variables that describe mineral surfaces for bubble–particle interactions, are largely neglected in these models; however, these physicochemical variables of mineral particles, including bubbles and pulp, influence the flotation behavior. Thus, this study aimed to advance the prediction of flotation behavior by including physicochemical variables. Among four ML models used for the prediction, the random forest model had the best performance and was therefore subsequently used to investigate variable importance. Contact angle, particle diameter, bubble diameter, particle charge, collector concentration, flotation time, and number of mineral species were the most important variables. Limitations (e.g., assumptions and empiricism) and implications of our study were presented. Finally, our expectation was to encourage more attention to physicochemistry in flotation using ML for a more generalized empirical flotation model.