Potential application of machine learning for exploring adsorption mechanisms of pharmaceuticals onto biochars

The increasing accumulation of pharmaceuticals in aquatic ecosystems could impair freshwater quality and threaten human health. Despite the adsorption of pharmaceuticals on biochars is one of the most cost-effective and eco-friendly removal methods, the wide variation of experimental designs and research aims among previous studies pose significant challenge in selecting biochar for optimal removal. In this work, literature data of 1033 sets with 21 variables collected from 267 papers over ten years (2010–2020) covering 19 pharmaceuticals onto 88 biochars were assessed by different machine learning (ML) algorithms i.e., Linear regression model (LM), Feed-forward neural networks (NNET), Deep neutral networks (DNN), Cubist, K-nearest neighbor (KNN), and Random forest (RF), to predict equilibrium adsorption capacity (Qe) and explore adsorption mechanisms. LM showed the best performance on ranking importance of input variables. Except for initial concentration of pharmaceuticals, Qe was strongly governed by biochars' properties including specific surface area (BET), pore volume (PV), and pore structure (PS) rather than pharmaceuticals’ properties and experimental conditions. The most accurate model for estimating Qe was achieved by Cubist, followed by KNN, RF, KNN, NNET and LM. The generalization ability was observed by the tuned Cubist with 26 rules for the prediction of the unseen data. This study not only provides an insightful evidence for data-based adsorption mechanisms of pharmaceuticals on biochars, but also offers a potential method to accurately predict the biochar adsorption performance without conducting any experiments, which will be of high interests in practice in terms of water/wastewater treatment using biochars. [Display omitted] •Comprehensive data of 19 pharmaceuticals onto 88 biochars were examined.•ML models of classification, regression, ensemble and deep learning were compared.•LM outcompeted RF, Cubist, and xgbTree for ranking importance of input variables.•Qe was governed by biochars' structure rather than pharmaceuticals' properties.•Cubist featured the best prediction, followed by KNN, RF, DNN, NNET and LM.