Laboratory of Energy and Environmental Science, Institute of Research and Development, Duy Tan University, Da Nang, 550000, Vietnam; Faculty of Environmental and Chemical Engineering, Duy Tan University, Da Nang, 550000, Vietnam.
Institute of Environmental Engineering & Nano-Technology, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, Guangdong, China.
Chemosphere. 2022 Jan;287(Pt 2):132203. doi: 10.1016/j.chemosphere.2021.132203. Epub 2021 Sep 8.
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 (Q) and explore adsorption mechanisms. LM showed the best performance on ranking importance of input variables. Except for initial concentration of pharmaceuticals, Q 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 Q 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.
越来越多的药品在水生生态系统中积累，可能会损害淡水质量并威胁人类健康。尽管吸附法是最具成本效益和环保的去除方法之一，但由于先前研究的实验设计和研究目的差异很大，因此在选择最适合去除的生物炭时存在很大的挑战。在这项工作中，通过不同的机器学习（ML）算法（即线性回归模型（LM）、前馈神经网络（NNET）、深度神经网络（DNN）、Cubist、K-最近邻（KNN）和随机森林（RF））评估了十年来（2010-2020 年）从 267 篇论文中收集的 21 个变量的 1033 组文献数据，这些论文涵盖了 19 种药物在 88 种生物炭上的吸附，以预测平衡吸附容量（Q）并探索吸附机制。LM 在对输入变量重要性的排序方面表现最好。除了药物的初始浓度外，Q 还受到生物炭特性的强烈影响，包括比表面积（BET）、孔体积（PV）和孔结构（PS），而不是药物特性和实验条件。通过 Cubist 实现了最准确的 Q 估算模型，其次是 KNN、RF、KNN、NNET 和 LM。通过具有 26 条规则的调谐 Cubist 观察到了泛化能力，用于预测未见数据。本研究不仅为基于数据的药物在生物炭上的吸附机制提供了有见地的证据，而且还提供了一种无需进行任何实验即可准确预测生物炭吸附性能的潜在方法，这在使用生物炭进行水/废水处理方面具有很高的实际意义。
