1
|
Wang F, Wang W, Wang H, Zhao Z, Zhou T, Jiang C, Li J, Zhang X, Liang T, Dong W. Experiments and machine learning-based modeling for haloacetic acids rejection by nanofiltration: Influence of solute properties and operating conditions. THE SCIENCE OF THE TOTAL ENVIRONMENT 2023; 883:163610. [PMID: 37088392 DOI: 10.1016/j.scitotenv.2023.163610] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/28/2023] [Revised: 04/13/2023] [Accepted: 04/16/2023] [Indexed: 05/03/2023]
Abstract
Because of potential risks to public health, the presence of haloacetic acids (HAAs) in drinking water is a major concern. Nanofiltration (NF) has shown potential for HAAs rejection, and several factors, namely, membrane properties, solute properties, and operating conditions, have been revealed key roles. However, knowledge of NF separation mechanism by quantifying these factors is limited. This study investigated and modeled NF performance on HAAs rejection. NF performance was experimentally investigated under various transmembrane pressure (TMP), cross-flow velocity (CV), temperature, pH, ionic strength (IS), and HAAs initial feed concentration (Cin). We used machine learning (ML) to understand the mechanism from the perspective of HAAs properties and operating conditions. Multiple linear regression (MLR), support vector machine (SVM), multsilayer perceptron (MLP), extreme gradient boosting (XGBoost), and random forest (RF) models were used. The MLP, XGBoost and RF models achieved significant performance with high R2 (0.970, 0.973, and 0.980) and low RMSE (4.71, 4.41, and 3.84). These three models were analyzed using the Shapley Additive explanation (SHAP) to quantify relative contributions of HAAs properties and operating conditions. XGBoost-SHAP produced the most logical results and was the best-performing model for selecting optimal input variables combinations. The results showed that Stokes radius (rs), logarithmic octanol-water partitioning coefficient (logKow), molecular weight (MW), pH, TMP, and temperature are key variables for interpreting NF process. The effects of HAAs properties were ranked as rs > logKow > MW, suggesting significance of size exclusion and hydrophobic interaction. The impact of the operational conditions followed the order pH > TMP > temperature, illustrating that pH was the major influencing operating condition. This study demonstrated significant capacity of ML, which reduced amount of experimental work. In addition, the main operating conditions can be evaluated in terms of their contributions, making ML an efficient tool for risk management and process optimization.
Collapse
Affiliation(s)
- Feifei Wang
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| | - Weikang Wang
- Shen Zhen LiYuan Water Design & Consultation CO, LTD, PR China
| | - Hongjie Wang
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China; Shenzhen Key Laboratory of Water Resource Utilization and Environmental Pollution Control, Shenzhen 518055, PR China; State Key Lab of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China.
| | - Zilong Zhao
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China; Shenzhen Key Laboratory of Water Resource Utilization and Environmental Pollution Control, Shenzhen 518055, PR China
| | - Ting Zhou
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| | - Chengjun Jiang
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| | - Ji Li
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China; Shenzhen Key Laboratory of Water Resource Utilization and Environmental Pollution Control, Shenzhen 518055, PR China; State Key Lab of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| | - Xiaolei Zhang
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| | - Tianzhe Liang
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| | - Wenyi Dong
- School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China; Shenzhen Key Laboratory of Water Resource Utilization and Environmental Pollution Control, Shenzhen 518055, PR China; State Key Lab of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology Shenzhen, Shenzhen 518055, PR China
| |
Collapse
|
2
|
Zhu T, Zhang Y, Tao C, Chen W, Cheng H. Prediction of organic contaminant rejection by nanofiltration and reverse osmosis membranes using interpretable machine learning models. THE SCIENCE OF THE TOTAL ENVIRONMENT 2023; 857:159348. [PMID: 36228787 DOI: 10.1016/j.scitotenv.2022.159348] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/22/2022] [Revised: 09/21/2022] [Accepted: 10/06/2022] [Indexed: 06/16/2023]
Abstract
Efficiency improvement in contaminant removal by nanofiltration (NF) and reverse osmosis (RO) membranes is a multidimensional process involving membrane material selection and experimental condition optimization. It is unrealistic to explore the contributions of diverse influencing factors to the removal rate by trial-and-error experimentation. However, the advanced machine learning (ML) method is a powerful tool to simulate this complex decision-making process. Here, 4 traditional learning algorithms (MLR, SVM, ANN, kNN) and 4 ensemble learning algorithms (RF, GBDT, XGBoost, LightGBM) were applied to predict the removal efficiency of contaminants. Results reported here demonstrate that ensemble models showed significantly better predictive performance than traditional models. More importantly, this study achieved a compelling tradeoff between accuracy and interpretability for ensemble models with an effective model interpretation approach, which revealed the mutual interaction mechanism between the membrane material, contaminants and experimental conditions in membrane separation. Additionally, feature selection was for the first time achieved based on the aforementioned model interpretation method to determine the most important variable influencing the contaminant removal rate. Ultimately, the four ensemble models retrained by the selected variables achieved distinguished prediction performance (R2adj = 92.4 %-99.5 %). MWCO (membrane molecular weight cut-off), McGowan volume of solute (V) and molecular weight (MW) of the compound were demonstrated to be the most important influencing factors in contaminant removal by the NF and RO processes. Overall, the proposed methods in this study can facilitate versatile complex decision-making processes in the environmental field, particularly in contaminant removal by advanced physicochemical separation processes.
Collapse
Affiliation(s)
- Tengyi Zhu
- School of Environmental Science and Engineering, Yangzhou University, Yangzhou 225127, Jiangsu, China.
| | - Yu Zhang
- School of Environmental Science and Engineering, Yangzhou University, Yangzhou 225127, Jiangsu, China
| | - Cuicui Tao
- School of Environmental Science and Engineering, Yangzhou University, Yangzhou 225127, Jiangsu, China
| | - Wenxuan Chen
- School of Civil Engineering, Southeast University, Nanjing 210096, China
| | - Haomiao Cheng
- School of Environmental Science and Engineering, Yangzhou University, Yangzhou 225127, Jiangsu, China
| |
Collapse
|
4
|
Xu X, Li H, Guo M, Zeng M, Liu W, Wu N, Liang J, Cao J. Deciphering performance and potential mechanism of anammox-based nitrogen removal process responding to nanoparticulate and ionic forms of different heavy metals through big data analysis. Sep Purif Technol 2022. [DOI: 10.1016/j.seppur.2022.122044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/31/2022]
|