Machine learning-assisted evaluation of potential biochars for pharmaceutical removal from water

Xiaocui Yang; X Cuong Nguyen; Quoc B Tran; T T Huyen Nguyen; Shengbo Ge; D Duc Nguyen; Van-Truc Nguyen; Phuoc-Cuong Le; Eldon R Rene; Pardeep Singh; Pankaj Raizada; Tansir Ahamad; Saad M Alshehri; Changlei Xia; Soo Young Kim; Quyet Van Le

doi:10.1016/j.envres.2022.113953

Machine learning-assisted evaluation of potential biochars for pharmaceutical removal from water

Environ Res. 2022 Nov;214(Pt 3):113953. doi: 10.1016/j.envres.2022.113953. Epub 2022 Aug 4.

Authors

Xiaocui Yang¹, X Cuong Nguyen², Quoc B Tran³, T T Huyen Nguyen⁴, Shengbo Ge⁵, D Duc Nguyen⁶, Van-Truc Nguyen⁷, Phuoc-Cuong Le⁴, Eldon R Rene⁸, Pardeep Singh⁹, Pankaj Raizada⁹, Tansir Ahamad¹⁰, Saad M Alshehri¹⁰, Changlei Xia¹¹, Soo Young Kim¹², Quyet Van Le¹³

Affiliations

¹ Engineering Training Center, Nanjing Vocational University of Industry Technology, Nanjing, Jiangsu, 210023, China.
² Center for Advanced Chemistry, Institute of Research and Development, Duy Tan University, Da Nang, 550000, Vietnam; Faculty of Environmental Chemical Engineering, Duy Tan University, Da Nang, 550000, Vietnam. Electronic address: nguyenxuancuong4@duytan.edu.vn.
³ Center for Advanced Chemistry, Institute of Research and Development, Duy Tan University, Da Nang, 550000, Vietnam; Faculty of Environmental Chemical Engineering, Duy Tan University, Da Nang, 550000, Vietnam.
⁴ Faculty of Environment, The University of Danang-University of Science and Technology, Da Nang, 550000, Vietnam.
⁵ Jiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, International Innovation Center for Forest Chemicals and Materials, College of Materials Science and Engineering, Nanjing Forestry University, Nanjing, Jiangsu, 210037, China.
⁶ Department of Environmental Energy Engineering, Kyonggi University, Suwon, 442-760, Republic of Korea.
⁷ Department of Environmental Sciences, Saigon University, Ho Chi Minh City, 700000, Vietnam.
⁸ Department of Environmental Engineering and Water Technology, IHE Delft Institute for Water Education, PO Box 3015, 2601 DA, Delft, the Netherlands.
⁹ School of Advanced Chemical Sciences, Shoolini University, Solan, Himachal Pradesh, 173212, India.
¹⁰ Department of Chemistry, College of Science, King Saud University, Riyadh 11451, Saudi Arabia.
¹¹ Jiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, International Innovation Center for Forest Chemicals and Materials, College of Materials Science and Engineering, Nanjing Forestry University, Nanjing, Jiangsu, 210037, China. Electronic address: changlei.xia@njfu.edu.cn.
¹² Department of Materials Science and Engineering, Institute of Green Manufacturing Technology, Korea University, Seoul, 02841, Republic of Korea. Electronic address: sooyoungkim@korea.ac.kr.
¹³ Department of Materials Science and Engineering, Institute of Green Manufacturing Technology, Korea University, Seoul, 02841, Republic of Korea. Electronic address: quyetkbk88@korea.ac.kr.

PMID: 35934147
DOI: 10.1016/j.envres.2022.113953

Abstract

A popular approach to select optimal adsorbents is to perform parallel experiments on adsorbents based on an initially decided goal such as specified product purity, efficiency, or binding capacity. To screen optimal adsorbents, we focused on the max adsorption capacity of the candidates at equilibrium in this work because the adsorption capacity of each adsorbent is strongly dependent on certain conditions. A data-driven machine learning tool for predicting the max adsorption capacity (Q_m) of 19 pharmaceutical compounds on 88 biochars was developed. The range of values of Q_m (mean 48.29 mg/g) was remarkably large, with a high number of outliers and large variability. Modified biochars enhanced the Q_m and surface area values compared with the original biochar, with a statistically significant difference (Chi-square value = 7.21-18.25, P < 0.005). K- nearest neighbors (KNN) was found to be the most optimal algorithm with a root mean square error (RMSE) of 23.48 followed by random forest and Cubist with RMSE of 26.91 and 29.56, respectively, whereas linear regression and regularization were the worst algorithms. KNN model achieved R² of 0.92 and RMSE of 16.62 for the testing data. A web app was developed to facilitate the use of the KNN model, providing a reliable solution for saving time and money in unnecessary lab-scale adsorption experiments while selecting appropriate biochars for pharmaceutical adsorption.

Keywords: Adsorption; Biochar; Data mining; Machine learning; Pharmaceutical.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adsorption
Charcoal
Machine Learning
Pharmaceutical Preparations
Water Pollutants, Chemical* / analysis
Water*

Substances

Pharmaceutical Preparations
Water Pollutants, Chemical
biochar
Water
Charcoal