Journal
ENVIRONMENTAL RESEARCH
Volume 214, Issue -, Pages -Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.envres.2022.113953
Keywords
Biochar; Pharmaceutical; Adsorption; Data mining; Machine learning
Funding
- Jiangsu Agricultural Science and Technology Innovation Fund [CX (22) 2045]
- Natural Science Foundation of Jiangsu Province [BK20200775]
- State Administration of Foreign Experts Affairs High-End Foreign Experts Project [G2021014041L]
- Brain Pool Program through the National Research Foundation of Korea (NRF) - Ministry of Science and ICT [2020H1D3A1A04081409]
- King Saud University, Riyadh, Saudi Arabia [RSP-2021/29]
- Master, PhD Scholarship Programme of Vingroup Innovation Foundation (VINIF)
Ask authors/readers for more resources
A data-driven machine learning tool was developed to predict the max adsorption capacity of pharmaceutical compounds on biochars, and K-nearest neighbors (KNN) was found to be the most optimal algorithm. Modified biochars can enhance adsorption capacity and surface area values.
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 ad-sorbents, 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 (Qm) of 19 pharmaceutical compounds on 88 biochars was developed. The range of values of Qm (mean 48.29 mg/g) was remarkably large, with a high number of outliers and large variability. Modified biochars enhanced the Qm 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available