Application of machine learning in predicting the adsorption capacity of organic compounds onto biochar and resin

Detailed prediction of the adsorption amounts of organic pollutants in water is essential to the clean development and management of water resources. In this study, Kriging and polyparameter linear free energy relationship model are coupled to predict adsorption capacity of organic pollutants by biochar and resin. It's based on 1750 adsorption experimental data sets which contains 73 organic compounds on 50 biochars and 30 polymer resins. The Kriging-LFER model shows better accuracy and predictive performance for adsorption (R-2 are 0.940 and 0.976) than the published NN-LFER model (R-2 are 0.870 and 0.880). Local sensitivity analysis method is adopted to evaluate the influence of each variable on the adsorption coefficient of resin and find out that top sensitive parameters are V and log Ce, to guide parameter optimization. Data's uncertainty analysis is presented by Monte Carlo method. It predicts that the adsorption coefficient will range from 0.062 to 0.189 under the 95% confi-dence interval. The Kriging-LFER model provides great significance for understanding the importance of various parameters, reducing the number of experiments, adjusting the direction of experimental improvement, and evaluating the fate of organic pollutants in the environment.

Automated summary

In this study, the Kriging and polyparameter linear free energy relationship model were used to predict the adsorption capacity of organic pollutants by biochar and resin. The results showed that the Kriging-LFER model had better accuracy and predictive performance compared to the published NN-LFER model. Local sensitivity analysis and uncertainty analysis methods were also applied to evaluate the influence of variables and analyze data uncertainty. The study highlights the significance of the Kriging-LFER model in understanding parameter importance, reducing experimental efforts, and evaluating pollutant fate.