Deep Learning Neural Network Approach for Predicting the Sorption of Ionizable and Polar Organic Pollutants to a Wide Range of Carbonaceous Materials

Abstract

Most contaminants of emerging concern are polar and/or ionizable organic compounds, whose removal from engineered and environmental systems is difficult. Carbonaceous sorbents include activated carbon, biochar, fullerenes, and carbon nanotubes, with applications such as drinking water filtration, wastewater treatment, and contaminant remediation. Tools for predicting sorption of many emerging contaminants to these sorbents are lacking because existing models were developed for neutral compounds. A method to select the appropriate sorbent for a given contaminant based on the ability to predict sorption is required by researchers and practitioners alike. Here, we present a widely applicable deep learning neural network approach that excellently predicted the conventionally used Freundlich isotherm fitting parameters log K_F and n (R² > 0.98 for log K_F, and R² > 0.91 for n). The neural network models are based on parameters generally available for carbonaceous sorbents and/or parameters freely available from online databases. A freely accessible graphical user interface is provided.

Figure 1

Measured Freundlich parameters log K_F and t·n (“target”) from the training set of polar and negatively charged compounds plotted against log K_F and n, as predicted by the neural network model. (A) Shows the model for log K_F (grey ▽) and the 95% confidence interval for the prediction (dashed red lines). (B) Shows the model for the exponent n (blue △) and the 95% confidence interval for the prediction (dashed red lines). (C) Shows the normalized error frequency associated with the predictions of K_F and n (sample size = 313).

Figure 2

Measured Freundlich fit parameters log K_F (grey ▼) and n (blue ▲) from the independent data set for negatively charged and polar compounds plotted against parameters predicted by the neural network model (sample size = 15).

Figure 3

GSA first-order indices (Si) for the prediction of the Freundlich parameters for negatively charged and polar compounds. Abbreviations: carbon content (C, %), molar ratios H/C and O/C, SSA (m²/g), and abundance of ionized negatively charged species (A^–, %), E (excess molar refraction), S (dipolarity/polarizability), A (H-bond acidity), B (H-bond basicity), and V (molar volume).

Figure 4

Measured Freundlich fit parameters log K_F and n (“target”) from the training set of cations and zwitterions plotted against log K_F and n predicted by the neural network model. (A) Shows the model for log K_F (▽) and the 95% confidence interval for the prediction (dashed red lines). (B) Shows the model for the exponent n (blue △) and the 95% confidence interval (dashed red lines). (C) Shows the normalized errors associated with the predictions of K_F and n (sample size = 133).

Figure 5

Measured Freundlich fit parameters log K_F (grey ▼) and n (blue ▲) from the independent data set for cations and zwitterions plotted against the parameters predicted by the neural network model (sample size = 6).

Figure 6

GSA first-order indices (Si) for the prediction of the Freundlich parameters for cations and zwitterions. Abbreviations: carbon content (C, %), molar ratios H/C and O/C, SSA (m²/g), amount of ionized negatively charged species (A^–, %), amount of ionized positively charged species (B⁺, %), E (excess molar refraction), S (dipolarity/polarizability), A (H-bond acidity), B (H-bond basicity), and V (molar volume).