Development of hybrid robust model based on computational modeling and machine learning for analysis of drug sorption onto porous adsorbents

This study investigates the utilization of three regression models, i.e., Kernel Ridge Regression (KRR), nu-Support Vector Regression ([Formula: see text]-SVR), and Polynomial Regression (PR) for the purpose of forecasting the concentration (C) of a drug within a specified environment, relying on the coordinates (x and y). The analyses were carried out for separation of drug from a solution by adsorption process where the concentration of drug was obtained in the solution and the adsorbent via computational fluid dynamics (CFD), and the results of concentration distribution were used or machine learning modeling. The model considered mass transfer and fluid flow equations to determine concentration distribution of solute in the system. The hyperparameter optimization was carried out using the Fruit-Fly Optimization Algorithm (FFOA), a nature-inspired optimization technique. Our results demonstrate the performance of each model in terms of key regression metrics. KRR achieved an R² score of 0.84851, with a Root Mean Square Error (RMSE) of 1.0384E-01 and a Mean Absolute Error (MAE) of 7.27762E-02. [Formula: see text]-SVR exhibited exceptional accuracy with an R² of 0.98593, accompanied by an RMSE of 3.5616E-02 and an MAE of 1.36749E-02. PR, a traditional regression method, attained an R² score of 0.94077, an RMSE of 7.2042E-02, and an MAE of 4.81533E-02.