Optimizing arsenic removal from groundwater using continuous flow electrocoagulation with iron and aluminum electrodes: An experimental and modeling approach

Journal of Water Process Engineering, Год журнала: 2024, Номер 66, С. 106082 - 106082

Опубликована: Авг. 30, 2024

Язык: Английский

Computational modeling of petroleum purification for removal of sulfur compounds: Process analysis for reduction of environmental impacts and material costs

Ain Shams Engineering Journal, Год журнала: 2024, Номер 15(11), С. 102986 - 102986

Опубликована: Авг. 5, 2024

In the course of this investigation, three machine learning models (Gaussian Process Regression, Decision Tree and Kernel Ridge Regression) were examined for determining correlation between input variables (x y) which are spatial coordinates model's geometry, content species in adsorption sulfur capture. For process modeling, mass transfer was analyzed, concentration distribution compound obtained via numerical solution equations, then used models. The trained using a dataset 19,000 observations, their performance assessed through metrics including R2 score, MAE, RMSE. Analysis results reveals that Regression surpassed other two performance, with an score 0.9989, MAE 6.64405E-01, RMSE 1.1277E+00. Gaussian had 0.97106, 3.65541E+00, 5.6821E+00, while 0.86347, 8.26121E+00, 1.1330E+01. Clonal Selection Algorithm hyper-parameter optimization all These findings demonstrate potential techniques accurately reliably predicting chemical highlight importance considering choice model optimal performance.

Язык: Английский

Optimizing Arsenic Removal from Groundwater Using Continuous Flow Electrocoagulation with Iron and Aluminum Electrodes: An Experimental and Modeling Approach

Опубликована: Янв. 1, 2024

Язык: Английский