Regression model, artificial intelligence, and cost estimation for phosphate adsorption using encapsulated nanoscale zero-valent iron

ABSTRACT

This study investigated the adsorption of PO₄³⁻ onto encapsulated nanoscale zero-valent iron (nZVI). At initial PO₄^3–: 10 mg · L⁻¹, the optimum condition was initial pH: 6.5, nZVI dosage: 20 g · L⁻¹, stirring-rate: 100 rpm, and time: 30 min, achieving PO₄³⁻ removal of 42%. The effect of pH and time on the PO₄³⁻ removal efficiency was quadratic-linear concave up, whereas the curve of nZVI dosage was quadratic-convex. Artificial neural network with a structure of 5−7−1 adequately predicted PO₄³⁻ removal (R²: 97.6%), and the sensitivity analysis demonstrated that pH was the most influential input. The cost of the adsorption unit was 3.15 $USD · m⁻³.

KEYWORDS:

• Artificial neural network
• cost analysis
• nZVI/Ca-beads
• phosphate adsorption
• response surface methodology

Disclosure statement

The authors declare that they have no conflict of interest.

Supplementary material

Supplemental data for this article can be access on the publisher’s website.

Additional information

Funding

This research was supported by the Egyptian Housing Building Research Center (HBRC).