نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
This study investigated the optimization of biological wastewater treatment and biomass production by the microalga Desmodesmus sp. while comparing two modeling approaches: Response Surface Methodology (RSM) and Artificial Neural Network (ANN). Samples were collected from Anzali Wetland, pretreated, enriched, and cultivated under controlled laboratory conditions. The operational variables included light intensity, aeration rate, pH, and retention time, which were optimized to achieve the best treatment performance. The results indicated that ANN provided more accurate predictions than RSM and was better able to capture the nonlinear relationships between process variables and responses. The optimal conditions were determined as a light intensity of 392 μ"mol photons"⋅"m" ^(-2)⋅"s" ^(-1), aeration rate of 1.37 "mg"⋅"L" ^(-1), pH 8.5, and retention time of 7.5 days. Under these conditions, the highest predicted efficiencies were 88.3% COD removal, 86.7% TN removal, 95.4% TP removal, and biomass production of 1.372 mg.L⁻¹. Overall, the findings suggest that Desmodesmus sp. can serve as an effective system for simultaneous wastewater treatment and valuable biomass production, with ANN offering superior predictive and optimization performance compared with RSM.
کلیدواژهها English
