Harnessing artificial neural networks to model caffeine degradation by High-Yield biodiesel algae Desmodesmus pannonicus

Dixita Phukan; Vipin Kumar; Wilson Kandulna; Ankur Singh; Saumya Anand; Nishant Pandey

doi:10.1016/j.biortech.2024.131935

Harnessing artificial neural networks to model caffeine degradation by High-Yield biodiesel algae Desmodesmus pannonicus

Bioresour Technol. 2024 Dec 10:418:131935. doi: 10.1016/j.biortech.2024.131935. Online ahead of print.

Authors

Dixita Phukan¹, Vipin Kumar², Wilson Kandulna³, Ankur Singh⁴, Saumya Anand¹, Nishant Pandey¹

Affiliations

¹ Laboratory of Applied Microbiology, Department of Environmental Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand 826004, India.
² Laboratory of Applied Microbiology, Department of Environmental Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand 826004, India. Electronic address: vipinmicro1@iitism.ac.in.
³ Applied Air and Soil Laboratory, Department of Environmental Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand 826004, India.
⁴ Laboratory of Applied Microbiology, Department of Environmental Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand 826004, India; Division of Environmental Hydrology, National Institute of Hydrology, Roorkee 247667, India.

PMID: 39667629
DOI: 10.1016/j.biortech.2024.131935

Abstract

In this study, Desmodesmus pannonicus IITISM-DIX2, outperforming Chlorella sorokiniana IITISM-DIX3 in caffeine degradation, was used to develop an artificial neural network (ANN) model for predicting caffeine removal efficiency under varying pH, photoperiods, caffeine, and indole acetic acid (IAA) concentrations. The ANN model, designed with a 4-15-1 multilayer perceptron and trained on 120 data points, achieved high predictive accuracy (R² > 0.96) and bias/accuracy factors between 0.95-1.11. Sensitivity analysis identified pH as the most critical factor. IAA enhanced lipid content in Desmodesmus by 91 % in caffeine-containing simulated wastewater. FAME analysis was performed under optimal lipid-producing conditions (10 ppm caffeine, 5 ppm IAA). IAA upregulated key metabolic pathways, increasing secondary metabolites in Desmodesmus and Chlorella. In summary, the modeling results are key for improving system performance, guiding parameter selection to enhance caffeine removal by Desmodesmus. IAA also enhanced resilience and lipid yield, increasing the economic feasibility of caffeine removal and biofuel production.

Keywords: Fatty acids; Indole acetic acid; Lipid enhancement; Predictive modeling; Sensitivity analysis.