Application of artificial neural network and dynamic adsorption models to predict humic substances extraction from municipal solid waste leachate

Salimeh Rezaeinia; Ali Asghar Ebrahimi; Arash Dalvand; Mohammad Hassan Ehrampoush; Hossien Fallahzadeh; Mehdi Mokhtari

doi:10.1038/s41598-023-39373-2

Application of artificial neural network and dynamic adsorption models to predict humic substances extraction from municipal solid waste leachate

Sci Rep. 2023 Aug 1;13(1):12421. doi: 10.1038/s41598-023-39373-2.

Authors

Salimeh Rezaeinia¹, Ali Asghar Ebrahimi¹, Arash Dalvand¹, Mohammad Hassan Ehrampoush¹, Hossien Fallahzadeh², Mehdi Mokhtari³

Affiliations

¹ Environmental Science and Technology Research Center, Department of Environmental Health Engineering, School of Public Health, Shahid Sadoughi University of Medical Sciences, Yazd, Iran.
² Department of Biostatistics and Epidemiology, Research Center of Prevention and Epidemiology of Non‑Communicable Disease, Shahid Sadoughi University of Medical Sciences, Yazd, Iran.
³ Environmental Science and Technology Research Center, Department of Environmental Health Engineering, School of Public Health, Shahid Sadoughi University of Medical Sciences, Yazd, Iran. mokhtari@ssu.ac.ir.

Abstract

Sustainable municipal solid waste leachate (MSWL) management requires a paradigm shift from removing contaminants to effectively recovering resources and decreasing contaminants simultaneously. In this study, two types of humic substances, fulvic acid (FA) and humic acid (HA) were extracted from MSWL. HA was extracted using HCl and NaOH solution, followed by FA using a column bed under diversified operations such as flow rate, input concentration, and bed height. Also, this work aims to evaluate efficiency of Artificial Neural Network (ANN) and Dynamic adsorption models in predicting FA. With the flow rate of 0.3 mL/min, bed height of 15.5 cm, and input concentration of 4.27 g/mL, the maximum capacity of FA was obtained at 23.03 mg/g. FTIR analysis in HA and FA revealed several oxygen-containing functional groups including carboxylic, phenolic, aliphatic, and ketone. The high correlation coefficient value (R²) and a lower mean squared error value (MSE) were obtained using the ANN, indicating the superior ability of ANN to predict adsorption capacity compared to traditional modeling.