The use of artificial neural networks in modelling migration pollutants from the degradation of microplastics

Małgorzata Kida; Kamil Pochwat; Sabina Ziembowicz; Henrique Pizzo

doi:10.1016/j.scitotenv.2023.166856

The use of artificial neural networks in modelling migration pollutants from the degradation of microplastics

Sci Total Environ. 2023 Dec 15:904:166856. doi: 10.1016/j.scitotenv.2023.166856. Epub 2023 Sep 7.

Authors

Małgorzata Kida¹, Kamil Pochwat², Sabina Ziembowicz³, Henrique Pizzo⁴

Affiliations

¹ Department of Chemistry and Environmental Engineering, Faculty of Civil and Environmental Engineering and Architecture Rzeszow University of Technology, 35-959 Rzeszów, Ave Powstańców Warszawy 6, Poland. Electronic address: mkida@prz.edu.pl.
² Department of Infrastructure and Water Management, Faculty of Civil and Environmental Engineering and Architecture Rzeszow University of Technology, 35-959 Rzeszów, Ave Powstańców Warszawy 6, Poland.
³ Department of Chemistry and Environmental Engineering, Faculty of Civil and Environmental Engineering and Architecture Rzeszow University of Technology, 35-959 Rzeszów, Ave Powstańców Warszawy 6, Poland.
⁴ Municipal Water and Sewage Company, Monsenhor Gustavo Freire St., 75, Juiz de Fora 36016-470, Brazil; College of Civil Engineering, Estácio University of Juiz de Fora, Pres. João Goulart Av., 600, Minas Gerais, Brazil.

PMID: 37683848
DOI: 10.1016/j.scitotenv.2023.166856

Abstract

The objective of this article was to assess the effectiveness of simulation models in predicting the emission of additives from microplastics. The variety of plastics, their chemical structure, physicochemical properties, as well as the influence of environmental factors on their decomposition generate countless cases for analysis in the laboratory. The search for methods to reduce unnecessary laboratory analyses is a necessary action to protect the environment and ensure economic efficiency. In this study, machine learning techniques, specifically the methodology of artificial neural networks (ANNs), were employed to predict the leaching of contaminants from microplastics. The network's development was based on laboratory test results obtained using gas chromatography coupled to a mass spectrometer (GC-MS). The conducted research revealed the significant utility of the multilayer perceptron (MLP) - type networks, which exhibited correlation levels exceeding 95 % for various predicted values. One comprehensive ANN was developed, encompassing all the parameters analyzed, alongside individual networks for each parameter. A common network for all factors enabled for satisfactory results. Temperature and holding time had the greatest influence on the values of parameters such as the electrolytic conductivity of water (EC), dissolved organic carbon (DOC), and di(2-ethylhexyl) phthalate (DEHP). Correlation results ranged from 0.94 to 0.99 for EC, DEHP and DOC between the model data and laboratory data in each set of training, test, and validation data. The conducted research demonstrated that ANNs are a valuable machine learning method for analyzing and predicting pollutant emissions during the decomposition of microplastics.

Keywords: Emission; Machine learning; Phthalates; Sensitivity analysis.