Machine Learning to Predict the Adsorption Capacity of Microplastics

• Published in: Nanomaterials (Basel, Switzerland) Vol. 13; no. 6; p. 1061
• Main Authors: Astray, Gonzalo, Soria-Lopez, Anton, Barreiro, Enrique, Mejuto, Juan Carlos, Cid-Samamed, Antonio
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 15-03-2023; MDPI
• Subjects: Adsorption; adsorption capacity; Analysis; Aquatic environment; Artificial intelligence; artificial neural network; Artificial neural networks; Chemical pollutants; Chemical pollution; Classification; Contaminants; Correlation coefficient; Correlation coefficients; Decision trees; Epoxy resins; Industrial areas; Learning algorithms; Machine learning; Mathematical models; Microplastics; Neural networks; Neurons; Organic contaminants; Plastic debris; Plastic pollution; Pollutants; Polyvinyl alcohol; Primary production; random forest; support vector machine; Support vector machines; Canada; artificial neural network; support vector machine; adsorption capacity; prediction; microplastics; random forest; machine learning
• ISSN: 2079-4991; 2079-4991
• DOI: 10.3390/nano13061061

Nowadays, there is an extensive production and use of plastic materials for different industrial activities. These plastics, either from their primary production sources or through their own degradation processes, can contaminate ecosystems with micro- and nanoplastics. Once in the aquatic environment, these microplastics can be the basis for the adsorption of chemical pollutants, favoring that these chemical pollutants disperse more quickly in the environment and can affect living beings. Due to the lack of information on adsorption, three machine learning models (random forest, support vector machine, and artificial neural network) were developed to predict different microplastic/water partition coefficients (log
) using two different approximations (based on the number of input variables). The best-selected machine learning models present, in general, correlation coefficients above 0.92 in the query phase, which indicates that these types of models could be used for the rapid estimation of the absorption of organic contaminants on microplastics.