The evaluation of the spatial and temporal distribution of pollutants is a crucial issue to assess the anthropogenic burden on the environment. Numerous chemometric approaches are available for data exploration and they have been applied for environmental health assessment purposes. Among the unsupervised methods, Self-Organizing Map (SOM) is an artificial neural network able to handle non-linear problems that can be used for exploratory data analysis, pattern recognition, and variable relationship assessment. Much more interpretation ability is gained when the SOM-based model is merged with clustering algorithms. This review comprises: (i) a description of the algorithm operation principle with a focus on the key parameters used for the SOM initialization; (ii) a description of the SOM output features and how they can be used for data mining; (iii) a list of available software tools for performing calculations; (iv) an overview of the SOM application for obtaining spatial and temporal pollution patterns in the environmental compartments with focus on model training and result visualization; (v) advice on reporting SOM model details in a paper to attain comparability and reproducibility among published papers as well as advice for extracting valuable information from the model results is presented.
Keywords: Air; Clustering and Factorial methods; Pollution; Sediment; Self-Organizing Map; Soil; Water.
Copyright © 2023 Elsevier B.V. All rights reserved.