Exploring seasonal coastal water quality parameter interactions through the self-organizing map neural network in...

Coastal water pollution poses significant environmental challenges, leading to severe ecological and public health consequences. Thus, new assessment tools should be developed and refined to manage water quality more efficiently. In this paper, we present the results of Self-Organizing Map (SOM) neural network models used to simulate interactions among several water quality parameters, monitored at 35 coastal stations in the South-Eastern Mediterranean Sea, namely in Lebanon. Four seasonal SOM models were developed and calibrated based on the available dataset (n = 1087). The SOM's visualization of the Component Planes (CPs) enabled the examination of water-quality parameter interactions and associations on a seasonal basis. Additionally, Pearson correlation analysis between the SOM's Best Matching Units was calculated for each monitored parameter to augment the CPs analysis. SOM's clustering of data samples and assessment of human activities near the associated monitoring stations enabled the evaluation of the potential effects of existing human activities in nearby areas for each monitoring station. Specifically, the seasonal models revealed spatial-seasonal patterns at stations located near specific land-use settings, such as ANT-2 (near a river mouth), SEL-2 (near a chemical plant), and BEY-6 (public beach), which may be associated with degraded coastal water quality in Lebanon. Overall, this paper demonstrates that the SOM model can reveal parameter interactions and highlight spatial-seasonal patterns that may indicate nutrient enrichment and/or fecal contamination pressures. Thus, SOM models may be valuable tools for coastal water quality management.