Abstract
Urban stormwater runoff represents a significant challenge for the practical assessment of diffuse pollution sources on receiving water bodies. Given the high dimensionality of the problem, the main goal of this study was the comparison of linear and non-linear machine learning (ML) methods to characterize urban nutrient runoff from impervious surfaces. In particular, the principal component analysis (PCA) for the linear technique and the self-organizing map (SOM) for the non-linear technique were chosen and compared considering the high number of successful applications in the water quality field. To strengthen this comparison, these techniques were supported by well-known linear and non-linear methods. Those techniques were applied to a complete dataset with precipitation, flow rate, and water quality (sediments and nutrients) records of 577 events gathered for a watershed located in Southern Italy. According to the results, both linear and non-linear techniques can represent build-up and wash-off, the two main processes that characterize urban nutrient runoff. In particular, non-linear methods are able to capture and represent better the rainfall-runoff process and the transport of dissolved nutrients in urban runoff (dilution process). However, their computational time is higher than the linear technique (0.0054 s vs. 15.24 s, for linear and non-linear, respectively, in our study). The outcomes of this study provide significant insights into the application of ML methods for the water quality field.
Highlights
Surface freshwater, among the aquatic ecosystems, is one of the fundamental components of the water cycle for human life worldwide
Taking into account the successful applications of the principal component analysis (PCA) and self-organizing map (SOM), this study aims to compare the results of these two approaches, which respectively belong to the linear and non-linear machine learning (ML) techniques, regarding the characterization of nutrient runoff from impervious surfaces in urban watersheds
Techniques, PCA and SOM, respectively, to characterize urban nutrient runoff. This comparison was based on three main aspects: (i) the ability to represent the correlation among the variables chosen to represent the system and, depict the build-up and wash-off processes; (ii) the ability to group the dataset based on the two variables that symbolize build-up and wash-off processes (ADP and Tot_Rainfall); (iii) the ability to identify and quantify the importance of each variable
Summary
Among the aquatic ecosystems, is one of the fundamental components of the water cycle for human life worldwide. It is generated from surface water bodies, which provide drinking water, preserve biodiversity, control climate, and maintain phosphorus and nitrate cycling [1]. In the management plan of pollution control at a watershed scale, a worthwhile initial step is the identification of the pollution sources. They can be point sources (PS) or non-point sources (NPS). NPS pollution occurs when contaminants from diverse and widely spread sources are transported by runoff into water bodies. NPS pollution is more difficult to quantify due to its diffuse
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
