Stormwater runoff is often contaminated by human activities. Stormwater discharge into water bodies significantly contributes to environmental pollution. The choice of suitable treatment technologies is dependent on the pollutant concentrations. Wastewater quality indicators such as biochemical oxygen demand (BOD5), chemical oxygen demand (COD), total suspended solids (TSS), and total dissolved solids (TDS) give a measure of the main pollutants. The aim of this study is to provide an indirect methodology for the estimation of the main wastewater quality indicators, based on some characteristics of the drainage basin. The catchment is seen as a black box: the physical processes of accumulation, washing, and transport of pollutants are not mathematically described. Two models deriving from studies on artificial intelligence have been used in this research: Support Vector Regression (SVR) and Regression Trees (RT). Both the models showed robustness, reliability, and high generalization capability. However, with reference to coefficient of determination R2 and root‐mean square error, Support Vector Regression showed a better performance than Regression Tree in predicting TSS, TDS, and COD. As regards BOD5, the two models showed a comparable performance. Therefore, the considered machine learning algorithms may be useful for providing an estimation of the values to be considered for the sizing of the treatment units in absence of direct measures.

Rainfall-runoff models can be classified into three types: physically based models, conceptual models, and empirical models. In this latter class of models, the catchment is considered as a black box, without any reference to the internal processes that control the transformation of rainfall to runoff. In recent years, some models derived from studies on artificial intelligence have found increasing use. Among these, particular attention should be paid to Support Vector Machines (SVMs). This paper shows a comparative study of rainfall-runoff modeling between a SVM-based approach and the EPA’s Storm Water Management Model (SWMM). The SVM is applied in the variant called Support Vector regression (SVR). Two different experimental basins located in the north of Italy have been considered as case studies. Two criteria have been chosen to assess the consistency between the recorded and predicted flow rates: the root-mean square error (RMSE) and the coefficient of determination. The two models showed comparable performance. In particular, both models can properly model the hydrograph shape, the time to peak and the total runoff. The SVR algorithm tends to underestimate the peak discharge, while SWMM tends to overestimate it. SVR shows great potential for applications in the field of urban hydrology, but currently it also has significant limitations regarding the model calibration.