Support Vector Regression for Rainfall-Runoff Modeling in Urban Drainage: A Comparison with the EPA’s Storm Water Management Model

Abstract

Abstract: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.

Evaluating the Effects of Low Impact Development Practices on Urban Flooding under Different Rainfall Intensities

“…Also, the SWMM model is widely used to simulate the hydrologic performance of natural channels, rain and sewage diversion systems or other drainage systems, and it can evaluate the design of LID practices and BMPs. Much research on the SWMM model can be found [40][41][42].…”

A Hybrid Modeling Technique to Predict Runoff

“…In addition, some researches have suggested the support vector regression (SVR) as an alternative algorithm for predicting runoff effectively. SVR showed the best performance as reported in [3], [4]. Rainfall lag time values are also used to consider for building a model to predict runoff [5], [6].…”

Quantifying Roughness Coefficient Uncertainty in Urban Flooding Simulations through a Simplified Methodology

“…The software can be used in the design, analysis, and planning of drainage systems as well as simulating the runoff quantity and quality [20][21][22][23][24][25][26][27][28]. In addition, several attempts have been made to calibrate the parameters required by the software [29,30] and using it in order to compare against machine learning techniques [31].…”