Selection of relevant input variables in storm water quality modeling by multiobjective evolutionary polynomial regression paradigm. Issue 4 (1st April 2016)

• Record Type: Journal Article
• Authors: Creaco, E.; Berardi, L.; Sun, Siao; Giustolisi, O.; Savic, D.
• Is Part Of: Water resources research. Volume 52:Issue 4(2016:Apr.)
• Page Start: 2403
• Page End: 2419
• Publication Date: 2016-04-01
• Subjects: data‐driven modeling -- input selection -- EPR -- storm water quality; Hydrology -- Periodicals; 333.91
• DOI: 10.1002/2015WR017971
• Languages: English
• ISSNs: 0043-1397

Abstract

Abstract: The growing availability of field data, from information and communication technologies (ICTs) in "smart" urban infrastructures, allows data modeling to understand complex phenomena and to support management decisions. Among the analyzed phenomena, those related to storm water quality modeling have recently been gaining interest in the scientific literature. Nonetheless, the large amount of available data poses the problem of selecting relevant variables to describe a phenomenon and enable robust data modeling. This paper presents a procedure for the selection of relevant input variables using the multiobjective evolutionary polynomial regression (EPR‐MOGA) paradigm. The procedure is based on scrutinizing the explanatory variables that appear inside the set of EPR‐MOGA symbolic model expressions of increasing complexity and goodness of fit to target output. The strategy also enables the selection to be validated by engineering judgement. In such context, the multiple case study extension of EPR‐MOGA, called MCS‐EPR‐MOGA, is adopted. The application of the proposed procedure to modeling storm water quality parameters in two French catchments shows that it was able to significantly reduce the number of explanatory variables for successive analyses. Finally, the EPR‐MOGA models obtained after the input selection are compared with those obtained by using the same technique without benefitting from input selection and with those obtained in previous works where other data‐modeling techniques were used on the same data. The comparison highlights the effectiveness of both EPR‐MOGA and the input selection procedure. Key Points: A procedure based on the regression technique ERP‐MOGA is proposed for relevant input selection Relevant input selection is made based on variable occurrence statistics and engineering judgment Input selection improves data fitting in storm water quality modeling