TY - JOUR

T1 - A fuzzy rule based metamodel for monthly catchment nitrate fate simulations

AU - van der Heijden, S.

AU - Haberlandt, U.

N1 - Achnowledgements: The authors are thankful for the valuable and constructive comments of three anonymous reviewers. Many thanks also to our colleague Markus Wallner who helped to improve the quality of the paper. We are also grateful to DWD and NLWKN for providing climate and hydrologic data, respectively.

PY - 2015/12

Y1 - 2015/12

N2 - The high complexity of nitrate dynamics and corresponding deterministic models make it very appealing to employ easy, fast, and parsimonious modelling alternatives for decision support. This study presents a fuzzy rule based metamodel consisting of eight fuzzy modules, which is able to simulate nitrate fluxes in large watersheds from their diffuse sources via surface runoff, interflow, and base flow to the catchment outlet. The fuzzy rules are trained on a database established with a calibrated SWAT model for an investigation area of 1000km2. The metamodel performs well on this training area and on two out of three validation areas in different landscapes, with a Nash-Sutcliffe coefficient of around 0.5-0.7 for the monthly nitrate calculations. The fuzzy model proves to be fast, requires only few readily available input data, and the rule based model structure facilitates a common-sense interpretation of the model, which deems the presented approach suitable for the development of decision support tools.

AB - The high complexity of nitrate dynamics and corresponding deterministic models make it very appealing to employ easy, fast, and parsimonious modelling alternatives for decision support. This study presents a fuzzy rule based metamodel consisting of eight fuzzy modules, which is able to simulate nitrate fluxes in large watersheds from their diffuse sources via surface runoff, interflow, and base flow to the catchment outlet. The fuzzy rules are trained on a database established with a calibrated SWAT model for an investigation area of 1000km2. The metamodel performs well on this training area and on two out of three validation areas in different landscapes, with a Nash-Sutcliffe coefficient of around 0.5-0.7 for the monthly nitrate calculations. The fuzzy model proves to be fast, requires only few readily available input data, and the rule based model structure facilitates a common-sense interpretation of the model, which deems the presented approach suitable for the development of decision support tools.

KW - Catchment scale

KW - Fuzzy rules

KW - Metamodel

KW - Nitrate

KW - SWAT

UR - http://www.scopus.com/inward/record.url?scp=84948148520&partnerID=8YFLogxK

U2 - 10.1016/j.jhydrol.2015.10.039

DO - 10.1016/j.jhydrol.2015.10.039

M3 - Article

AN - SCOPUS:84948148520

VL - 531

SP - 863

EP - 876

JO - Journal of hydrology

JF - Journal of hydrology

SN - 0022-1694

ER -