Reducing the Vulnerability of Societies to Water Related Risks at the Basin Scale (Proceedings of the third International Symposium on Integrated Water Resources Management, Bochum, Germany, September 2006). IAHS Publ. 317, 2007, 102–106.

Modelling of nitrogen leaching based on collective intelligence

UWE HABERLANDT & SVEN VAN DER HEIJDEN

Institute of Water Resources Management, University of Hannover, Appelstr. 9a, D-30167 Hannover, Germany

haberlandt@iww.uni-hannover.de

Abstract The aim of this study is to evaluate the possibility to predict nitrogen leaching from the “collective knowledge” available in the literature. Information about observed and modelled nitrogen leaching and influencing environmental and anthropogenic factors is collected from several published studies. Based on these data, fuzzy rules are defined, trained and validated for the prediction of mean annual nitrogen leaching. A multiple split sampling exercise shows good agreement between literature and simulated nitrogen loss encouraging the application of such a metamodel approach for decision support.

Key words diffuse pollution; fuzzy rules; metamodel; nitrogen leaching; water quality