Effect of watershed subdivision on water-phase phosphorus modelling: An artificial neural network modelling application

摘要

This study is an effort to incorporate low-cost time-variant remote sensing (RS) information in watershed-scalentotal phosphorus (TP) modelling. Four watershed subdivisions were delineated to assess the impact of watershed subdivisionnon the prediction accuracy of TP concentration in stream water. Four TP artificial neural network (ANN) modelsnwere designed to incorporate RS data into a semi-distributed approach. The remotely derived enhanced vegetation indexnand the normalized difference water index were successful in representing vegetation dynamics in the devised models. Thenmodels were applied to a 15.6 km2 watershed in the Canadian Boreal Plain. Eight measures of goodness-of-fit statisticsnwere used for model evaluation. Although statistical model evaluation did favour the finest resolution in this case study,nthe differences in performance indicators among the four models were insignificant for any practical application. The encouragingnresults from this exercise demonstrate the applicability of the ANN semi-distributed modelling approach and thenusefulness of RS data in simulating TP dynamics. Such models can potentially serve as valuable tools for watershed-scalenforest management.