|SENAVIRATNE, ANOMAA - University Of Missouri|
|UDAWATTA, RANJITH - University Of Missouri|
|ANDERSON, STEPHEN - University Of Missouri|
Submitted to: ASA-CSSA-SSSA Annual Meeting Abstracts
Publication Type: Abstract Only
Publication Acceptance Date: 6/26/2013
Publication Date: 11/3/2013
Citation: Senaviratne, A., Udawatta, R.P., Baffaut, C., Anderson, S.H. 2013. Performance of Geno-Fuzzy Model on rainfall-runoff predictions in claypan watersheds [abstract]. ASA-CSSA-SSSA Annual Meeting. 148-1.
Technical Abstract: Fuzzy logic provides a relatively simple approach to simulate complex hydrological systems while accounting for the uncertainty of environmental variables. The objective of this study was to develop a fuzzy inference system (FIS) with genetic algorithm (GA) optimization for membership functions (MFs) for event-based rainfall-runoff prediction of three small adjacent row crop watersheds (1.65 to 4.44 ha) with intermittent discharge in the claypan soils of North East Missouri, prior to and after the establishment of upland contour grass and agroforestry (tree+grass) buffers. A Mamdani type FIS with five MFs and five fuzzy rules was created using MATLAB 7.10.0. Two sets of MFs were developed and optimized using GA for pre- and post-buffer conditions using one of the three watersheds. They were then validated using either another watershed or a different time period. The FIS simulated event-based runoff with r2 and Nash-Sutcliffe Coefficient (NSC) values greater than 0.65 for calibration and validation. The pre-buffer FIS simulated event-based runoff of two larger similar watersheds (140 ha and 259 ha) with r2 values of 0.82 and 0.68 and NSC values of 0.77 and 0.53, respectively. The GA optimization of MFs moderately improved r2 and NSC values. These FIS predictions of event-based runoff were similar to those of the Agricultural Policy Environmental eXtender model, a physically–based hydrological model that requires extensive input data. FIS offers an alternate modeling tool for runoff estimation in the absence of detailed watershed data.