HR: 0830h
AN: H11F-0902    [PDF]
TI: Comparison of Data-Driven Takagi--Sugeno Models of Rainfall-Discharge Dynamics
AU: Vernieuwe, H
EM: hilde.vernieuwe@ugent.be
AF: Department of Applied Mathematics, Biometrics and Process Control, Coupure links 653, Gent, B-9000 Belgium
AU: Georgieva, O
EM: ogeorgieva@icsr.bas.bg
AF: Institute of Control and System Research, Bulgarian Academy of Sciences, P.O. Box 79, Sofia, 1113 Bulgaria
AU: * Verhoest, N E
EM: niko.verhoest@ugent.be
AF: Laboratory of Hydrology and Water Management, Coupure links 653, Gent, B-9000 Belgium
AU: Pauwels, V R
EM: Valentijn.Pauwels@ugent.be
AF: Laboratory of Hydrology and Water Management, Coupure links 653, Gent, B-9000 Belgium
AU: De Baets, B
EM: bernard.debaets@ugent.be
AF: Department of Applied Mathematics, Biometrics and Process Control, Coupure links 653, Gent, B-9000 Belgium
AU: De Troch, F P
EM: francois.detroch@ugent.be
AF: Laboratory of Hydrology and Water Management, Coupure links 653, Gent, B-9000 Belgium
AB: Three different methods for constructing fuzzy rule-based models of the Takagi--Sugeno type relating rainfall to catchment discharge are tested on the Zwalm catchment in Belgium. They correspond to the grid partitioning (GP), subtractive clustering (SC), and Gustafson--Kessel clustering (GK) identification methods. The data set used to parametrize and validate the models consists of hourly precipitation and discharge records. The models are parametrized using a one-year identification data set and are then applied to a four-year data set. All models are found to have a low computation cost. Although the models show a similar performance, the best results are obtained for the GK method. A real-time flood forecasting algorithm is then developed, in which discharge measurements are assimilated into the model at either an hourly or a daily time step. The results suggest that the GK method can potentially be used as an operational flood forecasting tool.
DE: 1860 Runoff and streamflow
DE: 1899 General or miscellaneous
SC: Hydrology [H]
MN: 2003 Fall Meeting