A nonlinear data‐driven model for synthetic generation of annual streamflows

Hydrological Processes - Tập 22 Số 12 - Trang 1831-1845 - 2008
K. P. Sudheer1, K. Srinivasan1, T. R. Neelakantan2, V. V. Srinivas3
1Department of Civil Engineering, Indian Institute of Technology Madras, Chennai—600036, India
2School of Civil Engineering, SASTRA Deemed University, Thanjavur 613402, India
3Department of Civil Engineering, Indian Institute of Science, Bangalore, 560012, India

Tóm tắt

AbstractA hybrid model that blends two non‐linear data‐driven models, i.e. an artificial neural network (ANN) and a moving block bootstrap (MBB), is proposed for modelling annual streamflows of rivers that exhibit complex dependence. In the proposed model, the annual streamflows are modelled initially using a radial basis function ANN model. The residuals extracted from the neural network model are resampled using the non‐parametric resampling technique MBB to obtain innovations, which are then added back to the ANN‐modelled flows to generate synthetic replicates. The model has been applied to three annual streamflow records with variable record length, selected from different geographic regions, namely Africa, USA and former USSR. The performance of the proposed ANN‐based non‐linear hybrid model has been compared with that of the linear parametric hybrid model. The results from the case studies indicate that the proposed ANN‐based hybrid model (ANNHM) is able to reproduce the skewness present in the streamflows better compared to the linear parametric‐based hybrid model (LPHM), owing to the effective capturing of the non‐linearities. Moreover, the ANNHM, being a completely data‐driven model, reproduces the features of the marginal distribution more closely than the LPHM, but offers less smoothing and no extrapolation value. It is observed that even though the preservation of the linear dependence structure by the ANNHM is inferior to the LPHM, the effective blending of the two non‐linear models helps the ANNHM to predict the drought and the storage characteristics efficiently. Copyright © 2007 John Wiley & Sons, Ltd.

Từ khóa


Tài liệu tham khảo

10.1061/(ASCE)1084-0699(2000)5:2(115)

10.1061/(ASCE)1084-0699(2000)5:2(124)

Bendat JS, 1986, Random Data: Analysis and Measurement Procedures

Box GEP, 1976, Time Series Analysis Forecasting and Control

10.1111/1468-0394.00137

10.1029/1998WR900086

10.1109/72.80341

DanielTM.1991.Neural networks—applications in hydrology and water resources engineering. InProceedings International Hydrology and Water Resources Symposium Institution of Engineers Perth Australia.

10.1017/CBO9780511802843

10.1080/02626669809492102

10.1177/030913330102500104

DeRoach JN, 1989, Neural networks: an artificial intelligence approach to the analysis of clinical data, Australasian Physical & Engineering Science in Medicine, 12, 100

10.1214/aos/1176344552

10.1007/978-1-4899-4541-9

10.1061/(ASCE)1084-0699(1998)3:3(203)

10.1016/0370-2693(93)90738-4

10.1029/95WR01955

10.1029/2003WR002355

10.1029/2000WR900049

10.1214/aos/1176347265

10.1016/0167-7152(93)90035-H

10.1029/95RG00343

10.1029/95WR02966

LePage R, 1992, Exploring the Limits of Bootstrap

Loucks DP, 1981, Water Resources Systems Planning and Analysis

10.1016/S1364-8152(99)00007-9

10.1162/neco.1989.1.2.281

PowellMJD.1987.Radial basis function approximations to polynomials. InProceedings of the 12th Biennial Numerical Analysis Conference Dundee;223–241.

PrairieJr.2002.Long‐term salinity prediction with uncertainty analysis: application for Colorado River above Glenwood Springs CO. MS thesis University of Colorado Boulder CO.

10.1029/1999WR900028

10.1007/BF02428426

10.5194/hess-6-641-2002

Salas JD, 1980, Applied Modeling of Hydrologic Time Series

10.1016/0022-1694(91)90082-S

10.1016/S0378-4754(99)00016-6

10.1029/96WR02839

10.1016/S0022-1694(00)00168-2

10.1016/S0022-1694(00)00363-2

10.1029/WR018i004p00909

10.1061/(ASCE)1084-0699(2003)8:3(161)

SudheerKP GosainAK RamasatriKS.2002.Comparisons between back propagation and radial basis function based neural networks in rainfall‐runoff modeling. InProceedings of the International Conference on Advances in Civil Engineering vol. 1 Kharagpur India; 449–456.

10.1002/hyp.5103

10.1029/97WR02429

Tong H, 1990, Nonlinear Time Series Analysis: A Dynamical Systems Perspective

YevjevichV.1967.An objective approach to definitions and investigations of continental hydrologic droughts. Hydrology Paper 23 Colorado State University Fort Collins CO.

Thông tin
Thông tin xuất bản

Hydrological Processes

Tập 22 Số 12

1831-1845

Thông tin tác giả