Abstract
Artificial neural network model (ANN) has been extensively used in hydrological prediction. Generally, most existing rainfall-runoff models including artificial neural network model are not very successful at simulating streamflow in karst watersheds. Due to the complex physical structure of karst aquifer systems, runoff generation processes are quite different during flood and non-flood periods. In this paper, an ANN model based on back-propagation algorithm was developed to simulate and predict daily streamflow in karst watersheds. The idea of threshold was introduced into artificial neural network model [hereafter called Threshold-ANN model (T-ANN)] to represent the nonlinear characteristics of the runoff generation processes in the flood and non-flood periods. The T-ANN model is applied to the Hamajing watershed, which is a small karst watershed in Hubei Province, China. The network input, the previous discharge, is determined by the correlative analysis, and the network structure is optimized with the maximum Nash coefficient as the objective function. And the precipitation and previous discharge are chosen as the threshold factors to reflect the effect of specificity of karst aquifer systems, respectively. By using the T-ANN, the simulation errors of streamflow have been reduced, and the simulation becomes more successful, which would be helpful for runoff prediction in karst watersheds.
Similar content being viewed by others
References
Abrahart JR, See L (2000) Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments. Hydrol Process 14:2157–2172
Arnold JG, Allen PM, Muttiah R, Bernhardt G (1995) Automated base flow separation and recession analysis techniques. Gr Water 33:1010–1018
ASCE (2000a) Task committee on application of artificial neural networks in hydrology, artificial neural networks in hydrology part I: preliminary concepts. J Hydrol Eng 5:115–123
ASCE (2000b) Task committee on application of artificial neural networks in hydrology, artificial neural networks in hydrology part II: hydrologic applications. J Hydrol Eng 5:124–137
Barrett ME, Charbeneau RJ (1997) A parsimonious model for simulating flow in a karst aquifer. J Hydrol 196:47–65
Bonacci O (2001) Analysis of the maximum discharge of karst springs. Hydrogeol J 9:328–338
Bras R, Rodriguez-Iturbe I (1985) Random functions and hydrology. Addison Wesley, Reading
Campbell CW, Sullivan SM (2002) Simulating time-varying cave flow and water levels using the storm water management model. Eng Geol 65:133–139
Chen JF, Jin QJ, Chao J (2012) Design of deep belief networks for short-term prediction of drought index using data in the Huaihe river basin. Math Probl Eng 2012:1–16
Cigizoglu HK (2004) Estimation and forecasting of daily suspended sediment data by multi-layer perceptrons. Adv Water Resour 27:185–195
Cigizoglu HK, Kisi O (2005) Flow prediction by three backpropagation techniques using k-fold partitioning of neural network training data. Nord Hydrol 36:1–16
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2:303–314
Dawson CW, Wilby RL (2001) Hydrological modeling using artificial neural networks. Prog Phys Geogr 25:80–108
Dreiss SJ (1982) Linear kernels for karst aquifers. Water Resour Res 18:865–876
Dreiss SJ (1983) Linear unit-response functions as indicators of recharge areas for large karst springs. J Hydrol 61:31–44
Eisenlohr L, Kiral L, Bouzelboudjen M, Rossier Y (1997) Numerical simulation as a tool for checking the interpretation of karst spring hydrographs. J Hydrol 193:306–315
Fan YH, Huo XL, Hao YH, Liu Y, Wang TK, Liu YC, Yeh TCJ (2013) An assembled extreme value statistical model of karst spring discharge. J Hydrol 504:57–68
Feisi Research and Development Center of Science and Technology (2003) MATAB 6.5 auxiliary neural network analysis and design. Electronics Industry Press, Beijing
Felton GK, Currens JC (1994) Peak flow rate and recession-curve characteristics of a karst spring in the inner bluegrass, central Kentucky. J Hydrol 162:119–141
Furundzic D (1998) Application example of neural networks for time series analysis: rainfall runoff modeling. Sig Process 64:383–396
Ge ZX, Sun ZQ (2007) Neural network theory and MATLAB R2007 realization. Electronic Industry Press, Beijing
Halihan T, Wicks CM (1998) Modeling of storm responses in conduit flow aquifers with reservoirs. J Hydrol 208:82–91
Hornik K, Stinchcombe M, White H (1989) Multilayer feed forward networks are universal approximators. Neural Netw 2:359–366
Hu HP, Tian FQ (2007) Advancement in research of physically based watershed hydrological model. J Hydraul Eng 38:511–517 (in Chinese)
Hu TS, Lam KC, Ng ST (2001) River flow time series prediction with a range-dependent neural network. Hydrol Sci J 46:729–745
Hu TS, Lam KC, Ng ST (2005) A modified neural network for improving river flow prediction. Hydrol Sci J 50(2):299–318
Hu CH, Hao YH, Yeh TC, Pang B, Wu ZN (2008) Simulation of spring flows from a karst aquifer with an artificial neural network. Hydrol Process 22:596–604
Jain A, Srinivasulu S (2004) Development of effective and efficient rainfall runoff models using integration of deterministic, real-coded GA, and ANN techniques. Water Resour Res 40:W043021–W0430212
Jiang LH, Wang AG, Tian NY, Zhang WC, Fan QL (2011) BP neural network of continuous casting technological parameters and secondary dendrite arm spacing of spring steel. J Iron Steel Res Int 18:25–29
Ju Q, Yu ZB, Hao ZC, Ou GX, Zhao J, Liu DD (2009) Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model. Neurocomputing 72:2873–2883
Jukic D, Denic-Jukic V (2006) Nonlinear kernel functions for karst aquifers. J Hydrol 328:360–374
Labat D, Ababou R, Mangin A (2000a) Rainfall-runoff relations for karstic springs, part I: convolution and spectral analyses. J Hydrol 238:123–148
Labat D, Ababou R, Mangin A (2000b) Rainfall-runoff relations for karstic springs, part II: continuous wavelet and discrete orthogonal multiresolution analyses. J Hydrol 238:149–178
Labat D, Ababou R, Mangin A (2001) Introduction of wavelet analyses to rainfall/runoffs relationship for a karstic basin: the case of Licq–Atherey karstic system (France). Gr Water 39:605–615
Lambrakis N, Andreou AS, Polydoropoulos P, Georgopoulos E, Bountis T (2000) Nonlinear analysis and forecasting of a brackish karstic spring. Water Resour Res 36:875–884
Liu YB, Batelaan O, De Smedt F, Huong NT, Tam VT (2005) Test of a distributed modelling approach to predict flood flows in the karst Suoimuoi catchment in Vietnam. Environ Geol 48:931–940
Makridakis S, Wheelwright SC, McGee VE (1983) Forecasting methods and applications, 2nd edn. Wiley, New York
Mangin A (1975a) Contribution a` l’e´tude hydrodynamique des aquife`res karstiques. Ann Spe´le´ologie 29(3):283–332
Mangin A (1975b) Contribution a` l’e´tude hydrodynamique des aquife`res karstiques. Ann Spe´le´ologie 29(4):495–601
Mangin A (1975c) Contribution a` l’e´tude hydrodynamique des aquife`res karstiques”. Ann Spe´le´ologie 30(1):21–124
Ministry of Water Resources of the People’s Republic of China (2000) Standard for hydrological information and hydrological forecasting, Beijing, China. Water Power Press, Beijing
Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models, part I. A discussion of principles. J Hydrol 10:282–290
Padilla A, Pulido-Bosch A (2008) Simple procedure to simulate karstic aquifers. Hydrol Process 22:1876–1884
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. Parallel Distrib Process 1:318–362
Sun AY, Painter SL, Green RT (2005) Modeling Barton springs segment of the Edwards aquifer using MODFLOW-DCM. In: Proceedings of sinkholes and the engineering and environmental impacts of Karst, pp 163–177
Wang W, van Gelder PHAJM, Vrijling JK, Ma J (2006) Forecasting daily streamflow using hybrid ANN models. J Hydrol 324:383–399
Zhang B, Govindaraju S (2000) Prediction of watershed runoff using bayesian concepts and modular neural networks. Water Resour Res 36:753–762
Zhang L, Subbarayan G (2002) An evaluation of back-propagation neural networks for the optimal design of structural systems: part I. Training procedures. Comput Methods Appl Mech Eng 191:2873–2886
Acknowledgments
This research was supported by the National Natural Science Foundation of China (51109192) and the Fundamental Research Funds for National University, China University of Geosciences (Wuhan) (CUGL100220) and Juzheng Fund on Environmental Protection (201203904).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Meng, X., Yin, M., Ning, L. et al. A threshold artificial neural network model for improving runoff prediction in a karst watershed. Environ Earth Sci 74, 5039–5048 (2015). https://doi.org/10.1007/s12665-015-4562-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12665-015-4562-9