Abstract
Traditional static neural networks often fail to describe dynamic flood processes, while recurrent neural networks can reflect this dynamic feature of flooding. In this paper, a real-time framework for probabilistic flood forecasting using an Elman neural network is presented. Based on this framework, flood forecasting models with different lead times are developed and trained by a real-time recurrent learning algorithm for forecasting the inflow of the Xianghongdian reservoir of the Huai River in East China. The performances of these models are evaluated. The forecasting model having a 3 h lead time meets the precision requirements and is chosen as the deterministic flood forecasting model. Compared with the multilayer perceptron having a 3 h lead time, the relative error of flood volume is 5.28% less, and the coefficient of efficiency is 0.105 greater. We further analyze the error characteristics of the selected model and derive the discharge probability density function based on the heterogeneity of error distributions. The forecasted discharge intervals with different confidence levels, the expected values, and the median values are obtained. The results show that the average relative errors of flood volume and peak discharge obtained by the median value forecasting are −1.66% and 5.69% respectively, and the coefficient of efficiency is 0.784. The performance of the median value forecasting was slightly better than that of the deterministic forecasting, and considerably better than that of the expected value forecasting. This study demonstrates that the proposed model has high practicability and can provide decision support for flood control.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Adhikary SK, Muttil N, Yilmaz AG (2017) Cokriging for enhanced spatial interpolation of rainfall in two Australian catchments. Hydrol Process 31:2143–2161. https://doi.org/10.1002/hyp.11163
Ahasan MN, Chowdhury MAM, Quadir DA (2013) Simulation of a heavy rainfall event of 11 June 2007 over Chittagong, Bangladesh using MM5 model. Mausam 64:405–416
Areu-Rangel OS, Cea L, Bonasia R, Espinosa-Echavarria VJ (2019) Impact of urban growth and changes in land use on river flood hazard in Villahermosa, Tabasco (Mexico). Water 11:304. https://doi.org/10.3390/w11020304
Bai P, Liu X, Liang K et al (2017) A comparison of simple and complex versions of the Xinanjiang hydrological model in predicting runoff in ungauged basins. Hydrol Res 48:1282–1295. https://doi.org/10.2166/nh.2016.094
Balanzino A, Castelli ST (2018) Numerical experiments with RAMS model in highly complex terrain. Environ Fluid Mech 18:357–381. https://doi.org/10.1007/s10652-017-9553-9
Berg P, Norin L, Olsson J (2016) Creation of a high resolution precipitation data set by merging gridded gauge data and radar observations for Sweden. J Hydrol 541:6–13. https://doi.org/10.1016/j.jhydrol.2015.11.031
Bogner K, Liechti K, Zappa M (2016) Post-processing of stream flows in Switzerland with an emphasis on low flows and floods. Water 8:115. https://doi.org/10.3390/w8040115
Bogner K, Meissner D, Pappenberger F, Salamon P (2014) Correction of model and forecast errors and the estimation of the predictive uncertainty of a probabilistic flood forecasting system. Hydrol Wasserbewirtsch 58:73–75. https://doi.org/10.5675/HyWa_2014,2_2
Chang F-J, Chang L-C, Huang H-L (2002) Real-time recurrent learning neural network for stream-flow forecasting. Hydrol Process 16:2577–2588. https://doi.org/10.1002/hyp.1015
Chang F-J, Chen P-A, Lu Y-R et al (2014) Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control. J Hydrol 517:836–846. https://doi.org/10.1016/j.jhydrol.2014.06.013
Chang L-C, Chang F-J, Chiang Y-M (2004) A two-step-ahead recurrent neural network for stream-flow forecasting. Hydrol Process 18:81–92. https://doi.org/10.1002/hyp.1313
Chao L, Zhang K, Li Z et al (2018) Geographically weighted regression based methods for merging satellite and gauge precipitation. J Hydrol 558:275–289. https://doi.org/10.1016/j.jhydrol.2018.01.042
Chen J, Zhong P-A, Zhang Y et al (2017) A decomposition-integration risk analysis method for real-time operation of a complex flood control system. Water Resour Res 53:2490–2506. https://doi.org/10.1002/2016WR019842
Chen P-A, Chang L-C, Chang F-J (2013) Reinforced recurrent neural networks for multi-step-ahead flood forecasts. J Hydrol 497:71–79. https://doi.org/10.1016/j.jhydrol.2013.05.038
Chen Y, Li J, Xu H (2016) Improving flood forecasting capability of physically based distributed hydrological models by parameter optimization. Hydrol Earth Syst Sci 20:375–392. https://doi.org/10.5194/hess-20-375-2016
Choi Y, Cha D-H, Kim J (2017) Tuning of length-scale and observation-error for radar data assimilation using four dimensional variational (4D-Var) method. Atmospheric Sci Lett 18:441–448. https://doi.org/10.1002/asl.787
Christian Refsgaard J, Storm B, Clausen T (2010) Systeme Hydrologique Europeen (SHE): review and perspectives after 30 years development in distributed physically-based hydrological modelling. Hydrol Res 41:355–377. https://doi.org/10.2166/nh.2010.009
Datta AR, Bolisetti T (2016) Uncertainty analysis of a spatially-distributed hydrological model with rainfall multipliers. Can J Civ Eng 43:1062–1074. https://doi.org/10.1139/cjce-2015-0413
Devi GK, Ganasri BP, Dwarakish GS (2015) A review on hydrological models. In: Dwarakish GS (ed) International conference on water resources, coastal and ocean engineering (icwrcoe’15). Elsevier Science Bv, Amsterdam, pp 1001–1007
Elman JL (1990) Finding structure in time. Cogn Sci 14:179–211. https://doi.org/10.1207/s15516709cog1402_1
Guo R, Liu Y, Zhou H, Zhu Y (2018) Precipitation downscaling using a probability-matching approach and geostationary infrared data: an evaluation over six climate regions. Hydrol Earth Syst Sci 22:3685–3699. https://doi.org/10.5194/hess-22-3685-2018
Hadadin AN (2006) Watershed models and their applicability to the simulation of the rainfall-runoff relationship. In: Advances in Fluid Mechanics VI WIT Press, Skiathos, Greece, pp 193–202
He B, Huang X, Ma M et al (2018) Analysis of flash flood disaster characteristics in China from 2011 to 2015. Nat Hazards 90:407–420. https://doi.org/10.1007/s11069-017-3052-7
Hu J, Zhou Y, Jin J (2015) Flood forecasting model on BP neural networks and its application in flood forecasting systems. J China Hydrol 35:20–25
Jekel CF (2018) Pwlf update: fitting continuous piecewise linear models to data. Charles Jekel. https://jekel.me/2018/Continous-piecewise-linear-regression/. Accessed 7 Dec 2018
Kolanowski K, Świetlicka A, Kapela R et al (2018) Multisensor data fusion using Elman neural networks. Appl Math Comput 319:236–244. https://doi.org/10.1016/j.amc.2017.02.031
Kuczera G, Kavetski D, Franks S, Thyer M (2006) Towards a Bayesian total error analysis of conceptual rainfall-runoff models: Characterising model error using storm-dependent parameters. J Hydrol 331:161–177. https://doi.org/10.1016/j.jhydrol.2006.05.010
Li B, He Y, Ren L (2018) Multisource hydrologic modeling uncertainty analysis using the IBUNE framework in a humid catchment. Stoch Environ Res Risk Assess 32:37–50. https://doi.org/10.1007/s00477-017-1424-x
Liang Z, Jiang X, Qian M et al (2017) Probabilistic flood forecasting considering heterogeneity of error distributions. J Hydroelectr Eng 36:18–25
Liu F, Xu F, Yang S (2017) A flood forecasting model based on deep learning algorithm via integrating stacked autoencoders with BP neural network. Ieee, New York
Liu H, Mi X, Li Y (2018) Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short term memory neural network and Elman neural network. Energy Convers Manag 156:498–514. https://doi.org/10.1016/j.enconman.2017.11.053
Lu J, Guo J, Yang L, Xu X (2017) Research of reservoir watershed fine zoning and flood forecasting method. Nat Hazards 89:1291–1306. https://doi.org/10.1007/s11069-017-3017-x
Ma Y, Yang Y, Han Z et al (2018) Comprehensive evaluation of ensemble multi-satellite precipitation dataset using the dynamic Bayesian model averaging scheme over the Tibetan plateau. J Hydrol 556:634–644. https://doi.org/10.1016/j.jhydrol.2017.11.050
Mantovan P, Todini E (2006) Hydrological forecasting uncertainty assessment: incoherence of the GLUE methodology. J Hydrol 330:368–381. https://doi.org/10.1016/j.jhydrol.2006.04.046
McKee JL, Binns AD (2016) A review of gauge-radar merging methods for quantitative precipitation estimation in hydrology. Can Water Resour J 41:186–203. https://doi.org/10.1080/07011784.2015.1064786
Oyebode O, Stretch D (2019) Neural network modeling of hydrological systems: a review of implementation techniques. Nat Resour Model 32:e12189. https://doi.org/10.1111/nrm.12189
Patel P, Ghosh S, Kaginalkar A et al (2019) Performance evaluation of WRF for extreme flood forecasts in a coastal urban environment. Atmospheric Res 223:39–48. https://doi.org/10.1016/j.atmosres.2019.03.005
Peng Y, Sun X, Zhang X et al (2016) A flood forecasting model that considers the impact of hydraulic projects by the simulations of the aggregate reservoir’s retaining and discharging. Water Resour Manag 31:1031–1045. https://doi.org/10.1007/s11269-016-1562-9
Phan MC, Hagan MT (2013) Error surface of recurrent neural networks. IEEE Trans Neural Netw Learn Syst 24:1709–1721. https://doi.org/10.1109/TNNLS.2013.2258470
Phitakwinai S, Aucphanwiriyakul S, Theera-Umpon N (2016) Multilayer perceptron with cuckoo search in water level prediction for flood forecasting. 2016 International Joint Conference on Neural Networks (ijcnn) Ieee, New York:519–524
Ren G, Cao Y, Wen S et al (2018) A modified Elman neural network with a new learning rate scheme. Neurocomputing 286:11–18. https://doi.org/10.1016/j.neucom.2018.01.046
Samadi S, Tufford DL, Carbone GJ (2018) Estimating hydrologic model uncertainty in the presence of complex residual error structures. Stoch Environ Res Risk Assess 32:1259–1281. https://doi.org/10.1007/s00477-017-1489-6
Seyam M, Othman F, El-Shafie A (2017) RBFNN versus empirical models for lag time prediction in tropical humid rivers. Water Resour Manag 31:187–204. https://doi.org/10.1007/s11269-016-1518-0
Shen Y, Zhao P, Pan Y, Yu J (2014) A high spatiotemporal gauge-satellite merged precipitation analysis over China. J Geophys Res-Atmospheres 119:3063–3075. https://doi.org/10.1002/2013JD020686
Shi L, Liang S, Cheng J, Zhang Q (2016) Integrating ASTER and GLASS broadband emissivity products using a multi-resolution Kalman filter. Int J Digit Earth 9:1098–1116. https://doi.org/10.1080/17538947.2016.1170897
Silver M, Karnieli A, Ginat H et al (2017) An innovative method for determining hydrological calibration parameters for the WRF-hydro model in arid regions. Environ Model Softw 91:47–69. https://doi.org/10.1016/j.envsoft.2017.01.010
State Administration for Market Regulation of the P.R.C., Standardization Administration of the P.R.C (2008) Standard for hydrological information and hydrological forecasting (GB/T 22482–2008). China Quality and Standards Publishing & Media Co.,Ltd, Beijing
Sun Y, Bao W, Jiang P et al (2018) Development of multivariable dynamic system response curve method for real-time flood forecasting correction. Water Resour Res 54:4730–4749. https://doi.org/10.1029/2018WR022555
Tan X, Shao D, Gu W (2018) Improving water reuse in paddy field districts with cascaded on-farm ponds using hydrologic model simulations. Water Resour Manag 32:1849–1865. https://doi.org/10.1007/s11269-018-1907-7
Tian J, Liu J, Yan D et al (2019) Ensemble flood forecasting based on a coupled atmospheric-hydrological modeling system with data assimilation. Atmospheric Res 224:127–137. https://doi.org/10.1016/j.atmosres.2019.03.029
Tomasella J, Sene Gonçalves A, Schneider Falck A et al (2019) Probabilistic flood forecasting in the Doce Basin in Brazil: effects of the basin scale and orientation and the spatial distribution of rainfall. J Flood Risk Manag 12:e12452. https://doi.org/10.1111/jfr3.12452
Valenca I, Ludermir T (2009) Hybrid systems for river flood forecasting using MLP, SOM and fuzzy systems. In: Alippi C, Polycarpou M, Panayiotou C, Ellinas G (eds) Artificial neural networks - Icann 2009. Pt I. Springer-Verlag, Berlin, Berlin, pp 557–566
Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. J Hydrol 476:433–441. https://doi.org/10.1016/j.jhydrol.2012.11.017
Wan X, Hua L, Yang S et al (2018) Evaluating the impacts of a large-scale multi-reservoir system on flooding: case of the Huai River in China. Water Resour Manag 32:1013–1033. https://doi.org/10.1007/s11269-017-1852-x
Wang J, Shi P, Jiang P et al (2017) Application of BP neural network algorithm in traditional hydrological model for flood forecasting. Water 9:48. https://doi.org/10.3390/w9010048
Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280. https://doi.org/10.1162/neco.1989.1.2.270
Xu D, Wang W, Chau K et al (2013) Comparison of three global optimization algorithms for calibration of the Xinanjiang model parameters. J Hydroinf 15:174–193. https://doi.org/10.2166/hydro.2012.053
Zhang D, Martinez N, Lindholm G, Ratnaweera H (2018a) Manage sewer in-line storage control using hydraulic model and recurrent neural network. Water Resour Manag 32:2079–2098. https://doi.org/10.1007/s11269-018-1919-3
Zhang X, Zhang Q, Zhang G et al (2018b) A hybrid model for annual runoff time series forecasting using elman neural network with ensemble empirical mode decomposition. Water 10:416. https://doi.org/10.3390/w10040416
Zheng F, Maier HR, Wu W et al (2018) On lack of robustness in hydrological model development due to absence of guidelines for selecting calibration and evaluation data: demonstration for data-driven models. Water Resour Res 54:1013–1030. https://doi.org/10.1002/2017WR021470
Acknowledgements
This research was supported by the National Key Research and Development Program of China (No. 2016YFC0400909).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
None.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wan, X., Yang, Q., Jiang, P. et al. A Hybrid Model for Real-Time Probabilistic Flood Forecasting Using Elman Neural Network with Heterogeneity of Error Distributions. Water Resour Manage 33, 4027–4050 (2019). https://doi.org/10.1007/s11269-019-02351-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11269-019-02351-3