Decomposition-ANN Methods for Long-Term Discharge Prediction Based on Fisher’s Ordered Clustering with MESA
Tóm tắt
Precise and reliable long-term streamflow prediction contributes to water resources planning and management. Artificial neural network (ANN) have shown its remarkable ability in forecasting non-linear hydrological processes without involvement of complex, dynamic, hydrological and hydro-climatologic physical process in the water shed. To improve its non-stationary responses, decomposition methods are adopted as pre-processing methods in this study including Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and Seasonal-Trend decomposition using Loess (STL). The original time sequence is decomposed to several components, which are then taken as the inputs of the ANN model. EMD and EEMD are data- adaptable methods, and thus the number of Intrinsic Mode Functions (IMFs) might differ for different sequences, leading to the discrepancy of the input number for ANN model in training and predicting. Fisher’s ordered clustering is thus used to classify the IMFs into a determined number of classes based on their frequency spectrum resulting from Maximum Entropy Spectral Analysis (MESA). The proposed methodology is applied on four important hydrological stations on the upper stream of the Yellow River and the Yangtze River in China, respectively, to forecast the streamflow of the next whole year with the historical daily data of the past 6 years. The Nash-Sutcliffe efficiencies of the monthly prediction are higher than 0.85 for all of the four cases, and various indicators indicates that the proposed hybrid method of STL-ANN performs better than other compared methods. The highlights of this study lies in that only historical daily streamflow data is used to derive an accurate long-term prediction by data mining based on decomposition technology and mapping relationships between the decomposed components and the original sequence in the future.
Tài liệu tham khảo
Badrzadeh H, Sarukkalige R, Jayawardena AW (2016) Improving ANN-based short-term and long-term seasonal river flow forecasting with signal processing techniques. River Res Appl 32:245–256
Burg JP (1967) Maximum entropy spectral analysis. In: 37th annual international meeting. Society of Exploration Geophysics, Oklahoma
Cleveland RB, Cleveland WS, McRae JE, Terpenning I (1990) STL: a seasonal-trend decomposition procedure based on loess. J Off Stat 6(1):3–73
Di CL, Yang XH, Wang XC (2014) A four-stage hybrid model for hydrological time series forecasting. PLoS One 9:8
Fisher DW (1958) On grouping for maximum homogeneity. J Am Stat Assoc 53(284):789–798
Holt CC (2004) Forecasting seasonals and trends by exponentially weighted moving averages. Int J Forecast 20:5–10
Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In: Proceedings of the Royal Society of London a: mathematical, physical and engineering sciences, the Royal Society
Huang NE, Wu ML, Qu W, Long SR, Shen SS (2003) Applications of Hilbert-Huang transform to non-stationary financial time series analysis. Appl Stoch Model Bus Ind 19(3):245–268
Huang SZ, Chang JX, Huang Q, Chen YT (2014) Monthly streamflow prediction using modified EMD-based support vector machine. Journal of Hydrology 511:764–775
Humphrey GB, Gibbs MS, Dandy GC, Maier HR (2016) A hybrid approach to monthly streamflow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network. J Hydrol 540:623–640
Hyndman RJ, Koehler AB, Snyder RD, Grose S (2002) A state space framework for automatic forecasting using exponential smoothing methods. Int J Forecast 18:439–454
Kasiviswanathan KS, He J, Sudheer KP, Tay JH (2016) Potential application of wavelet neural network ensemble to forecast streamflow for flood management. J Hydrol 536:161–173
Kisi O, Nia AM, Gosheh MG, Tajabadi MRJ, Ahmadi A (2012) Intermittent streamflow forecasting by using several data driven techniques. Water Resour Manag 26:457–474
Kisi O, Latifoglu L, Latifoglu F (2014) Investigation of empirical mode decomposition in forecasting of hydrological time series. Water Resour Manag 28:4045–4057
Latt ZZ, Wittenberg H (2014) Improving flood forecasting in a developing country: a comparative study of stepwise multiple linear regression and artificial neural network. Water Resour Manag 28:2109–2128
Ma ZK, Li ZJ, Zhang M, Fan ZW (2013) Bayesian statistic forecasting model for middle-term and long-term runoff of a hydropower station. J Hydrol Eng 18(11):1458–1463
Maheswaran R, Khosa R (2012) Comparative study of different wavelets for hydrologic forecasting. Comput & Geosci 46:284–295
Maslova I, Ticlavilca AM, McKee M (2016) Adjusting wavelet-based multiresolution analysis boundary conditions for long-term streamflow forecasting. Hydrol Process 30(1):57–74
Nanda T, Sahoo B, Beria H, Chatterjee C (2016) A wavelet-based non-linear autoregressive with exogenous inputs (WNARX) dynamic neural network model for real-time flood forecasting using satellite-based rainfall products. Journal of Hydrology 539: 57-73
Nourani V, Komasi M, Alami M (2012) Hybrid wavelet- genetic programming approach to optimize ANN modeling of rainfall- runoff process. J Hydrol Eng 17(6):724–741
Shi B, Hu CH, Yu XH, Hu XX (2016) New fuzzy neural network–Markov model and application in mid- to long-term runoff forecast. Hydrol Sci J 61(6):1157–1169
Singhrattna N, Babel MS, Perret SR (2012) Hydroclimate variability and long-lead forecasting of rainfall over Thailand by large-scale atmospheric variables. Hydrol Sci J 57(1):26–41
Sinha T, Sankarasubramanian A, Mazrooei A (2014) Decomposition of sources of errors in monthly to seasonal streamflow forecasts in a rainfall- runoff regime. J Hydrometeorol 15:2470–2483
Smiatek G, Kunstmann H, Werhahn J (2012) Implementation and performance analysis of a high resolution coupled numerical weather and river runoff prediction model system for an alpine catchment. Environ Model Softw 38:231–243
Sudheer C, Maheswaran R, Panigrahi BK, Mathur S (2014) A hybrid SVM-PSO model for forecasting monthly streamflow. Neural Comput & Applic 24:1381–1389
Sun AY, Wang DB, Xu XL (2014) Monthly streamflow forecasting using Gaussian process regression. J Hydrol 511:72–81
Tao J, Chen X-H, Wang L, Xie Y-W (2011) Study on fractal characteristics of runoff time series in the Beijiang River. Acta Scientiarum Naturalium Universitatis Sunyatseni 50:148–152
Vafakhah M (2012) Application of artificial neural networks and adaptive neuro-fuzzy inference system models to short-term streamflow forecasting. Can J Civ Eng 39(4):402–414
Wang W-C, Xu D-M, Chau K-W, Chen S (2013) Improved annual rainfall-runoff forecasting using PSO–SVM model based on EEMD. J Hydroinf 15(4):1377–1390
Wang WC, Chau KW, Qiu L, Chen YB (2015). Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition. Environmental Research 139:46–54
Wu Z, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 1(01):1–41
Wu JS, Han J, Annambhotla S, Bryant S (2005) Artificial neural networks for forecasting watershed runoff and stream flows. J Hydrol Eng 10:216–222
Yu JJ, Qin XS, Larsen O, Chua LHC (2014) Comparison between response surface models and artificial neural networks in hydrologic forecasting. J Hydrol Eng 19(3):473–481
Zhang XL, Peng Y, Zhang C, Wang BD (2015) Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences. J Hydrol 530:137–152
Zhu S, Zhou JZ, Ye L, Meng CQ (2016) Streamflow estimation by support vector machine coupled with different methods of time series decomposition in the upper reaches of Yangtze River, China. Environ Earth Sci 75(6):531