![]() Lahmiri S (2015) Long memory in international financial markets trends and short movements during 2008 financial crisis based on variational mode decomposition and detrended fluctuation analysis. Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Koza JR (1992) Genetic Programming: On the programming of computers by means of natural selection. Kisi O, Cimen M (2012) Precipitation forecasting by using wavelet-support vector machine conjunction model. Huang SZ, Chang JX, Huang Q, Chen YT (2014) Monthly streamflow prediction using modified EMD-based support vector machine. ![]() Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng QA, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Hinton GE (2002) Training products of experts by minimizing contrastive divergence. IEEE Sigrurl Processing Magazine 29(6):82–97 Hinton G, Deng L, Yu D, Dahl GE, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, Kingsbury B (2012) Deep neural networks for acoustic modeling in speech recognition. He Y, Wang F, Mu X, Yan H, Zhao G (2015) An assessment of human versus climatic impacts on Jing River Basin, Loess Plateau, China. PLoS One 9(8):e104663ĭragomiretskiy K, Zosso D (2014) Variational mode decomposition. IEEE Trans Inf Theory 36:6–7ĭi CL, Yang XH, Wang XC (2014) A four-stage hybrid model for hydrological time series forecasting. Mach Learn:160–167ĭabuechies I (1990) The wavelet transform, time-frequency localization and signal analysis. Proceedings of the 25th international conference on. Water Resour Manag 28(1):99–113Ĭollobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. Neural Comput 22(12):3207–3220Ĭitakoglu H, Cobaner M, Haktanir T, Kisi O (2014) Estimation of long-term monthly mean reference evapotranspiration in Turkey. Lect Notes Comput Sci 6791:10–17Ĭiresan DC, Meier U, Gambardella LM, Schmidhuber J (2010) Deep big simple neural nets excel on handwritten digit recognition. Water 7(8):4232–4246Ĭho KH, Ilin A, Raiko T (2011) Improved learning of Gaussian-Bernoulli restricted Boltzmann machines. Algeria Renew Energ 35(6):1214–1219Ĭheng CT, Niu WJ, Feng ZK, Shen JJ, Chau KW (2015) Daily reservoir runoff forecasting method using artificial neural network based on quantum-behaved particle swarm optimization. John Wiley & SonsĬhellali F, Khellaf A, Belouchrani A (2010) Wavelet spectral analysis of the temperature and wind speed data at Adrar. Adv Neural Inf Proces Syst 19:153–160īox GE, Jenkins GM, Reinsel GC, Ljung GM (2015) Time Series Analysis: Forecasting and Control. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828īengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. J Hydrol 532:193–206īengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. Int Trans Electr Energ Syst 28(1):e2466īai Y, Chen ZQ, Xie JJ, Li C (2016) Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models. Thus the proposed hybrid VMD-DNN model is a promising new method for daily runoff forecasting.Īli M, Khan A, Rehman NU (2018) Hybrid multiscale wind speed forecasting based on variational mode decomposition. The results reveal that the proposed hybrid VMD-DNN model produces the best performance based on the Nash-Sutcliffe efficiency (NSE = 0.95), root mean square error (RMSE = 9.92) and mean absolute error (MAE = 3.82) values. To fully illustrate the feasibility and superiority of this approach, the VMD-DNN hybrid model was compared with EMD-DNN, EEMD-DNN, and multi-scale feature extraction -based VMD-DNN, EMD-DNN and EEMD-DNN. The proposed model is demonstrated using daily runoff series data from the Zhangjiashan Hydrological Station in Jing River, China. Finally, the ensemble forecasting result is formulated by summing the prediction sub-results of the modelled IMFs. Second, predicted models of decomposed IMFs are established by learning the deep feature values of the DNN. First, VMD is applied to decompose the original runoff series into multiple intrinsic mode functions (IMFs), each with a relatively local frequency range. ![]() To improve the prediction accuracy, a hybrid model based on variational mode decomposition (VMD) and deep neural networks (DNN), referred to as VMD-DNN, is proposed to perform daily runoff forecasting. Accurate and reliable runoff forecasting plays an increasingly important role in the optimal management of water resources.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |