scholarly journals A Compound Approach for Monthly Runoff Forecasting Based on Multiscale Analysis and Deep Network with Sequential Structure

Water ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2274 ◽  
Author(s):  
Shi Chen ◽  
Shuning Dong ◽  
Zhiguo Cao ◽  
Junting Guo
Keyword(s):  
Water Resource Management ◽  
Sequential Structure ◽  
Runoff Forecasting ◽  
Mode Decomposition ◽  
Proposed Model ◽  
Runoff Series ◽  
Efficiency And Effectiveness ◽  
Predicted Values ◽  
Monthly Runoff ◽  
Gated Recurrent Unit

Accurate runoff forecasting is of great significance for the optimization of water resource management and regulation. Given such a challenge, a novel compound approach combining time-varying filtering-based empirical mode decomposition (TVFEMD), sample entropy (SE)-based subseries recombination, and the newly developed deep sequential structure incorporating convolutional neural network (CNN) into a gated recurrent unit network (GRU) is proposed for monthly runoff forecasting. Firstly, the runoff series is disintegrated into a collection of subseries adopting TVFEMD, considering the volatility of runoff series caused by complex environmental and human factors. The subseries recombination strategy based on SE and recombination criterion is employed to reconstruct the subseries possessing the approximate complexity. Subsequently, the newly developed deep sequential structure based on CNN and GRU (CNNGRU) is applied to predict all the preprocessed subseries. Eventually, the predicted values obtained above are aggregated to deduce the ultimate prediction results. To testify to the efficiency and effectiveness of the proposed approach, eight relevant contrastive models were applied to the monthly runoff series collected from Baishan reservoir, where the experimental results demonstrated that the evaluation metrics obtained by the proposed model achieved an average index decrease of 44.35% compared with all the contrast models.

scholarly journals Runoff forecasting model based on variational mode decomposition and artificial neural networks

2021 ◽  
Vol 19 (2) ◽  
pp. 1633-1648
Author(s):  
Xin Jing ◽  
◽  
Jungang Luo ◽  
Shangyao Zhang ◽  
Na Wei
Keyword(s):  
Neural Networks ◽  
Water Resource Management ◽  
Short Term Memory ◽  
Forecasting Model ◽  
Variational Mode Decomposition ◽  
Model Based ◽  
Runoff Forecasting ◽  
Mode Decomposition ◽  
Runoff Series ◽  
Correlation Information

<abstract> <p>Accurate runoff forecasting plays a vital role in water resource management. Therefore, various forecasting models have been proposed in the literature. Among them, the decomposition-based models have proved their superiority in runoff series forecasting. However, most of the models simulate each decomposition sub-signals separately without considering the potential correlation information. A neoteric hybrid runoff forecasting model based on variational mode decomposition (VMD), convolution neural networks (CNN), and long short-term memory (LSTM) called VMD-CNN-LSTM, is proposed to improve the runoff forecasting performance further. The two-dimensional matrix containing both the time delay and correlation information among sub-signals decomposing by VMD is firstly applied to the CNN. The feature of the input matrix is then extracted by CNN and delivered to LSTM with more potential information. The experiment performed on monthly runoff data investigated from Huaxian and Xianyang hydrological stations at Wei River, China, demonstrates the VMD-superiority of CNN-LSTM to the baseline models, and robustness and stability of the forecasting of the VMD-CNN-LSTM for different leading times.</p> </abstract>

A Novel Runoff Forecasting Model Based on the Decomposition-Integration-Prediction Framework

Water ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 3390
Author(s):  
Zhanxing Xu ◽  
Jianzhong Zhou ◽  
Li Mo ◽  
Benjun Jia ◽  
Yuqi Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Performance ◽  
Performance Model ◽  
Forecasting Model ◽  
Time Frequency ◽  
Runoff Forecasting ◽  
Proposed Model ◽  
Runoff Series ◽  
Parallel Input ◽  
Monthly Runoff

Runoff forecasting is of great importance for flood mitigation and power generation plan preparation. To explore the better application of time-frequency decomposition technology in runoff forecasting and improve the prediction accuracy, this research has developed a framework of runoff forecasting named Decomposition-Integration-Prediction (DIP) using parallel-input neural network, and proposed a novel runoff forecasting model with Variational Mode Decomposition (VMD), Gated Recurrent Unit (GRU), and Stochastic Fractal Search (SFS) algorithm under this framework. In this model, the observed runoff series is first decomposed into several sub-series via the VMD method to extract different frequency information. Secondly, the parallel layers in the parallel-input neural network based on GRU are trained to receive the input samples of each subcomponent and integrate their output adaptively through the concatenation layers. Finally, the output of concatenation layers is treated as the final runoff forecasting result. In this process, the SFS algorithm was adopted to optimize the structure of the neural network. The prediction performance of the proposed model was evaluated using the historical monthly runoff data at Pingshan and Yichang hydrological stations in the Upper Yangtze River Basin of China, and seven various single and decomposition-based hybrid models were developed for comparison. The results show that the proposed model has obvious advantages in overall prediction performance, model training time, and multi-step-ahead prediction compared to several comparative methods, which is a reasonable and more efficient monthly runoff forecasting method based on time series decomposition and neural networks.

RBF Prediction Model Based on EMD for Forecasting GPS Precipitable Water Vapor and Annual Precipitation

2013 ◽  
Vol 765-767 ◽  
pp. 2830-2834 ◽  
Author(s):  
Yan Ping Liu ◽  
Yong Wang ◽  
Zhen Wang
Keyword(s):  
Rbf Neural Network ◽  
Precipitable Water ◽  
Annual Precipitation ◽  
Maximum Deviation ◽  
Atmospheric Sciences ◽  
Precipitation Forecasting ◽  
Mode Function ◽  
Mode Decomposition ◽  
Proposed Model ◽  
Predicted Values

The forecast of precipitations is important in meteorology and atmospheric sciences. A new model is proposed based on empirical mode decomposition and the RBF neural network. Firstly, GPS PWV time series is broken down into series of different scales intrinsic mode function. Secondly, the phase space reconstruction is done. Thirdly, each component is predicted by RBF. Finally, the final prediction value is reconstructed. Next, the model is tested on annual precipitation sequence from 2001 to 2010 in northeast China. The result shows that predictive value is close to the actual precipitation, which can better reflect the actual precipitation change. From 2001 to 2010, the maximum deviation of the predicted values never exceeds 4%. The testing results show that the proposed model can increase precipitation forecasting accuracies not only in GPS PWV but also in annual precipitation.

Wavelet based relevance vector machine model for monthly runoff prediction

2018 ◽  
Vol 54 (2) ◽  
pp. 134-141 ◽  
Author(s):  
Fang Ruiming
Keyword(s):  
Historical Data ◽  
Relevance Vector Machine ◽  
Machine Model ◽  
Inverse Transform ◽  
Minjiang River ◽  
Proposed Model ◽  
Runoff Prediction ◽  
Variation Characteristics ◽  
Predicted Values ◽  
Monthly Runoff

Abstract In this study, wavelet transform (WT) and a relevance vector machine (RVM) are integrated to predict monthly runoff. First, the WT method is adopted to decompose the monthly runoff time series into subsequences of different scales, and the variation characteristics, especially the periodicity of the runoff, are analyzed. Then, the regression model of RVM is established in each subsequence. Finally, the prediction results of each subsequence are integrated to obtain the final predicted values of monthly runoff through wavelet inverse transform. The proposed model was tested using the historical data of Minjiang River; the results show that compared with the RVM model, the WT-RVM model has better precision and can be applied in the prediction of monthly runoff.

scholarly journals Monthly Mean Meteorological Temperature Prediction Based on VMD-DSE and Volterra Adaptive Model

2020 ◽  
Vol 2020 ◽  
pp. 1-17 ◽  
Author(s):  
Guohui Li ◽  
Wanni Chang ◽  
Hong Yang
Keyword(s):  
Prediction Model ◽  
Volterra Model ◽  
Forecasting Model ◽  
Temperature Prediction ◽  
Mean Temperature ◽  
Mode Decomposition ◽  
Proposed Model ◽  
Energy Environment ◽  
Predicted Values ◽  
Combined Forecasting

Climate is a complex and chaotic system, and temperature prediction is a challenging problem. Accurate temperature prediction is also concerned in the fields of energy, environment, industry, and agriculture. In order to improve the accuracy of monthly mean temperature prediction and reduce the calculation scale of hybrid prediction process, a combined prediction model based on variational mode decomposition-differential symbolic entropy (VMD-DSE) and Volterra is proposed. Firstly, the original monthly mean meteorological temperature sequence is decomposed into finite mode components by VMD. The DSE is used to analyze the complexity and reconstruct the sequences. Then, the new sequence is reconstructed in phase space. The delay time and embedding dimension are determined by the mutual information method and G-P method, respectively. On this basis, the Volterra adaptive prediction model is established to modeling and predicting each component. Finally, the final predicted values are obtained by superimposing the predicted results. The monthly mean temperature data of Xianyang and Yan’an are used to verify the prediction performance of the proposed model. The experimental results show that the VMD-DSE-Volterra model shows better performance in the prediction of monthly mean temperature compared with other benchmark models in this paper. In addition, the combined forecasting model proposed in this paper can reduce the modeling time and improve the forecasting accuracy, so it is an effective forecasting model.

scholarly journals Daily Runoff Forecasting Using Ensemble Empirical Mode Decomposition and Long Short-Term Memory

2021 ◽  
Vol 9 ◽  
Author(s):  
Ruifang Yuan ◽  
Siyu Cai ◽  
Weihong Liao ◽  
Xiaohui Lei ◽  
Yunhui Zhang ◽  
...  
Keyword(s):  
Empirical Mode Decomposition ◽  
Short Term Memory ◽  
Ensemble Empirical Mode Decomposition ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Runoff Forecasting ◽  
Mode Decomposition ◽  
Runoff Series ◽  
Long Short Term Memory

Hydrological series data are non-stationary and nonlinear. However, certain data-driven forecasting methods assume that streamflow series are stable, which contradicts reality and causes the simulated value to deviate from the observed one. Ensemble empirical mode decomposition (EEMD) was employed in this study to decompose runoff series into several stationary components and a trend. The long short-term memory (LSTM) model was used to build the prediction model for each sub-series. The model input set contained the historical flow series of the simulation station, its upstream hydrological station, and the historical meteorological element series. The final input of the LSTM model was selected by the MI method. To verify the effect of EEMD, this study used the Radial Basis Function (RBF) model to predict the sub-series, which was decomposed by EEMD. In addition, to study the simulation characteristics of the EEMD-LSTM model for different months of runoff, the GM(group by month)-EEMD-LSTM was set up for comparison. The key difference between the GM-EEMD-LSTM model and the EEMD-LSTM model is that the GM model must divide the runoff sequence on a monthly basis, followed by decomposition with EEMD and prediction with the LSTM model. The prediction results of the sub-series obtained by the LSTM and RBF exhibited better statistical performance than those of the original series, especially for the EEMD-LSTM. The overall GM-EEMD-LSTM model performance in low-water months was superior to that of the EEMD-LSTM model, but the simulation effect in the flood season was slightly lower than that of the EEMD-LSTM model. The simulation results of both models are significantly improved compared to those of the LSTM model.

scholarly journals Evaluating The Performance of Several Data Preprocessing Methods Based On GRU in Forecasting Monthly Runoff Time Series

2021 ◽  
Author(s):  
Wenchuan Wang ◽  
Yu-jin Du ◽  
Kwok-wing Chau ◽  
Chun-Tian Cheng ◽  
Dong-mei Xu ◽  
...  
Keyword(s):  
Time Series ◽  
Performance Metrics ◽  
Wavelet Packet ◽  
Singular Spectrum Analysis ◽  
Data Preprocessing ◽  
Ensemble Empirical Mode Decomposition ◽  
Runoff Forecasting ◽  
Mode Decomposition ◽  
Adaptive Noise ◽  
Monthly Runoff

Abstract The optimal planning and management of modern water resources depends highly on reliable and accurate runoff forecasting. Data preprocessing technology can provide new possibilities for improving the accuracy of runoff forecasting, when basic physical relationships cannot be captured using a single prediction model. Yet, few researches evaluated the performances of various data preprocessing technology in predicting monthly runoff time series so far. In order to fill this research gap, this paper investigates the potential of five data preprocessing techniques based on gated recurrent unit network (GRU) model in monthly runoff prediction, namely variational mode decomposition (VMD), wavelet packet decomposition (WPD), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), extreme-point symmetric mode decomposition (ESMD), and singular spectrum analysis (SSA). In this study, the original monthly runoff data is first decomposed into a set of subcomponents using five data preprocessing methods; second, each component is predicted by developing an appropriate GRU model; finally, the forecasting results of different two-stage hybrid models are obtained by aggregating of forecast results of the corresponding subcomponents. Four performance metrics are employed as the evaluation benchmarks. The experimental results from two hydropower stations in China show that five data preprocessing techniques can attain satisfying prediction results, while VMD and WPD methods can yield better performance than CEEMDAN, ESMD and SSA in both training and testing periods in terms of four indexes. Indeed, it is significantly important to carefully determine an appropriate data preprocessing method according to the actual characteristics of the study area.

Estimating Parameters of SAR Model by Recursive Least Square Method

2012 ◽  
Vol 518-523 ◽  
pp. 4171-4176
Author(s):  
Meng Cheng ◽  
Jo Song Guk ◽  
Jin Wen Wang
Keyword(s):  
Autoregressive Model ◽  
Least Square Method ◽  
Parameters Estimation ◽  
Least Square ◽  
Recursive Least Square ◽  
Moment Estimation ◽  
Runoff Forecasting ◽  
Runoff Series ◽  
Monthly Runoff ◽  
Recursive Least Square Method

Seasonal runoff series can be described by seasonal autoregressive model, which is extensively applied in long-term runoff forecasting. The common way of parameters estimation is moment estimation. This paper estimates parameters of seasonal autoregressive model by recursive least square method and applies the method in forecasting the monthly runoff for the Three Gorges. An effective procedure based upon the least fitting error is proposed to determine the model order. The forecasting results are satisfactory.

scholarly journals Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Jupeng Xie ◽  
Huajun Zhang ◽  
Linfan Liu ◽  
Mengchuan Li ◽  
Yixin Su
Keyword(s):  
Wind Speed ◽  
Wind Speed Data ◽  
Wind Speeds ◽  
Mode Decomposition ◽  
Proposed Model ◽  
High Volatility ◽  
Deep Layers ◽  
Sea Wind ◽  
Gated Recurrent Unit ◽  
Degradation Effect

Sea wind speed forecast is important for meteorological navigation system to keep ships in safe areas. The high volatility and uncertainty of wind make it difficult to accurately forecast multistep wind speed. This paper proposes a new decomposition-based model to forecast hourly sea wind speeds. Because mode mixing affects the accuracy of the empirical mode decomposition- (EMD-) based models, this model uses the variational mode decomposition (VMD) to alleviate this problem. To improve the accuracy of predicting subseries with high nonlinearity, this model uses stacked gate recurrent units (GRU) networks. To alleviate the degradation effect of stacked GRU, this model modifies them by adding residual connections to the deep layers. This model decomposes the nonlinear wind speed data into four subseries with different frequencies adaptively. Each stacked GRU predictor has four layers and the residual connections are added to the last two layers. The predictors have 24 inputs and 3 outputs, and the forecast is an ensemble of five predictors’ outputs. The proposed model can predict wind speed in the next 3 hours according to the past 24 hours’ wind speed data. The experiment results on three different sea areas show that the performance of this model surpasses those of a state-of-the-art model, several benchmarks, and decomposition-based models.

Sign in / Sign up

Export Citation Format

Share Document