Reservoir inflow forecasting is extremely important for the management of a reservoir. In practice, accurate forecasting depends on the feature learning performance. To better address this issue, this paper proposed a feature-enhanced regression model (FER), which combined stack autoencoder (SAE) with long short-term memory (LSTM). This model had two constituents: (1) The SAE was constructed to learn a representation as close as possible to the original inputs. Through deep learning, the enhanced feature could be captured sufficiently. (2) The LSTM was established to simulate the mapping between the enhanced features and the outputs. Under recursive modeling, the patterns of correlation in the short term and dependence in the long term were considered comprehensively. To estimate the performance of the FER model, two historical daily discharge series were investigated, i.e., the Yangtze River in China and the Sava Dolinka River in Slovenia. The proposed model was compared with other machine-learning methods (i.e., the LSTM, SAE-based neural network, and traditional neural network). The results demonstrated that the proposed FER model yields the best forecasting performance in terms of six evaluation criteria. The proposed model integrates the deep learning and recursive modeling, and thus being beneficial to exploring complex features in the reservoir inflow forecasting. Moreover, for smaller catchments with significant torrential characteristics, more data are needed (e.g., at least 20 years) to effectively train the model and to obtain accurate flood-forecasting results.
相似文献Middle-term and long-term streamflow forecasting is of great significance for water resources planning and management, cascade reservoirs optimal operation, agriculture and hydro-power generation. In this work, a framework was proposed which integrates least absolute shrinkage and selection operator (lasso), DBN and bootstrap to improve the performance and the stability of streamflow forecasting with the lead-time of one month. Lasso helps to screen the appropriate predictors for the DBN model, and the DBN model simulates the complex relationship between the selection predictors and streamflow, and then bootstrap with the DBN model contributes to evaluate the uncertainty. The Three-River Headwaters Region (TRHR) was taken as a case study. The results indicated that lasso-DBN-bootstrap model produced significantly more accurate forecasting results than the other three models and provides reliable information on the forecasting uncertainty, which will be valuable for water resources management and planning.
相似文献Monthly streamflow forecasting is vital for managing water resources. Recently, numerous studies have explored and evidenced the potential of artificial intelligence (AI) models in hydrological forecasting. In this study, the feasibility of the convolutional neural network (CNN), a deep learning method, is explored for monthly streamflow forecasting. CNN can automatically extract critical features from numerous inputs with its convolution–pooling mechanism, which is a distinct advantage compared with other AI models. Hydrological and large-scale atmospheric circulation variables, including rainfall, streamflow, and atmospheric circulation factors are used to establish models and forecast streamflow for Huanren Reservoir and Xiangjiaba Hydropower Station, China. The artificial neural network (ANN) and extreme learning machine (ELM) with inputs identified based on cross-correlation and mutual information analyses are established for comparative analyses. The performances of these models are assessed with several statistical metrics and graphical evaluation methods. The results show that CNN outperforms ANN and ELM in all statistical measures. Moreover, CNN shows better stability in forecasting accuracy.
相似文献Some previous studies have proved that prediction models using traditional overall decomposition sampling (ODS) strategy are unreasonable because the subseries obtained by the ODS strategy contain future information to be predicted. It is, therefore, necessary to put forward a new sampling strategy to fix this defect and also to improve the accuracy and reliability of decomposition-based models. In this paper, a stepwise decomposition sampling (SDS) strategy according to the practical prediction process is introduced. Moreover, an innovative input selection framework is proposed to build a strong decomposition-based monthly streamflow prediction model, in which sunspots and atmospheric circulation anomaly factors are employed as candidate input variables to enhance the prediction accuracy of monthly streamflow in addition to regular inputs such as precipitation and evaporation. Meanwhile, the partial correlation algorithm is employed to select optimal input variables from candidate input variables including precipitation, evaporation, sunspots, and atmospheric circulation anomaly factors. Four basins of the U.S. MOPEX project with various climate characteristics were selected as a case study. Results indicate that: (1) adding teleconnection factors into candidate input variables helps enhance the prediction accuracy of the support vector machine (SVM) model in predicting streamflow; (2) the innovative input selection framework helps to improve the prediction capacity of models whose candidate input variables interact with each other compared with traditional selection strategy; (3) the SDS strategy can effectively prevent future information from being included into input variables, which is an appropriate substitute of the ODS strategy in developing prediction models; (4) as for monthly streamflow, the hybrid variable model decomposition-support vector machine (VMD-SVM) models, using an innovative input selection framework and the SDS strategy, perform better than those which have not adopted this framework in all study areas. Generally, the findings of this study showed that the hybrid VMD-SVM model combining the SDS strategy and innovative input selection framework is a useful and powerful tool for practical hydrological prediction work in the context of climate change.
相似文献We have developed a hybrid model that integrates chaos theory and an extreme learning machine with optimal parameters selected using an improved particle swarm optimization (ELM-IPSO) for monthly runoff analysis and prediction. Monthly streamflow data covering a period of 55 years from Daiying hydrological station in the Chaohe River basin in northern China were used for the study. The Lyapunov exponent, the correlation dimension method, and the nonlinear prediction method were used to characterize the streamflow data. With the time series of the reconstructed phase space matrix as input variables, an improved particle swarm optimization was used to improve the performance of the extreme learning machine. Finally, the optimal chaotic ensemble learning model for monthly streamflow prediction was obtained. The accuracy of the predictions of the streamflow series (linear correlation coefficient of about 0.89 and efficiency coefficient of about 0.78) indicate the validity of our approach for predicting streamflow dynamics. The developed method had a higher prediction accuracy compared with an auto-regression method, an artificial neural network, an extreme learning machine with genetic algorithm and with PSO algorithm, suggesting that ELM-IPSO is an efficient method for monthly streamflow prediction.
相似文献Accurate and consistent annual runoff prediction in a region is a hot topic in management, optimization, and monitoring of water resources. A novel prediction model (ESMD-SE-WPD-LSTM) is presented in this study. Firstly, extreme-point symmetric mode decomposition (ESMD) is used to produce several intrinsic mode functions (IMF) and a residual (Res) by decomposing the original runoff series. Secondly, sample entropy (SE) method is employed to measure the complexity of each IMF. Thirdly, wavelet packet decomposition (WPD) is adopted to further decompose the IMF with the maximum SE into several appropriate components. Then long short-term memory (LSTM) model, a deep learning algorithm based recurrent approach, is employed to predict all components. Finally, forecasting results of all components are aggregated to generate the final prediction. The proposed model, which is applied to seven annual series from different areas in China, is evaluated based on four evaluation indexes (R, MAE, MAPE and RMSE). Results indicate that ESMD-SE-WPD-LSTM outperforms other benchmark models in terms of four evaluation indexes. Hence the proposed model can provide higher accuracy and consistency for annual runoff prediction, rendering it an efficient instrument for scientific management and planning of water resources.
相似文献Reasonable runoff forecasting is the foundation of water resource management. However, the impact of environmental change on streamflow was not fully revealed due to the lack of enough streamflow features in many previous studies. In contrast, too many features also could lead cause undesired problems, including unstable model, interpretation difficulty, overfitting, high computational complexity, and high memory complexity. To address the above problems, this study proposes a cause-driven runoff forecasting framework based on linear-correlated reconstruction and machine learning model and refers to this framework as CSLM. We use variance inflation factor (VIF), pairwise linear correlation (PLC) reconstruction, and long short-term memory (LSTM) to realize this framework, referred to as VIF-PLC-LSTM. Four experiments were conducted to demonstrate the accuracy and efficiency of the proposed framework and its VIF-PLC-LSTM realization. Four experiments compare 1) different filter thresholds of driving factors, 2) different combination prediction features, 3) different reconstruction methods of linear-correlated features, and 4) different CSLM models. Experimental results on daily streamflow data from the Tangnaihai station at the Yellow River source and the Yangxian station at the Han River show that 1) data filtering has the risk of feature information loss, 2) when the streamflow, ERA5L, and meteorology data are used as inputs at the same time, the performance of the model is superior to the combination of other prediction features; the prediction effect of different prediction features, 3) the reconstruction of linear-correlated features is not only better than dimension reduction but also can improve the forecasting performance for streamflow prediction, and 4) among different CSLM models, LSTM is superior to other models.
相似文献Accurate and reliable runoff forecasting plays an increasingly important role in the optimal management of water resources. 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. First, VMD is applied to decompose the original runoff series into multiple intrinsic mode functions (IMFs), each with a relatively local frequency range. Second, predicted models of decomposed IMFs are established by learning the deep feature values of the DNN. Finally, the ensemble forecasting result is formulated by summing the prediction sub-results of the modelled IMFs. The proposed model is demonstrated using daily runoff series data from the Zhangjiashan Hydrological Station in Jing River, China. 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 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. Thus the proposed hybrid VMD-DNN model is a promising new method for daily runoff forecasting.
相似文献Rainfall, which is one of the most important hydrologic processes, is influenced by many meteorological factors like climatic change, atmospheric temperature, and atmospheric pressure. Even though there are several stochastic and data driven hydrologic models, accurate forecasting of rainfall, especially smaller time step rainfall forecasting, still remains a challenging task. Effective modelling of rainfall is puzzling due to its inherent erratic nature. This calls for an efficient model for accurately forecasting daily rainfall. Singular Spectrum Analysis (SSA) is a time series analysis tool, which is found to be a very successful data pre-processing algorithm. SSA decomposes a given time series into a finite number of simpler and decipherable components. This study proposes integration of Singular Spectrum Analysis (SSA), Auto Regressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) into a hybrid model (SSA-ARIMA-ANN), which can yield reliable daily rainfall forecasts in a river catchment. In the present study, spatially averaged daily rainfall data over Koyna catchment, Maharashtra has been used. In this study SSA is proposed as a data pre-processing tool to separate stationary and non-stationary components from the rainfall data. Correlogram and Kwiatkowski–Phillips–Schmidt–Shin (KPSS) test has been used to validate the stationary and non-stationary components. In the developed hybrid model, the stationary components of rainfall data are modelled using ARIMA method and non-stationary components are modelled using ANN. The study of statistical performance of the model shows that the hybrid SSA-ARIMA-ANN model could forecast the daily rainfall of the catchment with reliable accuracy.
相似文献