Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences

Zhang, Xiaoli; Peng, Yong; Zhang, Chi; Ben-de, Wang

doi:10.1016/j.jhydrol.2015.09.047

Cited by 154 publications

(68 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Even for the EEMD-ARIMA model, R is 0.89 and 0.95 for ten-day and monthly prediction, respectively. The correlation coefficients R of the monthly prediction by both EMD-ARIMA and EEMD-ARIMA hybrid model are both higher than the previous studies of Zhu et al [40], Zhang et al [44], and Kisi et al [45], which use rainfall and runoff data, or monthly data directly. The performance of RMSE, MAPE, MAE and R of the monthly prediction is higher than that of the ten-day prediction in all models.…”

Section: Resultscontrasting

confidence: 57%

“…For sufficient information mining, we used ten-day average data instead of monthly data as most of the long-term forecast studies. In the existing study by Zhang et al [44], monthly data of over 50 years were used for prediction, and the MAPE was 0.22 and 0.19, respectively, for the two stations they selected, and the R was 0.602 and 0.519, respectively. While in this study, ten-day average data of only 6 years were used, and the MAPE of monthly prediction was 0.127, and 0.137 for the EMD-ARIMA, and EEMD-ARIMA models, respectively, and the R was also as high as 0.950 for both of the models.…”

Section: Discussionmentioning

confidence: 99%

“…Zhu et al [40] coupled EMD with SVM models for monthly streamflow forecasting and the best Mean Absolute Percentage Error (MAPE) of the hybrid model is 17%. Zhang et al [44] combined three preprocessing techniques including wavelet analysis (WA), EMD, and singular spectrum analysis (SSA) with autoregressive moving average (ARMA) model to develop three hybrid models WA-ARMA, EMD-ARMA and SSA-ARMA for monthly streamflow forecasting of two stations. The best MAPE of these hybrid methods for the first station and the second station are 34% and 26%, respectively, which perform poorer than the EEMD-ARIMA methods proposed in this study with an MAPE of 14.5%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid Models Combining EMD/EEMD and ARIMA for Long-Term Streamflow Forecasting

Wang

Qiu

2018

Water

View full text Add to dashboard Cite

Long-term streamflow forecast is of great significance for water resource application and management. However, accurate monthly streamflow forecasting is challenging due to its non-stationarity and uncertainty. Time series analysis methods have been proved to perform well in stationary time series forecasting, which can be derived from decomposition of the non-stationary sequence. As common decomposition methods in time domain, Empirical Mode Decomposition (EMD) and Ensemble Empirical Mode Decomposition (EEMD) are selected to decompose the components with different time-scale characteristics in the original hydrological time series in this study. The derived components are proved to be stationary by the stationarity test. Thus, Autoregressive Integrated Moving Average (ARIMA) model, a simple and effective time series analysis method, is used to forecast the components. A hybrid EMD/EEMD-ARIMA model is proposed in this study for long-term streamflow forecasting, which is applied to the upper stream of the Yellow River. The original daily streamflow time series of six years at the Tangnaihai station are firstly decomposed by EMD/EEMD into several stationary or simple non-stationary sub-series to explore detailed data information with different time scales. ARIMA models with appropriate parameters are then established for each subsequence to forecast the stream flow of the next year. Predicted ten-day and monthly stream flow is finally obtained combing the predictions of all the components. The EMD-ARIMA hybrid model performs best in forecasting high and moderate value of streamflow and fits best with the observation compared with EEMD-ARIMA and ARIMA models. The results not only verify the effectiveness of the proposed hybrid EMD/EEMD-ARIMA model in exploiting comprehensive information to improve the prediction but also indicate that the EMD-ARIMA model with end points disposal performs the best and can be used for long-term hydrological forecasting.

show abstract

Section: Resultscontrasting

confidence: 57%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Models Combining EMD/EEMD and ARIMA for Long-Term Streamflow Forecasting

Wang

Qiu

2018

Water

View full text Add to dashboard Cite

show abstract

“…The additional white noise exists through the whole timefrequency space uniformly with the constituting components of different scales. Zhang et al (2015) developed three hybrid models by combining three preprocessing techniques including wavelet analysis (WA), EMD, and singular spectrum analysis (SSA) with an ANN model for monthly discharge forecasting of two stations. Each IMF decomposed from EEMD represents a true instinct timescale characteristics change rule for different timescales of the original data; therefore the accuracy of the EEMD-ANN method is higher than that of EMD-ANN.…”

Section: Discussionmentioning

confidence: 99%

“…A number of research studies have been reported on hydrological forecasting in past decades, mainly including physical models and mathematical methods (X. L. Zhang, Peng, Zhang, & Wang, 2015). Physical models explore the hydrological dynamic process of watershed combing weather processes (Chen & Brissette, 2015;Smiatek, Kunstmann, & Werhahn, 2012;Ye et al, 2017), meteorological conditions (Hanna et al, 2013;Ralph, Coleman, Neiman, Zamora, & Dettinger, 2013) and underlying surface conditions (Rosenberg, Clark, Steinemann, & Lettenmaier, 2013;Sinha, Sankarasubramanian, & Mazrooei, 2014).…”

Section: Introductionmentioning

confidence: 99%

Long‐term streamflow forecasting using artificial neural network based on preprocessing technique

Wang²,

Qiu

2019

Journal of Forecasting

View full text Add to dashboard Cite

Artificial neural network (ANN) combined with signal decomposing methods is effective for long‐term streamflow time series forecasting. ANN is a kind of machine learning method utilized widely for streamflow time series, and which performs well in forecasting nonstationary time series without the need of physical analysis for complex and dynamic hydrological processes. Most studies take multiple factors determining the streamflow as inputs such as rainfall. In this study, a long‐term streamflow forecasting model depending only on the historical streamflow data is proposed. Various preprocessing techniques, including empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD) and discrete wavelet transform (DWT), are first used to decompose the streamflow time series into simple components with different timescale characteristics, and the relation between these components and the original streamflow at the next time step is analyzed by ANN. Hybrid models EMD‐ANN, EEMD‐ANN and DWT‐ANN are developed in this study for long‐term daily streamflow forecasting, and performance measures root mean square error (RMSE), mean absolute percentage error (MAPE) and Nash–Sutcliffe efficiency (NSE) indicate that the proposed EEMD‐ANN method performs better than EMD‐ANN and DWT‐ANN models, especially in high flow forecasting.

show abstract

On the role of the architecture for spring discharge prediction with deep learning approaches

Zhou

2022

Hydrological Processes

View full text Add to dashboard Cite

Understanding karst spring flow is important to accommodate the increasing water demand caused by the population growth and manage the freshwater water resource effectively. However, due to the spatial and temporal heterogeneity and complex hydrological processes in karst systems, predicting karst spring discharge remains challenging. In this study, three deep learning‐based models, including long short‐term memory (LSTM), gated recurrent unit (GRU) and simple recurrent neural network (RNN), are framed with an encoder–decoder architecture to provide multiple‐step‐ahead spring discharge prediction. The encoder–decoder architecture includes an encoder that reads and encodes the input sequence into a vector and decoder that deciphers the vector and outputs the predicted sequence. Three hybrid models called LSTM‐ED, GRU‐ED and simple RNN‐ED are compared with single‐step models and multiple‐step models without the encoder–decoder architecture to investigate the role of the encoder–decoder architecture on multi‐step‐ahead prediction. The sensitivity of the selection of input time and lead time steps on the karst spring discharge prediction is evaluated. The predicted results are compared with the observed spring discharge. It implies that: (1) LSTM‐ED, GRU‐ED and RNN‐ED models obtain similar results on predicting karst spring discharge multiple time steps ahead; (2) three hybrid multiple‐step models outperform the single‐step models in making consistent and accurate spring discharge predictions; (3) the multiple‐step models framed with an encoder–decoder architecture obtain better spring discharge prediction results than the single‐step models and multiple‐step models without the encoder–decoder structure; (4) the LSTM‐ED, GRU‐ED and simple RNN‐ED models are sensitive to the selection of lead time and insensitive to the selection of input time step. A short lead time typically yields a more accurate spring discharge prediction.

show abstract

Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences

Cited by 154 publications

References 34 publications

Hybrid Models Combining EMD/EEMD and ARIMA for Long-Term Streamflow Forecasting

Hybrid Models Combining EMD/EEMD and ARIMA for Long-Term Streamflow Forecasting

Long‐term streamflow forecasting using artificial neural network based on preprocessing technique

On the role of the architecture for spring discharge prediction with deep learning approaches

Contact Info

Product

Resources

About