Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework

Quilty, John; Adamowski, Jan

doi:10.1016/j.jhydrol.2018.05.003

Cited by 181 publications

(103 citation statements)

References 112 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…Kisi and Cimen (2011) conducted a study investigating the improvement in the SVM model obtained by conjugating it with DWT and reported that the conjugated model DWT-SVM had a higher performance in forecasting monthly streamflow [4]. However, most of these studies have applied hybrid models in such a way that future information is sent to the model, but must not be included in the forecasting experiment [32], [33]. In the case of DWT, such studies have been implemented in such a way that all of the data are decomposed and reconstructed to produce the sub time series.…”

Section: Research Motivation and Enthusiasmmentioning

confidence: 99%

The Capacity of the Hybridizing Wavelet Transformation Approach With Data-Driven Models for Modeling Monthly-Scale Streamflow

et al. 2020

View full text Add to dashboard Cite

Hybrid models that combine wavelet transformation (WT) as a pre-processing tool with datadriven models (DDMs) as modeling approaches have been widely investigated for forecasting streamflow. The WT approach has been applied to original time series for decomposing processes prior to the application of DDM modeling. This procedure has been applied to eliminate redundant patterns or information that lead to a dramatic increase in the model performance. In this study, three experiments were implemented, including stand-alone data-driven modeling, hind cast decomposing using WT divided and entered into the extreme learning machine (ELM), and the extreme gradient boosting (XGB) model to forecast streamflow data. The WT method was applied in two forms: discrete and continuous (DWT and CWT). In this paper, a new hybrid model is proposed based on an integrative prediction model where XGB is used as an input selection tool for the importance attributes of the prediction matrix that are then supplied to the ELM model as a predictive model. The monthly streamflow, upstream flow, rainfall, temperature, and potential evapotranspiration of a basin named in 1805 and located in the south east of Turkey, are used for development of the model. The modeling results show that applying the WT method improved the performance in the hindcast experiment based on the CWT form with minimum root mean square error (RMSE = 4.910 m 3 /s). On the contrary, WT deteriorated the performance of the forecasting and the stand-alone models exhibited a better performance. WT increased the performance of the hindcast experiment due to the inclusion of future information caused by convolution of the time series. However, the forecast experiment experienced deterioration due to the border effect at the end of the time series. Hence, WT was found not to be a useful pre-processing technique in forecasting the streamflow.

show abstract

Section: Research Motivation and Enthusiasmmentioning

confidence: 99%

The Capacity of the Hybridizing Wavelet Transformation Approach With Data-Driven Models for Modeling Monthly-Scale Streamflow

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The boundary effect is a barrier for practical streamflow forecasting using decomposition-based models. Previous researchers handled the boundary effects by improving the decomposition algorithms (Quilty and Adamowski, 2018) or fixing the https://doi.org/10.5194/hess-2019-565 Preprint. Discussion started: 20 December 2019 c Author(s) 2019.…”

Section: Runoff Forecasting Of Long Leading Times For the Tsdp Modelsmentioning

confidence: 99%

“…Other relevant research contributions are those of Zhang et al (2015), Du et al (2017) , Tan et al (2018), Quilty and Adamowski (2018), and Fang et al (2019) who recently pointed out and explicitly criticized the afore-mentioned unpractical (and even incorrect) usage of signal processing techniques. Zhang et al (2015) evaluated and compared the outcomes of hindcast and forecast experiments (with and without validation information, respectively) for decomposition models based on WA, EMD, SSA, ARMA and ANN.…”

Section: Introductionmentioning

confidence: 99%

“…Tan et al (2018) assessed the impractical usage of forecasting scheme based on the EEMD and ANN. Quilty and Adamowski (2018) addressed the incorrect usage of the waveletbased models for hydrological forecasting. Fang et al (2019) demonstrated that EMD is not suitable for practical streamflow forecasting.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al (2015) tested several extended mathematical models to reduce the boundary effects and suggested that a properly-designed extension model can improve the forecasting performance. Quilty and Adamowski (2018) proposed a new wavelet data-driven forecasting framework, in which boundary-affected coefficients were removed by adopting either the stationary wavelet transform (SWT) algorithm (also known as "algorithme à trous") or the maximal-overlap discrete wavelet transform. Based on the abovementioned streamflow forecasting approaches, we would like to highlight three desirable improvements to attain more reliable and efficient decomposition-based models.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Two-stage Variational Mode Decomposition and Support Vector Regression for Streamflow Forecasting

Zuo¹,

Luo²,

Wang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Abstract. Streamflow forecasting is a crucial component in the management and control of water resources. Decomposition-based approaches have particularly demonstrated improved streamflow forecasting performance. However, it is not practical to firstly decompose the entire streamflow into several signal components and then divide the data samples of each component into training and validation sets for signal component prediction. This impracticality is due to the fact that some validation information, that is not available in practical streamflow forecasting, is used in that training process. Unfortunately, firstly dividing the entire streamflow into training and validation sets and then decomposing each set separately lead to undesirable boundary effects and complicated forecasting. Moreover, establishing a model for each signal component is quite laborious and summing the component predictions may lead to error accumulation. In addition, summing the decomposition results may sometimes lead to inaccurate reconstruction of the original streamflow. In order to address these shortcomings of decomposition-based models and improve the forecasting performance in basins lacking meteorological observations (e.g., precipitation and temperature), we propose a two-stage decomposition prediction (TSDP) framework, realize this framework using variational mode decomposition (VMD) and support vector machines (SVR), and refer to this realization as VMD-SVR. In the first stage of the TSDP framework, the entire streamflow data was divided into training and validation sets, each of which was then separately decomposed to avoid the influence of validation information on training. In the second stage, a single model for streamflow prediction was established using a set of mixed shuffled samples. This scheme saves the modelling time and reduces the influence of the boundary effects. We demonstrate experimentally the effectiveness, efficiency and reliability of the TSDP framework and its VMD-SVR realization in terms of the boundary effect reduction, decomposition performance, prediction outcomes, time consumption, overfitting, and forecasting capability for long leading times. Specifically, five comparative experiments were conducted based on the ensemble empirical mode decomposition (EEMD), singular spectrum analysis (SSA), discrete wavelet transform (DWT) and SVR. The experimental results on monthly runoff collected from three stations at the Wei River show the superiority of the TSDP framework compared to benchmark models.

show abstract

Noise Filter With Wavelet Analysis in Artificial Neural Networks (NOWANN) for Flow Time Series Prediction

Vázquez,

Corzo Perez,

Solomatine

2023

Advanced Hydroinformatics

View full text Add to dashboard Cite

Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework

Cited by 181 publications

References 112 publications

The Capacity of the Hybridizing Wavelet Transformation Approach With Data-Driven Models for Modeling Monthly-Scale Streamflow

The Capacity of the Hybridizing Wavelet Transformation Approach With Data-Driven Models for Modeling Monthly-Scale Streamflow

Two-stage Variational Mode Decomposition and Support Vector Regression for Streamflow Forecasting

Noise Filter With Wavelet Analysis in Artificial Neural Networks (NOWANN) for Flow Time Series Prediction

Contact Info

Product

Resources

About