Daily streamflow forecasting in Sobradinho Reservoir using machine learning models coupled with wavelet transform and bootstrapping

Saraiva, Samuel Vitor; Carvalho, Frede de Oliveira; Santos, Celso Augusto Guimarães; Barreto, Lucas Costa; Freire, Paula K. M. M.

doi:10.1016/j.asoc.2021.107081

Cited by 83 publications

(22 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has made very significant progress compared in the area of hydrology. The application in the hydrology field has shown its success since the beginning of the last decade, in particular in the hydrological time series analysis and forecasting (e.g., Chen et al 2021;Zhang et al 2021;Shi et al 2021;Saraiva et al 2021;Abda et al 2021;Freire et al 2019;Abda and Chettih 2018;Reddy and Adarsh 2016;Huang et al 2014;. It is worth highlighting that although CWT could give information and solution for our requirements, DWT and HHT are more flexible.…”

Section: New Insights From the Proposed Hybrid Methodsmentioning

confidence: 99%

Improving the visualization of rainfall trends using various innovative trend methodologies with time–frequency-based methods

et al. 2022

Self Cite

View full text Add to dashboard Cite

In this paper, the Innovative Trend Methodology (ITM) and their inspired approaches, i.e., Double (D-ITM) and Triple (T-ITM), were combined with Hilbert Huang transform (HHT) time frequency-based method. The new hybrid methods (i.e., ITM-HHT, D-ITM-HHT, and T-ITM-HHT) were proposed and compared to the DWT-based methods in order to recommend the best method. Three total annual rainfall time series from 1920 to 2011 were selected from three hydrological basins in Northern Algeria. The new combined models (ITM-HHT, D-ITM-HHT, and T-ITM-HHT) revealed that the 1950–1975 period has significant wet episodes followed by a long-term drought observed in the western region of Northern Algeria, while Northeastern Algeria presented a wet period since 2001. The proposed approaches successfully detected, in a visible manner, hidden trends presented in the signals, which proves that the removal of some modes of variability from the original rainfall signals can increase the accuracy of the used approaches.

show abstract

Section: New Insights From the Proposed Hybrid Methodsmentioning

confidence: 99%

Improving the visualization of rainfall trends using various innovative trend methodologies with time–frequency-based methods

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dumka et al [47] developed a hybrid WANN model for monthly rainfall-runoff modelling on the Bhakhara River, Uttarakhand. Saraiva et al [48] enhanced ANN prediction accuracy in the context of the daily flow of intermittent rivers by employing WANN models. Bajirao et al [2] estimated the SSL by using different soft computing approaches and concluded that the performance of the ANN model was enhanced by coupling WT analysis.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Soft Computing Techniques for the Prediction of Suspended Sediment Loads in Rivers

2021

View full text Add to dashboard Cite

A key goal of sediment management is the quantification of suspended sediment load (SSL) in rivers. This research focused on a comparison of different means of suspended sediment estimation in rivers. This includes sediment rating curves (SRC) and soft computing techniques, i.e., local linear regression (LLR), artificial neural networks (ANN) and the wavelet-cum-ANN (WANN) method. Then, different techniques were applied to predict daily SSL at the Pirna and Magdeburg Stations of the Elbe River in Germany. By comparing the results of all the best models, it can be concluded that the soft computing techniques (LLR, ANN and WANN) better predicted the SSL than the SRC method. This is due to the fact that the former employed non-linear techniques for the data series reconstruction. The WANN models were the overall best performer. The WANN models in the testing phase showed a mean R2 of 0.92 and a PBIAS of −0.59%. Additionally, they were able to capture the suspended sediment peaks with greater accuracy. They were more successful as they captured the dynamic features of the non-linear and time-variant suspended sediment load, while other methods used simple raw data. Thus, WANN models could be an efficient technique to simulate the SSL time series because they extract key features embedded in the SSL signal.

show abstract

“…19 To predict hydropower generation, the flow of rivers must be predicted for the coming years. 20 Using climatic parameters as input to hydrological models, flow can be simulated for years to come. Different types of hydrological models can simulate river flow, including these models can be referred to as models HACRES, SWAT, SIMHYD, and so forth.…”

Section: Introductionmentioning

confidence: 99%

Forecasting hydropower generation byGFDL‐CM3climate model and hybrid hydrological‐Elman neural network model based on Improved Sparrow Search Algorithm (ISSA)

Wang

Gholinia

2021

Concurrency and Computation

View full text Add to dashboard Cite

One of the most sensitive factors affecting hydropower generation is climate change.The objective of this study is to forecast the hydropower generation under the influence of climate change for the next 50 years. For this purpose, the GFDL-CM3 model is used under three scenarios: RCP2.6, RCP4.5, and RCP8.5 to predict precipitation and temperature. Any change in the inlet flow to the turbine will cause changes in the hydropower output. Therefore, the more accurately the flow is estimated, the hydropower generation is forecasted more accurately. In this research, a hydrological-neural network hybrid model for flow prediction is presented in which the Improved Sparrow Search Algorithm (ISSA) has been used. The results forecasting climate parameters showed that the average annual rainfall, runoff, and evaporation have a downward trend compared to the control period. The minimum and maximum annual temperatures have an increasing trend compared to the control period. To evaluate the hydropower generation Aras dam, the HEC-Ressim reservoir model is utilized. By comparing the average annual hydropower with the control period, it is known that the power generation will decrease in future years. The average annual electricity generated by hydropower under the scenario RCP2.6 and RCP4.5 and RCP8.

show abstract

Daily streamflow forecasting in Sobradinho Reservoir using machine learning models coupled with wavelet transform and bootstrapping

Cited by 83 publications

References 42 publications

Improving the visualization of rainfall trends using various innovative trend methodologies with time–frequency-based methods

Improving the visualization of rainfall trends using various innovative trend methodologies with time–frequency-based methods

Assessment of Soft Computing Techniques for the Prediction of Suspended Sediment Loads in Rivers

Forecasting hydropower generation byGFDL‐CM3climate model and hybrid hydrological‐Elman neural network model based on Improved Sparrow Search Algorithm (ISSA)

Contact Info

Product

Resources

About