Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model

Yang, Shuyu; Yang, Dawen; Chen, Jinsong; Zhao, Baoxu

doi:10.1016/j.jhydrol.2019.124229

Cited by 135 publications

(93 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) First, the periodic annual cycle of the time series is removed, by the procedure explained in detail in [27]. The process consists in standardizing the input time series x i of length N as follows:…”

Section: Detrended Fluctuation Analysis For Long-term Persistence Evamentioning

confidence: 99%

“…Both errors are measured in the same units as the variable under study (in our case, hm 3 ) and have been widely used for model evaluation [25][26][27][28][29]. While MAE gives the same weight to all errors, RMSE penalizes variance as it gives errors with larger absolute values more weight than errors with smaller absolute values.…”

Section: Experimental Designmentioning

confidence: 99%

“…In [1], the performances of different ML algorithms such as neural networks, support vector regression, and deep learning algorithms are evaluated in a problem of reservoir operation (mainly inflow and outflow prediction) at different time scales, in the Gezhouba dam, across the Yangtze River, in China. In [27], a recurrent neural network is proposed for estimating the inflow of a reservoir from a distributed hydrological model. In addition, different hybrid ML approaches have been proposed for problems of water level prediction in reservoirs, e.g., [28], hybridized a neural network with a genetic algorithm to improve the network training.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis and Prediction of Dammed Water Level in a Hydropower Reservoir Using Machine Learning and Persistence-Based Techniques

Castillo-Botón

Casillas-Pérez

Casanova-Mateo

et al. 2020

Water

View full text Add to dashboard Cite

This paper presents long- and short-term analyses and predictions of dammed water level in a hydropower reservoir. The long-term analysis was carried out by using techniques such as detrended fluctuation analysis, auto-regressive models, and persistence-based algorithms. On the other hand, the short-term analysis of the dammed water level in the hydropower reservoir was modeled as a prediction problem, where machine learning regression techniques were studied. A set of models, including different types of neural networks, Support Vector regression, or Gaussian processes was tested. Real data from a hydropower reservoir located in Galicia, Spain, qwew considered, together with predictive variables from upstream measuring stations. We show that the techniques presented in this paper offer an excellent tool for the long- and short-term analysis and prediction of dammed water level in reservoirs for hydropower purposes, especially important for the management of water resources in areas with hydrology stress, such as Spain.

show abstract

Section: Detrended Fluctuation Analysis For Long-term Persistence Evamentioning

confidence: 99%

Section: Experimental Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis and Prediction of Dammed Water Level in a Hydropower Reservoir Using Machine Learning and Persistence-Based Techniques

Castillo-Botón

Casillas-Pérez

Casanova-Mateo

et al. 2020

Water

View full text Add to dashboard Cite

show abstract

“…In agreement with the general trend in the field of hydrology, the abovementioned papers have covered most components of the hydrologic cycle. Outside of this Research Topic, machine learning has been applied to soil moisture (Fang et al, 2019), soil data extraction (Chaney et al, 2019), hydrology-influenced water quality variables including in-stream water temperature (Rahmani et al, 2020) and dissolved oxygen (Zhi et al, 2021), human water management through reservoirs (Yang et al, 2019;Ouyang et al, 2021), subsurface reactive transport (Laloy and Jacques, 2019;He et al, 2020), and vadose zone hydrology (Bandai and Ghezzehei, 2021), among others. ML is not only applicable in data-rich regions but can also be leveraged by data-scarce regions (Feng et al, 2021;Ma et al, 2021).…”

Section: Broadening the Use Of Machine Learning In Hydrologymentioning

confidence: 99%

Editorial: Broadening the Use of Machine Learning in Hydrology

Laloy

2021

Front. Water

View full text Add to dashboard Cite

“…Among AI models, artificial neural networks (ANN) and support vector machine or regression (SVM or SVR) are the two main models used in this field (Zhang et al, 2018). Yang et al (2019) point out that although the Recurrent Neural Network (RNN), a class of ANN, still suffers from limitations including longer run times, gradient vanishing, and exploding problems, it is well-suited for simulation of reservoir operation with dynamic process and high dependence on the historical information. Jain et al (1999) implemented ANNs to map functional relations between inflow, storage, demand and release of a reservoir operating policy.…”

Section: Introductionmentioning

confidence: 99%

Análise do comportamento operacional de reservatórios com redes neurais artificiais: o caso de Luiz Gonzaga, Brasil

Dalcin¹,

Pedrollo²,

Finck³

et al. 2021

REGA

View full text Add to dashboard Cite

Reservoirs are operated following specific policies, constrained by hydrological and structural conditions. When modeling anthropized water systems with reservoirs, the incorporation of existing operating policies is important to improve model capability. However, operating policies are not always available or easy to identify within large-scale multi-reservoir systems, where operation derives from large number of variables and constraints rather than a clear-cut local objective function. This study applies Artificial Neural Networks (ANNs) with the objective of analyzing if local variables (inflow, storage level, and evaporation) of a sub-system part of a large-scale coordinated multi-reservoir system are sufficient predictors of the operational behavior (release decisions) in a daily time step. The sub-system includes the Luiz Gonzaga and Sobradinho reservoirs. Results pointed to a Nash-Sutcliffe efficiency coefficient (NS) of 0.67 to 0.74 and a coefficient of determination (r 2 ) of 0.75, showing that we can predict the subsystem operational behavior most of the time but with some outflow peaks under predicted.

show abstract

Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model

Cited by 135 publications

References 88 publications

Analysis and Prediction of Dammed Water Level in a Hydropower Reservoir Using Machine Learning and Persistence-Based Techniques

Analysis and Prediction of Dammed Water Level in a Hydropower Reservoir Using Machine Learning and Persistence-Based Techniques

Editorial: Broadening the Use of Machine Learning in Hydrology

Análise do comportamento operacional de reservatórios com redes neurais artificiais: o caso de Luiz Gonzaga, Brasil

Contact Info

Product

Resources

About