Enhancing real-time streamflow forecasts with wavelet-neural network based error-updating schemes and ECMWF meteorological predictions in Variable Infiltration Capacity model

Nanda, Trushnamayee; Sahoo, Bhabagrahi; Chatterjee, Chandranath

doi:10.1016/j.jhydrol.2019.05.051

Cited by 40 publications

(9 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While a considerable research effort has been made to evaluate and improve the quality of streamflow forecasts (Gibbs et al, 2018;Nanda et al, 2019;Sharma et al, 2019;Van Osnabrugge et al, 2019;Feng et al, 2020;Pechlivanidis et al, 2020), how forecasts impact decision-making in the real-time reservoir operations has also gradually gained researchers' attention (Goddard et al, 2010;Shamir, 2017;Anghileri et al, 2019;Alexander et al, 2020;Hadi et al, 2020), e.g., do high-quality forecasts mean improved decision? Traditionally, a skillful forecast is vital for the reliability of the forecasts and is essential to promote the use of forecasts in real-world applications by decision makers.…”

Section: Introductionmentioning

confidence: 99%

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Guo

et al. 2021

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Streamflow forecasts are traditionally effective in mitigating water scarcity and flood defense. This study developed an artificial intelligence (AI)-based management methodology that integrated multi-step streamflow forecasts and multi-objective reservoir operation optimization for water resource allocation. Following the methodology, we aimed to assess forecast quality and forecast-informed reservoir operation performance together due to the influence of inflow forecast uncertainty. Varying combinations of climate and hydrological variables were input into three AI-based models, namely a long short-term memory (LSTM), a gated recurrent unit (GRU), and a least-squares support vector machine (LSSVM), to forecast short-term streamflow. Based on three deterministic forecasts, the stochastic inflow scenarios were further developed using Bayesian model averaging (BMA) for quantifying uncertainty. The forecasting scheme was further coupled with a multi-reservoir optimization model, and the multi-objective programming was solved using the parameterized multi-objective robust decision-making (MORDM) approach. The AI-based management framework was applied and demonstrated over a multi-reservoir system (25 reservoirs) in the Zhoushan Islands, China. Three main conclusions were drawn from this study: (1) GRU and LSTM performed equally well on streamflow forecasts, and GRU might be the preferred method over LSTM, given that it had simpler structures and less modeling time; (2) higher forecast performance could lead to improved reservoir operation, while uncertain forecasts were more valuable than deterministic forecasts, regarding two performance metrics, i.e., water supply reliability and operating costs; (3) the relationship between the forecast horizon and reservoir operation was complex and depended on the operating configurations (forecast quality and uncertainty) and performance measures. This study reinforces the potential of an AI-based stochastic streamflow forecasting scheme to seek robust strategies under uncertainty.

show abstract

Section: Introductionmentioning

confidence: 99%

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Guo

et al. 2021

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

show abstract

“…With recent advances in meteorology and computing science, global scale short‐to‐medium‐range numerical weather predictions (NWPs) are increasingly accurate over catchment scale, making them more valuable in informing reservoir operations (Ahmad & Hossain, 2020; Anghileri et al, 2019; Bauer et al, 2015; Monhart et al, 2019; Nanda et al, 2019; Sharma et al, 2018). Current reservoir inflow forecasting methods can be divided into two categories: physically‐based modeling chains (Ahmad & Hossain, 2020; Deng et al, 2015; Georgakakos et al, 2014; Nanda et al, 2019; Peng et al, 2019) and data‐driven direct forecast models (Ahmad & Hussain, 2019; Liao et al, 2020; Liu & Coulibaly, 2011; Zhong et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Exploring the role of the long short‐term memory model in improving multi‐step ahead reservoir inflow forecasting

Luo

Liu

Dong

et al. 2022

J Flood Risk Management

View full text Add to dashboard Cite

Daily inflow forecasting is of vital importance in reservoir economic operation.In the context of hydrometeorological forecasting, the effectiveness of the datadriven models has been demonstrated as bias correctors for physically-based models or direct forecasting models. However, existing studies only highlight the performance improvements provided by the data-driven model, lacking a comprehensive investigation on whether the data-driven model should be used as bias correctors or direct forecasting models. This study constructs long short-term memory (LSTM)-based preprocessing and postprocessing techniques for a hydrological model, which are tested by linear scaling preprocessing and autoregressive (AR) postprocessing models. The integrated model is compared with the LSTM-only model. The Shuibuya and Zuojiang reservoirs in China are selected as case studies. Results indicate that: (1) LSTM-based bias correctors are effective in both preprocessing and postprocessing and(2) the integrated model is comparable to the LSTM-only model when trained with four or more years of data, while it is better than the LSTM-only model when trained with less data. These findings demonstrate that data-driven methods can effectively correct the bias in physically-based model output, and integrating the physical and data-driven models is useful in improving multistep ahead reservoir inflow forecasting if limited data can be obtained.

show abstract

“…The limitation of using the finite training dataset is that there is no certainty that the selected minimization algorithm can achieve the global minimum rather it may stop at the local minima. For river flow forecasting, several studies emphasized for the use of different kinds of hybrid ANN models such as the modular ANN, integrated ANN and bootstrapping and wavelet analysis (Zhang and Govindaraju 2000;Wang et al 2006;Tiwari and Chatterjee 2010a, b;Tiwari and Chatterjee 2011;Huo et al 2012;Nanda et al 2016Nanda et al , 2019. Similarly, to deal with the complex time series flow pattern of river discharge, data clustering technique has been found satisfactory to avoid the ambiguity associated with the different patterns in the time series data (Ju et al 2009).…”

Section: Introductionmentioning

confidence: 99%

Flood Forecasting Using Simple and Ensemble Artificial Neural Networks

Sahoo

Nanda

Chatterjee

2021

Geospatial Technologies for Land and Water Resources Management

Self Cite

View full text Add to dashboard Cite

With the increased flood havoc in many river basins worldwide, flood forecasting has been recognized as one of the feasible nonstructural measures of flood management. For accurate and reliable extreme flood forecasts, different artificial neural networks (ANNs)-based modelling approaches are developed in this study. For daily streamflow forecasting, a non-clustered feedforward backpropagation ANN (NCANN) model is developed using the daily observed streamflow training dataset. Further, in order to forecast high flow with ANN, two different types of models are developed, namely pre-classified ANN and post-processed ANN model. The preclassified ANN models are basically the cluster-based ANN (CANN), and the postprocessed ANN models are the ensemble ANNs (EANN). The high flow forecasting efficacy of the ANN models is compared for a common set of high flow regimes at one-, two-and three-day lead times in the flood-prone Mahanadi River basin in Eastern India. The results reveal that consideration of the training dataset consisting of various flow stratifications does not ensure a better forecasting of the high flow regime by NCANN model; rather the use of homogeneous set of training dataset gives improved forecasting during testing. Moreover, the high flow forecasting error is further reduced when the model ensembles are used. Seasonal flow assessment can be improved by using these developed models equally effectively.

show abstract

Enhancing real-time streamflow forecasts with wavelet-neural network based error-updating schemes and ECMWF meteorological predictions in Variable Infiltration Capacity model

Cited by 40 publications

References 69 publications

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Exploring the role of the long short‐term memory model in improving multi‐step ahead reservoir inflow forecasting

Flood Forecasting Using Simple and Ensemble Artificial Neural Networks

Contact Info

Product

Resources

About