Over the past 15 years, artificial neural networks (ANNs) have been used increasingly for prediction and forecasting in water resources and environmental engineering. However, despite this high level of research activity, methods for developing ANN models are not yet well established. In this paper, the steps in the development of ANN models are outlined and taxonomies of approaches are introduced for each of these steps. In order to obtain a snapshot of current practice, ANN development methods are assessed based on these taxonomies for 210 journal papers that were published from 1999 to 2007 and focus on the prediction of water resource variables in river systems. The results obtained indicate that the vast majority of studies focus on flow prediction, with very few applications to water quality. Methods used for determining model inputs, appropriate data subsets and the best model structure are generally obtained in an ad-hoc fashion and require further attention. Although multilayer perceptrons are still the most popular model architecture, other model architectures are also used extensively. In relation to model calibration, gradient based methods are used almost exclusively. In conclusion, despite a significant amount of research activity on the use of ANNs for prediction and forecasting of water resources variables in river systems, little of this is focused on methodological issues. Consequently, there is still a need for the development of robust ANN model development approaches.

Review: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions

The ultimate source of water for plants is precipitation; rain falling upon soil penetrates it at a rate depending upon the physical properties of that particular soil; snow and hail do the same after melting. If the rate of rainfall or the rate of production of water by melting exceeds the infiltration rate, then surface runoff occurs and the excess water drains into streams and eventually reaches the sea. That water which penetrates the soil replenishes the soil reservoir and when this is filled to capacity (see chapter 3) the surplus drains through into the aquifers. These are strata such as sand or chalk which can hold substantial quantities of recoverable water. Water held in the soil reservoir is drawn into plant roots and up their stems to be evaporated from the leaves back into the atmosphere, where it rejoins water evaporated from the sea, lakes and rivers and from the surface of wet soil. This so-called hydrological cycle (figure 1.2) depends for its continuance upon energy derived from the sun’s radiation and as will be shown in later chapters its rate is governed largely by meteorological factors.

The Water Balance

An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction

This paper presents details of an open access web site that can be used by hydrologists and other scientists to evaluate time series models. There is at present a general lack of consistency in the way in which hydrological models are assessed that handicaps the comparison of reported studies and hinders the development of superior models. The HydroTest web site provides a wide range of objective metrics and consistent tests of model performance to assess forecasting skill. This resource is designed to promote future transparency and consistency between reported models and includes an open forum that is intended to encourage further discussion and debate on the topic of hydrological performance evaluation metrics. It is envisaged that the provision of such facilities will lead to the creation of superior forecasting metrics and the development of international benchmark time series datasets.

/pdf/hydrotest-a-web-based-toolbox-of-evaluation-metrics-for-the-c41y55p7ti.pdf

HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts

This paper presents a survey of simulation and optimization modeling approaches used in reservoir systems operation problems. Optimization methods have been proved of much importance when used with simulation modeling and the two approaches when combined give the best results. The main objective of this review article is to discuss simulation, optimization and combined simulation–optimization modeling approach and to provide an overview of their applications reported in literature. In addition to classical optimization techniques, application and scope of computational intelligence techniques, such as, evolutionary computations, fuzzy set theory and artificial neural networks, in reservoir system operation studies are reviewed. Conclusions and suggestive remarks based on this survey are outlined, which could be helpful for future research and for system managers to decide appropriate methodology for application to their systems.

/pdf/simulation-optimization-modeling-a-survey-and-potential-1xvkgabzfk.pdf

Simulation-optimization modeling: a survey and potential application in reservoir systems operation.

Previous ensemble streamflow prediction (ESP) studies in Korea reported that modelling error significantly affects the accuracy of the ESP probabilistic winter and spring (i.e. dry season) forecasts, and thus suggested that improving the existing rainfall-runoff model, TANK, would be critical to obtaining more accurate probabilistic forecasts with ESP. This study used two types of artificial neural network (ANN), namely the single neural network (SNN) and the ensemble neural network (ENN), to provide better rainfall-runoff simulation capability than TANK, which has been used with the ESP system for forecasting monthly inflows to the Daecheong multipurpose dam in Korea. Using the bagging method, the ENN combines the outputs of member networks so that it can control the generalization error better than an SNN. This study compares the two ANN models with TANK with respect to the relative bias and the root-mean-square error. The overall results showed that the ENN performed the best among the three rainfall-runoff models. The ENN also considerably improved the probabilistic forecasting accuracy, measured in terms of average hit score, half-Brier score and hit rate, of the present ESP system that used TANK. Therefore, this study concludes that the ENN would be more effective for ESP rainfall-runoff modelling than TANK or an SNN. Copyright © 2005 John Wiley & Sons, Ltd.

Rainfall-runoff models using artificial neural networks for ensemble streamflow prediction

Comparison of hydrological models for the assessment of water resources in a data-scarce region, the Upper Blue Nile River Basin

This paper presents a Bayesian Stochastic Dynamic Programming (BSDP) model to investigate the value of seasonal flow forecasts in hydropower generation. The proposed BSDP framework generates monthly operating policies for the Skagit Hydropower System (SHS), which supplies energy to the Seattle metropolitan area. The objective function maximizes the total benefits resulting from energy produced by the SHS and its interchange with the Bonneville Power Administration. The BSDP-derived operating policies for the SHS are simulated using historical monthly inflows, as well as seasonal flow forecasts during 60 years from January 1929 through December 1988. Performance of the BSDP model is compared with alternative stochastic dynamic programming models. To illustrate the potential advantage of using the seasonal flow forecasts and other hydrologic information, the sensitivity of SHS operation is evaluated by varying (1) the reservoir capacity; (2) the energy demand; and (3) the energy price. The simulation results demonstrate that including the seasonal forecasts is beneficial to SHS operation.

Value of seasonal flow forecasts in Bayesian stochastic programming

This study presents state-of-the-art optimization techniques for enhancing reservoir operations which use sampling stochastic dynamic programming (SSDP) with ensemble streamflow prediction (ESP). SSDP used with historical inflow scenarios (SSDP/Hist) derives an off-line optimal operating policy through a backward-moving solution procedure. In contrast, SSDP used with monthly forecasts of ESP (SSSDP/ESP) reoptimizes the off-line policy. These stochastic models are used to derive a monthly joint operating policy during the drawdown period of the Geum River multireservoir system in Korea. A cross-validation test of 1,900 simulation runs demonstrates that: (1) proposed stochastic models that explicitly include inflow uncertainty are superior to those that do not; (2) updating policy with ESP forecasts is appropriate in this reservoir system; (3) the lower dam of the Geum River multireservoir system should maintain elevation of 66.5 m during the beginning of the drawdown period to avoid significant increase in...

Young-Oh Kim

Papers

Rainfall-runoff models using artificial neural networks for ensemble streamflow prediction

Comparison of hydrological models for the assessment of water resources in a data-scarce region, the Upper Blue Nile River Basin

Value of seasonal flow forecasts in Bayesian stochastic programming

Optimizing Operational Policies of a Korean Multireservoir System Using Sampling Stochastic Dynamic Programming with Ensemble Streamflow Prediction

Combining single-value streamflow forecasts - a review and guidelines for selecting techniques.