Daily Reservoir Inflow Research Articles

Hydrology Properties At Sembrong Dam Reservoir in Johor

Water is fresh potable water is not always available at the right time or the right place for human or ecosystem use [1]. According to Straskraba and Tundisi (1999), water impoundments constructed by damming rivers are called dam reservoirs. Under the Malaysian Western Johore Agricultural Development Project, the main function of the Sembrong dam is flood mitigation. The secondary function of the dam is to provide clean water supply to 240,000 consumers in Kluang district area [2]. Water from the Sembrong dam reservoir is treated at the West Sembrong Water Treatment Plant before the distribution. Daily reservoir inflow data were extracted by applying the water balance model to the Sembrong dam reservoir. Developing hydrologic hazard curves for risk assessment uses the length of record and type of data to determine the extrapolation limits for flood frequency analysis [5]. Extrapolation beyond the data is often necessary to provide information needed for dam safety risk assessments [6]. The sources of information used for flood hazard analyses include stream flow and precipitation records and pale flood data.

Chaotic Analysis of Reservoir Inflow Series: A Case Study on Koyna Reservoir Inflow

The significance of treating the reservoir inflow as a chaotic system instead of a stochastic system is gaining interest in the recent past. Out of various chaotic methods available to analyse time series data, correlation dimension method, the most commonly employed method in hydrology is used in the present study. Apart from identifying the behaviour of the series, correlation dimension method indicates the number of dimensions required to predict the future value in the time series. Correlation dimension of a time series is estimated using Heaviside step function through Grassberger–Procaccia algorithm. In order to prove the reliability of Grassberger–Procaccia algorithm, initially a deterministic series and two types of random number series are analyzed to identify their behaviour as well as to determine the correlation dimension. The daily reservoir inflow observed at Koyna reservoir for a period of 49 years (1961–2009) in Maharashtra, India, has been taken up to study its behaviour. From the detailed non-linear dynamic analysis using correlation dimension method it is found that the Koyna reservoir inflow is showing a low chaotic behaviour. The minimum correlation dimension for the daily Koyna reservoir inflow is around one and maximum correlation dimension is around four. It is also evident that only short term prediction is reasonable in this reservoir. This study proves the strength of Grassberger–Procaccia algorithm in classifying the behaviour of time series.

Applicability of Adaptive Neuro-Fuzzy Inference Systems in Daily Reservoir Inflow Forecasting

Applicability of Adaptive Neuro-Fuzzy Inference Systems in Daily Reservoir Inflow Forecasting

Improving the performance of data-driven techniques through data pre-processing for modelling daily reservoir inflow

The effect of data pre-processing while developing artificial intelligence (AI) -based data-driven techniques, such as artificial neural networks (ANN), model trees (MT) and linear genetic programming (LGP), is studied for Pawana Reservoir in Maharashtra, India. The daily one-step-ahead inflow forecasts are compared with flows generated from a univariate autoregressive integrated moving average (ARIMA) model. For the full-year data series, a large error is found mainly due to the occurrence of zero values, since the reservoir is located in an intermittent river. Hence, all the techniques are evaluated using two data series: 18 years of daily full-year inflow data (from 1 January to 31 December); and 18 years of daily monsoon season inflow data (from 1 June to 31 October) to take into account the intermittent nature of the data. The relevant range of inputs for each category is selected based on autocorrelation and partial autocorrelation analyses of the inflow series. Conventional pre-processing methods, such as transformation and/or normalization of data, do not perform well because of the large variation in magnitudes, as well as the many zero values (65% of the full-year data series). Therefore, the input data are pre-processed into un-weighted moving average (MA) series of 3 days, 5 days and 7 days. The 3-day MA series performs better, maintaining the peak inflow pattern as in the actual data series, while the coarser-scale (5-day and 7-day) MA series reduce the peak inflow pattern, leading to more errors in peak inflow prediction. The results indicate that AI methods are powerful tools for modelling the daily flow time series with appropriate data pre-processing, in spite of the presence of many zero values. The time-lagged recurrent network (TLRN) ANN modelling technique applied in this study maps the inflow forecasting in a better way than the standard multilayer perceptron (MLP) neural networks, especially in the case of the seasonal data series. The MT technique performs equally well for low and medium inflows, but fails to predict the peak inflows. However, LGP outperforms the other AI models, and also the ARIMA model, for all inflow magnitudes. In the LGP model, the daily full-year data series with more zero inflow values performs better than the daily seasonal models. Citation Jothiprakash, V. & Kote, A. S. (2011) Improving the performance of data-driven techniques through data pre-processing for modelling daily reservoir inflow. Hydrol. Sci. J. 56(1), 168–186.

Improving Daily Reservoir Inflow Forecasts with Model Combination

A major issue in real-time management of water resources is the need for accurate and reliable hydrologic forecasts at least 24 or 48 h ahead. An experiment on improving the accuracy of a conceptual hydrologic model used for daily reservoir inflow forecasting, by resorting to model combination, is presented. A robust weighted-average method is used to take advantage of three dynamically different models: a nearest-neighbor model, a conceptual model, and an artificial neural network model. At each time step, the output of each of these three models is computed, and either the absolute best result is considered or the competitive results are combined using the improved weighted-average method. The latter approach has shown a significant forecast improvement for up to 4-day-ahead prediction. Moreover, it is found that with the model combination, there is no need for postcorrection of the conceptual model forecasts. It is also found that the prediction accuracy is mainly driven by the nearest-neighbor method for the 2-day-ahead forecasts, and relatively by each model afterwards. However, none of the three models appears significantly better than the combined model approach, whatever the prediction lead time.

Assessment of Folsom lake response to historical and potential future climate scenarios: 1. Forecasting

In collaboration with operational forecast and management Agencies, an integrated forecast-control system is designed and applied to a major reservoir in California to evaluate the potential benefits of climate information for flood control, hydroelectric energy production, and low flow augmentation. In addition to retrospective studies involving the historical period 1964–1993, system simulations were performed for the future period 2001–2030, under a control and a 1% greenhouse-gas-increase scenario. This paper presents the forecast component formulation and validates ensemble 30-day reservoir-inflow forecasts under a variety of situations. The control component formulation and corresponding reservoir management results are presented in Yao and Georgakakos, this issue. The forecast component is based on ensemble flow forecasting. Quantiles of the distribution of climate-model precipitation simulations are used to select catchment-scale historical daily precipitation time series for the generation of an ensemble of daily reservoir-inflow by hydrologic models. Ensemble generation takes into consideration both atmospheric-forcing and hydrologic-model uncertainties. Principal conclusions of this paper are that the integrated system provides reliable ensemble inflow volume forecasts for the majority of the deciles of forecast frequency, and that the use of climate model simulations is beneficial mainly during high flow periods. It is also found that to maintain reliability for future climate periods, generation of ensemble inflow forecasts should use input time series that reflect potential sharp changes in precipitation amount.

Daily reservoir inflow forecasting using artificial neural networks with stopped training approach

In this paper, an early stopped training approach (STA) is introduced to train multi-layer feed-forward neural networks (FNN) for real-time reservoir inflow forecasting. The proposed method takes advantage of both Levenberg–Marquardt Backpropagation (LMBP) and cross-validation technique to avoid underfitting or overfitting on FNN training and enhances generalization performance. The methodology is assessed using multivariate hydrological time series from Chute-du-Diable hydrosystem in northern Quebec (Canada). The performance of the model is compared to benchmarks from a statistical model and an operational conceptual model. Since the ultimate goal concerns the real-time forecast accuracy, overall the results show that the proposed method is effective for improving prediction accuracy. Moreover it offers an alternative when dynamic adaptive forecasting is desired.