Reservoir Inflow Prediction Research Articles

Fine-tuning inflow prediction models: integrating optimization algorithms and TRMM data for enhanced accuracy.

This research explores machine learning algorithms for reservoir inflow prediction, including long short-term memory (LSTM), random forest (RF), and metaheuristic-optimized models. The impact of feature engineering techniques such as discrete wavelet transform (DWT) and XGBoost feature selection is investigated. LSTM shows promise, with LSTM-XGBoost exhibiting strong generalization from 179.81 m3/s RMSE (root mean square error) in training to 49.42 m3/s in testing. The RF-XGBoost and models incorporating DWT, like LSTM-DWT and RF-DWT, also perform well, underscoring the significance of feature engineering. Comparisons illustrate enhancements with DWT: LSTM and RF reduce training and testing RMSE substantially when using DWT. Metaheuristic models like MLP-ABC and LSSVR-PSO benefit from DWT as well, with the LSSVR-PSO-DWT model demonstrating excellent predictive accuracy, showing 133.97 m3/s RMSE in training and 47.08 m3/s RMSE in testing. This model synergistically combines LSSVR, PSO, and DWT, emerging as the top performers by effectively capturing intricate reservoir inflow patterns.

Daily reservoir inflow prediction using stacking ensemble of machine learning algorithms

ABSTRACT The present study aims to evaluate the potentiality of Bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Networks (CNNs), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and Random Forest (RF) for predicting daily inflows to the Sri Ram Sagar Project (SRSP), Telangana, India. Inputs to the model are rainfall, evaporation, time lag inflows, and climate indices. Seven combinations (S1–S7) of inputs were made. Fifteen and a half years of data were considered, out of which 11 years were used for training. Hyperparameter tuning is performed with the Tree-Structured Parzen Estimator. The performance of the algorithms is assessed using Kling–Gupta efficiency (KGE). Results indicate that Bi-LSTM with combination S7 performed better than others, as evident from KGE values of 0.92 and 0.87 during the training and testing, respectively. Furthermore, the Stacking Ensemble Mechanism (SEM) has also been employed to ascertain its efficacy over other chosen algorithms, resulting in KGE values of 0.94 and 0.89 during training and testing. It has also been able to simulate peak inflow events satisfactorily. Thus, SEM is a better alternative for reservoir inflow predictions.

Reservoir Inflow Prediction: A Comparison between Semi Distributed Numerical and Artificial Neural Network Modelling

Reservoir Inflow Prediction: A Comparison between Semi Distributed Numerical and Artificial Neural Network Modelling

Improving the reservoir inflow prediction using TIGGE ensemble data and hydrological model for Dharoi Dam, India

Abstract Flooding occurs frequently compared to other natural disasters. Less developed countries are severely affected by floods. This research provides an integrated hydrometeorological system that forecasts hourly reservoir inflows using a full physically based rainfall–runoff and numerical weather models. This study develops a 5-day lead time reservoir inflow prediction using TIGGE ensemble datasets from ECMWF, UKMO, and NCEP for the Dharoi Dam in Gujarat, India. The ensemble data were post-processed using censored non-homogeneous Linear Regression and Bayesian model averaging approach. These post-processed data were used in a hydrological model to simulate hydrological processes and predict Dharoi Dam reservoir inflows. Results show that ECMWF with a BMA approach and HEC-HMS hydrological model can predict reservoir inflows in the Sabarmati River basin. The correlation result of an observed reservoir inflow is 0.91. This research can help regional water resource managers and government officials to plan and manage water resources.

Prediction of hourly inflow for reservoirs at mountain catchments using residual error data and multiple-ahead correction technique

Abstract This study coupled the ensemble learning method with residual error (RE) correction to propose a more accurate hydrologic model for the time-series prediction of the reservoir inflow. To enhance the prediction capability of the model in mountain catchments, three deep learning (DL) models, namely the encoder–decoder gated recurrent units (ED-GRU), encoder–decoder long short-term memory network (ED-LSTM), and combined convolutional neural network with LSTM (CNN-LSTM), were deployed to train reservoir inflow prediction model for the lead times of 1–24 h. The prediction outputs from three DL models were then incorporated into the categorical gradient boosting regression (CGBR) model to resolve the highly non-linear relationship between model inputs and outputs. In the final procedure, the RE correction method was implemented by using the outcomes of the CGBR model to construct the proposed hybrid model. The proposed model was applied to simulate the hourly inflow in the Shihmen and Feitsui Reservoirs. The proposed model achieved improved performance by an average proportion of 66.2% compared to the three DL models. It is demonstrated that the proposed model is accurate in predicting the reservoir peak and total inflows and also performs well for storm events with multi-peak hydrographs.

Two-step daily reservoir inflow prediction using ARIMA-machine learning and ensemble models

The reservoirs play a crucial role in the development of civilisation as they facilitate the storage of water for multiple purposes like hydroelectric power generation, flood control, irrigation, and drinking water etc. In order to effectively meet these multiple purposes, the knowledge of the inflow in the reservoir is essential. Apart from the historical data, future prediction of the inflows is also necessary specially in context of climate change. A two-step algorithm for the prediction of reservoir inflow to enable meticulous planning and execution of daily reservoir operation keeping the historical variation of inflow in account has been proposed. The developed algorithm takes into account the patterns in the historic inflow data using the time series analysis along with the variability in the climatic patterns using the different predictors in the machine learning model. The first step uses time series model, ARIMA method to forecast the monthly inflows, which are then used as the targets in the second step for the month-wise daily forecasting of the inflows using the two types of ensemble models, namely, averaging and boosting models in machine learning. The test results show that for both the monthly models and daily models the NRMSE and NMAE values were low for the monsoon periods compared to the non-monsoon periods. The averaging ensemble models were found to perform better than the boosting ensemble models for maximum number of months. The yearly results show an error of less than 5% between actual and predicted values for all the test cases, showing the precision in the developed algorithm. Further, the uncertainty analysis shows that the prediction done using the weighted average of the different inflow scenarios performs better than the prediction against the single inflow scenario.

Short-range reservoir inflow forecasting using hydrological and large-scale atmospheric circulation information

Short and long range reservoir inflow forecast is essential for efficient real time operational planning, scheduling of hydroelectric power system and management of water resources. Large-scale climate phenomenon indices have a strong influence on hydrological processes under complex weather conditions, and it should be considered to forecast reservoir inflow for efficient dam operation strategies. This study aims to explore the relevance of large-scale climate phenomenon indices in improving the reservoir inflow prediction at short-term time scales. This paper presents a simple and effective framework to combine various data-driven machine learning (ML) algorithms for short-range reservoir inflow forecasting. Random Forest (RF), Gradient Boosting Regressor (GBR), K-Nearest Neighbors Regressor (KNN), and Long Short-Term Memory (LSTM) were employed for predicting daily reservoir inflows considering various climate phenomenon indices (e.g., Arctic Oscillation, North Atlantic Oscillation, and Southern Oscillation Index) and hydroclimatic variables (precipitation), accounting for time-lag effects. After training the individual ML algorithm, a framework was developed to create an ensemble model using a robust weighted voting ensemble method to quantify forecasting uncertainty and to improve the model performance by combining the inflow results of the single ML model and the highest vote is chosen based on the weights assigned to the single ML model. The developed framework was examined in two distinct reservoirs located in India and California, USA. The ensemble model consistently outperformed the standalone RF, GBR, KNN, and LSTM in predicting high (flood control and monsoon seasons) and low flows (runoff and non-monsoon seasons) of both study reservoirs. The demonstrated short-term reservoir forecasting model allows reservoir operators to adapt and add regional hydrological and large-scale climate indices in real-time decision-making. The presented framework can be applied for any reservoir inflow forecasting.

Response Surface Models Using the Wavelet Technique for Reservoir Inflow Prediction

Reliable streamflow prediction is vital to improving river operations, flood avoidance, water supply, and water resources management. Recently, response surface models have been launched in reservoir inflow prediction due to their potential to model composite nonlinear behaviour. Authors develop a hybrid model, wavelet quadratic response surface for reservoir inflow prediction in Chenab river basin, Pakistan. Wavelet transform has extensive applications in the field biomedical, engineering, and hydrology. Discrete wavelet transform technique discloses the structure of nonstationary signals. A proper and careful selection of mother wavelet ensure the best performance of wavelet transform. The choice of a suitable wavelet function participates in implementing the wavelet function used in response surface based models for reliable prediction. The performance of the proposed model is checked on different performance indices for model evaluation. The new developed model, wavelet quadratic response surface, depicts excellent results than other studied models.

Improving reservoir inflow prediction via rolling window and deep learning-based multi-model approach: case study from Ermenek Dam, Turkey

Improving reservoir inflow prediction via rolling window and deep learning-based multi-model approach: case study from Ermenek Dam, Turkey

Reservoir Inflow Prediction by Employing Response Surface-Based Models Conjunction with Wavelet and Bootstrap Techniques

Reservoir inflow prediction is a vital subject in the field of hydrology because it determines the flood event. The negative impact of the floods could be minimized greatly if the flood frequency is predicted accurately in advance. In the present study, a novel hybrid model, bootstrap quadratic response surface is developed to test daily streamflow prediction. The developed bootstrap quadratic response surface model is compared with multiple linear regression model, first-order response surface model, quadratic response surface model, wavelet first-order response surface model, wavelet quadratic response surface model, and bootstrap first-order response surface model. Time series data of monsoon season (1 July to 30 September) for the year 2010 of the Chenab river basin are analyzed. The studied models are tested by using performance indices: Nash–Sutcliffe coefficient of efficiency, mean absolute error, persistence index, and root mean square error. Results reveal that the proposed model, i.e., bootstrap quadratic response surface shows good performance and produces optimum results for daily reservoir inflow prediction than other models used in the study.

Monthly reservoir inflow prediction based on artificial neural network over the Saguling catchment area

In line with the objectives of the Impact-Based Forecast, hydrological predictions are used to support water resources management, mitigation of natural disasters, and climate variability impacts. The Artificial Neural Network algorithm was applied to build the prediction model for the Saguling Reservoir monthly inflow by utilizing observation data; the monthly rainfall (P) and inflow (Q) as the predictors in different lag time; t (recent), t-1 (previous month), and t-11 (11 months ago). The predictors are simulated in three variations of hidden layer numbers (2, 6, and 10). The best model under the normal period is model nine with RMSE 31.23 and R 0.88. This model is also the best model under La Nina's condition with RMSE 30.01 and R 0.83. For the El Nino period. We found that model five is the best model with the highest accuracy at the level of generalization in both the training process and predict extreme conditions at the validation stage. Overall, this model has a good performance and high potential usage from a practical point of view and costs but needs further simulation to make it more reliable and robust in any climate conditions.

Real-time optimization of a large-scale reservoir operation in Thailand using adaptive inflow prediction with medium-range ensemble precipitation forecasts

Study regionThe Sirikit Dam in the Nan River Basin is located on a main tributary of the Chao Phraya River in Thailand. Study focusThis study investigates forecasting river flows and real-time optimization of dam release using a distributed hydrological model with ensemble weather forecasting for reservoir operations which provide hydropower and irrigation facilities in Thailand during a case study of the 2019 drought event. Medium-range ensemble precipitation forecasts were employed using a hydrological model to predict the real-time reservoir inflow. Real-time optimization of the water release strategy determined a week in advance with an effective initial condition for hydropower generation and irrigation was conducted with different scenarios using dynamic programming considering inflow predictions. New hydrological insights for the regionThe medium-range ensemble precipitation forecast conducted by the European Centre for Medium Range Weather Forecasts was used to quantify precipitation for the study basin. The ensemble precipitation forecast with the hydrological model was employed for inflow prediction of the study basin which was located in a tropical climate with a distinct wet and dry season. The initial conditions of the hydrological model largely influenced the real-time inflow forecast. To determine the initial conditions of the model, the empirical data assimilation considering a drainage area factor was utilized and observed precipitation data were used for model input forcing data during the initial analysis period. This method improved the reservoir inflow prediction and real-time reservoir optimization using dynamic programming with considering ensemble forecasts provided more efficient operating decisions than employing historical data. The resulting information will be useful for water resource management, which may be adapted to other basins in the study region.

Quantifying the Uncertainties in Data-Driven Models for Reservoir Inflow Prediction

Reservoir inflow prediction is subject to high uncertainties in data-driven modelling. In this study, a decomposition scheme is proposed to evaluate the individual and combined contributions of uncertainties from input sets and data-driven models to the total predictive uncertainty. Six variables (i.e., inflow (Q), precipitation (P), relative humidity (H), minimum temperature (Tmin), maximum temperature (Tmax) and precipitation forecast (F)), and three data-driven models (i.e., artificial neural network (ANN), support vector machine (SVM), and adaptive neuro fuzzy inference systems (ANFIS)) are used to produce an ensemble of 10-day inflow forecast for Huanren reservoir in China, and the analysis of variance (ANOVA) method is employed to decompose the uncertainty. The ensemble forecast results show that when the three variables, i.e., Q, P and F, are used only, the predictive accuracy of the data-driven models is very high and the addition of the other three variables, i. e., H, Tmin and Tmax, can slightly improve the predictive accuracy. The decomposition results indicate that the input set is the dominant source of uncertainty, the contribution of the data-driven model is limited and has a strong seasonal variation: larger in winter and summer, smaller in spring and autumn. Most importantly, the interactive contribution of the input set and the data-driven model to the total predictive uncertainty is very high and is more significant than the individual contribution from the model itself, implying that the combined effects of the input set and the data-driven model should be carefully considered in the modelling process.

Reservoir inflow prediction using a hybrid model based on deep learning

Reservoir inflow prediction plays a significant role in the field of hydrological prediction. Accurate and reliable prediction of reservoir inflow is the key to flood control decision. In this paper, we combine the deep belief network (DBN) with the Long Short-Term Memory (LSTM) to present a hybrid model based on deep learning (HDL) for reservoir inflow prediction. We take a full consideration of the basin flow and rainfall factors, which significantly affect the inflow flow. According to the rainfall data, we divide the corresponding flow data into two cases: rain and no rain. The proposed approach consists of three parts: we apply the DBN to learn the characteristics of the flow data and get predicted values of the reservoir inflow in case of rain and in case of no rain respectively. Then, we use the basin rainfall data and adopt the LSTM to fit the differential between the predicted inflow value generated by DBN in case of rain and the real inflow value, and get the predicted differential. Finally, the outputs of these three parts are added to obtain the final predicted result. Experiments are evaluated by the historical flow and rainfall data of a reservoir in China, and the results have proved that our method is effective and has higher prediction accuracy.

Reservoir Inflow Prediction by Ensembling Wavelet and Bootstrap Techniques to Multiple Linear Regression Model

In this study, a new hybrid model, bootstrap multiple linear regression (BMLR) is suggested to investigate the potential of bootstrap resampling technique for daily reservoir inflow prediction. The proposed model compares with three other models: Multiple linear regression (MLR), wavelet multiple linear regression (WMLR) and wavelet bootstrap multiple linear regression (WBMLR). River stage data of monsoon season (1st July 2010 to 30 September 2010) from three gauging stations of Chenab river basin are used. In wavelet transformation, input vectors are decomposed using discrete wavelet transformation (DWT) into discrete wavelet components (DWCs). Then suitable DWCs are used to provide input to MLR model to develop WMLR model. Bootstrap technique coupled with MLR model to build up BMLR model. While WBMLR model is the conjunction of suitable DWCs and bootstrap technique to MLR model. Performance indices namely root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe coefficient of efficiency (NSC), and persistence index (CP) are used in study to evaluate the performance of model. Results showed that hybrid model BMLR produce significantly better results on performance indices than other models MLR, WMLR and WBMLR.

An analysis of effects of seasonal weather forecasting on dam reservoir inflow prediction

An analysis of effects of seasonal weather forecasting on dam reservoir inflow prediction

A fusion-based neural network methodology for monthly reservoir inflow prediction using MODIS products

ABSTRACTA model fusion approach was developed based on five artificial neural networks (ANNs) and MODIS products. Static and dynamic ANNs – the multi-layer perceptron (MLP) with one and two hidden layers, general regression neural network (GRNN), radial basis function (RBF) and nonlinear autoregressive network with exogenous inputs (NARX) – were used to predict the monthly reservoir inflow in Mollasadra Dam, Fars Province, Iran. Leaf area index and snow cover from MODIS, and rainfall and runoff data were used to identify eight different combinations to train the models. Statistical error indices and the Borda count method were used to verify and rank the identified combinations. The best results for individual ANNs were combined with MODIS products in a fusion model. The results show that using MODIS products increased the accuracy of predictions, with the MLP with two hidden layers giving the best performance. Also, the fusion model was found to be superior to the best individual ANNs.

Performance evaluation of ANNs and an M5 model tree in Sattarkhan Reservoir inflow prediction

In this research, done from 2002 to 2012 at the Sattarkhan Reservoir in Iran, different combinations of values of a time series related to precipitation, evaporation, and discharge at upstream stations were used as the inputs and the next-day discharge was used as the output, in order to evaluate an artificial neural network (ANN), Support Vector Regression (SVR), Wavelet Neural Networks (WANN) and M5 model tree. Twelve scenarios consisting of input variables with different combinations of flow and climatological data by different lag times were created to study the role played by input variables in the accuracy of the model. Results of the various scenarios showed that when the inputs were consisted of the amount of temperature, precipitation and previous discharges (scenario 2), the next-day discharge could be estimated with higher accuracy by the WANN model with a RMSE value of 0.31 m3/s in comparison with the SVR model with RMSE value of 0.873 m3/s, M5 model tree with RMSE value of 0.880 m3/s and ANN model with RMSE value of 0.896 m3/s. Conclusively, the obtained results revealed that the wavelet transformation creates significant effect for increasing the prediction accuracies of the ANN model.

Reservoir Inflow Prediction under GCM Scenario Downscaled by Wavelet Transform and Support Vector Machine Hybrid Models

Climate change has significant impacts on changing precipitation patterns causing the variation of the reservoir inflow. Nowadays, Indonesian hydrologist performs reservoir inflow prediction according to the technical guideline of Pd-T-25-2004-A. This technical guideline does not consider the climate variables directly, resulting in significant deviation to the observation results. This research intends to predict the reservoir inflow using the statistical downscaling (SD) of General Circulation Model (GCM) outputs. The GCM outputs are obtained from the National Center for Environmental Prediction/National Center for Atmospheric Research Reanalysis (NCEP/NCAR Reanalysis). A new proposed hybrid SD model named Wavelet Support Vector Machine (WSVM) was utilized. It is a combination of the Multiscale Principal Components Analysis (MSPCA) and nonlinear Support Vector Machine regression. The model was validated at Sutami Reservoir, Indonesia. Training and testing were carried out using data of 1991–2008 and 2008–2012, respectively. The results showed that MSPCA produced better extracting data than PCA. The WSVM generated better reservoir inflow prediction than the one of technical guideline. Moreover, this research also applied WSVM for future reservoir inflow prediction based on GCM ECHAM5 and scenario SRES A1B.

Including spatial distribution in a data-driven rainfall-runoff model to improve reservoir inflow forecasting in Taiwan

Multi-step ahead inflow forecasting has a critical role to play in reservoir operation and management in Taiwan during typhoons as statutory legislation requires a minimum of 3-hours warning to be issued before any reservoir releases are made. However, the complex spatial and temporal heterogeneity of typhoon rainfall, coupled with a remote and mountainous physiographic context makes the development of real-time rainfall-runoff models that can accurately predict reservoir inflow several hours ahead of time challenging. Consequently, there is an urgent, operational requirement for models that can enhance reservoir inflow prediction at forecast horizons of more than 3-hours. In this paper we develop a novel semi-distributed, data-driven, rainfall-runoff model for the Shihmen catchment, north Taiwan. A suite of Adaptive Network-based Fuzzy Inference System solutions is created using various combinations of auto-regressive, spatially-lumped radar and point-based rain gauge predictors. Different levels of spatially-aggregated radar-derived rainfall data are used to generate 4, 8 and 12 sub-catchment input drivers. In general, the semi-distributed radar rainfall models outperform their less complex counterparts in predictions of reservoir inflow at lead-times greater than 3-hours. Performance is found to be optimal when spatial aggregation is restricted to 4 sub-catchments, with up to 30% improvements in the performance over lumped and point-based models being evident at 5-hour lead times. The potential benefits of applying semi-distributed, data-driven models in reservoir inflow modelling specifically, and hydrological modelling more generally, is thus demonstrated.