Implications of uncertainty in inflow forecasting on reservoir operation for irrigation

Abstract

Accurate and reliable forecasting of reservoir inflows is crucial for efficient reservoir operation to decide the quantity of the water to be released for various purposes. In this paper, an artificial neural network (ANN) model has been developed to forecast the weekly reservoir inflows along with its uncertainty, which was quantified through accounting the model's input and parameter uncertainties. Further, to investigate how the effect of uncertainty is translated in the process of decision making, an integrated simulation-optimization framework that consists of (i) inflow forecasting model; (ii) reservoir operation model; and (iii) crop simulation model was developed to assess the impacts of uncertainty in forecasted inflow on the irrigation scheduling and total crop yield from the irrigation system. A genetic algorithm was used to derive the optimal reservoir releases for irrigation and the area of irrigation. The proposed modeling framework has been demonstrated through a case example, Chittar river basin, India. The upper, lower, and mean of forecasted inflow from the ANN model were used to arrive at the prediction interval of the depth of irrigation, total crop yield, and area of irrigation. From the analysis, the ANN model forecast error of ± 69% to the mean inflow was estimated. However, the error to mean value of simulation for total irrigation, total yield, and area of irrigation was ± 13.3%, ± 6.5%, and ± 4.6%, respectively. The optimizer mainly contributed to the reduction in the errors (i.e., maximizing the total production with the optimal water releases from the reservoir irrespective of inflow to the reservoir). The results from this study suggested that the information on the uncertainty quantification helps in better understanding the reliability of the systems and for effective decision making.

A Novel Physics‐Aware Machine Learning‐Based Dynamic Error Correction Model for Improving Streamflow Forecast Accuracy

“…This is evident from the results of Sunkoshi river basin where the random approach performed well in capturing the low flows. Overall, the performance indices were observed to achieve a good match between the observed and forecast discharge and remain stable with the increase in lead time, contrary to most of the previous studies, where the forecast begins to deteriorate with the increase in lead time (Kasiviswanathan et al., 2013, 2016). The lack of deterioration in the forecast with the increase in lead time could be attributed to the dynamic error correction scheme, where the error gets updated at each time step with the availability of observed data.…”

“…These data‐driven algorithms intend to establish the empirical relationship between the set of predictor variables (e.g., precipitation, temperature, soil moisture, and discharge data) to estimate streamflow (Alexander et al., 2018; Curceac et al., 2020; Kurian et al., 2020; Senent‐Aparicio et al., 2019). Several machine learning algorithms including artificial neural network, support vector machine, adaptive neuro‐fuzzy inference systems, multilayer perceptron, etc (Curceac et al., 2020; Jimeno‐Sáez et al., 2018; Kasiviswanathan et al., 2013, 2016; Kurian et al., 2020; Mosavi et al., 2018) have been investigated. The key advantages of these algorithms are the non‐requirement of detailed catchment‐related information, the ability to solve complex nonlinear problems, and less computation time (Mosavi et al., 2018; Sudheer, 2005).…”

“…While being an active area of research, streamflow forecasting has been widely explored using different modeling approaches, such as process‐based and empirical models (Curceac et al., 2020; S. Han et al., 2019; Kasiviswanathan et al., 2016; Kurian et al., 2020; Ouédraogo et al., 2018; Parra et al., 2018). However, the reliability and accuracy of the streamflow forecasts generated from any form of modeling approach are highly dependent on lead time, and often that deteriorates as the lead time increases (Kasiviswanathan et al., 2013, 2016). Despite several attempts being made to improve the forecast accuracy of streamflow at longer lead times, several practical challenges still remain.…”

“…Recently, machine learning algorithms were widely investigated as an alternative to the process‐based models to improve the accuracy of streamflow simulation at longer lead times (Alexander et al., 2018; Demirel et al., 2009; Guo et al., 2011; Kasiviswanathan et al., 2016; Kisi, 2010; Latt & Wittenberg, 2014; Moeeni & Bonakdari, 2017; Nguyen & Chen, 2020; Rezaeianzadeh et al., 2014). These data‐driven algorithms intend to establish the empirical relationship between the set of predictor variables (e.g., precipitation, temperature, soil moisture, and discharge data) to estimate streamflow (Alexander et al., 2018; Curceac et al., 2020; Kurian et al., 2020; Senent‐Aparicio et al., 2019).…”

Prediction Interval Estimation Methods for Artificial Neural Network (ANN)-Based Modeling of the Hydro-Climatic Processes, a Review

“…It was mentioned that this method could overcome the problem of trapping in local minima. Kasiviswanathan, Sudheer, Soundharajan and Adeloye [67] applied upper lower bound and mean of forecasting to evaluate uncertainty in inflow modeling via the ANN for optimizing the reservoir operation and decision making. An integrated simulation-optimization was applied, which led to minimizing the error.…”