Machine Learning Assisted Reservoir Operation Model for Long‐Term Water Management Simulation

Abstract

This study explores strategies for long‐term reservoir simulations by combining generic rule‐based reservoir management model (RMM) and machine learning (ML) models for two major multipurpose reservoirs — Allatoona Lake and Lake Sidney Lanier in the southeastern United States. First, a standalone RMM is developed to simulate daily release and storage during Water Year 1981–2015. Next, using Long‐Short Term Memory (LSTM) as the ML technique, a standalone LSTM model is trained based on reservoir inflow and meteorological observations to simulate reservoir release and estimate reservoir storage through water balance calculation. Three hybrid modeling strategies are developed, one using RMM output as an additional LSTM input (H1), another using LSTM as the initial release estimate in RMM (H2), and the third combining the first two strategies (H3). The Nash–Sutcliffe efficiency (NSE) for release (NSE‐r), storage (NSE‐s), and their mean (NSE‐avg) are used for model evaluation. Overall, H1 improves NSE‐r to 0.65 and 0.54 for Allatoona and Lanier, respectively, compared to standalone RMM (0.44 and 0.21); however, its storage trajectory did not produce a physically feasible solution, similar to LSTM. H2 and especially H3 show that they can retain the best features from RMM and LSTM, with H3 NSE‐avg being 0.695 and 0.55 for Allatoona and Lanier outperforming RMM (0.615 and 0.29). The findings suggest a robust simulation capacity for large‐scale water management in future studies.

A Hierarchical Temporal Scale Framework for Data‐Driven Reservoir Release Modeling

“…The feasibility of data‐driven reservoir simulations can be further boosted through the use of hybrid strategies that combine rule‐based or conceptual operation schemes with machine learning techniques (Dong et al., 2023; Gangrade et al., 2022). By leveraging expert knowledge in the form of appropriate feature engineering (Yang et al., 2016, 2017), and by incorporating reservoir storage dynamics derived from a range of advanced sensing techniques (T. Chen et al., 2022; Y. Chen et al., 2022; Eilander et al., 2014; Sorkhabi et al., 2022; Van Den Hoek et al., 2019), it is possible to use DDMs to better reconstruct downstream flow in data‐sparse regions, using meteorological forcing and inflow generated by hydrological models.…”

“…Data‐driven models (DDMs) offer a promising alternative to derive reservoir operation rules from historical records of hydrologic and reservoir data (Aboutalebi et al., 2015; Hipni et al., 2013; Lin et al., 2006; Turner, Doering, & Voisin, 2020; Turner, Xu, & Voisin, 2020; C. C. Wei & Hsu, 2008; Yang et al., 2017; Zhang et al., 2018; Q. Zhao & Cai, 2020). Recent studies have demonstrated the capability of various machine learning techniques in capturing reservoir release decisions (T. Chen et al., 2022; Y. Chen et al., 2022; Coerver et al., 2018; Dong et al., 2023; Gangrade et al., 2022; Mateo et al., 2014; Yassin et al., 2019). The rationale is straightforward: if a manager determines the reservoir releases based on some principles (either empirical or optimal) depending on hydroclimatic variation, DDMs can recover the patterns of operation from the reservoir records and other hydroclimatic variables.…”

“…Zhao & Cai, 2020). Recent studies have demonstrated the capability of various machine learning techniques in capturing reservoir release decisions (T. Coerver et al, 2018;Dong et al, 2023;Gangrade et al, 2022;Mateo et al, 2014;Yassin et al, 2019). The rationale is straightforward: if a manager determines the reservoir releases based on some principles (either empirical or optimal) depending on hydroclimatic variation, DDMs can recover the patterns of operation from the reservoir records and other hydroclimatic variables.…”

Insights From Dayflow: A Historical Streamflow Reanalysis Dataset for the Conterminous United States

“…Gutenson et al (2020) demonstrated in their test study the potential of using D03 (Döll et al, 2009) and H06 (Hanasaki et al, 2006) reservoir routing models to improve RAPID performance. Incorporating these models or downstream reservoir release data (e.g., Tavakoly et al, 2017) and machine learning-based hybrid approaches (e.g., Gangrade et al, 2022) into the RAPID framework should be able to improve downstream streamflow predictions.…”

Modelling and forecasting daily streamflow with reservoir operationin the upper Chao Phraya River basin, Thailand

“…Despite the extensive applications of RNN, LSTM and GRU in real-time reservoir operation modelling, previous studies have primarily focused on historical reservoir outflow simulations. Some studies have implemented the aforementioned algorithms to simulate real-time outflows for small or single-purpose reservoirs (e.g., Zhang et al, 2019;He et al, 2021;Hong et al, 2021;Yang et al, 2021;Gangrade et al, 2022). Some other studies have investigated the algorithms' performance in simulating real-time outflows for large or multi-purpose reservoirs (e.g., Chen et al, 2018;Zhang et al, 2018a;Zheng et al, 2022).…”