Nat. Hazards Earth Syst. Sci., 22, 3859–3874, 2022
Reservoirs play a key role in many human soci- eties due to their capability to manage water resources. In addition to their role in water supply and hydropower pro- duction, their ability to retain water and control the flow makes them a valuable asset for flood mitigation. This is a key function, since extreme events have increased in the last few decades as a result of climate change, and therefore, the application of mechanisms capable of mitigating flood dam- age will be key in the coming decades. Having a good esti- mation of the outflow of a reservoir can be an advantage for water management or early warning systems. When histori- cal data are available, data-driven models have been proven a useful tool for different hydrological applications. In this sense, this study analyzes the efficiency of different machine learning techniques to predict reservoir outflow, namely mul- tivariate linear regression (MLR) and three artificial neu- ral networks: multilayer perceptron (MLP), nonlinear au- toregressive exogenous (NARX) and long short-term mem- ory (LSTM). These techniques were applied to forecast the outflow of eight water reservoirs of different characteristics located in the Miño River (northwest of Spain). In general, the results obtained showed that the proposed models pro- vided a good estimation of the outflow of the reservoirs, im- proving the results obtained with classical approaches such as to consider reservoir outflow equal to that of the previous day. Among the different machine learning techniques anaAbstract. Reservoirs play a key role in many human soci- eties due to their capability to manage water resources. In addition to their role in water supply and hydropower pro- duction, their ability to retain water and control the flow makes them a valuable asset for flood mitigation. This is a key function, since extreme events have increased in the last few decades as a result of climate change, and therefore, the application of mechanisms capable of mitigating flood dam- age will be key in the coming decades. Having a good esti- mation of the outflow of a reservoir can be an advantage for water management or early warning systems. When histori- cal data are available, data-driven models have been proven a useful tool for different hydrological applications. In this sense, this study analyzes the efficiency of different machine learning techniques to predict reservoir outflow, namely mul- tivariate linear regression (MLR) and three artificial neu- ral networks: multilayer perceptron (MLP), nonlinear au- toregressive exogenous (NARX) and long short-term mem- ory (LSTM). These techniques were applied to forecast the outflow of eight water reservoirs of different characteristics located in the Miño River (northwest of Spain). In general, the results obtained showed that the proposed models pro- vided a good estimation of the outflow of the reservoirs, im- proving the results obtained with classical approaches such as to consider reservoir outflow equal to that of the previous day. Among the different machine learning techniques analyzed, the NARX approach was the option that provided the best estimations on average.
