ARTIFICIAL-INTELLIGENCE-BASED PREDICTION OF STORAGE CAPACITIES IN WATER RESERVOIRS

Predicting the storage capacities of water reservoirs is an important planning activity for effective conservation and water release practices. However, current state-of-the-art solutions are not generalizable to all water reservoirs. Accordingly, disclosed embodiments train a machine-learning model using a training dataset that comprises labeled feature vectors that each includes a time series of tuples and is labeled with the target value of at least one storage parameter for a water reservoir. Each tuple may comprise climate parameter(s), such as temperature, precipitation, and/or soil moisture, for the watershed of the water reservoir, and/or reservoir parameter(s), such as water level, water storage, storage capacity, water inflow, and/or water outflow of the water reservoir. The machine-learning model may be a recurrent neural network with long short-term memory, that is trained to predict the value of the storage parameter at least seven days into the future.