Reservoir Water Level Forecasting using Deep Learning

Reservoirs play a vital role in water resource management and provide essential ecosystem services. The study focuses on extracting the water extent of Maithon reservoir, Jharkhand, India, from 2017 to 2023 by delineating the boundaries between the water and non-water class extracted from Sentinel-1 data. The scenes were processed using Google Earth Engine to obtain water extent using the Otsu method. This research extends the application of the extracted water extent values, precipitation data from CHIRPS, and weekly historical water level data of the reservoir obtained from the Central Water Commission to monthly forecasts of the water level using the Long Short-Term Memory (LSTM) model. The forecasts were obtained with a mean absolute error of around 80 cm with test data. The study provides initial results and is under further modification, where the improved estimation shall be integrated into flood early warning systems and help to provide actionable insights to stakeholders and decision-makers to mitigate risks and optimize water usage.