Predicting Urban Flooding Due to Extreme Precipitation Using a Long Short-Term Memory Neural Network

Extreme precipitation events can lead to the exceedance of sewer capacity in urban areas. To mitigate effects flooding, a model is required that capable predicting flood timing and volumes based on forecasts while computational times are significantly low. In this study, long short-term memory (LSTM) neural network set up predict time series at 230 manhole locations present system. For first time, an LSTM applied such large system wide variety synthetic terms intensities patterns also captured training procedure. Even though was trained using events, it found predicts number manholes accurately for historic events. The able reduce forecasting order milliseconds, showing applicability as early flood-warning