Real time probabilistic inundation forecasts using a LSTM neural network

Optimizing flood predictions by integrating LSTM and physical-based models with mixed historical and simulated data

“…The emergence of machine learning (ML) and artificial intelligence (AI) algorithms offers new possibilities in flood forecasting, increasing availability of monitoring data [ 10 , 11 ]. For instance, a data-driven flood emulation approach using deep convolutional neural networks (CNNs) was proposed to speed up urban flood predictions [ 12 ].…”