JAVELLE , Pierre

To date, long short-term memory (LSTM) networks have been successfully applied to a key problem in hydrology: the prediction of runoff. Unlike traditional conceptual models, LSTM models are built on concepts that avoid the need for our knowledge of hydrology to be formally encoded into the model. The question, then, is how we can still make use...

In the field of deep learning, LSTM lies in the category of recurrent neural network architectures. The distinctive capability of LSTM is learning non-linear long-term dependency structures. This makes LSTM a promising candidate for prediction tasks in non-linear time dependent systems such as prediction of runoff in a catchment. This work...

In the field of Deep Learning, the long short-term memory (LSTM) networks lie in the category of recurrent neural network (RNN) architectures. The distinctive capability of the LSTM is learning non linear long term dependency structures. This makes the LSTM a good candidate for prediction tasks in non linear time dependent systems such as...

International audience

On the 3rd of October 2015, an outstanding hydrometeorological event hit the Mediterranean coast in the Alpes-Maritimes region in south-eastern France. Despite this rainstorm event was very short in time (approximatively 2 hours of intense rainfall), it caused a large rainfall accumulation reaching up to 180 mm. Intense flash floods were...

The 15th of June 2010 an exceptional flash flood occurred in the Var region in southeastern France. This flood caused 25?casualties and catastrophic damages in the area of Draguignan. After this event several researchers and engineers teams conducted field surveys in order to gather information on the dynamics of the flood: peak discharge...