Statistical prediction of extreme events from small datasets
This work addresses the challenge of statistical prediction of extreme events in turbulence, offering a method that works with limited data, though it appears incremental as it applies an existing network type to a specific domain.
The authors tackled the problem of predicting extreme events in turbulent flows using Echo State Networks trained on small, incomplete datasets, and found that the networks correctly predicted events and improved system statistics in nearly all cases.
We propose Echo State Networks (ESNs) to predict the statistics of extreme events in a turbulent flow. We train the ESNs on small datasets that lack information about the extreme events. We asses whether the networks are able to extrapolate from the small imperfect datasets and predict the heavy-tail statistics that describe the events. We find that the networks correctly predict the events and improve the statistics of the system with respect to the training data in almost all cases analysed. This opens up new possibilities for the statistical prediction of extreme events in turbulence.