Using Echo-State Networks to Reproduce Rare Events in Chaotic Systems
This work addresses the challenge of modeling rare events in chaotic ecological systems, but it is incremental as it applies an existing method to a specific domain.
The researchers tackled the problem of predicting rare events in chaotic systems by applying Echo-State Networks to the competitive Lotka-Volterra model, successfully reproducing histograms and tail behavior using the Generalized Extreme Value distribution.
We apply the Echo-State Networks to predict the time series and statistical properties of the competitive Lotka-Volterra model in the chaotic regime. In particular, we demonstrate that Echo-State Networks successfully learn the chaotic attractor of the competitive Lotka-Volterra model and reproduce histograms of dependent variables, including tails and rare events. We use the Generalized Extreme Value distribution to quantify the tail behavior.