Tree-based Learning for High-Fidelity Prediction of Chaos

arXiv:2403.13836v1 Announce Type: new
Abstract: Model-free forecasting of the temporal evolution of chaotic systems is crucial but challenging. Existing solutions require hyperparameter tuning, significantly hindering their wider adoption. In this work, we introduce a tree-based approach not requiring hyperparameter tuning: TreeDOX. It uses time delay overembedding as explicit short-term memory and Extra-Trees Regressors to perform feature reduction and forecasting. We demonstrate the state-of-the-art performance of TreeDOX using the Henon map, Lorenz and Kuramoto-Sivashinsky systems, and the real-world Southern Oscillation Index.

abstract adoption arxiv chaos cs.lg delay evolution extra fidelity forecasting free hyperparameter math.ds memory nlin.cd physics.data-an prediction solutions stat.ml systems temporal tree trees type work