Neural Networks for Lorenz Map Prediction: A Trip Through Time
This work addresses forecasting challenges in chaotic systems like the Lorenz model, but it is incremental as it revisits and updates existing methods without introducing major innovations.
The paper tackles one-step-ahead forecasting of Lorenz dynamical system trajectories, showing that multitask learning improves prediction of the challenging z trajectory, and reflects on neural network evolution for this canonical task.
In this article the Lorenz dynamical system is revived and revisited and the current state of the art results for one step ahead forecasting for the Lorenz trajectories are published. Multitask learning is shown to help learning the hard to learn z trajectory. The article is a reflection upon the evolution of neural networks with respect to the prediction performance on this canonical task.