Large statistical learning models effectively forecast diverse chaotic systems

03/13/2023
by   William Gilpin, et al.
0

Chaos and unpredictability are traditionally synonymous, yet recent advances in statistical forecasting suggest that large machine learning models can derive unexpected insight from extended observation of complex systems. Here, we study the forecasting of chaos at scale, by performing a large-scale comparison of 24 representative state-of-the-art multivariate forecasting methods on a crowdsourced database of 135 distinct low-dimensional chaotic systems. We find that large, domain-agnostic time series forecasting methods based on artificial neural networks consistently exhibit strong forecasting performance, in some cases producing accurate predictions lasting for dozens of Lyapunov times. Best-in-class results for forecasting chaos are achieved by recently-introduced hierarchical neural basis function models, though even generic transformers and recurrent neural networks perform strongly. However, physics-inspired hybrid methods like neural ordinary equations and reservoir computers contain inductive biases conferring greater data efficiency and lower training times in data-limited settings. We observe consistent correlation across all methods despite their widely-varying architectures, as well as universal structure in how predictions decay over long time intervals. Our results suggest that a key advantage of modern forecasting methods stems not from their architectural details, but rather from their capacity to learn the large-scale structure of chaotic attractors.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2020

Forecasting with sktime: Designing sktime's New Forecasting API and Applying It to Replicate and Extend the M4 Study

We present a new open-source framework for forecasting in Python. Our fr...
research
05/30/2023

Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting

Existing relationships among time series can be exploited as inductive b...
research
01/30/2022

N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting

Recent progress in neural forecasting accelerated improvements in the pe...
research
04/21/2020

Neural forecasting: Introduction and literature overview

Neural network based forecasting methods have become ubiquitous in large...
research
10/07/2021

Multivariate Anomaly Detection based on Prediction Intervals Constructed using Deep Learning

It has been shown that deep learning models can under certain circumstan...
research
12/23/2020

Machine Learning Advances for Time Series Forecasting

In this paper we survey the most recent advances in supervised machine l...
research
11/27/2021

Deep Learning with Multiple Data Set: A Weighted Goal Programming Approach

Large-scale data analysis is growing at an exponential rate as data prol...

Please sign up or login with your details

Forgot password? Click here to reset