Probabilistic forecasting improves time series predictions using Koopman autoencoders
Variational Augmented Invertible Koopman Autoencoder for probabilistic time series forecasting
Machine Learning
Summary
Making good long-term predictions from time series data often assumes the future can be guessed precisely, but uncertainty is common. This paper proposes a method that uses a special kind of neural network to not only predict future states but also estimate how confident those predictions are. By treating the hidden parts of the system as probabilities rather than fixed values, the method can better handle the unpredictability of real-world data. The authors also introduce ways to update their model’s predictions as new information comes in, improving accuracy over time.
What this means in practice
- •For weather prediction teams: Enhance long-term weather forecasts by providing probabilistic estimates that quantify uncertainties in atmospheric model predictions.
- •For energy grid operators: Improve planning by probabilistically forecasting time series of power demand and supply with uncertainty-aware latent models.
Authors
Anthony Frion, Lucas Drumetz, Guillaume Tochon, Mauro Dalla Mura, Ali Can Bekar, Abdeldjalil Aïssa El Bey
Abstract
Neural Koopman autoencoder models have been shown to successfully build a latent embedding with linear dynamics for arbitrary dynamical systems, enabling strong performance in long-term time series forecasting. However, these models usually work in a deterministic setting, which does not allow the quantification of the uncertainty of their predictions. Thus, we propose the new Variational Augmented Invertible Koopman AutoEncoder (VAIKAE), in which the latent embedding follows a Gaussian distribution instead of being deterministic. A key property of the VAIKAE architecture is that it leverages normalizing flow models, enabling the use of likelihood computations in the state space of dynamical systems for training a model. We further propose new strategies for uncertainty-aware latent data assimilation with a trained VAIKAE model. The effectiveness of our methods is demonstrated in a series of experiments on long-term time series forecasting benchmarks.