Deep Probabilistic Koopman: Long-term time-series forecasting under periodic uncertainties

06/10/2021
by   Alex Mallen, et al.
19

Probabilistic forecasting of complex phenomena is paramount to various scientific disciplines and applications. Despite the generality and importance of the problem, general mathematical techniques that allow for stable long-term forecasts with calibrated uncertainty measures are lacking. For most time series models, the difficulty of obtaining accurate probabilistic future time step predictions increases with the prediction horizon. In this paper, we introduce a surprisingly simple approach that characterizes time-varying distributions and enables reasonably accurate predictions thousands of timesteps into the future. This technique, which we call Deep Probabilistic Koopman (DPK), is based on recent advances in linear Koopman operator theory, and does not require time stepping for future time predictions. Koopman models also tend to have a small parameter footprint (often less than 10,000 parameters). We demonstrate the long-term forecasting performance of these models on a diversity of domains, including electricity demand forecasting, atmospheric chemistry, and neuroscience. For electricity demand modeling, our domain-agnostic technique outperforms all of 177 domain-specific competitors in the most recent Global Energy Forecasting Competition.

READ FULL TEXT

page 6

page 11

research
04/11/2023

Electricity Demand Forecasting with Hybrid Statistical and Machine Learning Algorithms: Case Study of Ukraine

This article presents a novel hybrid approach using statistics and machi...
research
02/21/2020

A copula-based time series model for global horizontal irradiation

The increasing importance of solar power for electricity generation lead...
research
07/14/2021

M5 Competition Uncertainty: Overdispersion, distributional forecasting, GAMLSS and beyond

The M5 competition uncertainty track aims for probabilistic forecasting ...
research
01/08/2022

Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Electricity Demand Forecasting

Some real-world decision-making problems require making probabilistic fo...
research
05/09/2020

Probabilistic Multi-Step-Ahead Short-Term Water Demand Forecasting with Lasso

Water demand is a highly important variable for operational control and ...
research
09/09/2021

Sigmoids behaving badly: why they usually cannot predict the future as well as they seem to promise

Sigmoids (AKA s-curves or logistic curves) are commonly used in a divers...
research
09/09/2019

Real Time Trajectory Prediction Using Deep Conditional Generative Models

Data driven methods for time series forecasting that quantify uncertaint...

Please sign up or login with your details

Forgot password? Click here to reset