Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equations

TL;DR

This paper introduces LTSF-DNODE, a novel long-term time series forecasting model combining linear ODEs and data decomposition, outperforming existing methods on real-world datasets.

Contribution

The paper proposes a new LTSF model based on linear ODEs and data decomposition, addressing limitations of previous approaches and enhancing forecasting accuracy.

Findings

LTSF-DNODE outperforms baseline models on multiple datasets.

Regularization impacts in NODE framework are dataset-dependent.

Decomposition improves model interpretability and performance.

Abstract

Long-term time series forecasting (LTSF) is a challenging task that has been investigated in various domains such as finance investment, health care, traffic, and weather forecasting. In recent years, Linear-based LTSF models showed better performance, pointing out the problem of Transformer-based approaches causing temporal information loss. However, Linear-based approach has also limitations that the model is too simple to comprehensively exploit the characteristics of the dataset. To solve these limitations, we propose LTSF-DNODE, which applies a model based on linear ordinary differential equations (ODEs) and a time series decomposition method according to data statistical characteristics. We show that LTSF-DNODE outperforms the baselines on various real-world datasets. In addition, for each dataset, we explore the impacts of regularization in the neural ordinary differential equation (NODE) framework.