DESTformer: A Transformer Based on Explicit Seasonal–Trend Decomposition for Long-Term Series Forecasting
Open Access
- 20 September 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10505
Abstract
Seasonal–trend-decomposed transformer has empowered long-term time series forecasting via capturing global temporal dependencies (e.g., period-based dependencies) in disentangled temporal patterns. However, existing methods design various auto-correlation or attention mechanisms in the seasonal view while ignoring the fine-grained temporal patterns in the trend view in the series decomposition component, which causes an information utilization bottleneck. To this end, a Transformer-based seasonal–trend decomposition methodology with a multi-scale attention mechanism in the trend view and a multi-view attention mechanism in the seasonal view is proposed, called DESTformer. Specifically, rather than utilizing the moving average operation in obtaining trend data, a frequency domain transform is first applied to extract seasonal (high-frequency) and trend (low-frequency) components, explicitly capturing different temporal patterns in both seasonal and trend views. For the trend component, a multi-scale attention mechanism is designed to capture fine-grained sub-trends under different receptive fields. For the seasonal component, instead of the frequency-only attention mechanism, a multi-view frequency domain (i.e., frequency, amplitude, and phase) attention mechanism is designed to enhance the ability to capture the complex periodic changes. Extensive experiments are conducted on six benchmark datasets covering five practical applications: energy, transportation, economics, weather, and disease. Compared to the state-of-the-art FEDformer, our model shows reduced MSE and MAE by averages of 6.5% and 3.7%, respectively. Such experimental results verify the effectiveness of our method and point out a new way towards handling trends and seasonal patterns in long-term time series forecasting tasks.Keywords
Funding Information
- National Defense Basic Scientific Research Program of China (JCKY2020212B003)
This publication has 23 references indexed in Scilit:
- Employing long short-term memory and Facebook prophet model in air temperature forecastingCommunications in Statistics - Simulation and Computation, 2021
- A spatio-temporal decomposition based deep neural network for time series forecastingApplied Soft Computing, 2020
- Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks2018
- Forecasting at ScaleThe American Statistician, 2018
- Stock Price Prediction Using the ARIMA Model2014
- Facilitating Joint Chaos and Fractal Analysis of Biosignals through Nonlinear Adaptive FilteringPLOS ONE, 2011
- Denoising Nonlinear Time Series by Adaptive Filtering and Wavelet Shrinkage: A ComparisonIEEE Signal Processing Letters, 2009
- Automatic Time Series Forecasting: TheforecastPackage forR2008
- Some Recent Advances in Forecasting and ControlJournal of the Royal Statistical Society Series C: Applied Statistics, 1968
- Generalized harmonic analysisActa Mathematica, 1930