Improving long-term multivariate time series forecasting with a seasonal-trend decomposition-based 2-dimensional temporal convolution dense network
Authors:
Open Access
- 19 January 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-13
Abstract
Improving the accuracy of long-term multivariate time series forecasting is important for practical applications. Various Transformer-based solutions emerging for time series forecasting. Recently, some studies have verified that the most Transformer-based methods are outperformed by simple linear models in long-term multivariate time series forecasting. However, these methods have some limitations in exploring complex interdependencies among various subseries in multivariate time series. They also fall short in leveraging the temporal features of the data sequences effectively, such as seasonality and trends. In this study, we propose a novel seasonal-trend decomposition-based 2-dimensional temporal convolution dense network (STL-2DTCDN) to deal with these issues. We incorporate the seasonal-trend decomposition based on loess (STL) to explore the trend and seasonal features of the original data. Particularly, a 2-dimensional temporal convolution dense network (2DTCDN) is designed to capture complex interdependencies among various time series in multivariate time series. To evaluate our approach, we conduct experiments on six datasets. The results demonstrate that STL-2DTCDN outperforms existing methods in long-term multivariate time series forecasting.Keywords
Funding Information
- National Natural Science Foundation of China (61772321)
- Shandong Natural Science Foundation (ZR202011020044)
This publication has 37 references indexed in Scilit:
- Bidirectional LSTM-RNN-based hybrid deep learning frameworks for univariate time series classificationThe Journal of Supercomputing, 2021
- Research Progress of RNN Language Model2020
- A CNN–LSTM model for gold price time-series forecastingNeural Computing and Applications, 2020
- DSTP-RNN: A dual-stage two-phase attention-based recurrent neural network for long-term and multivariate time series predictionExpert Systems with Applications, 2020
- A hybrid method of exponential smoothing and recurrent neural networks for time series forecastingInternational Journal of Forecasting, 2020
- Improving DWT-RNN model via B-spline wavelet multiresolution to forecast a high-frequency time seriesExpert Systems with Applications, 2019
- Deep Residual Learning for Image Recognition2016
- Methodology for long-term prediction of time seriesNeurocomputing, 2007
- DIRECT MULTI‐STEP ESTIMATION AND FORECASTINGJournal of Economic Surveys, 2007
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989