Temporal Spatial Decomposition and Fusion Network for Time Series Forecasting*

Feature engineering is required to obtain better results for time series forecasting, and decomposition is a crucial one. One decomposition approach often cannot be used for numerous forecasting tasks since the standard time series decomposition lacks flexibility and robustness. Traditional feature selection relies heavily on preexisting domain knowledge, has no generic methodology, and requires a lot of labor. However, most time series prediction models based on deep learning typically suffer from interpretability issues, so the “black box” results lead to a lack of confidence. Dealing with the above matters forms the motivation of the thesis. In the paper, we propose TSDFNet as a neural network with a self-decomposition mechanism and an attentive feature fusion mechanism. It abandons feature engineering as a preprocessing convention and creatively integrates it as an internal module with the deep model. The self-decomposition mechanism empowers TSDFNet with extensible and adaptive de-composition capabilities for any time series and is more effective in predicting problems than traditional decomposition methods. Users can choose their own basis functions to decompose the sequence into temporal and generalized spatial dimensions. The attentive feature fusion mechanism has the ability to capture the importance of external variables and the causality with target variables. It can automatically suppress the unimportant features while enhancing the effective ones so that users do not have to struggle with feature selection. The basic idea of TDFNNet is straightforward. It integrates feature decomposition, feature selection, and prediction into one model. Moreover, TSDFNet can quickly look into the “black box” of the deep neural network by feature visualization and analyzing the prediction results. We demonstrate performance improvements over existing widely accepted models on more than a dozen datasets, and three experiments showcase the interpretability of TSDFNet.