A spatio-temporal decomposition based deep neural network for time series forecasting

• Published in: Applied soft computing 2020-02, Vol.87, p.105963, Article 105963
• Main Authors: Asadi, Reza, Regan, Amelia C.
• Format: Article
• Language: English
• Subjects: Deep learning; Spatio-temporal data; Time series forecasting; Traffic flow prediction
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2019.105963

Spatio-temporal problems arise in a broad range of applications, such as climate science and transportation systems. These problems are challenging because of unique spatial, short-term and long-term patterns, as well as the curse of dimensionality. In this paper, we propose a deep learning framework for spatio-temporal forecasting problems. We explicitly design the neural network architecture for capturing various types of spatial and temporal patterns, and the model is robust to missing data. In a preprocessing step, a time series decomposition method is applied to separately feed short-term, long-term and spatial patterns into different components of the neural network. A fuzzy clustering method finds clusters of neighboring time series residuals, as these contain short-term spatial patterns. The first component of the neural network consists of multi-kernel convolutional layers which are designed to extract short-term features from clusters of time series data. Each convolutional kernel receives a single cluster of input time series. The output of convolutional layers is concatenated by trends and followed by convolutional-LSTM layers to capture long-term spatial patterns. To have a robust forecasting model when faced with missing data, a pretrained denoising autoencoder reconstructs the model’s output in a fine-tuning step. In experimental results, we evaluate the performance of the proposed model for the traffic flow prediction. The results show that the proposed model outperforms baseline and state-of-the-art neural network models. •A deep neural network is proposed for the short-term spatio-temporal forecasting.•A clustering method and a multi-kernel convolutional layer capture spatial patterns.•Time series decomposition helps the model to better capture temporal patterns.•The model generates more robust outcomes when faced with missing data.•The performance of the model is evaluated for the traffic flow prediction.