A Spatial-Temporal Decomposition Based Deep Neural Network for Time Series Forecasting

TL;DR

This paper introduces a deep neural network framework that combines spatial-temporal decomposition, clustering, and advanced neural architectures to improve large-scale time series forecasting, especially in environmental and transportation contexts.

Contribution

It presents a novel neural network architecture that explicitly captures spatial, short-term, and long-term patterns through decomposition, clustering, and specialized convolutional and LSTM layers.

Findings

Outperforms baseline models in traffic flow prediction.

Effectively captures diverse spatial-temporal patterns.

Robust to missing data with autoencoder reconstruction.

Abstract

Spatial time series forecasting problems arise in a broad range of applications, such as environmental and transportation problems. These problems are challenging because of the existence of specific spatial, short-term and long-term patterns, and the curse of dimensionality. In this paper, we propose a deep neural network framework for large-scale spatial time series forecasting problems. We explicitly designed the neural network architecture for capturing various types of patterns. In preprocessing, a time series decomposition method is applied to separately feed short-term, long-term and spatial patterns into different components of a neural network. A fuzzy clustering method finds cluster of neighboring time series based on similarity of time series residuals; as they can be meaningful short-term patterns for spatial time series. In neural network architecture, each kernel of a multi-kernel convolution layer is applied to a cluster of time series to extract short-term features in neighboring areas. The output of convolution layer is concatenated by trends and followed by convolution-LSTM layer to capture long-term patterns in larger regional areas. To make a robust prediction when faced with missing data, an unsupervised pretrained denoising autoencoder reconstructs the output of the model in a fine-tuning step. The experimental results illustrate the model outperforms baseline and state of the art models in a traffic flow prediction dataset.