Forecasting Multivariate Urban Data via Decomposition and Spatio-Temporal Graph Analysis

TL;DR

This paper introduces DST, a graph neural network-based model that combines decomposition and spatio-temporal analysis to improve long-term multivariate urban data forecasting, demonstrating significant accuracy gains on real-world datasets.

Contribution

The paper proposes a novel DST model integrating graph attention, temporal convolution, and decomposition-based preprocessing for enhanced urban data forecasting.

Findings

Achieves 2.89% to 9.10% accuracy improvement over existing models.

Effectively captures complex spatiotemporal dependencies in urban datasets.

Demonstrates robustness across diverse datasets and forecast horizons.

Abstract

Long-term forecasting of multivariate urban data poses a significant challenge due to the complex spatiotemporal dependencies inherent in such datasets. This paper presents DST, a novel multivariate time-series forecasting model that integrates graph attention and temporal convolution within a Graph Neural Network (GNN) to effectively capture spatial and temporal dependencies, respectively. To enhance model performance, we apply a decomposition-based preprocessing step that isolates trend, seasonal, and residual components of the time series, enabling the learning of distinct graph structures for different time-series components. Extensive experiments on real-world urban datasets, including electricity demand, weather metrics, carbon intensity, and air pollution, demonstrate the effectiveness of DST across a range of forecast horizons, from several days to one month. Specifically, our approach achieves an average improvement of 2.89% to 9.10% in long-term forecasting accuracy over state-of-the-art time-series forecasting models.