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

2025/05/28 by Amirhossein Sohrabbeig, Omid Ardakanian, Sohrabbeig, Amirhossein +3
Engineering · Social Sciences · Environmental Science · #Traffic Prediction and Management Techniques #Human Mobility and Location-Based Analysis #Air Quality Monitoring and Forecasting

paper · pdf · doi:10.48550/arxiv.2505.22474

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.

Citations

• CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
• Is Mamba Effective for Time Series Forecasting?
• Unified Training of Universal Time Series Forecasting Transformers
• A decoder-only foundation model for time-series forecasting
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• Are Transformers Effective for Time Series Forecasting?
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking
• MSTL: A Seasonal-Trend Decomposition Algorithm for Time Series with Multiple Seasonal Patterns
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Carbon-Aware Computing for Datacenters
• How Attentive are Graph Attention Networks?
• Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Graph Attention Networks
• Greedy function approximation: A gradient boosting machine.
• Forecasting Sales by Exponentially Weighted Moving Averages

Related

• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Temporal Attention Evolutional Graph Convolutional Network for Multivariate Time Series Forecasting
• It is all Connected: A New Graph Formulation for Spatio-Temporal Forecasting
• A lightweight Spatial-Temporal Graph Neural Network for Long-term Time Series Forecasting