From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction

2026-06-08

AI Summary

This study addresses the challenge that coarse-grained traffic data often lack the resolution required for fine-grained prediction tasks, while simultaneously facing a trade-off between storage cost and prediction accuracy. To this end, the paper formally defines the “coarse-to-fine” traffic forecasting problem and introduces the Spatio-Temporal Refinement Predictor (STRP). STRP integrates tree-based convolutions to model spatial dependencies, employs inverse dilated convolutions to progressively recover temporal details, and incorporates a granularity-aware mechanism to fuse multi-scale information, thereby supporting both window-based and continuous forecasting scenarios. Extensive experiments on six benchmark datasets demonstrate that STRP significantly outperforms existing methods in both prediction accuracy and computational efficiency.

Abstract

Efficient acquisition, storage, and utilization of traffic data are critical challenges in spatio-temporal data management. Most traffic data systems collect and store observations at fixed, coarse-grained temporal intervals to reduce storage and computation costs. However, such coarse-grained data severely limits downstream applications that require predictions at a finer temporal granularity. Collecting and maintaining fine-grained traffic data across all locations and time periods would impose a substantial burden on database storage and preprocessing pipelines. To address this temporal granularity mismatch, we formulate a novel problem: predicting fine-grained future traffic using coarse-grained sampled data. We propose the Spatial-Temporal Refinement Predictor (STRP), a granularity-aware framework for spatio-temporal data systems. STRP integrates two components: Tree Convolution for efficient and interpretable spatial dependency modeling, and Inverse Dilated Convolution for progressive temporal extrapolation. STRP supports two practical prediction settings: window-based and duration-based, to handle different forms of granularity mismatch. Experiments on six benchmark datasets show that STRP significantly outperforms state-of-the-art baselines in both accuracy and efficiency. Our work offers a practical and interpretable approach to managing granularity mismatches in spatio-temporal traffic data systems.

Problem

• temporal granularity
• spatio-temporal data
• traffic prediction
• granularity mismatch
• fine-grained prediction

Innovation

• temporal granularity
• spatio-temporal prediction
• tree convolution
• inverse dilated convolution
• traffic forecasting