# From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction Source: [From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction]() Collection index: [llms.txt]() Data updated: 2026-06-10T05:15:22.625Z Authors: Shuhao Li, Weidong Yang, Yue Cui, Zizhuo Xu, Lipeng Ma, Fan Zhang, Xiaofang Zhou Published: 2026-06-08T12:07:13.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Duration-Based Fine-Grained Prediction on METR-LA](): Duration-Based Fine-Grained Prediction; METR-LA; MAE: 5.22. - [Duration-Based Fine-Grained Prediction on PeMS-Bay](): Duration-Based Fine-Grained Prediction; PEMS-BAY; MAE: 2.8. - [Duration-Based Fine-Grained Prediction on PeMS03](): Duration-Based Fine-Grained Prediction; PeMS03; MAE: 12.28. - [Duration-Based Fine-Grained Prediction on PeMS04](): Duration-Based Fine-Grained Prediction; PeMS04; MAE: 16.51. - [Duration-Based Fine-Grained Prediction on PeMS07](): Duration-Based Fine-Grained Prediction; PeMS07; MAE: 30.24. - [Duration-Based Fine-Grained Prediction on PeMS08](): Duration-Based Fine-Grained Prediction; PeMS08; MAE: 13.66. ## Original sources and implementation [Original paper]() [PDF]()