analiza aiqbench
This research introduces STRP, a framework that enables accurate fine-grained traffic predictions by learning from coarse-grained historical data, effectively bypassing the storage and computational costs of collecting high-frequency observations. By integrating tree convolution for spatial modeling with inverse dilated convolution for temporal extrapolation, the method addresses a critical bottleneck in spatio-temporal data systems where downstream applications often require higher temporal resolution than is economically feasible to store. The approach offers a practical solution for optimizing resource usage in traffic management systems without sacrificing prediction accuracy or interpretability.
From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction
arXiv:2606.09392v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI)
arXiv:2606.09392 [cs.AI]
(or arXiv:2606.09392v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.09392 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 271 cuvinte
Subiecte conexe
TRACE: Spatiotemporal Contact Memory Graph Network Simulator for Granular Dynamics
arXiv · 4 sept. 2026
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
arXiv · 17 iun. 2026
Local Intrinsic Dimensionality of Ground Motion Data for Early Detection of Catastrophic Slope Failure
arXiv · 5 iun. 2026
Transfer Learning for Socioeconomic Estimation in Forced-Displacement Settings
arXiv · 16 sept. 2026