CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection

Existing traffic flow modeling approaches typically rely on real-time observations, such as road sensors or GPS trajectories, which constrain their research scope and application scenarios. This study proposes a novel cross-spatiotemporal graph-based network method to rapidly reconstruct traffic flo...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Zhang, Mei-Po Kwan, Jiannan Cai, Jianying Wang, Peifeng Ma
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2528640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224363807604736
author Yan Zhang
Mei-Po Kwan
Jiannan Cai
Jianying Wang
Peifeng Ma
author_facet Yan Zhang
Mei-Po Kwan
Jiannan Cai
Jianying Wang
Peifeng Ma
author_sort Yan Zhang
collection DOAJ
description Existing traffic flow modeling approaches typically rely on real-time observations, such as road sensors or GPS trajectories, which constrain their research scope and application scenarios. This study proposes a novel cross-spatiotemporal graph-based network method to rapidly reconstruct traffic flow speed based on remote sensing images. The method is designed to address the challenges of traffic modeling in the absence of ground observation data. Combining high-resolution remote sensing imagery, vehicle object detection, and graph modeling technology, our approach could handle the discontinuous spatiotemporal graph information. The method incorporates two key modules: a two-layer masked structure mechanism and a cross-spatiotemporal attention computation. This innovative design enables the model to continuously synthesize learning from discontinuous remote sensing images and sparse ground-based sensor data during pre-training, optimizing its parameters and improving prediction accuracy over time. Once pre-trained, the graph model can directly estimate street-level traffic flow speed based solely on remote sensing images. Our results demonstrate state-of-the-art performance (MSE=40.117, MAE=4.768, RMSE=6.334, RSE=0.228), outperforming previous graph-based and sequence-based models. This study showcases the potential of utilizing remote sensing techniques to reconstruct traffic speed in urbanizing regions. It can even be used in scenarios lacking sufficient ground stations and with discontinuous remote sensing data, and enables low-cost, large-scale, and multi-temporal traffic flow speed reconstruction.
format Article
id doaj-art-5f4d01c68904444586012defcebe1fb1
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-5f4d01c68904444586012defcebe1fb12025-08-25T11:25:08ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2528640CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detectionYan Zhang0Mei-Po Kwan1Jiannan Cai2Jianying Wang3Peifeng Ma4Institute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaExisting traffic flow modeling approaches typically rely on real-time observations, such as road sensors or GPS trajectories, which constrain their research scope and application scenarios. This study proposes a novel cross-spatiotemporal graph-based network method to rapidly reconstruct traffic flow speed based on remote sensing images. The method is designed to address the challenges of traffic modeling in the absence of ground observation data. Combining high-resolution remote sensing imagery, vehicle object detection, and graph modeling technology, our approach could handle the discontinuous spatiotemporal graph information. The method incorporates two key modules: a two-layer masked structure mechanism and a cross-spatiotemporal attention computation. This innovative design enables the model to continuously synthesize learning from discontinuous remote sensing images and sparse ground-based sensor data during pre-training, optimizing its parameters and improving prediction accuracy over time. Once pre-trained, the graph model can directly estimate street-level traffic flow speed based solely on remote sensing images. Our results demonstrate state-of-the-art performance (MSE=40.117, MAE=4.768, RMSE=6.334, RSE=0.228), outperforming previous graph-based and sequence-based models. This study showcases the potential of utilizing remote sensing techniques to reconstruct traffic speed in urbanizing regions. It can even be used in scenarios lacking sufficient ground stations and with discontinuous remote sensing data, and enables low-cost, large-scale, and multi-temporal traffic flow speed reconstruction.https://www.tandfonline.com/doi/10.1080/17538947.2025.2528640Traffic flow reconstructionGeoAIvehicle detectiongraph neural networkmultimodal fusionground-based sensors
spellingShingle Yan Zhang
Mei-Po Kwan
Jiannan Cai
Jianying Wang
Peifeng Ma
CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
International Journal of Digital Earth
Traffic flow reconstruction
GeoAI
vehicle detection
graph neural network
multimodal fusion
ground-based sensors
title CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
title_full CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
title_fullStr CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
title_full_unstemmed CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
title_short CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
title_sort crossgraphnet a cross spatiotemporal graph based method for traffic speed reconstruction using remote sensing vehicle detection
topic Traffic flow reconstruction
GeoAI
vehicle detection
graph neural network
multimodal fusion
ground-based sensors
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2528640
work_keys_str_mv AT yanzhang crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection
AT meipokwan crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection
AT jiannancai crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection
AT jianyingwang crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection
AT peifengma crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection