Graph neural network modeling of pedestrian space vitality in campus waterfront space: a Flow–Dwell perspective for design translation
6 affiliations
- 1State Key Laboratory of Subtropical Building and Urban Science, School of Architecture, South China University of Technology
- 2Architectural Design & Research Institute, South China University of Technology
- 3School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology
- 4Energy Saving Technology Research Institute, South China University of Technology
- 5Centre for Climate–Resilient and Low–Carbon Cities, School of Architecture and Urban Planning, Key Laboratory of New Technology for Construction of Cities in Mountain Area, Ministry of Education, Chongqing University
- 6School of Architecture, Design and Planning, The University of Queensland
Abstract
In campus landscapes, waterfront pedestrian spaces support both movement and staying activities and may contribute to activity- and health-supportive environments. This study examined the associations between built-environment features and waterfront pedestrian-space vitality across 42 spatial units at two campuses of the South China University of Technology (20 at Wushan Campus and 22 at Guangzhou International Campus). Wi-Fi probe data were collected during weekday and weekend observation periods on December 11–14, 2025 (Wushan Campus) and December 18–21, 2025 (Guangzhou International Campus) to derive two device-based vitality proxies: Flow for transient activity and Dwell for staying-oriented activity, distinguished using unit-specific traversal-time thresholds. A Flow–Dwell quadrant framework was used to classify the spatial contexts, and graph neural network node regression was employed to incorporate spatial adjacency relationships. Feature perturbation was further used to quantify the model-prediction sensitivity at the node level and to support design interpretation. The results showed that (1) Flow and Dwell exhibited distinct spatial distributions and environmental sensitivity patterns; (2) Flow was better predicted by graph neural networks than Dwell (best overall R ² = 0.48, versus 0.04 for Dwell), whereas Dwell showed a substantially weaker model fit; and (3) the selected GNNs outperformed the best-performing conventional baselines for both targets, reducing the RMSE by 36.2% for Flow and 14.0% for Dwell. This study provides a spatially explicit framework for interpreting campus waterfront vitality and translating model-derived sensitivity patterns into design priorities, offering evidence for planning activity-supportive campus environments, and contributing to public-health-oriented spatial design.
Related
- Evaluating Pedestrian Crossing Safety: Implementing and Evaluating a Convolutional Neural Network Model Trained on Paired Aerial and Subjective Perspective Images (Vol 11, E42428, 2025)
- Patient-Derived Organoids in Functional Precision Oncology: Tumor Modeling, Drug-Response Prediction, and Clinical Translation.
- Patient-derived organoids for precision oncology in colorectal cancer: from tumor modeling to clinical translation.
- The vitality infant algorithm: A validated tool to classify food allergy outcomes in research studies
- Vitality capacity association with lifelong aerobic physical activity in older adults
BibTeX
@article{yu2026graph,
title = {{Graph neural network modeling of pedestrian space vitality in campus waterfront space: a Flow–Dwell perspective for design translation}},
author = {Zhiye Yu and Ying Bao and Shijie Li and Xiao Liu and Yue Pei and Bao-Jie He},
journal = {Frontiers in Public Health},
year = {2026},
month = oct,
doi = {10.3389/fpubh.2026.1963816},
url = {https://www.frontiersin.org/articles/10.3389/fpubh.2026.1963816/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Graph neural network modeling of pedestrian space vitality in campus waterfront space: a Flow–Dwell perspective for design translation
AU - Zhiye Yu
AU - Ying Bao
AU - Shijie Li
AU - Xiao Liu
AU - Yue Pei
AU - Bao-Jie He
PY - 2026
DA - 2026/10/29
JO - Frontiers in Public Health
DO - 10.3389/fpubh.2026.1963816
UR - https://www.frontiersin.org/articles/10.3389/fpubh.2026.1963816/full
AB - In campus landscapes, waterfront pedestrian spaces support both movement and staying activities and may contribute to activity- and health-supportive environments. This study examined the associations between built-environment features and waterfront pedestrian-space vitality across 42 spatial units at two campuses of the South China University of Technology (20 at Wushan Campus and 22 at Guangzhou International Campus). Wi-Fi probe data were collected during weekday and weekend observation periods on December 11–14, 2025 (Wushan Campus) and December 18–21, 2025 (Guangzhou International Campus) to derive two device-based vitality proxies: Flow for transient activity and Dwell for staying-oriented activity, distinguished using unit-specific traversal-time thresholds. A Flow–Dwell quadrant framework was used to classify the spatial contexts, and graph neural network node regression was employed to incorporate spatial adjacency relationships. Feature perturbation was further used to quantify the model-prediction sensitivity at the node level and to support design interpretation. The results showed that (1) Flow and Dwell exhibited distinct spatial distributions and environmental sensitivity patterns; (2) Flow was better predicted by graph neural networks than Dwell (best overall R ² = 0.48, versus 0.04 for Dwell), whereas Dwell showed a substantially weaker model fit; and (3) the selected GNNs outperformed the best-performing conventional baselines for both targets, reducing the RMSE by 36.2% for Flow and 14.0% for Dwell. This study provides a spatially explicit framework for interpreting campus waterfront vitality and translating model-derived sensitivity patterns into design priorities, offering evidence for planning activity-supportive campus environments, and contributing to public-health-oriented spatial design.
SN - 2296-2565
ER -