Ring-based Spatial Transformer: Learning Non-linear Spatial Interactions between Building Distribution and Pedestrian Flow
Summary
This study proposes a ring-based Spatial Transformer to model non-linear spatial interactions between building distribution and pedestrian flow around railway stations in Tokyo, outperforming Geographically Weighted Regression and challenging compact city assumptions in urban planning.
View Cached Full Text
Cached at: 08/18/26, 10:22 AM
# Ring-based Spatial Transformer: Learning Non-linear Spatial Interactions between Building Distribution and Pedestrian Flow Source: [https://arxiv.org/abs/2608.14660](https://arxiv.org/abs/2608.14660) [View PDF](https://arxiv.org/pdf/2608.14660) > Abstract:This study proposes a ring\-based SpatialTransformer to learn how building uses at different distances from a railway station interact to generate pedestrian flow\. Concentric ring buffers at 100\-meter intervals up to 800 meters were defined around 100 randomly selected stations in Tokyo, treating each ring as a spatial token\. Self\-Attention was applied to learn inter\-zone interactions directly from data, without prior structural assumptions\. GPS\-derived walking trip counts served as the target variable and Geographically Weighted Regression as the baseline\. Across 30 independent trials, the SpatialTransformer consistently outperformed GWR in predictive accuracy\. SHAP analysis revealed that mid\-to\-outer distance zone features dominate pedestrian flow prediction, while features from the 0\-100m zone contributed little\. The attention matrix showed that each distance zone attends most strongly to spatially distant zones, demonstrating that pedestrian flow is regulated by structural interactions across the entire catchment area rather than by any single zone in isolation\. These findings challenge the compact city assumption that station\-proximate development maximizes pedestrian flow, and suggest that land use distribution across the full walkable catchment area deserves greater consideration in urban planning practice\. ## Submission history From: Shun Nakayama \[[view email](https://arxiv.org/show-email/ad10ea4c/2608.14660)\] **\[v1\]**Fri, 31 Jul 2026 22:49:44 UTC \(805 KB\)
Similar Articles
STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
STAGformer introduces a spatio-temporal agent graph transformer with linear complexity for bike-sharing demand forecasting, outperforming baselines on NYC and Chicago datasets.
PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks
PatchSTG introduces a patch-based spatiotemporal graph Transformer for traffic forecasting on irregular sensor networks, achieving near-linear complexity while maintaining competitive performance.
Spatiotemporal Graph Transformer for Traffic Intelligence in Edge Computing
This paper proposes a spatiotemporal graph Transformer framework for traffic forecasting in edge computing, combining graph neural networks for spatial correlations and Transformer self-attention for long-range temporal dependencies. Experiments on real-world cellular data show it outperforms recurrent graph-based baselines like GCN-LSTM and GCN-GRU.
Do We Really Need Transformers for Global Spatial Information Extraction in Traffic Forecasting?
This paper investigates whether complex transformer-based attention is necessary for global spatial information extraction in traffic forecasting, finding that simple global aggregation operators achieve comparable performance with lower computational complexity.
Geometric and Behavioral Stratification in Transformer Residual Streams
This paper investigates the residual stream geometry of trained transformers, showing that the prediction direction acts as a privileged anchor that stratifies residual-stream variation into narrow, readout-relevant and broad, computational regions across 18 models. The findings have implications for interpretability and evaluation.