Exploring the nonlinear and spatially heterogeneous associations between the built environment and shared electric-bike–bus transfer demand

Although a wealth of research has examined the built environment (BE)-travel association, evidence on shared electric-bike (e-bike)–bus transfers remains limited. To address this gap, this study applies an integrated framework combining automated machine learning and GeoShapley to analyze the nonlinear associations between the BE and potential shared e-bike–bus transfer demand, along with identifying spatial heterogeneity in these associations. The research results indicate that geographic locations, land use mix, and bus route density make the largest contributions to model predictions. The associations between BE variables and potential transfer demand are nonlinear; the predictive contributions of some variables tend to level off at higher values. Additionally, GeoShapley reveals that the predictive contributions of bus route density, land use mix, distance to central business district, and sports and leisure facilities vary across geographic locations. This study provides empirical evidence and planning implications for optimizing urban multimodal transportation systems.

Authors

Institutions

Publication Details

Journal
Transportation Planning and Technology
Published
2026-11-17
DOI
https://doi.org/10.1080/03081060.2026.2764296
Primary Topic
Urban Transport and Accessibility
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Exploring the nonlinear and spatially heterogeneous associations between the built environment and shared electric-bike–bus transfer demand

Chaoying Yin, Yue Zhou, Haoze Lü, Xiaoquan Wang et al.
2 links
Transportation Planning and Technology
Urban Transport and Accessibility
article

Exploring the nonlinear and spatially heterogeneous associations between the built environment and shared electric-bike–bus transfer demand

Chaoying Yin, Yue Zhou, Haoze Lü, Xiaoquan Wang, Lan Wu
article en

Abstract

Although a wealth of research has examined the built environment (BE)-travel association, evidence on shared electric-bike (e-bike)–bus transfers remains limited. To address this gap, this study applies an integrated framework combining automated machine learning and GeoShapley to analyze the nonlinear associations between the BE and potential shared e-bike–bus transfer demand, along with identifying spatial heterogeneity in these associations. The research results indicate that geographic locations, land use mix, and bus route density make the largest contributions to model predictions. The associations between BE variables and potential transfer demand are nonlinear; the predictive contributions of some variables tend to level off at higher values. Additionally, GeoShapley reveals that the predictive contributions of bus route density, land use mix, distance to central business district, and sports and leisure facilities vary across geographic locations. This study provides empirical evidence and planning implications for optimizing urban multimodal transportation systems.

Transportation Planning and Technology
Hohai University (CN), Nanjing Forestry University (CN)
National Natural Science Foundation of China, China Postdoctoral Science Foundation
Sustainable cities and communities, Industry, innovation and infrastructure
Urban Transport and Accessibility
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon