Nonlinear and threshold effects of the built environment, road vehicles and air pollution on urban vitality

Landscape and Urban Planning, Год журнала: 2024, Номер 253, С. 105204 - 105204

Опубликована: Сен. 19, 2024

Язык: Английский

---

Disentangling the non-linear relationships and interaction effects of urban digital transformation on carbon emission intensity

Urban Climate, Год журнала: 2025, Номер 59, С. 102283 - 102283

Опубликована: Янв. 5, 2025

Язык: Английский

---

Environmental determinants of dynamic jogging patterns: Insights from trajectory big data analysis and interpretable machine learning

Applied Geography, Год журнала: 2025, Номер 178, С. 103596 - 103596

Опубликована: Март 14, 2025

Язык: Английский

---

Crafting a jogging-friendly city: Harnessing big data to evaluate the runnability of urban streets

Journal of Transport Geography, Год журнала: 2024, Номер 121, С. 104015 - 104015

Опубликована: Окт. 1, 2024

Язык: Английский

---

Utilizing Multi-Source Geospatial Big Data to Examine How Environmental Factors Attract Outdoor Jogging Activities

Remote Sensing, Год журнала: 2024, Номер 16(16), С. 3056 - 3056

Опубликована: Авг. 20, 2024

In the post-pandemic era, outdoor jogging has become an increasingly popular form of exercise due to growing emphasis on health. It is essential comprehensively analyze factors influencing spatial distribution activities and propose planning strategies with practical guidance. Using multi-source geospatial big data multiple models, this study constructs a comprehensive analytical framework examine association between environmental variables frequency in Guangzhou. Firstly, trajectory were collected from fitness app, potential selected based perspectives built environment, street perception, natural environment. For example, using street-view imagery, objective elements such as greenery subjective safety perception extracted human-centric perspective. Secondly, included three models: backward stepwise regression, optimal parameters-based geographical detector, geographically weighted regression (GWR) model. These models served, screen significant variables, identify synergistic effects among quantify heterogeneity effects, respectively. Finally, area was clustered results GWR model urban clear positions significance. The indicated following: (1) Factors related environment significantly influence distribution. (2) Public sports facilities, level greenery, identified key activities, representing aspects service (3) Specifically, each factor displayed variation. instance, facilities positively correlated city center. (4) Lastly, divided into four clusters, different local associative characteristics activities. zonal recommendations have implications for planners policymakers aiming create jogging-friendly environments.

Язык: Английский

---

Spatiotemporal variations of private e-bike trips with explainable data-driven technologies

Cities, Год журнала: 2025, Номер 158, С. 105712 - 105712

Опубликована: Янв. 6, 2025

Язык: Английский

---

A cross-scale indicator framework for the study of annual stability of land surface temperature in different land uses

Sustainable Cities and Society, Год журнала: 2024, Номер unknown, С. 105936 - 105936

Опубликована: Окт. 1, 2024

Язык: Английский

---

Unraveling nonlinear effects of environment features on green view index using multiple data sources and explainable machine learning

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Дек. 4, 2024

Urban greening plays a crucial role in maintaining environmental sustainability and enhancing people's well-being. However, limited by the shortcomings of traditional methods, studying heterogeneity nonlinearity between factors green view index (GVI) still faces many challenges. To address concerns nonlinearity, spatial heterogeneity, interpretability, an interpretable machine learning framework incorporating Geographically Weighted Random Forest (GWRF) model SHapley Additive exPlanation (Shap) is proposed this paper. In paper, we combine multi-source big data, such as Baidu Street View data remote sensing images, utilize semantic segmentation models geographic processing techniques to study global local interpretation Beijing region with GVI key indicator. Our research results show that: (1) Within Sixth Ring Road Beijing, shows significant clustering phenomenon positive correlation linkage, at same time exhibits differences; (2) Among variables, increase coverage rate has most effect on GVI, while building density strong negative GVI; (3) The performance GWRF predicting excellent far exceeds that comparison models.; (4) Whether it rate, urban built environment or socioeconomic factors, their influence non-linear characteristics certain threshold effect. With help these influences explicit effects, quantitative analyses are provided, which can assist planners making more scientific rational decisions when allocating resources.

Язык: Английский

---

What factors influence the willingness and intensity of regular mobile physical activity?— A machine learning analysis based on a sample of 290 cities in China

Frontiers in Public Health, Год журнала: 2025, Номер 13

Опубликована: Янв. 23, 2025

Introduction This study, based on Volunteered Geographic Information (VGI) and multi-source data, aims to construct an interpretable macro-scale analytical framework explore the factors influencing urban physical activities. Using 290 prefecture-level cities in China as samples, it investigates impact of socioeconomic, geographical, built environment both overall activity levels specific types mobile Methods Machine learning methods were employed analyze data systematically. Socioeconomic, indicators used explanatory variables examine their influence willingness intensity across different activities (e.g., running, walking, cycling). Interaction effects non-linear patterns also assessed. Results The study identified three key findings: (1) A significant difference exists between intensity. Socioeconomic primarily drive willingness, whereas geographical have a stronger (2) vary significantly by type. Low-threshold walking) tend amplify promotional inhibitory factors. (3) Some display typical effects, consistent with findings from micro-scale studies. Discussion provide comprehensive theoretical support for understanding optimizing among residents. Based these results, proposes guideline-based macro-level intervention strategies aimed at improving through effective public resource allocation. These can assist policymakers developing more scientific targeted approaches promote activity.

Язык: Английский

---

Exploring nonlinear and interaction effects of urban campus built environments on exercise walking using crowdsourced data

Frontiers in Public Health, Год журнала: 2025, Номер 13

Опубликована: Янв. 30, 2025

Introduction University campuses, with their abundant natural resources and sports facilities, are essential in promoting walking activities among students, faculty, nearby communities. However, the mechanisms through which campus environments influence remain insufficiently understood. This study examines universities Wuhan, China, using crowdsourced data machine learning methods to analyze nonlinear interactive effects of built on exercise walking. Methods utilized incorporated diverse characteristics construct a multidimensional variable system. By applying XGBoost algorithm SHAP (SHapley Additive exPlanations), an explainable framework was established evaluate importance various factors, explore relationships between variables activity, interaction these variables. Results The findings underscore significant impact several key including proportion land, proximity water bodies, Normalized Difference Vegetation Index NDVI, alongside notable six distinct area types. analysis revealed thresholds patterns that differ from other urban environments, some exhibiting fluctuated or U-shaped effects. Additionally, strong interactions were identified combinations, highlighting synergistic elements like green spaces, waterfront areas when strategically integrated. Conclusion research contributes understanding how affect activities, offering targeted recommendations for planning design. Recommendations include optimizing spatial configuration bodies maximize impacts activity. These insights can foster development inclusive, health-promoting, sustainable campuses.

Язык: Английский

---