Assessing the differential impact of vegetated and built-up areas on heat exposure environment: A case study of Los Angeles

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 112538 - 112538

Published: Jan. 1, 2025

Language: Английский

---

Predicting long-term urban overheating and their Mitigations from nature based solutions using Machine learning and field measurements

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115720 - 115720

Published: April 1, 2025

Language: Английский

---

Quantifying seasonal bias in street view imagery for urban form assessment: A global analysis of 40 cities

Computers Environment and Urban Systems, Journal Year: 2025, Volume and Issue: 120, P. 102302 - 102302

Published: May 9, 2025

Language: Английский

---

Interpretable Machine Learning Insights into the Factors Influencing Residents’ Travel Distance Distribution

ISPRS International Journal of Geo-Information, Journal Year: 2025, Volume and Issue: 14(1), P. 39 - 39

Published: Jan. 20, 2025

Understanding intra-urban travel patterns through quantitative analysis is crucial for effective urban planning and transportation management. In previous studies, a range of distribution functions were modeled to lay the groundwork human mobility research. However, few studies have explored nonlinear relationships between distance environmental factors. Using data from ride-hailing services, this research divides study area into 1 × km grid cells, modeling best calculating coefficients each grid. A machine learning framework (Extreme Gradient Boosting combined with Shapley Additive Explanations) introduced interpret factors influencing these distributions. Our results emphasize that movement tends follow log-normal exhibits spatial heterogeneity. Key affecting distributions include city center, bus station density, land use entropy, density companies. Most variables exhibit threshold effects on coefficients. These findings significantly advance our understanding offer valuable insights dynamics mobility.

Language: Английский

---

Spatiotemporal Assessment and Monitoring of Urban Heat Islands in Metropolitan Areas Using Machine Learning and Downscaling

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106365 - 106365

Published: April 1, 2025

Language: Английский

---

Spatiotemporal Analysis of Urban Vitality and Its Drivers from a Human Mobility Perspective

ISPRS International Journal of Geo-Information, Journal Year: 2025, Volume and Issue: 14(4), P. 167 - 167

Published: April 11, 2025

Urban vitality is a critical metric for assessing the development and appeal of urban areas, playing pivotal role in planning management. Traditionally, surveys census data have been used to measure vitality; however, these methods are often time-consuming, resource-intensive, limited coverage. This study addresses limitations by employing mobile phone signaling develop model quantifying exploring its spatiotemporal distribution patterns. By integrating socioeconomic, street view, points-of-interest (POI) data, this utilizes linear regression geographically weighted (GWR) models analyze influence various factors on vitality. The SHapley Additive exPlanations (SHAP) method then applied interpret predictions identify key determinants Using Shenzhen as case study, results reveal pronounced spatial disparities Among all variables, bus stop density, cultural services, employment density consistently exhibit significant effects proposed quantification framework enables high-resolution wide-coverage monitoring vitality, providing scientific support decision-making guidance understanding dynamic characteristics spaces optimizing functional layouts.

Language: Английский

---

Uncovering nonlinear urban factors of homelessness: Evidence from New York City using interpretable machine learning

Environment and Planning B Urban Analytics and City Science, Journal Year: 2025, Volume and Issue: unknown

Published: May 9, 2025

Urban homelessness is a complex issue rooted in structural inequalities and spatial disparities, significantly affecting urban life well-being. Existing research often relies on survey-based or linear regression methods, which are limited scope, coverage, their ability to capture nonlinear associations. This study addresses these gaps by combining homeless incident reports from New York City’s 311 service with multi-source big data employing Light Gradient Boosting Machine (LightGBM) model alongside SHapley Additive Explanations (SHAP). Through census tract-level analysis, we examine how socioeconomic, built environment, transportation, landscape factors relate incidence. Our findings show that (1) the importance of predictive varies across location types, for instance, information, communication POIs most commercial areas, while felony crime median income dominate residential zones; (2) socioeconomic environment features consistently more important than transportation visual indicators; (3) many exhibit relationships threshold effects, such as sharp increases beyond rent $1800 Gini index 0.53. These offer new insights into distribution drivers underscore value interpretable machine learning analytics. By identifying key environmental thresholds, this provides evidence-based guidance spatially targeted interventions, prioritizing support services high-risk areas designing inclusive public spaces can help mitigate promote sustainable equitable cities.

Language: Английский

---

An Examination and Analysis of the Clustering of Healthcare Centers and their Spatial Accessibility in Tehran Metropolis: Insights from Google POI Data

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 117, P. 105845 - 105845

Published: Sept. 25, 2024

Language: Английский

---

Unravelling Impacts of Street Environment on Biking Using Explainable Spatial-Temporal Machine Learning

Published: Jan. 1, 2024

Language: Английский

---