Comprehensive Comparative Analysis and Innovative Exploration of Green View Index Calculation Methods

Land, Год журнала: 2025, Номер 14(2), С. 289 - 289

Опубликована: Янв. 30, 2025

Despite the widespread use of street view imagery for Green View Index (GVI) analyses, variations in sampling methodologies across studies and potential impact these differences on results, including associated errors, remain largely unexplored. This study aims to investigate effectiveness various GVI calculation methods, with a focus analyzing point selection coverage angles results. Through systematic review extensive relevant literature, we synthesized six predominant methods: four-quadrant method, six-quadrant eighteen-quadrant panoramic fisheye method pedestrian method. We further evaluated strengths weaknesses each approach, along their applicability different research domains. In addition, address limitations existing methods specific contexts, developed novel technique based three 120° images experimentally validated its feasibility accuracy. The results demonstrate method’s high reliability, making it valuable tool acquiring images. Our findings that choice significantly influences calculations, underscoring necessity researchers select optimal approach context. To mitigate errors arising from initial angles, this introduces concept, “Green Circle”, which enhances precision calculations through meticulous segmentation observational particularly complex urban environments.

Язык: Английский

---

Evaluating the impact of roadside vegetation barriers on urban air pollution using low-cost mobile sensors

Environmental Pollution, Год журнала: 2025, Номер unknown, С. 126106 - 126106

Опубликована: Март 1, 2025

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

---

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

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Авг. 21, 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 Google 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 vegetation coverage has most effect on GVI, while building density strong negative GVI; (3) Whether it cover rate, urban built environment or socio-economic factors, their influence non-linear characteristics certain threshold effect; (4) The performance GWRF simulating predicting excellent far exceeds that existing models. Based these findings, can provide important reference for planners enhance greening.

Язык: Английский

---

Demonstrating multi-benefits of green infrastructure to schools through collaborative approach

The Science of The Total Environment, Год журнала: 2024, Номер 958, С. 177959 - 177959

Опубликована: Дек. 20, 2024

Язык: Английский

---