As a key indicator for measuring urban green visibility, the Green View Index (GVI) reflects actual visible greenery from a human perspective, playing a vital role in assessing urban greening levels and optimizing green space layouts. Existing studies predominantly rely on single-source remote sensing image analysis or traditional statistical regression methods such as Ordinary Least Squares and Geographically Weighted Regression. These approaches struggle to capture spatial variations in human-perceived greenery at the street level and fail to identify the non-stationary effects of different drivers within localized areas. This study focuses on the Luolong District in the central urban area of Luoyang City, China. Utilizing Baidu Street View imagery and semantic segmentation technology, an automated GVI extraction model was developed to reveal its spatial differentiation characteristics. Spearman correlation analysis and Multiscale Geographically Weighted Regression were employed to identify the dominant drivers of GVI across four dimensions: landscape pattern, vegetation cover, built environment, and accessibility. Field surveys were conducted to validate the findings. The Multiscale Geographically Weighted Regression method allows different variables to have distinct spatial scales of influence in parameter estimation. This approach overcomes the limitations of traditional models in revealing spatial non-stationarity, thereby more accurately characterizing the spatial response mechanism of the Global Vulnerability Index (GVI). Results indicate the following: (1) The study area’s average GVI is 15.24%, reflecting a low overall level with significant spatial variation, exhibiting a “polar core” distribution pattern. (2) Fractal dimension, normalized vegetation index (NDVI), enclosure index, road density, population density, and green space accessibility positively influence GVI, while connectivity index, Euclidean nearest neighbor distance, building density, residential density, and water body accessibility negatively affect it. Among these, NDVI and enclosure index are the most critical factors. (3) Spatial influence scales vary significantly across factors. Euclidean nearest neighbor distance, building density, population density, green space accessibility, and water body accessibility exert global effects on GVI, while fractal dimension, connectivity index, normalized vegetation index, enclosure index, road density, and residential density demonstrate regional dependence. Field survey results confirm that the analytical conclusions align closely with actual greening conditions and socioeconomic characteristics. This study provides data support and decision-making references for green space planning and human habitat optimization in Luoyang City while also offering methodological insights for evaluating urban street green view index and researching ecological spatial equity.

Preservation and revitalization of historic districts are critical for quality urban development and renewal. Accurately assessing what drives district vitality is essential for sustainable historic area development. Current research often uses cross-sectional data and single models, limiting understanding. This study uses Xigong District, Luoyang, and integrates multi-source data—street view imagery, points of interest, road networks, and nighttime lighting—from 2014 to 2021. MGWR and XGBoost models create a dynamic framework for analyzing how the built environment affects street vitality over time. Results: (1) Spatial effects: Physically, green exposure, functional mix, and road network access are highly spatially sensitive. Morphological indicators—commercial frontage, street continuity, complexity, and building texture—show reduced local variation over time. Perceptually, the influence of abstract color narrows each year, and subjective preference broadens. (2) Nonlinear effects: Green exposure and openness dominate but show negative inhibition and diminishing returns. Morphological, functional, and road network indicators have moderate explanatory power with clear thresholds. Perceptual importance shifts from abstract color to architectural texture, which now rises while color influence steadies. Renewal should go beyond basic greening and surface color. Instead, focus on refined, threshold-based control of form and function, and preserve authentic historic texture. This approach enables scientific, sustainable vitality.

In promoting the “dual-carbon goals” and sustainable development strategy, analyzing the spatio-temporal response mechanism of landscape patterns to carbon emissions is a critical foundation for achieving carbon emission reductions. However, existing research primarily targets urbanized zones or individual ecosystem types, often overlooking how landscape pattern affects carbon emissions across entire watersheds. This research examines spatial–temporal characteristics of carbon emissions and landscape patterns in China’s Yellow River Basin, utilizing Kernel Density Estimation, Moran’s I, and landscape indices. The Geographically and Temporally Weighted Regression model is used to analyze the impact of landscape patterns and their spatial–temporal changes, and recommendations for sustainable low-carbon development planning are made accordingly. The findings indicate the following: (1) The overall carbon emissions show a spatial pattern of “low upstream, high midstream and medium downstream”, with obvious spatial clustering characteristics. (2) The degree of fragmentation in the upstream area decreases, and the aggregation and heterogeneity increase; the landscape fragmentation in the midstream area increases, the aggregation decreases, and the diversity increases; the landscape pattern in the downstream area is generally stable, and the diversity increases. (3) The number of patches, staggered adjacency index, separation index, connectivity index and modified Simpson’s evenness index are positively correlated with carbon emissions; landscape area, patch density, maximum number of patches, and average shape index are negatively correlated with carbon emissions; the distribution of areas positively or negatively correlated with average patch area is more balanced, while the spread index shows a nonlinear relationship. (4) The effects of landscape pattern indices on carbon emissions exhibit substantial spatial heterogeneity. For example, the negative impact of landscape area expands upstream, patch density maintains a strengthened negative effect downstream, and the diversity index shifts from negative to positive in the upper reaches but remains stable downstream. This study offers scientific foundation and data support for optimizing landscape patterns and promoting low-carbon sustainable development in the basin, aiding in the establishment of carbon reduction strategies.