Urban forests affect the filtration and absorption of airborne particulate matter, which can minimize the harmful effects to human health caused by airborne particulate pollution. Evergreen plants in urban forests play a major role in absorbing dust and purifying the air, especially in winter. Studying the spatial distribution of leaf dust and exploring the dust retention effect of evergreen shrubs are important for scientifically guiding urban forest construction and improving the living environment of cities in winter. The purpose of this study was to establish a dust inversion model by correlation analysis of spectral reflectance and the amount of dust absorption (ADA) of vegetation, using Sentinel-2 satellite remote-sensing images to obtain the dust distribution of the evergreen vegetation (mainly Euonymus japonicus Thunb.) in the Beijing urban area, and to determine the effect of the spatial pattern of E. japonicus woodland on ADA intensity. The result showed that the red band and near-infrared band are most sensitive to dust. The normalized difference phenology index (NDPI) is more suitable for building an inversion model, where the determination coefficient (R²) of the inversion model constructed by the ratio of the NDPI (R_NDPI) was 0.879. The inversion results show that the mean ADA in the enclosed area is smaller than that in semi-enclosed and open areas, and the regional distribution of high ADA in the urban area of Beijing was higher in the south with a tendency of the ADA to decrease from city center to the surrounding area. The size, shape, and percentage of landscape (PLAND) of E. japonicus woodland have a significant effect on ADA intensity. We found that, in the study area, when the PLAND of E. japonicus woodland is higher than 40%, its ADA intensity remains basically unchanged. When the vegetation coverage is fixed, the landscape shape index is negatively correlated with ADA intensity, and reduction of the overall shape complexity of forestland can enhance its dust retention effect and improve the air environment of the surrounding areas. The results of this study can be used as a reference for urban planners and landscape architects when building urban forests, providing a scientific basis for controlling and reducing air particulate pollution in Beijing’s winter and improving the living environment.

Continuous spatial reconstruction in highly fragmented landscapes remains a persistent challenge in remote sensing and geographic information systems. Standardized products such as MODIS Net Primary Productivity (NPP) provide temporally consistent ecological baselines, but their moderate spatial resolution can obscure abrupt transitions in disturbed environments. This study develops a biophysical index-guided 1 × 1 Convolutional Neural Network (CNN) framework for NPP reconstruction over a mega-scale open-pit mining landscape. The framework uses five Landsat-derived biophysical tensors—Vegetation Moisture Stress Index (VMSI), Anti-Vegetation Environment Index (AVEI), Soil Adjusted Vegetation Environment Index (SAVEI), AAI-VHI, and Tasseled Cap Wetness (WET)—as point-wise predictors aligned to the MODIS NPP baseline grid. By restricting convolutional kernels to 1 × 1, the model performs nonlinear channel-wise mapping without incorporating neighboring grid cells, thereby reducing boundary mixing that can occur in conventional multi-pixel CNNs. Benchmark comparisons with Random Forest and a standard 3 × 3 CNN showed that the 3 × 3 CNN achieved slightly higher global accuracy, whereas the 1 × 1 CNN provided stronger gradient correspondence and lower full-domain spatial error in the 2020 spatial fidelity assessment. The results indicate that point-wise convolution guided by physically interpretable indices provides a conservative and interpretable option for standardized ecological reconstruction at the MODIS baseline grid scale.