The spatiotemporal distribution patterns and impact factors of bird species richness: A case study of urban built-up areas in Beijing, China

• Multi-dimensional analyses of bird distribution were conducted. • The number of bird species in older urban core areas has decreased annually. • The bird species and individuals were lowest in build-up areas during the summer. • Three distinct algorithms were used to compare and validate the impact factors. • Bird distribution exhibits adaptability during the urbanization process. This study aims to investigate the distribution patterns of bird species in urban built-up areas and their impact factors from multiple dimensions, including spatiotemporal distribution, environmental changes, and anthropogenic disturbances, as well as overall distribution and local hotspots. Leveraging geographic distribution data of 383 bird species from 70 families and 21 orders, the study recorded dynamic changes in bird distribution within urban built-up areas characterized by highly heterogeneous core areas and suburban areas. It examined species distribution across different seasons and land cover types, evaluated population fluctuations based on migratory behaviors, and assessed the relative abundance of bird families and species in hotspot areas. Additionally, this study employed three tree-based machine learning algorithms—Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—to investigate the influence of environmental factors on bird species distribution within urban built-up areas. The findings showed that, temporally, the number of observed bird species in the study area peaked in May and September, while the lowest numbers of species (54.83 %) and individuals (5.45 %) were recorded during the high-temperature period from June to August. Spatially, (1) woodlands, including stable mature forests, unstable juvenile forests, and sparse vegetation, recorded the highest frequencies of bird observations (2,053 times), bird species (369 species), and bird individuals (38,623 individuals); (2) comprehensive parks, where bird species demonstrated higher adaptability to anthropogenic disturbances, experienced a more significant decline in species richness compared to country parks; and (3) the number of bird species in hotspot areas located in the core areas, which developed earlier, has decreased annually, while the number of species in suburban areas, which developed later, has increased annually. In terms of impact factors, water area (WA), point of interest kernel density (DPOI), relative humidity (RH), green space area (GSA), and nighttime light pollution (NL) were identified as the five most important environmental factors affecting bird species richness. These results suggest that although birds exhibit some adaptability to environmental changes and anthropogenic disturbances, species distribution remains significantly impacted. This research aims to provide a planning framework for future urban development that promotes biodiversity and adaptability, thereby bolstering the resilience of urban ecosystems.