Staying for food by urban birds: Insights from neural network analysis into adaptive strategies.

Abstract

Previous work showed that animals have demonstrated remarkable adaptability by actively integrating into urban environments. However, there is no essential difference between urban and rural areas but food availability. The behavioral mechanisms and processes by which animals adapt to cities still require further experimental validation. In this study, field surveys of the flight initiation distance (FID) of black-headed gulls (Chroicocephalus ridibundus) were performed at three scenic sites in Kunming City, Yunnan, southwest China. Our results showed that, within the same area, the FID of black-headed gulls was significantly shorter in areas with increased human activity. Moreover, in areas with earlier human contact, black-headed gulls showed shorter FID. The FID data were further analyzed by a multilayer perceptron regression model with a neural network (ANN-MLP) approach to delineate FID thresholds for black-headed gulls in different human disturbance spots. The analysis revealed that black-headed gulls exhibit a high degree of behavioral flexibility in cities, with food availability playing a key role in increasing the birds' tolerance to humans. These findings highlight the significant impact of human behaviors, such as feeding, on wildlife behavior patterns. Understanding this mechanism is essential for understanding the coexistence of humans and wildlife. The establishment of FID models for black-headed gulls will provide new possibilities and tools for animal behavior research.