Each winter, tens of thousands of black-headed gulls travel from as far as Siberia to Kunming, a city in southwest China’s Yunnan Province famed as the “Spring City.”
This year, these regular visitors are greeted not only by local residents but also by high-definition cameras and drones positioned around Dianchi Lake, ready to operate in AI-driven “bird facial recognition” mode.
The long-standing connection between the people and these gulls is a unique ecological and cultural hallmark of Kunming. Technology is now reshaping this relationship, as research teams work with institutes and tech companies to deeply integrate artificial intelligence into bird protection, creating an intelligent observation system centered on this innovative identification method.
Since October 2022, the Kunming Dianchi Plateau Lake Research Institute has been using an intelligent observation program at a monitoring station near Haigeng Dam.
“After two years of continuous tracking, this system revealed that the main flock's arrival in Kunming in 2024 was about 10 days later compared to 2022 and 2023. The system will continue monitoring arrival times and population numbers this year, accumulating crucial data for migratory bird research,” the institute said.
Unlike conventional manual observation, the system employs high-definition cameras, drones, microphones, and deep neural network algorithms to identify birds. Features such as plumage, body size, and beak shape act as unique “identity markers,” enabling real-time species recognition, population counts, migration tracking, and the creation of a dynamic Dianchi bird archive.
“Previously, manual monitoring of the same area required at least two professional birders for a full day. Now, the AI system accomplishes this in just hours with 90-percent accuracy, while simultaneously recording behavioral data like feeding and roosting,” said Pan Min, deputy director of the institute.
Traditional methods relied heavily on human effort, demanded high expertise, and often struggled with consistent accuracy. AI integration is now driving a digital transformation in bird surveys across China.
Deployed at several demonstration sites in Kunming, the AI system has identified 17 bird species, building a database with hundreds of thousands of images, videos, and audio recordings. The team has also installed acoustic recognition systems that can identify species such as night herons and magpies by their distinctive calls.
According to Zhang Zhizhong, an engineer at the institute, the AI system allows researchers to monitor long-term changes in bird communities, as well as study activity patterns, breeding behavior, and migration routes. This generates essential data for evaluating wetland ecological health and biodiversity.
The reliability of “bird facial recognition” technology was validated in a research paper published in the Journal of Environmental Management in May 2025, offering new insights for future biodiversity studies.
The use of AI monitoring is now expanding beyond Kunming. In Shuangguihu National Wetland Park in Chongqing, a big data platform employs ultra-high-definition cameras for real-time, multi-target bird detection. Similarly, at the Yellow River Delta National Nature Reserve in Shandong Province, an AI system operating since 2022 has recorded over 1,200 birds, including oriental white storks and whooper swans, providing robust data for reserve management.
“The use of technological means allows us to understand and protect nature more scientifically and gently,” Zhang said.
Zhang added that while minimizing human disturbance, the adoption of AI and intelligent monitoring systems also addresses the limitations of incomplete and inaccurate data in traditional methods, opening new opportunities for biodiversity conservation.