Translation. Region: Russian Federation –
Source: People's Republic of China in Russian – People's Republic of China in Russian –
An important disclaimer is at the bottom of this article.
Source: People's Republic of China – State Council News
KUNMING, Oct. 11 (Xinhua) — Every winter, tens of thousands of black-headed gulls make the long journey from distant Siberia to Kunming, known as the "city of eternal spring," in southwest China's Yunnan Province.
This year, regular visitors will be treated not only to the friendly residents of Kunming, but also to high-definition cameras and drones installed at the city's Dianchi Lake, ready to activate their AI-powered "bird face recognition" mode.
The strong bond between humans and these seagulls has already become a distinctive ecological and cultural feature of Kunming. Now, this relationship is being reimagined through technology, as research teams collaborate with institutes and tech companies to deeply integrate AI into bird conservation, creating an intelligent surveillance system based on this new identification method.
Since October 2022, the Kunming Dianchi Highland Lake Research Institute has been using an intelligent seagull monitoring program at the monitoring station near Haigeng Dam.
After two years of continuous tracking, the system showed that the main flock of seagulls arrived in Kunming approximately 10 days later in 2024 than in 2022 and 2023. This year, the system will continue to track arrival times and population sizes to accumulate fresh data for migratory bird research, according to the institute.
Unlike traditional manual observation, the new system uses high-definition cameras, drones, microphones, and deep neural network algorithms to identify birds.
Distinctive features such as plumage, body size, and bill shape serve as unique “identification markers” that enable the system to perform real-time species identification, population counts, migratory route tracking, and the creation of a dynamic archive of Dianchi Lake birds.
"Previously, manually monitoring the same area required at least two professional ornithologists for an entire day. Now, the AI system can do this in just a few hours with 90 percent accuracy, while simultaneously recording bird behavior data, such as feeding and roosting," said Pan Min, deputy director of the aforementioned institute.
Traditional methods based on visual observation were labor-intensive, required highly skilled personnel, and struggled to achieve consistent accuracy. Now, the integration of AI is driving digital transformation in bird research across China.
The AI system, used at several demonstration sites in Kunming, has already identified a total of 17 bird species, creating a database of hundreds of thousands of images, videos, and audio recordings. The team has also implemented acoustic recognition systems capable of identifying species such as the night heron and magpie based on the unique characteristics of their calls.
According to Zhang Zhizhong, an engineer at the institute, using the AI system, researchers can not only track long-term changes in bird communities but also study activity patterns, breeding habits, and migratory routes. This provides important data for assessing the ecological health of wetlands and biodiversity levels.
The reliability of the "bird recognition" technology was confirmed in a paper published by the research team in the Journal of Environmental Management in May 2025, opening up new avenues for future biodiversity research.
The application of AI in bird monitoring extends beyond Kunming. At the Shuangguihu National Wetland Park in the metropolis of Chongqing (southwest China), a big data platform uses ultra-high-definition cameras for multi-purpose capture and real-time identification of birds. Similarly, at the Yellow River Delta National Nature Reserve in Shandong Province (east China), an AI system, operational since 2022, has recorded over 1,200 birds, including oriental white storks and whooper swans, thereby providing reliable information support for the reserve's management.
"The use of technological tools allows us to understand and protect nature more scientifically and carefully," said Zhang Zhizhong.
He added that the introduction of AI and intelligent monitoring systems, while minimizing anthropogenic impact, eliminates the shortcomings of traditional methods – incomplete and inaccurate data, thereby opening up new opportunities for biodiversity conservation. -0-
Please note: This information is raw content obtained directly from the source. It represents an accurate account of the source's assertions and does not necessarily reflect the position of MIL-OSI or its clients.
