In recent years, "blue tears" chasing has become a popular tourism activity along coasts such as Pingtan, drawing large crowds eager to witness the spectacular natural phenomenon. However, the unpredictable occurrence and movement of algal blooms have made it difficult to ensure satisfying tourist experiences while posing safety risks and ecological pressures.
In a recent study published in Ecological Informatics led by Professor LI Jianping from the Optoelectronic Engineering Technology Center at the Shenzhen Institutes of Advanced Technology (SIAT) of the Chinese Academy of Sciences, in collaboration with the Island Research Center and the Third Institute of Oceanography of the Ministry of Natural Resources, developed an innovative real-time video monitoring algorithm named BT-YOLO.
Unlike conventional methods that only detect the presence of "blue tears," the BT-YOLO algorithm achieves pixel-level segmentation of the glowing areas in video footage, enabling precise localization and quantitative analysis of bloom intensity and distribution. This provides a scientific basis for grading the severity of blooms and supports the future development of a forecasting system.
"We have built precise 'scales' and 'rulers' to measure 'blue tears'," explained Professor Li, "Once the coastal surveillance camera network is deployed, this algorithm will allow us to perform rapid quantification and move closer to an operational forecasting system." The framework is also adaptable for monitoring other marine phenomena, such as red tides and marine debris, offering a versatile solution for intelligent coastal management.
Notably, the research was driven by young scientists, including first author Naseeb Abbas, a Pakistani graduate student from the University of Chinese Academy of Sciences, and co-author Zheng Kaijian, a joint Ph.D. candidate from SIAT and Hong Kong Polytechnic University. The collaboration combined expertise in marine ecology, environmental monitoring, and engineering, ensuring the solution is both innovative and practical.
The study lays a technical foundation for predicting the timing, location, scale, and intensity of "blue tears." Further validation using data from coastal camera networks will bring the forecasting system closer to reality, helping balance ecological protection and sustainable tourism.
File Download：