In recent years, "blue tears" chasing has become a popular tourism activity along coasts to witness the spectacular natural phenomenon. However, the occurrence and movement of algal blooms are unpredictable, which impacts the quality of tourist experiences while posing safety risks and ecological pressures.

In a study published in Ecological Informatics, a team led by Prof. LI Jianping from the Shenzhen Institute of Advanced Technology of the Chinese Academy of Sciences, along with the collaborators from the Ministry of Natural Resources, developed an innovative real-time video monitoring algorithm named BT-YOLO.

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. Unlike conventional methods that only detect the presence of "blue tears," this algorithm provides a scientific basis for grading the severity of blooms and supports the development of a forecasting system.

"We have built precise 'scales' and 'rulers' to measure 'blue tears'. 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," explained Prof. LI. The algorithm is also adaptable for monitoring other marine phenomena, such as red tides and marine debris, providing a solution for intelligent coastal management.

The study lays a 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, which helps balance ecological protection and sustainable tourism.