Shrimp Fatten Up 30% More: Underwater Cameras and AI Systems Help Gauge the Right Feeding Time
On the 23rd, a research team from National Sun Yat-sen University presented its "AI Smart Aquaculture Results" - using underwater cameras to record shrimp activity levels and automatic bait-spraying equipment, allowing shrimp to gain 3 grams per week, a 30% increase in fattening compared with traditional shrimp pond farming methods. Currently, 2 shrimp farms have already installed the underwater cameras and bait-spraying equipment. Over the next 3 years, the research team will take on outdoor farms, improving the underwater cameras' recognition capability to become the sharpest eyes underwater for aquaculture farmers.
Hong Qingzhang, a professor in the Department of Oceanography at National Sun Yat-sen University, said the research team spent a year on trials and developed a central drainage system that can be activated based on dissolved oxygen parameters, as well as an AI-recognition-integrated underwater camera system and bait-spraying equipment. Farmers have shown the greatest interest in the underwater camera and bait-spraying system.
This underwater camera system uses visible light and infrared technology to monitor shrimp activity around the clock, and can be combined with AI recognition and automatic bait-spraying equipment. When image recognition detects that the bait density in the feeding area is below 15% or another set value, the bait-spraying equipment can be activated by remote control or by the system. On one hand, this can reduce water pollution caused by bait; on the other hand, it can precisely determine the right feeding time. Hong Qingzhang said that after 6 months of trials, grass shrimp (Penaeus monodon) raised with this system in the university's seawater aquaculture pond increased their weekly weight gain from 2 grams to 3 grams, a 30% increase in fattening compared with shrimp raised in traditional shrimp ponds.
Hong Qingzhang, who moved from water quality research into the shrimp farming industry, said water quality control is the key to shrimp farming. When the water is good, bacteria and viruses are less likely to target the shrimp. Through AI-recognition-assisted precise feeding with underwater cameras and a central drainage facility integrated with variable-frequency air compressors, the research team raised the survival rate of grass shrimp to 70%, while also saving 30% of electricity compared with traditional paddlewheel aerators.
However, the underwater camera system has not yet been tested in fully outdoor aquaculture ponds. Hong Qingzhang explained that outdoor ponds have different algal ecologies, which test both the underwater cameras' image-recording capability and the AI's recognition capability. Huang Yingzhe, a chair professor in the Department of Computer Science and Engineering at National Sun Yat-sen University, said the team is also developing AI chip modules to improve the performance of the recognition system, reduce the power consumption of the underwater imaging system, and meet users' network bandwidth and data storage needs.