MySheen

AI intelligent agricultural technology: the underwater camera controls the timing of shrimp feeding, and the AI agricultural system allows 30% of shrimp fertilizer.

Published: 2024-11-05 Author: mysheen
Last Updated: 2024/11/05, Photo courtesy of Zhuang Xiaoping / the research team of National Sun Yat-sen University / National Sun Yat-sen University released the "presentation of AI Intelligent farming results" on the 23rd, using underwater cameras to record shrimp activity and automatic bait spraying facilities, so that shrimp can gain 3 grams per week, 30% more than traditional shrimp culture methods. At present, there are 2 shrimp.

The research team of National Sun Yat-sen University released the "presentation of AI Intelligent farming results" on the 23rd, using underwater cameras to record shrimp activity and automatic bait spraying facilities, so that shrimp can gain 3 grams per week, 30% more than traditional shrimp culture methods. At present, two shrimp farms have been equipped with underwater cameras and bait spraying facilities. In the next three years, the research team will challenge outdoor farms, hoping to improve the recognition ability of underwater cameras and turn them into the sharpest eyes of farmers underwater.

Hong Qingzhang, a professor in the Department of Marine Science at National Sun Yat-sen University, said that after three years of experiments, the research team has developed a central sewage discharge system that can be activated for dissolved oxygen parameters, as well as an underwater photography system and bait spraying equipment identified by AI. Farmers have the highest degree of inquiry about underwater photography and bait spraying systems.

The underwater photography system monitors the dynamics of shrimp all day long by means of visible and infrared technology, and can be combined with AI identification and automatic bait spraying equipment. When the image identifies that the bait density in the feeding area is less than 15% or other set values, the bait spraying facility can be remotely controlled or started by the system, on the one hand, the water pollution caused by bait can be reduced, and on the other hand, the feeding timing can be accurately grasped. Hong Qingzhang said that after six months of experiments, the weight of grass shrimp raised through this system in the school's mariculture pond can be increased from 2 grams to 3 grams per week, which is 30% more than that of traditional shrimp culture.

Huang Yingzhe, chair professor of the Sun Yat-sen Engineering Department, added that both water quality sensors and underwater cameras are developed by the company, but with cameras, "it depends on what is important." so the research team contacted farmers at the beginning of the plan. understand the needs before starting to develop. This system can not only integrate the data in the pond to help farmers remotely manage shrimp ponds, but also record water quality data, feeding records and activity status on the cloud platform, so that the experience of farmers can be converted into storable data. in order to replicate the experience in different places and achieve the results of highly quantitative production.

Hong Qingzhang, who jumped from water quality research to the shrimp farming industry, said that water quality control is the key to the shrimp farming industry. when the water is good, it is not easy for bacteria and viruses to find shrimp. The research team uses underwater cameras to help AI identify precise bait, and integrates the central sewerage facilities of frequency conversion air compressors to increase the shrimp breeding rate to 70%. It can also save 30% of electricity than traditional water wheels.

However, underwater photography equipment has not yet been tested in outdoor aquaculture ponds. Hong Qingzhang explains that because of different algae ecology and sunlight changes in outdoor ponds, the image recording ability of underwater cameras and the ability to identify AI are all tested. Huang Yingzhe, chair professor of Zhongshan Engineering Department, said that in order to cope with the changeable and complex environmental data of outdoor aquaculture ponds, the team is also developing edge smart chip modules. In the future, the system can process data at the pool side and can make decisions without uploading to the cloud platform, in order to meet the needs of users' network bandwidth and data storage, improve the efficiency of the identification system, and reduce the shortcomings of power consumption of the underwater imaging system.

 
0