Communications of the ACM
Artificial Intelligence Fights Notorious Crop Pest
The Oriental fruit fly is known to target over 230 different fruit, vegetable, and plant commodities.
Credit: Farm Progress
National Taiwan University researchers have developed an artificial intelligence system that can predict an outbreak of crop-damaging fruit fly swarms.
Fruit fly populations are historically monitored using traps that are manually checked every 10 days, and the researchers, led by Cheng-Long Chuang, automated the counting process by placing infrared beams in the traps. Each trap records when the beam is broken, indicating that a fruit fly has entered the trap. The results are sent to a local station every 30 minutes, allowing real-time measurements of the fruit fly population. Machine-learning algorithms pool the continuous data arriving from each trap and predict when the local fruit fly population is ready to boom.
The traps also are equipped with weather sensors that monitor temperature, humidity, wind speed, and rainfall. The system also can learn what can be described as a normal level of fruit flies in an area and alter its warnings based on the current weather and time of the year. When a potentially devastating infestation is predicted, the system automatically sends a text message to government officials, providing the time, location, and severity of the potential outbreak.
From New Scientist
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found