Role of Artificial Intelligence in Pest Management

 

According to the Food and Agriculture Organization [1,2], agricultural pests cost 20-40% loss of worldwide crop output each year. Pesticides used in excess to control pests cause serious difficulties. Farmers may use artificial intelligence (AI) approaches combined with contemporary information and communication technologies to manage these hazardous insect pests using smart agriculture. Machine learning (ML), deep learning, and computer vision are all examples of artificial intelligence (AI). Machine Learning is at the heart of AI (ML). AI can aid with taxonomic investigations, ecological studies, and pest control in agricultural entomology. The major focus of this chapter is on AI’s use in pest management, namely through pest detection, monitoring, prediction, and identification, which aids in timely pest treatment. Plantix, Leaf-Byte, Bioleaf, Cotton Ace, Apizoom, and more software have been created to diagnose and identify insect pests in order to control them. The following are some of the key applications of AI in pest management that are mentioned in the chapter: Chen et al. [3] created a 90 percent accurate AIoT-based Smart Agricultural System for Tessaratoma papillosa (lychee gigantic stink bug) identification. Aphids, leaf hoppers, flax budworm, and other insect pests were detected using a mobile application created by Karar et al. [4]. All examined pest photos had 99.0 percent accuracy, including flea beetles and red spider mites. Due to the importance of monitoring insect pests in pheromone-based pest management systems, Ding and Taylor [5] created an automatic moth identification approach based on AI and photos received from pheromone traps for timely pest control, as opposed to traditional counting methods. Liu et al. [6] built an autonomous robotic vehicle in a natural farm scenario for the recognition of pyralidae insects with 94.3 percent recognition accuracy for successful pyralidae insect control in the farm using artificial intelligence. Potamitis and Rigakis [7] created a smart trap for remote monitoring of Rhynchophorus ferrugineus (Red palm weevil) in order to execute essential management measures based on ETLs. Selvaraj et al. [8] created an AI-based model for detecting banana illnesses and pests, which has a high success rate and may be used for early disease and pest detection. As a result, combining artificial intelligence with entomology will aid in the effective and timely control of pests and illnesses, as well as forecasting.

Author(s) Details:

Shaik Moizur Rahman,
Department of Entomology, College of Agriculture, Rajendranagar, PJTSAU, Hyderabad- 500030, India.

Gollapelly Ravi,
Department of Entomology, Faculty of Agriculture, BCKV, Nadia, West Bengal- 741252, India.

Please see the link here: https://stm.bookpi.org/CTAS-V7/article/view/6780

Leave A Comment