ARTIFICIAL INTELLIGENCE IN ENTOMOLOGY: ADVANCES IN INSECT IDENTIFICATION, BEHAVIOURAL ANALYSIS, MONITORING AND PRECISION PEST MANAGEMENT

Abstract

Artificial Intelligence (AI) is revolutionizing entomology by providing automated, scalable, and data-driven methods for insect identification, behaviour, monitoring, biodiversity, pest management, and ecological interpretation. This review explores the use of AI in entomological research, focusing on machine learning, deep learning, computer vision, multimodal AI, Internet of Things (IoT), edge computing, generative AI and large language models. The use of AI-driven image analysis and deep-learning architectures, such as convolutional neural networks and object-detection models, has enhanced the ability to recognize and monitor insects, but their performance is still limited by the availability of small, geographically restricted datasets and domain shifts in the field. Computer-vision-based tracking allows quantitative measurement of insect movement and behaviour, and automated monitoring systems can be used for population estimation, biodiversity assessment, pest forecasting, invasive-pest surveillance, and biological-control applications. New multimodal and generative AI systems combine images, environmental data, sensor data, and knowledge to facilitate ecological interpretation and context-aware decision making. The IoT and edge AI enable real-time, low latency field monitoring. While significant advances have been made, there are still issues with data quality, model generalisation, field validation, computational needs, connectivity, transparency, and expert verification. Geographically diverse datasets, standardised validation, lightweight and interpretable models, and human–AI collaboration will be key to future progress. In conclusion, AI has the promise of revolutionizing entomological research by enhancing efficiency, scalability, and ecological awareness.