AI-APPLICATIONS IN APPLIED ENTOMOLOGY

Insect pests are responsible for the loss of an estimated 20-40% of global crop production annually, with projections indicating that warming climates will further exacerbate these losses in coming decades. Simultaneously, the formal description of the world's estimated 5.5 million insect species remains incomplete, with fewer than one million currently catalogued, a taxonomic deficit that conventional morphology-based methods are ill-equipped to resolve at scale. Against this backdrop, artificial intelligence (AI) has emerged as a transformative computational paradigm in applied entomology, offering high-throughput, automated, and scalable solutions to longstanding challenges in pest management, species identification, biodiversity monitoring, and food safety. Conventional entomological practices, which depend predominantly on manual field inspection and expert morphological assessment, are inherently labour-intensive, geographically constrained, and limited in their capacity for real-time decision-making. AI addresses these constraints by integrating machine learning, deep learning, computer vision, and big data analytics to process complex biological and environmental datasets with high efficiency and reproducibility. Among these techniques, convolutional neural networks (CNNs) have demonstrated classification accuracies exceeding 95% in controlled insect identification tasks, substantially reducing dependence on specialist taxonomic expertise. The integration of AI with Internet of Things (IoT) devices, smart traps, hyperspectral sensors, and unmanned aerial vehicles further enables continuous, field-scale pest monitoring and early detection of infestations. These capabilities contribute to optimized pesticide application, reduced environmental contamination, and improved food safety across the production-to-storage continuum. Within Integrated Pest Management (IPM) frameworks, AI-powered decision support systems facilitate predictive modelling of pest population dynamics using climatic, phenological, and remote sensing data, enabling proactive rather than reactive management interventions. Additionally, AI enhances biological control programmes through optimization of mass rearing conditions and release strategies for natural enemies. Despite these advances, critical challenges persist, including the scarcity of high-quality annotated datasets, limited model generalisability across agroecological zones, inadequate infrastructure in developing agricultural regions, and unresolved ethical and regulatory concerns. This chapter provides a comprehensive review of AI applications across the spectrum of applied entomology, critically assessing current achievements, technological limitations, and future directions toward sustainable pest management and global food security.