Artificial intelligence in the mass production of natural enemies for biological control in modern agriculture

Abstract:The increasing challenges posed by pest infestations in contemporary agriculture demand sustainable alternatives to conventional
pesticides. Biological control (BC), which utilizes natural enemies (NEs) such as predators and parasitoids, offers an ecofriendly
approach to pest management. However, large-scale production of NEs faces significant challenges, including high
costs, time-consuming processes, and inconsistent quality. Artificial intelligence (AI) is increasingly being applied in modern
agriculture to enhance the efficient mass production of NEs for BC. By leveraging automation, machine learning (ML), computer
vision, and real-time data analytics, AI can improve key aspects of NEs production, including diet formulation, environmental
control, behavioral monitoring, and quality assurance. AI-driven systems promote consistency and scalability in NE
manufacturing, while adaptive feedback mechanisms enable continuous process optimization. Furthermore, AI supports the
development of predictive models and customized distribution strategies, ensuring the timely and effective deployment of
NEs. Despite challenges such as high initial investment and limited data availability, the integration of AI in NEs production
holds considerable promise for cost-effective, scalable, and sustainable BC strategies. This review explores the intersection of
AI and BC, highlighting current applications, key challenges, and future opportunities in AI-enhanced BC and NEs mass production.
It synthesizes recent advancements and identifies research gaps, providing a comprehensive overview of AI's evolving
impact on crop protection. By optimizing NE production and reducing dependence on chemical inputs, AI contributes to
improved biodiversity, alignment with global sustainability goals, and a more resilient agricultural future. These insights are valuable
for researchers, practitioners, and policymakers working toward sustainable and inclusive pest management solutions.

Publication year:2025

Keywords:Artifical Neural Networks, Deep Learning, Internet of Things, Artificial intelligence, Biological control, Computer vision, Convolutional neural networks, Crop protection, Digital literacy, Machine learning, Natural enemies, Sustainable agriculture, Unmanned aerial vehicles, Plant & soil science & technology, Animal sciences

Accessibility:Open

Review status:Peer-reviewed