Molecular Entomology 2024, Vol.15, No.5, 209-220 http://emtoscipublisher.com/index.php/me 216 The data from IoT sensors and drones were integrated into a cloud-based platform that used machine learning algorithms to predict potential pest outbreaks based on historical data and real-time environmental conditions. When the system flagged areas of concern, farm workers were alerted and deployed targeted pesticide applications using UAVs. This approach significantly reduced pesticide usage and improved the precision of pest control efforts. The use of drones for pesticide application, informed by real-time data, ensured that only affected areas were treated, minimizing chemical exposure to the rest of the plantation (Thereza et al., 2020). Figure 2 Generated orthomosaic of studied sites; two vineyards in the Yarra valley, Victoria, Australia (Adopted from Vanegas et al., 2018) 6.3 Effectiveness of precision management in pest reduction The introduction of IoT and remote sensing technologies in this tea plantation led to substantial improvements in pest management. The most significant outcome was a 35% reduction in pesticide use, primarily due to the ability to apply chemicals only in areas where pests were detected, rather than treating the entire plantation. This not only reduced the environmental impact of chemical use but also resulted in cost savings on pesticides. Furthermore, the targeted approach prevented over-application, thus reducing the risk of pests developing resistance to the pesticides (Sarangi et al., 2020). Crop yields improved by approximately 15%, attributed to healthier plants with less pest damage. Early detection of infestations through drone surveillance allowed for timely interventions, preventing pests from spreading and causing more extensive damage. For example, red spider mite infestations, which typically affected large sections of the plantation, were contained to smaller, manageable areas, reducing crop losses significantly. The
RkJQdWJsaXNoZXIy MjQ4ODYzNA==