Molecular Entomology 2024, Vol.15, No.5, 209-220 http://emtoscipublisher.com/index.php/me 212 Hyperspectral sensors, mounted on UAVs or satellites, are capable of detecting minute differences in plant reflectance, which can signal the early stages of pest infestations. In vineyards, for example, hyperspectral imaging has been used to monitor pest-related stress with high accuracy, and similar methodologies can be applied to tea plantations (Vanegas et al., 2018). Additionally, hyperspectral imaging has been shown to outperform traditional RGB or NIR sensors by providing more detailed spectral data, making it easier to differentiate between healthy and pest-infested plants. These imaging techniques not only help in pest detection but also assist in precision pesticide application, ensuring that chemicals are applied only where necessary, thus reducing environmental impact and costs (Adão et al., 2017). 3.3 Analyzing vegetation indices to assess pest infestation Vegetation indices derived from remote sensing data are powerful tools for assessing plant health and detecting pest infestations. Indices such as the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI) are commonly used to monitor changes in plant biomass and vigor, which can indicate the presence of pests. For instance, lower NDVI values typically correspond to areas of poor plant health, potentially caused by pest damage. The use of vegetation indices is particularly effective in large-scale tea plantations, where manual monitoring of every plant is impractical. A study using hyperspectral data to monitor rice plants infested with brown planthoppers demonstrated that specific vegetation indices could accurately reflect the severity of the infestation (Tan et al., 2019). Similarly, in tea plantations, these indices help farmers identify hotspots of pest activity, enabling them to focus their pest control efforts precisely where needed. By analyzing the spectral signatures of healthy versus pest-infested plants, vegetation indices provide an efficient means of monitoring crop health over time. This allows tea growers to implement more proactive pest management strategies, ultimately improving crop yield and quality. 4 Synergistic Use of IoT and Remote Sensing 4.1 Combining data from iot sensors and remote sensing Combining IoT sensors and remote sensing technologies allows for comprehensive, multi-dimensional data collection in tea plantations, offering real-time insights into environmental conditions and crop health. IoT sensors placed within the fields continuously monitor factors such as soil moisture, temperature, humidity, and light intensity, which are critical for understanding the overall health of the tea plants. These sensors can detect subtle changes in the environment that might suggest the early onset of pest activity, such as prolonged dry conditions that could stress plants and make them more susceptible to pests. Meanwhile, remote sensing technologies, particularly drones and satellites equipped with multispectral or hyperspectral imaging, provide large-scale monitoring of plant health and pest outbreaks. These imaging technologies can detect changes in leaf color, chlorophyll levels, and other physiological indicators that are often early signs of pest infestations. The integration of these data sources enhances the ability of farmers to monitor their crops with a high degree of precision. For instance, IoT sensors might detect localized changes in soil moisture, while drone imagery could reveal pest hotspots based on changes in vegetation indices, such as the Normalized Difference Vegetation Index (NDVI). This combination of ground-based and aerial data allows for a more accurate diagnosis of potential threats to the tea plants, facilitating early interventions and minimizing crop losses. Additionally, this data fusion allows for continuous monitoring, reducing the reliance on manual inspections and enabling more efficient resource use (Figure 1) (Thereza et al., 2020). 4.2 Data-driven decision making in pest control Data-driven decision-making is a key benefit of integrating IoT and remote sensing technologies in pest control. The real-time data collected from IoT sensors and remote sensing tools enable farmers to make informed decisions based on current conditions in the field, rather than relying on generalized assumptions or outdated information. This approach allows for predictive pest management, where patterns and trends identified in the data can inform decisions before significant damage occurs. For example, if IoT sensors detect rising temperatures and decreasing humidity, combined with remote sensing data showing changes in leaf color indicative of stress, farmers can preemptively apply treatments or adjust irrigation before pest populations proliferate.
RkJQdWJsaXNoZXIy MjQ4ODYzNA==