Monitoring soybean pests using remote sensing

• Ano de defesa: 2023
• Autor(a) principal: Iost Filho, Fernando Henrique
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Biblioteca Digitais de Teses e Dissertações da USP
• Palavras-chave em Português: Glycine max; Amostragem; Caterpillars; Integrated Pest Management; Lagartas; Manejo Integrado de Pragas; Percevejos; Sampling; Stink bugs
• Link de acesso: https://www.teses.usp.br/teses/disponiveis/11/11146/tde-23032023-155535/

Arthropod pests are among the major problems in soybean production, and regular field sampling is required as a basis for decision-making. However, traditional sampling methods are laborious and time-consuming. Therefore, our first goal was to evaluate hyperspectral remote sensing as a tool to establish reflectance patterns from soybean plants infested by various densities of two species of stinkbugs [Euschistus heros and Diceraeus melacanthus (Hemiptera: Pentatomidae)], and two species of caterpillars [Spodoptera eridania and Chrysodeixis includens (Lepidoptera: Noctuidae)]. Bioassays were carried out in greenhouses with potted plants placed in cages with 5 plants infested with 0, 2, 5 and 10 insects. Plants were classified according to their reflectance, based on acquiring spectral data before and after infestation, using a hyperspectral push-broom spectral camera (Resonon Pika L, that works in the region 400-1000 nm). Infestation by stinkbugs did not cause significant differences in the reflectance patterns of infested or non-infested plants. In contrast, caterpillars caused changes in the reflectance patterns, which were classified using a deep-learning approach based on multilayer perceptron artificial neural network. High accuracies (> 70%) were achieved when the models classified low (0+2) or high (5+10) infestation and presence or absence of insects. This study provides an initial assessment to apply a non-invasive detection method to monitor caterpillars in soybean before causing economic damage. Future studies should be carried out under field conditions, using other sensors, such as multispectral cameras to automatize the detection of pest problems in the field. Such digital tools, among others, are shaping the new way to perform agriculture, where decisions are based on data and, therefore, are more precise. Regarding pest management, these new technologies offer growers the possibility of identifying problems at early stages and providing localized solutions. While the traditional Integrated Pest Management (IPM) approach suggests that control solutions should be delivered throughout the whole field, new approaches involving digital technologies will need to consider adaptations in the concepts of economic thresholds, sampling, population forecast, injury identification, and ultimately the localized use of control tactics. Therefore, our second goal was to review how the traditional IPM concepts could be adapted, considering this ongoing digital transformation in agriculture.