Remote sensing techniques for monitoring arthropod pests in agricultural fields

• Grant number: 17/19407-4
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• Start date: April 01, 2019
• End date: March 31, 2021
• Field of knowledge: Agronomical Sciences - Agronomy - Plant Health
• Agreement: IBM Brasil
• Principal Investigator: Pedro Takao Yamamoto
• Grantee: Pedro Takao Yamamoto
• Host Institution: Escola Superior de Agricultura Luiz de Queiroz (ESALQ). Universidade de São Paulo (USP). Piracicaba , SP, Brazil
• Company: IBM Brasil - Indústria, Máquinas e Serviços Ltda
• City: Piracicaba
• Associated researchers: David Luciano Rosalen ; Fernando Henrique Iost Filho

Abstract

Outbreaks of many arthropod pests are not uniformly distributed within fields, and the timing of pest outbreaks is also unpredictable. Moreover, effective pest management relies heavily on early-detection, allowing the growers to make decisions before pests are well-established and crop losses amount. Crop monitoring procedures, to detect emerging pest outbreaks, are time-consuming, practically challenging, and in some cropping systems, effective scouting is hampered by lack of reliable pest sampling techniques. Biotic stress, such as, herbivory by arthropod pests elicits physiological defense responses in plants, which leads to changes in leaf reflectance. Advanced imaging technologies can be used to detect such reflectance changes in crops, and therefore be used as a non-invasive crop monitoring method. Our main objective is to describe reflectance patterns from agricultural plants stressed by arthropod infestation. The first models to be used will be the white fly, Bemisia tabaci (Gennadius, 1889) (Hemiptera: Aleyrodidae) infesting soybean plants and the spider mite, Tetranychus urticae (Koch, 1836) (Acari: Tetranychidae). Different remote sensing tools will be used and compared, such as aerial multispectral sensors, orbital multispectral sensors and ground multi and hyperspectral sensors. The method will be considered successful if it allows us to identify canopy reflectance patterns in plants infested by arthropods, both in field and semi-field conditions. Also, different approaches to process the data collected will be tested, aiming at finding less complex and more reliable methods. Reflectance data will always be correlated with the number of insects sampled and collected in loco, in order to have robust data representing real infestations. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

IOST FILHO, FERNANDO HENRIQUE; PAZINI, JULIANO DE BASTOS; DE MEDEIROS, ANDRE DANTAS; ROSALEN, DAVID LUCIANO; YAMAMOTO, PEDRO TAKAO. Assessment of Injury by Four Major Pests in Soybean Plants Using Hyperspectral Proximal Imaging. AGRONOMY-BASEL, v. 12, n. 7, p. 20-pg., 2022-07-01. (19/26099-0, 18/02317-5, 17/19407-4, 19/26145-1)

BARROS, PEDRO P. S.; SCHUTZE, INANA X.; IOST FILHO, FERNANDO H.; YAMAMOTO, PEDRO T.; FIORIO, PETERSON R.; DEMATTE, JOSE A. M.. Monitoring Bemisia tabaci (Gennadius) (Hemiptera: Aleyrodidae) Infestation in Soybean by Proximal Sensing. INSECTS, v. 12, n. 1, JAN 2021. (17/19407-4, 19/26145-1, 13/22435-9)

YASSUE, RAFAEL MASSAHIRO; GALLI, GIOVANNI; FRITSCHE-NETO, ROBERTO; MOROTA, GOTA. Classification of plant growth-promoting bacteria inoculation status and prediction of growth-related traits in tropical maize using hyperspectral image and genomic data. CROP SCIENCE, v. 63, n. 1, p. 13-pg., 2022-11-29. (17/19407-4, 17/24327-0, 19/04697-2)