Selection of soybean resistant to the stink bug complex using phenomics and machine learning

• Grant number: 25/22165-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2025
• End date: October 31, 2026
• Field of knowledge: Agronomical Sciences - Agronomy - Crop Science
• Principal Investigator: José Baldin Pinheiro
• Grantee: Marina Ferreira
• Host Institution: Escola Superior de Agricultura Luiz de Queiroz (ESALQ). Universidade de São Paulo (USP). Piracicaba , SP, Brazil
• Associated research grant: 24/15430-5 - Machine learning-based multi-modal data fusion and growth modeling for soybean production improvement, AP.PFPMCG.TEM

Abstract

Soybeans are a species of strategic importance in Brazil, being the most economically important crop in the country. The stink bug complex stands out among the primary pests that attack crops, causing significant reductions in grain production and seed quality. The most efficient strategy to overcome the problem is to obtain resistant cultivars, and high-precision phenotyping has shown promising results for this purpose. Therefore, the present study aims to develop a high-precision phenotyping platform for identifying superior lines, taking into account the response to infestation by the soybean stink bug complex and the crop cycle. The Soybean Breeding Programme at the Genetic Diversity and Breeding Laboratory of the Luiz de Queiroz School of Agriculture (ESALQ/USP) generated the first dataset, comprising 290 soybean lines and 14 cultivars. These lines originate from synthetic populations created by crossing commercial cultivars BRS-133, CD-215, Conquista, Dowling, IAC-100 and Pintado with other genotypes that carry resistance to Asian soybean rust. The sources of resistance comprise introduced plants (PI): PI 200487 (Kinoshita), PI 471904 (Orba), and PI 200526 (Shiranui), which carry the Rpp5 gene; and PI 459025 (Bing Nan), which carries the Rpp4 gene. Four crops were evaluated in different years (see Table 1). This encompassed the assessment of the number of days to maturity (NDM), Leaf retention (LR), Grain Yield (GY), and Healthy seed weight (HSW). The developed platform can be utilized in genetic improvement programs targeting early selection for strains resistant to the soybean stink bug complex. In addition, applying prediction models to soybean crops can help define effective real-time pest control strategies, leading to the rational application of inputs and a reduction in environmental and crop production costs.