Evaluation of high-throughput drone phenotyping for vegetative development and yield characters in soybean cultivars, with and without foliar fertilizer application

• Grant number: 22/02526-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2022
• End date: May 31, 2024
• Field of knowledge: Agronomical Sciences - Agronomy - Crop Science
• Principal Investigator: Rafael Simões Tomaz
• Grantee: João Vitor Braga Visioli
• Host Institution: Faculdade de Ciências Agrárias e Tecnológicas. Universidade Estadual Paulista (UNESP). Campus de Dracena. Dracena , SP, Brazil

Abstract

Soybean (Glycine Max (L.) Merrill) is the main leguminous crop in the world, with the USA, Brazil, and Argentina being the main producers. The use of soybean in human and animal diets in several countries stems from its nutritional value, mainly for its high protein content, of about 40%. In Brazil, much of the success of the crop stems from the use of improved varieties, better adapted to the soil and climate conditions of the region, and improvements in the production system. The use of technologies such as foliar fertilizers based on cobalt and molybdenum, coupled with the most current analysis technologies such as high-yield phenotyping using drones, and the use of artificial intelligence in data analysis has allowed an increase in crop productivity in recent years. In order to evaluate the factors mentioned above in the development of soybean yields, an experiment will be conducted in a randomized block design, with three repetitions, in a 4x2 factorial scheme, considering four varieties and two levels of treatment with foliar fertilizer. The experiment will be implemented in the irrigated experimental area of FCAT UNESP - Dracena Campus. Agronomic characteristics of crop development and product attributes will be evaluated. Additionally, high yield phenotyping will be performed with a Phanton 4 Pro V2.0 drone. Periodic flights will be conducted in the crop in order to collect images and make the association these with the agronomic characteristics measured, using the method of Artificial Intelligence (Artificial Neural Networks). We hope, with the execution of this experiment, to analyze the behavior of the varieties under the conditions evaluated, providing knowledge to the scientific community as well as the popularization of the proposed methodologies, in order to allow the use of such technologies in a conscious and sustainable way.(AU)