Métodos de determinaçao de zonas de manejo a partir de dados de produtividade de milho

Abstract

Precision agriculture, which uses a modern approach to farm management, aims to optimize the use of inputs and maximize productivity while respecting spatial variations within an agricultural field. The identification and delimitation of management zones are crucial steps in this process, allowing for a differentiated application of inputs based on the specific needs of each zone. Thus, the objective of this study was to evaluate the data from the grain harvester's productivity monitor and methods for generating management zones from three corn harvests, referring to the years 2019, 2020 and 2021. For this work, productivity data obtained from sensors present in the harvester on a commercial property were used. The data were subjected to a process of filtering, statistical and geospatial analysis to identify patterns and variations within the cultivation areas. The methodology used in the generation of management zones included weighting techniques and the application of clustering algorithms for zone segmentation. The use of the method of normalization of productivity by average can be used to generate management zones, as long as it is with more restrictive ranges, such as low productivity less than 95% and high productivity greater than 105%. The use of MZA software and the Smart-Map add-on of QGIS are an option for generating management zones and present similar results. The generation of management zones from productivity data is a valuable strategy for precision agriculture, providing an increase in the efficiency of resource use and contributing to more efficient decision-making.