Analysis of digital land use classifications using multisensor data and organization of geospatial databases

• Grant number: 26/14882-5
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: August 01, 2026
• End date: July 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Édson Luis Bolfe
• Grantee: Diogo Olivetti
• Host Institution: Embrapa Agricultura Digital. Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA). Campinas , SP, Brazil
• Associated research grant: 22/09319-9 - Center of Science for Development in Digital Agriculture - CCD-AD/SemeAr, AP.CCD

Abstract

Different agricultural mapping initiatives have been carried out to support rural planning and crop prediction. However, due to the complexity and large scale of Brazilian agriculture, there is a need for methods with greater detail, frequency, and accuracy to distinguish agricultural crops, fruit production, pasturelands, and forestry. The increase in the spatial, temporal, and spectral resolution of satellite images, together with greater computing power for processing large amounts of data and advances in artificial intelligence, especially machine learning algorithms, has boosted research in agricultural remote sensing focused on classification, monitoring, and management. With this postdoctoral fellowship, the objective is to analyze the accuracy of different machine learning algorithms in the digital classification of data obtained from the individual and/or combined use of multi-sensor images, as well as to organize a geospatial database for the regions of the Agrotechnological Districts (DATs) defined by the Center for Science for Development in Digital Agriculture (CCD-AD/SemeAr Digital). The expected results include the development of new methodologies for agricultural monitoring, the publication of scientific papers, and the strengthening of postgraduate-level human resource training. (AU)