Identification of soybean and corn crops in the Brazilian Cerrado via satellite images

• Grant number: 24/08083-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2024
• Status: Discontinued
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Michel Eustáquio Dantas Chaves
• Grantee: Livia Gabriele Dias Soares
• Host Institution: Faculdade de Ciências e Engenharia. Universidade Estadual Paulista (UNESP). Campus de Tupã. Tupã , SP, Brazil
• Associated scholarship(s): 25/00099-4 - Improvement of phenological metrics and computational application to identify soybean and corn in the Cerrado biome, BE.EP.IC

Abstract

Crop production estimates based on interviews and questionnaires applied to rural producers cause uncertainties that compromise food security. Therefore, improving accuracy is essential. Remote sensing techniques, for example, make it possible to monitor the phenological development of crops via satellite images. Currently, space agencies allow free access and use of image collections from space missions, such as Landsat, from the National Aeronautics and Space Administration (NASA). Such collections allow for the monitoring of different surface targets as long as interpretation keys related to the identification of each agricultural target are applied based on inherent characteristics, such as shape, spectrality, and phenological cycle. The present proposal aims to integrate time series of Landsat 8/Operational Land Imager (OLI) images, field data, agricultural calendars, and Machine Learning algorithms to identify soybean and corn crops in the Cerrado biome. To this end, we will use the Google Earth Engine (GEE) cloud computing platform, which has tools for such integration and allows the creation of banks of representative samples and maps derived from agricultural monitoring. We will assess the 2020/2021, 2021/2022 and 2022/2023 harvests. As a result, we seek to generate sample banks for the biome and increase the assertiveness of classification methods, which aligns with Sustainable Development Goals (SDGs) 2, 12, 13, and 15, entitled "Zero Hunger and Sustainable Agriculture ", "Responsible Consumption and Production", "Combating climate change" and "Life on Earth", respectively.

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)

CHAVES, MICHEL E. D.; SOARES, LIVIA G. D.; BARROS, GUSTAVO H. V.; PESSOA, ANA LETICIA F.; ELIAS, RONALDO O.; GOLZIO, ANA CLAUDIA; CONCEICAO, KATYANNE V.; MORAIS, FLAVIO J. O.. Mixing Data Cube Architecture and Geo-Object-Oriented Time Series Segmentation for Mapping Heterogeneous Landscapes. AGRIENGINEERING, v. 7, n. 1, p. 15-pg., 2025-01-01. (21/07382-2, 23/09903-5, 24/08083-7)