%0 Conference Proceedings
%4 sid.inpe.br/marte2/2023/04.19.12.10
%2 sid.inpe.br/marte2/2023/04.19.12.10.58
%@isbn 978-65-89159-04-9
%T Nitrogen recommendation based on machine learning approach and active remote sensing
%D 2023
%A Carneiro, Franciele Morlin,
%A Brito Filho, Armando Lopes de,
%A Martins, Murilo de Santana,
%A Brandão, Ziany Neiva,
%A Shiratsuchi, Luciano Shozo,
%@affiliation Universidade Tecnológica Federal do Paraná (UTFPR)
%@affiliation Universidade Estadual Paulista (UNESP)
%@affiliation Louisiana State University (LSU)
%@affiliation Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA)
%@affiliation Louisiana State University (LSU)
%@electronicmailaddress fmcarneiro@utfpr.edu.br
%@electronicmailaddress armando.brito@unesp.br
%@electronicmailaddress
%@electronicmailaddress ziany.brandao@embrapa.br
%@electronicmailaddress lshiratsuchi@agcenter.lsu.edu
%E Gherardi, Douglas Francisco Marcolino,
%E Aragão, Luiz Eduardo Oliveira e Cruz de,
%E Sanches, Ieda DelArco,
%B Simpósio Brasileiro de Sensoriamento Remoto, 20 (SBSR)
%C Florianópolis
%8 02-05 abril 2023
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P e156257
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%K active sensor, Random Forest, remote sensing, corn, yield estimate.
%X Nitrogen (N) fertilizer recommendation tools are vital to precise agricultural management. The objectives of this research were to determine how many variables and remote sensor data are needed to prescribe N fertilizer in corn, PFP (partial factor productivity), and yield integrating remote sensing and soil sensor technologies. The variables of this work were NIR, Red, Red Edge wavelengths, plant height, canopy temperature, LAI, and apparent soil electrical. Random Forest Classifier was used to select the best input to estimate N rates, PFP, and corn yield. A confusion matrix was used to identify the accuracy of the Random Forest Classifier to detect the best inputs to estimate for which input we evaluated in this work. According to Random Forest, the best inputs to estimate the N rate and PFP were red edge, red, and nir wavelengths, plant height, and canopy temperature. For estimate corn yield were: nir wavelengths, N rates, plant height, red edge, and canopy temperature.
%9 Sistemas sensores: projeto, calibração e avaliação
%@language en
%3 156257.pdf