Author(s): Luciano, Ana Claudia dos Santos, 1989- ; Rocha, Jansle Vieira, 1961- ; Lamparelli, Rubens Augusto Camargo, 1955- ; Leal, Manoel Regis Lima Verde ; Le Maire, Guerric Beaudouin Cathel Marie, 1979-
Date: 2019
Persistent ID: https://hdl.handle.net/20.500.12733/1650801
Origin: Oasisbr
Subject(s): Cana-de-açúcar; Mineração de dados (Computação); Aprendizado de máquina; Data mining; Machine learning; Sugarcane; Classifier extension; Artigo original
Agradecimentos: This work was supported by the Brazilian Bioethanol Science and Technology Laboratory/United Nations Development Program (CTBE/UNDP)-funded "Sugarcane Renewable Electricity (SUCRE)" project BRA/10/G31; the Brazilian Research Council, CNPq (grant number 454292/2014-7); the Brazilian Coordination for the Improvement of Higher Education Personnel, CAPES (grant number 88882.143488/2017-01); the Microsoft Research–São Paulo Research Foundation (FAPESP) Institute-funded project "Characterizing and Predicting Biomass Production in Sugarcane and Eucalyptus Plantations in Brazil" (grant number 2014/50715-9); the French Space Agency (CNES) TOSCA Program-funded CESOSO project; and the SIGMA European Collaborative Project FP7-ENV-2013 SIGMA, "Stimulating Innovation for Global Monitoring of Agriculture and its Impact on the Environment" in support of the GEOGLAM Project 603719. The authors gratefully acknowledge all the agencies mentioned above that helped to fund this project, and also thank NASA for sharing the Landsat data
Abstract: The monitoring of sugarcane areas is important for sustainable planning and management of the sugarcane industry in Brazil. We developed an operational Object-Based Image Analysis (OBIA) classification scheme, with generalized space-time classifier, for mapping sugarcane areas at the regional scale in São Paulo State (SP). Binary random forest (RF) classification models were calibrated using multi-temporal data from Landsat images, at 10 sites located across SP. Space and time generalization were tested and compared for three approaches: a local calibration and application; a cross-site spatial generalization test with the RF model calibrated on a site and applied on other sites; and a unique space–time classifier calibrated with all sites together on years 2009-2014 and applied to the entire SP region on 2015. The local RF models Dice Coefficient (DC) accuracies at sites 1 to 8 were between 0.83 and 0.92 with an average of 0.89. The cross-site classification accuracy showed an average DC of 0.85, and the unique RF model had a DC of 0.89 when compared with a reference map of 2015. The results demonstrated a good relationship between sugarcane prediction and the reference map for each municipality in SP, with R² = 0.99 and only 5.8% error for the total sugarcane area in SP, and compared with the area inventory from the Brazilian Institute of Geography and Statistics, with R² = 0.95 and -1% error for the total sugarcane area in SP. The final unique RF model allowed monitoring sugarcane plantations at the regional scale on independent year, with efficiency, low-cost, limited resources and a precision approximating that of a photointerpretation
CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQ
COORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPES
FUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULO - FAPESP
Fechado
