International journal of applied earth observation and geoinformation2019，Vol.8010.DOI:10.1016/j.jag.2019.04.013

A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm

dos Santos Luciano, Ana Claudia Araujo Picoli, Michelle Cristina Rocha, Jansle Vieira Camargo Lamparelli, Rubens Augusto Lima Verde Leal, Manoel Regis Le Maire, Guerric Duft, Daniel Garbellini
International journal of applied earth observation and geoinformation2019，Vol.8010.DOI:10.1016/j.jag.2019.04.013
✕
  • NSTL
  • Elsevier

A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm

dos Santos Luciano, Ana Claudia 1Araujo Picoli, Michelle Cristina 2Rocha, Jansle Vieira 3Camargo Lamparelli, Rubens Augusto 4Lima Verde Leal, Manoel Regis 1Le Maire, Guerric 1Duft, Daniel Garbellini1
扫码查看

作者信息

  • 1. Brazilian Ctr Res Energy & Mat CNPEM, Brazilian Bioethanol Sci & Technol Lab CTBE, BR-13083970 Campinas, SP, Brazil
  • 2. Natl Inst Space Res INPE, BR-12227010 Sao Jose Dos Campos, Brazil
  • 3. Univ Estadual Campinas, UNICAMP, Fac Agr Engn FEAGRI, BR-13083875 Campinas, SP, Brazil
  • 4. Univ Estadual Campinas, Interdisciplinary Ctr Energy Planning NIPE, BR-13083896 Campinas, SP, Brazil
  • 折叠

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 Sao 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 R-2 = 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 R-2 = 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.

Key words

Classifier extension/Data mining/Machine learning/Sugarcane mapping

引用本文复制引用

出版年

2019
International journal of applied earth observation and geoinformation

International journal of applied earth observation and geoinformation

SCI
ISSN：0303-2434
被引量12
参考文献量53
段落导航相关论文