Mapping maize cropping patterns in Dak Lak, Vietnam through MODIS EVI time series

Thi Thu Ha Nguyen* (Corresponding Author), Loc Van Nguyen, C.A.J.M. de Bie, Ignacio Ciampitti, Doc Anh Nguyen, Minh Van Nguyen, Rai Schwalbert, Long Viet Nguyen

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

23 Downloads (Pure)

Abstract

Land use maps specifying up-to-date acreage information on maize (Zea mays L.) cropping patterns are required by many stakeholders in Vietnam. Government statistics, however, lag behind by one year, and the official land use maps are only updated at 5-year intervals. The aim of this study was to apply the Savitzky–Golay algorithm to reconstruct noisy Enhanced Vegetation Index (EVI) time series (2003–2018) from Terra Moderate Resolution Imaging Spectroradiometer (MODIS)
Vegetation Indices (MOD13Q1) to allow timely detection of changes in maize crop phenology, and then to employ a linear kernel Support Vector Machine (SVM) classifier on the reconstructed EVI time series to prepare the present-day maize cropping pattern map of Dak Lak province of Vietnam. The method was able to specify the spatial extent of areas cropped to maize with an overall map accuracy of 79% and could also differentiate the areas cropped to maize just once versus twice annually. The by-district mapped maize acreage shows a good agreement with the official governmental data, with a 0.93 correlation coefficient (r) and a root mean square deviation (RMSD) of 1624 ha.
Original languageEnglish
Article number 478
Pages (from-to)1-16
Number of pages16
JournalAgronomy
Volume10
Issue number4
DOIs
Publication statusPublished - 1 Apr 2020

Keywords

  • maize
  • cropping pattern
  • MODIS MOD13Q1
  • EVI
  • Savitzky-Golay
  • SVM classifier
  • ITC-ISI-JOURNAL-ARTICLE
  • ITC-GOLD

Fingerprint Dive into the research topics of 'Mapping maize cropping patterns in Dak Lak, Vietnam through MODIS EVI time series'. Together they form a unique fingerprint.

Cite this