Back

Title
  • en Crop classification from Sentinel-2 derived vegetation indices using ensemble learning
Creator
Accessrights open access
Rights
  • en © 2018 Society of Photo-Optical Instrumentation Engineers(SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited., Rei Sonobe, Yuki Yamaya, Hiroshi Tani, Xiufeng Wang, Nobuyuki Kobayashi, Kan-ichiro Mochizuki, “Crop classification from Sentinel-2 derived vegetation indices using ensemble learning,” The Journal of Applied Remote Sensing, 12(2), 026019, (2018); https://doi.org/10.1117/1.JRS.12.026019.
Subject
  • Other en crop
  • Other en random forests
  • Other en Sentinel-2
  • Other en stacking
  • Other en support vector machine
  • Other en vegetation index
  • NDC 614
Description
  • Abstract en The identification and mapping of crops are important for estimating potential harvest as well as for agricultural field management. Optical remote sensing is one of the most attractive options because it offers vegetation indices and some data have been distributed free of charge. Especially, Sentinel-2A, which is equipped with a multispectral sensor (MSI) with blue, green, red and near-infrared-1 bands at 10 m; red edge 1 to 3, near-infrared-2 and shortwave infrared 1 and 2 at 20 m; and 3 atmospheric bands (Band 1, Band 9 and Band 10) at 60 m, offers some vegetation indices calculated to assess vegetation status. However, sufficient consideration has not been given to the potential of vegetation indices calculated from MSI data. Thus, 82 published indices were calculated and their importance were evaluated for classifying crop types. In this study, the two most common classification algorithms, random forests (RF) and support vector machine (SVM), were applied to conduct cropland classification from MSI data. Additionally, super learning was applied for more improvement, achieving overall accuracies of 90.2–92.2%. Of the two algorithms applied (RF and SVM), the accuracy of SVM was superior and 89.3-92.0% of overall accuracies were confirmed. Furthermore, stacking contributed to higher overall accuracies (90.2-92.2%) and significant differences were confirmed with the results of SVM and RF. Our results showed that vegetation indices had the greatest contributions in identifying specific crop types.
Publisher en SPIE
Date
    Issued2018-05-18
Language
  • eng
Resource Type journal article
Version Type AM
Identifier HDL http://hdl.handle.net/2115/71029
Relation
  • isVersionOf DOI https://doi.org/10.1117/1.JRS.12.026019
Journal
  • en The Journal of Applied Remote Sensing
  • Volume Number12 Issue Number2 Page Start026019
File
Oaidate 2023-07-26