Crop classification from Sentinel-2-derived vegetation indices using ensemble learning

Rei Sonobe; Yuki Yamaya; Hiroshi Tani; Xiufeng Wang; Nobuyuki Kobayashi; Kan-ichiro Mochizuki

doi:10.1117/1.JRS.12.026019

18 May 2018 Crop classification from Sentinel-2-derived vegetation indices using ensemble learning

Rei Sonobe, Yuki Yamaya, Hiroshi Tani, Xiufeng Wang, Nobuyuki Kobayashi, Kan-ichiro Mochizuki

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 12, Issue 2, 026019 (May 2018). https://doi.org/10.1117/1.JRS.12.026019

Abstract

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, offer 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. 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% to 92.2%. Of the two algorithms applied (RF and SVM), the accuracy of SVM was superior and 89.3% to 92.0% of overall accuracies were confirmed. Furthermore, stacking contributed to higher overall accuracies (90.2% to 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.

Citation Download Citation

Rei Sonobe, Yuki Yamaya, Hiroshi Tani, Xiufeng Wang, Nobuyuki Kobayashi, and Kan-ichiro Mochizuki "Crop classification from Sentinel-2-derived vegetation indices using ensemble learning," Journal of Applied Remote Sensing 12(2), 026019 (18 May 2018). https://doi.org/10.1117/1.JRS.12.026019

Received: 12 February 2018; Accepted: 7 May 2018; Published: 18 May 2018

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
16 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

CITATIONS

Cited by 116 scholarly publications.

Explore citations on Lens.org

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Vegetation

Reflectivity

Multispectral imaging

Data modeling

Agriculture

Machine learning

Short wave infrared radiation

Show All Keywords

RELATED CONTENT

The responses of vegetation water content (EWT) along a coastal...
Proceedings of SPIE (October 08 2014)

Estimation of chlorophyll content in radish leaves using hyperspectral remote...
Proceedings of SPIE (September 12 2021)

Application of MODIS-derived parameters for regional yield assessment
Proceedings of SPIE (January 28 2002)

Spatial distribution of soil water content from airborne thermal and...
Proceedings of SPIE (September 18 2009)

Prediction of winter wheat grain protein content by ASTER image
Proceedings of SPIE (October 02 2008)

A critical analysis of three remote sensing based actual evapotranspiration...
Proceedings of SPIE (October 22 2010)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years