Next Article in Journal
Lidar Studies of Wind Turbulence in the Stable Atmospheric Boundary Layer
Next Article in Special Issue
Assessing the Variability of Corn and Soybean Yields in Central Iowa Using High Spatiotemporal Resolution Multi-Satellite Imagery
Previous Article in Journal
UAV Multispectral Imagery Can Complement Satellite Data for Monitoring Forest Health
Previous Article in Special Issue
Fusion of Moderate Resolution Earth Observations for Operational Crop Type Mapping
Open AccessArticle

Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France

1
UMR TETIS, IRSTEA, University of Montpellier, 34093 Montpellier, France
2
UMR 1114 EMMAH, INRA, University of Avignon, 84914 Avignon, France
3
UMR 0951 INNOVATION, INRA, University of Montpellier, 34060 Montpellier, France
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(8), 1217; https://doi.org/10.3390/rs10081217
Received: 5 July 2018 / Revised: 30 July 2018 / Accepted: 1 August 2018 / Published: 3 August 2018
(This article belongs to the Special Issue High Resolution Image Time Series for Novel Agricultural Applications)
  |  
PDF [3723 KB, uploaded 3 August 2018]
  |  

Abstract

The development and improvement of methods to map agricultural land cover are currently major challenges, especially for radar images. This is due to the speckle noise nature of radar, leading to a less intensive use of radar rather than optical images. The European Space Agency Sentinel-1 constellation, which recently became operational, is a satellite system providing global coverage of Synthetic Aperture Radar (SAR) with a 6-days revisit period at a high spatial resolution of about 20 m. These data are valuable, as they provide spatial information on agricultural crops. The aim of this paper is to provide a better understanding of the capabilities of Sentinel-1 radar images for agricultural land cover mapping through the use of deep learning techniques. The analysis is carried out on multitemporal Sentinel-1 data over an area in Camargue, France. The data set was processed in order to produce an intensity radar data stack from May 2017 to September 2017. We improved this radar time series dataset by exploiting temporal filtering to reduce noise, while retaining as much as possible the fine structures present in the images. We revealed that even with classical machine learning approaches (K nearest neighbors, random forest, and support vector machines), good performance classification could be achieved with F-measure/Accuracy greater than 86% and Kappa coefficient better than 0.82. We found that the results of the two deep recurrent neural network (RNN)-based classifiers clearly outperformed the classical approaches. Finally, our analyses of the Camargue area results show that the same performance was obtained with two different RNN-based classifiers on the Rice class, which is the most dominant crop of this region, with a F-measure metric of 96%. These results thus highlight that in the near future these RNN-based techniques will play an important role in the analysis of remote sensing time series. View Full-Text
Keywords: SAR; Sentinel-1; agricultural land cover map; recurrent neural network; long-short term memory; gated recurrent unit; K nearest neighbors; random forest; vector support machines; Camargue; France SAR; Sentinel-1; agricultural land cover map; recurrent neural network; long-short term memory; gated recurrent unit; K nearest neighbors; random forest; vector support machines; Camargue; France
Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Ndikumana, E.; Ho Tong Minh, D.; Baghdadi, N.; Courault, D.; Hossard, L. Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France. Remote Sens. 2018, 10, 1217.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top