Next Article in Journal
Relation between Changes in Photosynthetic Rate and Changes in Canopy Level Chlorophyll Fluorescence Generated by Light Excitation of Different Led Colours in Various Background Light
Previous Article in Journal
Statistical Characteristics of Raindrop Size Distribution in the Monsoon Season Observed in Southern China
Previous Article in Special Issue
Assessment of Sentinel-2 MSI Spectral Band Reflectances for Estimating Fractional Vegetation Cover
Article Menu
Issue 4 (February-2) cover image

Export Article

Open AccessArticle
Remote Sens. 2019, 11(4), 433; https://doi.org/10.3390/rs11040433

Validation of Copernicus Sentinel-2 Cloud Masks Obtained from MAJA, Sen2Cor, and FMask Processors Using Reference Cloud Masks Generated with a Supervised Active Learning Procedure

1
CESBIO, Université de Toulouse, CNES-CNRS-INRA-IRD-UPS, 18 avenue E.Belin, 31401 Toulouse CEDEX 9, France
2
Centre National d’Etudes Spatiales, 18 avenue E.Belin, 31401 Toulouse Cedex 9, France
*
Author to whom correspondence should be addressed.
Received: 1 February 2019 / Accepted: 16 February 2019 / Published: 20 February 2019
(This article belongs to the Collection Sentinel-2: Science and Applications)
  |  
PDF [11056 KB, uploaded 20 February 2019]
  |  

Abstract

The Sentinel-2 satellite mission, developed by the European Space Agency (ESA) for the Copernicus program of the European Union, provides repetitive multi-spectral observations of all Earth land surfaces at a high resolution. The Level 2A product is a basic product requested by many Sentinel-2 users: it provides surface reflectance after atmospheric correction, with a cloud and cloud shadow mask. The cloud/shadow mask is a key element to enable an automatic processing of Sentinel-2 data, and therefore, its performances must be accurately validated. To validate the Sentinel-2 operational Level 2A cloud mask, a software program named Active Learning Cloud Detection (ALCD) was developed, to produce reference cloud masks. Active learning methods allow reducing the number of necessary training samples by iteratively selecting them where the confidence of the classifier is low in the previous iterations. The ALCD method was designed to minimize human operator time thanks to a manually-supervised active learning method. The trained classifier uses a combination of spectral and multi-temporal information as input features and produces fully-classified images. The ALCD method was validated using visual criteria, consistency checks, and compared to another manually-generated cloud masks, with an overall accuracy above 98%. ALCD was used to create 32 reference cloud masks, on 10 different sites, with different seasons and cloud cover types. These masks were used to validate the cloud and shadow masks produced by three Sentinel-2 Level 2A processors: MAJA, used by the French Space Agency (CNES) to deliver Level 2A products, Sen2Cor, used by the European Space Agency (ESA), and FMask, used by the United States Geological Survey (USGS). The results show that MAJA and FMask perform similarly, with an overall accuracy around 90% (91% for MAJA, 90% for FMask), while Sen2Cor’s overall accuracy is 84%. The reference cloud masks, as well as the ALCD software used to generate them are made available to the Sentinel-2 user community. View Full-Text
Keywords: Sentinel-2; cloud mask; cloud shadow; validation; active learning; MAJA; Sen2Cor; FMask Sentinel-2; cloud mask; cloud shadow; validation; active learning; MAJA; Sen2Cor; FMask
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).

Supplementary material

SciFeed

Share & Cite This Article

MDPI and ACS Style

Baetens, L.; Desjardins, C.; Hagolle, O. Validation of Copernicus Sentinel-2 Cloud Masks Obtained from MAJA, Sen2Cor, and FMask Processors Using Reference Cloud Masks Generated with a Supervised Active Learning Procedure. Remote Sens. 2019, 11, 433.

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