New paper ! An active learning cloud detection tool to generate reference cloud masks for Sentinel-2. Application to the validation of MAJA, Sen2cor and FMask cloud masks

Example of reference cloud mask generated by ALCD, and comparison with the cloud masks generated by three operational processors (Sen2cor, FMask and MAJA). True positive invalid pixels appear in blue, true negative in green, false negative in red and false positive in purple..

It is not that frequent when the work of a trainee ends up as a peer reviewed publication, but Louis Baetens was a brilliant trainee. In a six months training period at CESBIO, funded by CNES, here is what Louis Baetens did:

  • developed an active learning method to generate reference cloud masks for Sentinel-2, using multi-temporal data as input
  • validated the quality of the produced masks (around 99% overall accuracy)
  • generated cloud and shadow masks covering 32 entire Sentinel-2 images
  • produced these same scenes with Sen2cor 2.5.5, FMask 4.0 and MAJA 3.3
  • evaluated the results using ALCD masks
  • wrote a report and a user manual for ALCD
  • released the masks and tools on open access platforms
  • And wrote (with Camille and myself) a scientific publication


The publication was just released by remote sensing :

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.


The remaining of the post provides a plain language summary (but it's better to read the paper !)

Continue reading

A pause in MUSCATE production, end of February

The MUSCATE production centre will be offline for a week from February 25th to March 4th (or maybe the week after, please see Theia's RSS feed to see the exact date). This pause will be necessary to upgrade the processing centre to V2.5. As a result, we will not be able, for a week, to process Sentinel-2 data in real time, and hope it will not be too inconvenient to you. In case you need some data urgently, you can ask PEPS to produce MAJA L2A data for you during that period.


The main change regards the internal format used by MUSCATE for Sentinel-2 Level 2A products. This internal format is different from the external format that we distribute, and this results in unnecessary product format conversions, as well as the necessity to develop drivers for the various formats (internal and external) for the processors that use Sentinel-2 L2A data within MUSCATE. To enable this modification, it will be necessary to convert all the L2A data from the internal format to the external format, which will take a whole week.


MUSCATE V2.5 will bring other improvements, such as the integration of MAJA 3.1, with possibility to use Copernicus Atmosphere data, or a new version of LIS, the processor that delivers the snow maps.

MUSCATE  V2.6 is also ready and queuing to be installed, with MAJA 3.2, WASP and the possibility to process Venµs L2A data within MUSCATE and not externally on Venµs ground segent.




Black snow in Prokopyevsk

The snow cover is not always white. Sometimes it is orange, sometimes it is black. The images below were captured by Sentinel-2 in Prokopyevsk, Russia.

According to the Siberian Times the deposition of black dust on snow in February 2019 was due to the failure of a filtering system in a coal processing plant. Looking at the picture below, I have the feeling that this kind of event was not exceptional in Prokopyevsk this winter...

Pictures from Kemerovo region by Orlovprklife, Willravilov, Typical Kemerovo

Source: Siberian Times 15 Feb 2019. Pictures from Kemerovo region by Orlovprklife, Willravilov, Typical Kemerovo

Thanks to François Tuzet for pointing this to me!

Diffusion d'un premier lot des données Sentinel-2A de niveau 2A sur le Sahel

Il y a quelques semaines, nous annoncions la sélection d'une nouvelle zone de production de données Sentinel-2 au niveau 2A par Theia, au Sahel. La production a démarré, et Theia a déjà produit les tuiles de la zone UTM28 (à l'ouest). Les tuiles en vert foncé existaient déjà, mais nous avons rajouté celles en vert clair, qui permettent de couvrir l'ensemble du Sénégal, la Gambie,  une partie de la Guinée Bissau, de la Guinée, et le nord de la Sierra Leone.


Les données disponibles ont été traitées du premier janvier 2017 à hier, soit plus de deux ans de données. Les nouvelles données seront maintenant traitées en temps réel au fur et à mesure de leur arrivée.

Nous procéderons de même avec les différentes zones  de l'ouest vers l'est : UTM29, UTM30...


4 thèses en cours à Toulouse pour étudier les forêts tempérées par télédétection

Le pôle toulousain de recherche publique en télédétection est surtout connu sur la thématique forestière grâce à la mission BIOMASS, qui sera lancée vers 2021 et qui est portée par le CESBio, mais qui concerne surtout les forêts tropicales. L’objectif de cet article est de présenter les travaux en cours sur les forêts tempérées, dans le contexte de la France métropolitaine, qui sont portées en synergie par l’UMR Dynafor (collègues INRA, Ensat et EI Purpan) et par l’UMR CESBio. En effet, 4 thèses sont actuellement en cours dont 2 qui seront soutenues fin 2019. Le point commun à ces 4 thèses comme aux travaux qui les ont précédées est l’utilisation de séries temporelles, d’abord basse résolution (Modis), puis, depuis 2015, en haute résolution spatiale avec Sentinel 1 et 2 (‘S1’ et ‘S2’).


Différence de phenologie entre chênes

Figure 1. Différences de phénologie entre espèces de chênes.

Continue reading

Sentinel-2 + OpenStreetMap = ♡

You may have heard about the tailings dam collapse at Feijão mine in Brumadinho, Brazil. The disaster occurred two days ago on Jan 25 and at least 58 people were found dead, while 300 are still missing. A Sentinel-2 acquisition was planned for today, therefore tonight I checked the EO Browser to see if the mud flow was visible.

Before/after images of Brumadinho mudflow from Sentinel2 imagery (false color composite using the near-infrared band)

Continue reading

Near-real time analysis of the 2018-2019 snow season in the Pyrenees and the Alps from satellite data

Here in southwest France ski lovers did not really enjoy the beginning of the snow season... But how does it compare to the previous years? Using Sentinel-2 and Landsat-8 data, we computed the snow cover duration since September 01 until January 20 for the past three snow seasons in the Alps and Pyrenees.

Snow cover duration (in days) from 01 September of year N-1 to 20 January of year N

Continue reading

Anak Krakatau before and after the December 2018 eruption

Anak Krakatau (Indonesia) erupted on 22 December 2018. During the eruption the collapse of the volcano summit triggered a tsunami in Sunda Strait causing a death toll of 437. The first post-event clear-sky image was finally acquired by Sentinel-2 today on 13 Jan 2019 (after 10 cloudy acquisitions). Here is an image comparison of the Krakatau Island before and after the eruption.

View in full screen

Improvement of water vapour retrieval in MAJA

Similarly to the aerosol retrieval, the retrieval of water vapour in MAJA atmospheric correction has also been improved, thanks to the work of Elsa Bourgeois (Cap Gemini) and Camille Desjardins (CNES). An accurate estimation of water vapour is not necessary to perform an accurate atmospheric correction, because water vapour absorption in most of Sentinel-2 bands is much lower than 5%. But the Sentinel-2 water vapour product could also prove useful, and when we plot validation results, showing a large bias for high water vapour contents is not nice.




Here is the kind of results we have been having with MAJA from the beginning, with a large bias when water vapour content is high :

Our very simple method uses the ratio between Sentinel-2 B9 and B8a bands to estimate the water vapour. B9 is located within a water vapour absorption band at 940 nm, while B8a serves as reference and is only moderately affected by water vapour. The ratio is converted thanks to the use of a Look-up table, which is obtained using radiative transfer calculations. Our method assumes that the water vapour is above the scattering layer, which is obviously not true. The errors due to this assumption increase with the amount of water vapour.


Elsa and Camille just empirically computed a new water vapour LUT to cancel this bias, and it works! As you can see, the RMS errors have been divided by a factor 2, from 0.2 g/cm2 to 0.1 g/cm2.

We will put this new parameter set in production in January within Theia, and make it available to the users of MAJA processor.