SkillAgentSearch skills...

ALCD

The Active Learning for Cloud Detection (ALCD) software enables to generate reference cloud masks which may be used to validate operational cloud masks, such as those generated by MAJA. The reference cloud masks are generated interactively using an iterative active learning procedure which enables to generate an accurate reference cloud mask in less than two hours. ALCD works on linux systems and relyes on the OTB library. It also requires a GIS software such as QGIS. The tool was written by Louis Baetens during a training period at CESBIO, funded by CNES, under supervision of Olivier Hagolle.

Install / Use

/learn @CNES/ALCD
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

ALCD

<img title="ALCD Cloud mask mosaic" src="http://www.cesbio.ups-tlse.fr/multitemp/wp-content/uploads/2019/02/mosaique.jpg" width="300" /> The Active Learning for Cloud Detection (ALCD) software enables to generate reference cloud masks which may be used to validate operational cloud masks, such as those generated by MAJA. The reference cloud masks are generated interactively using an iterative active learning procedure which enables to generate an accurate reference cloud mask in less than two hours.

The tool was written by Louis Baetens during a training period at CESBIO, funded by CNES, under supervision of Olivier Hagolle. The tool led to a publication which is provided as a reference.

ALCD is written in python. To run ALCD, you will need to install the Orfeo Toolbox and the selection of samples relies on QGIS. A detailed user manual for ALCD is available.

Reference : 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.

Related Skills

View on GitHub
GitHub Stars20
CategoryEducation
Updated2mo ago
Forks10

Languages

Python

Security Score

90/100

Audited on Jan 19, 2026

No findings