Smart Cloud Mask (SCM) is a cloud and surface classification algorithm designed to perform reliable scene identification over various types of sub-surfaces such as snow, sea ice, bare land, vegetation and ocean. The core of SCM is a threshold-free machine learning based classifier trained exclusively by extensive radiative transfer simulations. SCM is designed for easy adoption to different satellite sensors. The SCM code will be made available in the near future, so please stay tuned.
The development of the SCM algorithms is described in two key papers:
Chen N., W. Li, C. Gatebe, T. Tanikawa, M. Hori, R. Shimada; T. Aoki, and K. Stamnes, New cloud mask algorithm based on machine learning methods and radiative transfer simulations, Remote Sensing of the Environment, 219, 62-71, 2018.
Chen, N., W. Li, T. Tanikawa, M. Hori, T. Aoki, and K. Stamnes, Cloud mask over snow/ice covered areas for the GCOM-C1/SGLI cryosphere mission: Validations over Greenland, J. Geophys. Res. Atmos., 119, 12,287-12,300, 2014. doi: 10.1002/2014JD022017.
Currently SCM supports the following satellite instruments:
MODIS
VIIRS
GCOM-C/SGLI
GOCI