Time-series of optical satellite data can be used to map a range of different biophysical parameters, and has been used on Svalbard to map the growing season and plant productivity. Cloud detection is the most crucial step during the pre-processing of time-series of optical satellite images. The last years, machine learning techniques in cloud detection has developed as a new method with promising results. Applying machine learning techniques needs both training and validation samples, and, is to our knowledge, not been used in Arctic areas yet. In this project we explore the use of machine learning methods in cloud detection on Sentinel-2 satellite images covering Adventdalen on Svalbard. These cloud-free time-series will be processed to seasonal maps showing the development of the growing season, by using calibration/validation data established in the area and up-scaled from UAV data. The project supports several SIOS-InfraNor instruments.
Project manager: Stein Rune karlsen
Project code: 962018