Assessment of Cloud Cover in Sentinel-2 Data Using Random Forest Classifier

Nevavuori, Petteri; Lipping, Tarmo; Narra Girish, Nathaniel; Linna, Petri (2020)
 
Avaa tiedosto
Lataukset: 



Nevavuori, Petteri
Lipping, Tarmo
Narra Girish, Nathaniel
Linna, Petri
2020

This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
doi:10.1109/IGARSS39084.2020.9323683
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202205034255

Kuvaus

Peer reviewed
Tiivistelmä
In this paper, a novel cloud coverage assessment method for the Sentinel-2 data is presented. The method is based on the Random Forest classifier and the target values used in the training process are obtained by comparing the NDVI indexes calculated from the satellite and the UAV data. The developed method is shown to outperform the Sentinel Cloud Probability Mask (CLDPRB) and Scene Classification (SCL) data layers in detecting cloudy areas.
Kokoelmat