Evaluation of Cloud Masking Methods using Sentinel-2 Satellite Images on Google Earth Engine: A Case Study in Vietnam

Abstract

The production of cloudless images from the optical satellite are critical in Earth surface monitoring. In 2015,
Sentinel-2A was successfully launched into orbit by the European Space Agency. Sentinel-2 imagery is currently the
primary source of data for Earth monitoring. There are several ways to create cloudless images from multi-temporal
Sentinel-2 optical satellite imagery on the Google Earth Engine (GEE) platform. These include the Fmask (Function of
mask) method, the Fmask CDI (Cloud Displacement Index) method, and the Fmask CSP (Cloud Score Plus) method. In
this paper, the authors build a program and evaluate the cloud masking methods on the GEE platform in Song Hinh
district, Phu Yen province, which is situated in the South-Central Coast region of Central Vietnam. The Song Hinh district
is a suitable study area for the evaluation of cloud masking methods on optical satellite images due to its diverse and
complex terrain, which includes numerous peaks and valleys and a variety of climatic conditions. This article illustrates
the results of three cloud masking methods on Sentinel-2 images. In contrast to the Fmask method, the Fmask CDI and
Fmask CSP methods provide more benefits in detecting clouds and cloud shadows, resulting in more accurate outcomes