Multitemporal Cloud Masking in the Google Earth Engine

TLDR

Accurate cloud detection is essential for Earth observation, and multitemporal methods outperform single‑scene approaches, yet their use is limited by archive access and computational demands. This study introduces a cloud‑detection and removal method built on Google Earth Engine to overcome those limitations. The method was evaluated on Landsat‑8 imagery using a large set of manually labeled Biome cloud masks. It achieves 4–5 % higher classification accuracy and 3–10 % lower commission errors than FMask and ACCA, and the GEE implementation and resulting masks are publicly released.

Abstract

The exploitation of Earth observation satellite images acquired by optical instruments requires an automatic and accurate cloud detection. Multitemporal approaches to cloud detection are usually more powerful than their single scene counterparts since the presence of clouds varies greatly from one acquisition to another whereas surface can be assumed stationary in a broad sense. However, two practical limitations usually hamper their operational use: the access to the complete satellite image archive and the required computational power. This work presents a cloud detection and removal methodology implemented in the Google Earth Engine (GEE) cloud computing platform in order to meet these requirements. The proposed methodology is tested for the Landsat-8 mission over a large collection of manually labeled cloud masks from the Biome dataset. The quantitative results show state-of-the-art performance compared with mono-temporal standard approaches, such as FMask and ACCA algorithms, yielding improvements between 4–5% in classification accuracy and 3–10% in commission errors. The algorithm implementation within the Google Earth Engine and the generated cloud masks for all test images are released for interested readers.