Cloud detection machine learning algorithms for PROBA-V

TL;DR

This paper develops a machine learning-based cloud detection algorithm for Proba-V satellite images, aiming to improve accuracy in cloud masking which is crucial for remote sensing applications.

Contribution

It introduces a novel statistical machine learning approach for pixel-level cloud detection in Proba-V data, enhancing existing cloud masking techniques.

Findings

Effective cloud detection demonstrated on real Proba-V images

Improved accuracy over traditional methods

Provides reliable cloud flags for remote sensing applications

Abstract

This paper presents the development and implementation of a cloud detection algorithm for Proba-V. Accurate and automatic detection of clouds in satellite scenes is a key issue for a wide range of remote sensing applications. With no accurate cloud masking, undetected clouds are one of the most significant sources of error in both sea and land cover biophysical parameter retrieval. The objective of the algorithms presented in this paper is to detect clouds accurately providing a cloud flag per pixel. For this purpose, the method exploits the information of Proba-V using statistical machine learning techniques to identify the clouds present in Proba-V products. The effectiveness of the proposed method is successfully illustrated using a large number of real Proba-V images.