A deep network approach to multitemporal cloud detection

TL;DR

This paper introduces a deep learning model with temporal memory for accurate, pixel-level cloud detection in satellite image time series, capable of handling day and night conditions across the year.

Contribution

The novel approach combines recurrent neural networks with deep learning to improve multitemporal cloud detection in satellite imagery.

Findings

High accuracy in cloud detection across all seasons

Effective day and night cloud mapping with a single model

Real-time pixel-level confidence estimation

Abstract

We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.