Abstract

This study develops a novel automatic all-sky imaging system, namely, an all-sky camera (ASC) system, for cloud cover assessment. The proposed system does not require conventional solar occulting devices and can capture complete hemispheric sky images. Cloud detection is performed innovatively using a convolutional neural network model (i.e., the optimized U-Net model). Experiments demonstrate that the optimized U-Net model can effectively detect clouds from sky images. In terms of cloud cover, the estimation results of the ASC system exhibit a high correlation with those obtained via manual observation, thereby indicating the applicability of the ASC system in ground-based cloud observation and analysis.

© 2019 Optical Society of America

Development of a sky imager for cloud cover assessment

A. Cazorla, F. J. Olmo, and L. Alados-Arboledas
J. Opt. Soc. Am. A 25(1) 29-39 (2008)

All-sky polarization imaging of cloud thermodynamic phase

Laura M. Eshelman, Martin Jan Tauc, and Joseph A. Shaw
Opt. Express 27(3) 3528-3541 (2019)

All-sky imaging: a simple, versatile system for atmospheric research

Axel Kreuter, Matthias Zangerl, Michael Schwarzmann, and Mario Blumthaler
Appl. Opt. 48(6) 1091-1097 (2009)

Day/night whole sky imagers for 24-h cloud and sky assessment: history and overview

Janet E. Shields, Monette E. Karr, Richard W. Johnson, and Art R. Burden
Appl. Opt. 52(8) 1605-1616 (2013)

Atmospheric cloud algorithms for day/night whole sky imagers

Janet E. Shields, Art R. Burden, and Monette E. Karr
Appl. Opt. 58(26) 7050-7062 (2019)