Cloud cover retrieved from skyviewer: A validation with human observations

Kim, Bu-Yo; Jee, Joon-Bum; Zo, Il-Sung; Lee, Kyu‐Tae

doi:10.1007/s13143-015-0083-4

Cited by 15 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Going further, recent methodologies based on background substraction take account of the clear-sky spatial and temporal variability through the use of a modeled (or so-called "virtual") clear sky (Yabuki et al, 2014;Chauvin et al, 2015;Yang et al, 2016). Note that Koehler et al (1991) already used a "perturbation" ratio of RBR, relative to a haze-adjusted background RBR, to optimize thin cloud detection.…”

Section: Elifan Algorithmmentioning

confidence: 99%

ELIFAN, an algorithm for the estimation of cloud cover from sky imagers

et al. 2019

View full text Add to dashboard Cite

Abstract. In the context of a network of sky cameras installed on atmospheric multi-instrumented sites, we present an algorithm named ELIFAN, which aims to estimate the cloud cover amount from full-sky visible daytime images with a common principle and procedure. ELIFAN was initially developed for a self-made full-sky image system presented in this article and adapted to a set of other systems in the network. It is based on red-to-blue ratio thresholding for the distinction of cloudy and cloud-free pixels of the image and on the use of a cloud-free sky library, without taking account of aerosol loading. Both an absolute (without the use of a cloud-free reference image) and a differential (based on a cloud-free reference image) red-to-blue ratio thresholding are used. An evaluation of the algorithm based on a 1-year-long series of images shows that the proposed algorithm is very convincing for most of the images, with about 97 % of relevance in the process, outside the sunrise and sunset transitions. During those latter periods, however, ELIFAN has large difficulties in appropriately processing the image due to a large difference in color composition and potential confusion between cloud-free and cloudy sky at that time. This issue also impacts the library of cloud-free images. Beside this, the library also reveals some limitations during daytime, with the possible presence of very small and/or thin clouds. However, the latter have only a small impact on the cloud cover estimate. The two thresholding methodologies, the absolute and the differential red-to-blue ratio thresholding processes, agree very well, with departure usually below 8 % except in sunrise–sunset periods and in some specific conditions. The use of the cloud-free image library gives generally better results than the absolute process. It particularly better detects thin cirrus clouds. But the absolute thresholding process turns out to be better sometimes, for example in some cases in which the sun is hidden by a cloud.

show abstract

Section: Elifan Algorithmmentioning

confidence: 99%

ELIFAN, an algorithm for the estimation of cloud cover from sky imagers

et al. 2019

View full text Add to dashboard Cite

show abstract

Section: Background On the Retrieval Of Cloud Cover From A Visible-skmentioning

confidence: 99%

Reply to Referee #1

Lothon¹

2019

Preprint

View full text Add to dashboard Cite

In the context of a network of sky cameras installed on atmospheric multi-instrumented sites, we present an algorithm named ELIFAN, which aims to estimate the cloud cover amount from full-sky visible daytime images with a common principle and procedure. ELIFAN was initially developed for a self-made full-sky image system presented in this article and adapted to a set of other systems in the network. It is based on red-to-blue ratio thresholding for the distinction of cloudy and cloud-free pixels of the image and on the use of a cloud-free sky library, without taking account of aerosol loading. Both an absolute (without the use of a cloud-free reference image) and a differential (based on a cloud-free reference image) red-to-blue ratio thresholding are used. An evaluation of the algorithm based on a 1-year-long series of images shows that the proposed algorithm is very convincing for most of the images, with about 97 % of relevance in the process, outside the sunrise and sunset transitions. During those latter periods, however, ELIFAN has large difficulties in appropriately processing the image due to a large difference in color composition and potential confusion between cloud-free and cloudy sky at that time. This issue also impacts the library of cloud-free images. Beside this, the library also reveals some limitations during daytime, with the possible presence of very small and/or thin clouds. However, the latter have only a small impact on the cloud cover estimate. The two thresholding methodologies, the absolute and the differential red-to-blue ratio thresholding processes, agree very well, with departure usually below 8 % except in sunrise-sunset periods and in some specific conditions. The use of the cloud-free image library gives generally better results than the absolute process. It particularly better detects thin cirrus clouds. But the absolute thresholding process turns out to be better sometimes, for example in some cases in which the sun is hidden by a cloud.

show abstract

“…To date, ground-based cloud cover observation has been performed using the human eye, in accordance with the normalized synoptic observation rule of the World Meteorological Organization (WMO), and recorded in tenths or oktas (Kim et al, 2016;Yun and Whang, 2018). However, human-eye observation of cloud cover lacks consistency and depends on the observer conditions and the observation term (Mantelli Neto et al, 2010;Yang et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

24-hour cloud cover calculation using ground-based imager with machine learning

Kim

Wan

Chang

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract. In this study, image data features and machine learning methods were used to calculate 24-h continuous cloud cover from image data obtained by a camera-based imager on the ground. The image data features were the time (Julian day and hour), solar zenith angle, and statistical characteristics of the red-blue ratio, blue–red difference, and luminance. These features were determined from the red, green, and blue brightness of images subjected to a pre-processing process involving masking removal and distortion correction. The collected image data were divided into training, validation, and test sets and were used to optimize and evaluate the accuracy of each machine learning method. The cloud cover calculated by each machine learning method was verified with human-eye observation data from a manned observatory. Supervised machine learning models suitable for nowcasting, namely, support vector regression, random forest, gradient boosting machine, k-nearest neighbor, artificial neural network, and multiple linear regression methods, were employed and their results were compared. The best learning results were obtained by the support vector regression model, which had an accuracy, recall, and precision of 0.94, 0.70, and 0.76, respectively. Further, bias, root mean square error, and correlation coefficient values of 0.04 tenth, 1.45 tenths, and 0.93, respectively, were obtained for the cloud cover calculated using the test set. When the difference between the calculated and observed cloud cover was allowed to range between 0, 1, and 2 tenths, high agreement of approximately 42 %, 79 %, and 91 %, respectively, were obtained. The proposed system involving a ground-based imager and machine learning methods is expected to be suitable for application as an automated system to replace human-eye observations.

show abstract

Cloud cover retrieved from skyviewer: A validation with human observations

Cited by 15 publications

References 12 publications

ELIFAN, an algorithm for the estimation of cloud cover from sky imagers

ELIFAN, an algorithm for the estimation of cloud cover from sky imagers

Reply to Referee #1

24-hour cloud cover calculation using ground-based imager with machine learning

Contact Info

Product

Resources

About