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

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.

[1]  Kyu-Tae Lee,et al.  Cloud cover retrieved from skyviewer: A validation with human observations , 2016, Asia-Pacific Journal of Atmospheric Sciences.

[2]  E. Pereira,et al.  The Use of Euclidean Geometric Distance on RGB Color Space for the Classification of Sky and Cloud Patterns , 2010 .

[3]  S. Bony,et al.  SIRTA, a ground-based atmospheric observatory for cloud and aerosol research , 2005 .

[4]  J. Kleissl,et al.  Development of a sky imaging system for short-term solar power forecasting , 2014 .

[5]  Lucas Alados-Arboledas,et al.  Multi-exposure adaptive threshold technique for cloud detection with sky imagers , 2015 .

[6]  Weitao Lu,et al.  An Automated Cirrus Cloud Detection Method for a Ground-Based Cloud Image , 2012 .

[7]  G. Roberts,et al.  All-sky photogrammetry techniques to georeference a cloud field , 2017 .

[8]  W. Philip Kegelmeyer,et al.  The Computation of Cloud-Base Height from Paired Whole-Sky Imaging Cameras , 1996 .

[9]  Jan Kleissl,et al.  Stereographic methods for cloud base height determination using two sky imagers , 2014 .

[10]  Wen Yao,et al.  A total sky cloud detection method using real clear sky background , 2015 .

[11]  Chunheng Wang,et al.  Automatic Cloud Detection for All-Sky Images Using Superpixel Segmentation , 2015, IEEE Geoscience and Remote Sensing Letters.

[12]  Josep Calbó,et al.  Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition , 2008 .

[13]  Hsu-Yung Cheng,et al.  Cloud tracking using clusters of feature points for accurate solar irradiance nowcasting , 2017 .

[14]  George Economou,et al.  Cloud detection and classification with the use of whole-sky ground-based images , 2012 .

[15]  Victoria E. Cachorro,et al.  Cloud cover detection combining high dynamic range sky images and ceilometer measurements , 2017 .

[16]  Jean-Charles Dupont,et al.  ReOBS: a new approach to synthesize long-term multi-variable dataset and application to the SIRTA supersite , 2018 .

[17]  Jun Yang,et al.  A Hybrid Thresholding Algorithm for Cloud Detection on Ground-Based Color Images , 2011 .

[18]  Carlos R. Martinis,et al.  A New Method to Estimate Cloud Cover Fraction over El Leoncito Observatory from an All-Sky Imager Designed for Upper Atmosphere Studies , 2013 .

[19]  Josep Calbó,et al.  Retrieving Cloud Characteristics from Ground-Based Daytime Color All-Sky Images , 2006 .

[20]  Wen Yao,et al.  An automated cloud detection method based on the green channel of total-sky visible images , 2015 .

[21]  Petr Páta,et al.  Colour transformations and K-means segmentation for automatic cloud detection , 2015 .

[22]  Dong Huang,et al.  3D cloud detection and tracking system for solar forecast using multiple sky imagers , 2015 .

[23]  Shantikumar S. Ningombam,et al.  Long-term (1995–2018) aerosol optical depth derived using ground based AERONET and SKYNET measurements from aerosol aged-background sites , 2019, Atmospheric Pollution Research.

[24]  Fabio Del Frate,et al.  Neural Networks and Support Vector Machine Algorithms for Automatic Cloud Classification of Whole-Sky Ground-Based Images , 2015, IEEE Geoscience and Remote Sensing Letters.

[25]  Evgueni I. Kassianov,et al.  Cloud-Base-Height Estimation from Paired Ground-Based Hemispherical Observations , 2005 .

[26]  Stéphane Grieu,et al.  Modelling the clear-sky intensity distribution using a sky imager , 2015 .

[27]  Walter Richardson,et al.  A Low Cost, Edge Computing, All-Sky Imager for Cloud Tracking and Intra-Hour Irradiance Forecasting , 2017 .

[28]  Abel A. Silva,et al.  Ground-based measurements of local cloud cover , 2013, Meteorology and Atmospheric Physics.

[29]  Janet E. Shields,et al.  Day/night whole sky imagers for 24-h cloud and sky assessment: history and overview. , 2013, Applied optics.

[30]  Carlos F.M. Coimbra,et al.  A Smart Image-Based Cloud Detection System for Intrahour Solar Irradiance Forecasts , 2014 .

[31]  A. Heinle,et al.  Automatic cloud classification of whole sky images , 2010 .

[32]  Jan Kleissl,et al.  Measuring diffuse, direct, and global irradiance using a sky imager , 2017 .

[33]  Jeffrey J. Rodriguez,et al.  A New Contrast-Enhancing Feature for Cloud Detection in Ground-Based Sky Images , 2015 .

[34]  Jan Kleissl,et al.  Cloud base height from sky imager and cloud speed sensor , 2016 .

[35]  Armin Gruen,et al.  Cloud mapping with ground‐based photogrammetric cameras , 2007 .

[36]  A. V. Sinitsyn,et al.  Adaptive algorithm for cloud cover estimation from all-sky images over the sea , 2016, Oceanology.

[37]  A Cazorla,et al.  Development of a sky imager for cloud cover assessment. , 2008, Journal of the Optical Society of America. A, Optics, image science, and vision.

[38]  Enio Bueno Pereira,et al.  A Simple Method for the Assessment of the Cloud Cover State in High-Latitude Regions by a Ground-Based Digital Camera , 2006 .

[39]  Victoria E. Cachorro,et al.  Aerosol optical depth retrievals at the Izaña Atmospheric Observatory from 1941 to 2013 by using artificial neural networks , 2015 .

[40]  A. Smirnov,et al.  AERONET-a federated instrument network and data archive for aerosol Characterization , 1998 .

[41]  J. Kleissl,et al.  Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed , 2011 .

[42]  Harald Flentje,et al.  Contrail study with ground-based cameras , 2013 .

[43]  Jun Yang,et al.  Cloud Type Classification of Total-Sky Images Using Duplex Norm-Bounded Sparse Coding , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[44]  C. W. Chow,et al.  A method for cloud detection and opacity classification based on ground based sky imagery , 2012 .

[45]  Ying Ma,et al.  A hybrid method based on extreme learning machine and k-nearest neighbor for cloud classification of ground-based visible cloud image , 2015, Neurocomputing.

[46]  Masanori Yabuki,et al.  Development of a cloud detection method from whole-sky color images , 2014 .

[47]  James Zijun Wang,et al.  Thin Cloud Detection of All-Sky Images Using Markov Random Fields , 2012, IEEE Geoscience and Remote Sensing Letters.