Automatic Cloud‐Type Classification Based On the Combined Use of a Sky Camera and a Ceilometer

A methodology, aimed to be fully operational, for automatic cloud classification based on the synergetic use of a sky camera and a ceilometer is presented. The Random Forest Machine Learning algorithm was used to train the classifier with 19 input features: 12 extracted from the sky-camera images and 7 from the ceilometer. The method was developed and tested based on a set of 717 images collected at the radiometric stations of the Univ. of Jaen (Spain). Up to 9 different types of clouds (plus clear sky) were considered (clear sky, cumulus, stratocumulus, nimbostratus, altocumulus, altostratus, stratus, cirrocumulus, cirrostratus, and cirrus) plus an additional category multi-cloud, aiming to account for the frequent cases in which the sky is covered by several cloud types. A total of 8 experiments were conducted by: 1) excluding/including the ceilometer information; 2) including/excluding the multi-cloud category and 3) using 6 or 9 different cloud types, aside from the clear sky and multi-cloud category. The method provided accuracies ranging from 45% to 78%, being highly dependent on the use of the ceilometer information. This information showed to be particularly relevant for accurately classifying “cumuliform” clouds and to account for the multi-cloud category. At this regard, the camera information alone was found to be not suitable to deal with this category. Finally, while the use of the ceilometer provided an overall superior performance, some limitations were found, mainly related to the classification of clouds with similar cloud base height and geometric thickness.

[1]  Maneesha Singh,et al.  Automated ground-based cloud recognition , 2005, Pattern Analysis and Applications.

[2]  Josep Calbó,et al.  Modeling atmospheric longwave radiation at the surface during overcast skies: The role of cloud base height , 2015 .

[3]  J. L. Bosch,et al.  Cloud classification in a mediterranean location using radiation data and sky images , 2011 .

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

[5]  C. Schär,et al.  The global energy balance from a surface perspective , 2013, Climate Dynamics.

[6]  Luca Bugliaro,et al.  Ground-based observations for the validation of contrails and cirrus detection in satellite imagery , 2009 .

[7]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[8]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[9]  Oleg A. Krasnov,et al.  Continuous Evaluation of Cloud Profiles in Seven Operational Models Using Ground-Based Observations , 2007 .

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

[11]  Ronald M. Welch,et al.  A neural network approach to cloud classification , 1990 .

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

[13]  Hsu-Yung Cheng,et al.  Block-based cloud classification with statistical features and distribution of local texture features , 2014 .

[14]  Josep Calbó,et al.  Comparing the Cloud Vertical Structure Derived from Several Methods Based on Radiosonde Profiles and Ground-based Remote Sensing Measurements , 2014 .

[15]  A R Smith,et al.  Color Gamut Transformation Pairs , 1978 .

[16]  M. R. de Quervain.  SNOW CLASSIFICATION OF THE INTERNATIONAL ASSOCIATION OF SCIENTIFIC HYDROLOGY (IASH) AND CLASSIFICATION OF SOLID HYDROMETEORS OF THE INTERNATIONAL CLOUD ATLAS OF THE WORLD METEOROLOGICAL ORGANISATION (WMO) , 1956 .

[17]  Jun Yang,et al.  From pixels to patches: a cloud classification method based on a bag of micro-structures , 2015 .

[18]  C. Coimbra,et al.  Intra-hour DNI forecasting based on cloud tracking image analysis , 2013 .

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  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.

[21]  Mario Blumthaler,et al.  All-sky imaging: a simple, versatile system for atmospheric research. , 2009, Applied optics.

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

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

[24]  Hsu-Yung Cheng,et al.  Cloud detection in all-sky images via multi-scale neighborhood features and multiple supervised learning techniques , 2016 .

[25]  W. Thomas,et al.  What is the benefit of ceilometers for aerosol remote sensing? An answer from EARLINET , 2014 .

[26]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[27]  David Kerr,et al.  Automated cloud classification using a ground based infra-red camera and texture analysis techniques , 2013, Remote Sensing.

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

[29]  Marion Schroedter-Homscheidt,et al.  APOLLO Cloud Product Statistics , 2014 .

[30]  David Pozo-Vázquez,et al.  Macroscopic cloud properties in the WRF NWP model: An assessment using sky camera and ceilometer data , 2015 .

[31]  Paul Kalb,et al.  A hybrid approach to estimate the complex motions of clouds in sky images , 2016 .

[32]  Graeme L. Stephens,et al.  A global survey of the instantaneous linkages between cloud vertical structure and large‐scale climate , 2014 .

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

[34]  Rich Caruana,et al.  An empirical evaluation of supervised learning in high dimensions , 2008, ICML '08.

[35]  K. T. Kriebel,et al.  The cloud analysis tool APOLLO: Improvements and validations , 2003 .

[36]  Koby Crammer,et al.  On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines , 2002, J. Mach. Learn. Res..

[37]  Giovanni Martucci,et al.  Detection of Cloud-Base Height Using Jenoptik CHM15K and Vaisala CL31 Ceilometers , 2010 .

[38]  Apichat Heednacram,et al.  Feature extraction techniques for ground-based cloud type classification , 2015, Expert Syst. Appl..

[39]  Lucas Alados-Arboledas,et al.  Efficiency of clouds on shortwave radiation using experimental data , 2014 .

[40]  A. Bais,et al.  The effect of clouds on surface solar irradiance, based on data from an all-sky imaging system , 2016 .

[41]  Andreas Kazantzidis,et al.  Cloud observations in Switzerland using hemispherical sky cameras , 2015 .

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

[43]  Alvy Ray Smith,et al.  Color gamut transform pairs , 1978, SIGGRAPH.

[44]  Carlos F.M. Coimbra,et al.  Cloud-tracking methodology for intra-hour DNI forecasting , 2014 .

[45]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[46]  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.

[47]  Detlev Heinemann,et al.  Evaluating the spatio-temporal performance of sky-imager-based solar irradiance analysis and forecasts , 2015 .

[48]  Charles N. Long,et al.  Optimized fractional cloudiness determination from five ground-based remote sensing techniques , 2010 .

[49]  Robert Pincus,et al.  Can Fully Accounting for Clouds in Data Assimilation Improve Short-Term Forecasts by Global Models? , 2011 .