Atmospheric Measurement Techniques Discussions www.atmos-meas-tech-discuss.net 1867-8610 3 1 2010 10.5194/amtd-3-269-2010 http://www.atmos-meas-tech-discuss.net/3/269/2010/ http://www.atmos-meas-tech-discuss.net/3/269/2010/amtd-3-269-2010.html http://www.atmos-meas-tech-discuss.net/3/269/2010/amtd-3-269-2010.pdf 269 299 2010-01-27 Automatic cloud classification of whole sky images A. Heinle ahe@informatik.uni-kiel.de A. Macke A. Srivastav Excellence Cluster "The Future Ocean", Department of Computer Science, Kiel University, Kiel, Germany Leibniz Institute of Marine Sciences at Kiel University (IFM-GEOMAR), Kiel, Germany The recently increasing development of whole sky imagers enables temporal and spatial high-resolution sky observations. One application already performed in most cases is the estimation of fractional sky cover. A distinction between different cloud types, however, is still in progress. Here, an automatic cloud classification algorithm is presented, based on a set of mainly statistical features describing the color as well as the texture of an image. The <i>k</i>-nearest-neighbour classifier is used due to its high performance in solving complex issues, simplicity of implementation and low computational complexity. Seven different sky conditions are distinguished: high thin clouds (cirrus and cirrostratus), high patched cumuliform clouds (cirrocumulus and altocumulus), stratocumulus clouds, low cumuliform clouds, thick clouds (cumulonimbus and nimbostratus), stratiform clouds and clear sky. Based on the Leave-One-Out Cross-Validation the algorithm achieves an accuracy of about 97%, outperforming previous algorithms with accuracies of at most 62%. An additional test run of random images is presented, still yielding a success rate of about 75%, or up to 88% if only "serious" errors with respect to radiation impact are considered. Reasons for the decrement in accuracy are discussed, and ideas to further improve the classification results, especially in problematic cases, are investigated. Bankert, R L. and Wade, R H.: Optimization of an instance-based GOES cloud classification algorithm, J. Appl. Meteorol. Clim., 46, 36–49, 2007. Calbó, J. and Sabburg, J.: Feature extraction from whole-sky ground-based images for cloud-type recognition, J. Atmos. Ocean. Tech., 25, 3–14, 2008. Cazorla, A., Olmo, F J., and Alados-Arboledas, L.: Devlopment of a sky imager for cloud cover assessment, J. Opt. Soc. Am. A., 25, 29–39, 2008. Christodoulou, C I., Michaelides, S., and Pattichis, C.: Multifeature texture analysis for the classification of clouds in satellite imagery, IEEE T. Geosci. Remote, 41, 2662–2668, 2003. Duda, R O. and Hart, P E.: Pattern classification, John Wiley and Sons, 2001. Dybbroe, A., Karlsson, K.-G., and Thoss, A.: NWCSAF AVHRR Cloud Detection and Analysis Using Dynamic Tresholds and Radiative Modeling. Part II: Tuning and Validation, J. Appl. Meteorol., 44, 55–71, 2005. Feister, U. and Shields, J.: Cloud and radiance measurements with the VIS/NIR Daylight Whole Sky Imager at Lindenberg (Germany), Meteorol. Z., 14, 627–639, 2005. Haralick, R M., Shanmugam, K., and Dinstein, I.: Textural features for image classification, IEEE T. Syst. Man Cyb., 3, 610–621, 1973. Houghton, J T., Ding, Y., Griggs, D J., Noguer, M., van~der Linden, P J., Dai, X., Maskell, K., and Johnson, C A.: Climate Change 2001: The Scientific Basis, Cambridge University Press, 2001. Kalisch, J. and Macke, A.: Estimation of the total cloud cover with high temporal resolution and parametrization of short-term fluctuations of sea surface insolation, Meteorol. Z., 17, 603–611, 2008. Kassianov, E., Long, C N., and Christy, J.: Cloud-base-height estimation from paired ground-based hemispherical observations, J. Appl. Meteorol., 44, 1221–1233, 2005. Long, C N., Sabburg, J., Calbó, J., and Pagès, D.: Retrieving cloud characteristics from ground-based daytime colorall-sky images, J. Atmos. Ocean. Tech., 23, 633–652, 2006. Obasi, G. O.: International Cloud Atlas, Vol. 2, WMO, 1987. Pagès, D., Calbo, J., Long, C N., González, J.-A., and Badosa, J.: Comparison of several ground-based cloud detection techniques, in: Extended Abstracts, European Geophysical Society XXVII General Assembly, 26–28~April, Nice, France, 2002. Pankiewicz, G S.: Pattern recognition techniques for the identification of cloud and cloud systems, Meteorol. Appl., 2, 257–271, 1995. Parisi, A V., Sabburg, J., Turner, J., and Dunn, P K.: Cloud observations for the statistical evaluation of the UV index at Toowoomba, Australia, Int. J. Biometeorol., 52, 159–166, 2008. Petty, G W.: A first course in atmospheric radiation, Sundog Publishing, 2006. Pfister, G., McKenzie, R L., Liley, J B., Thomas, A., Forgan, B W., and Long, C N.: Cloud coverage based on all-sky imaging and its impact on surface solar irradiance, J. Appl. Meteorol., 42, 1421–1434, 2003. Ricciardelli, F., Romano, F., and Cuomo, V.: Physical and statistical approaches for cloud identification using Meteosat Second Generation-Spinning Enhanced Visible and Infrared Imager Data, Remote Sens. Environ., 112, 2741–2760, 2008. Ripley, B D.: Pattern Recognition and Neural Networks, Cambridge University Press, 8 Edn., 2005. Rossow, W B. and Schiffer, R A.: ISCCP cloud data products, B. Am. Meteorol. Soc., 71, 2–20, 1991. Sakellariou, N K., Varotsos, C A., and Lykoudis, S P.: On the intercomparison of satellite and ground-based observations of prevailing cloud types over Athens, Int. J. Remote Sens., 16, 1799–1804, 1995. Schiel, S.: The expedition of the research vessel "Polarstern" to the Antarctic in 2007 (ANT-XXIV/1), in: Berichte zur Polar- und Meeresforschung, 592, 2009. Seiz, G., Baltsavias, E P., and Gruen, A.: Cloud mapping from the ground: Use of photogrammetric methods, Photogramm. Eng. Rem. S., 68, 941–951, 2002. Serpico, S B., Bruzzone, L., and Roli, F.: An experimental comparison of neural and statistical non-parametric algorithms for supervised classification of remote-sensing images, Pattern Recognit. Lett., 17, 1331–1341, 1996. Shields, J E., Johnson, R W., Karr, M E., and Wertz, J L.: Automated day/night whole sky imagers for field assessment of cloud cover distributions and radiance distributions, in: Proc. 10th Symp. on Meteorological Observations and Instrumentation, 11–16~January, Boston, MA, 1998. Shields, J E., Johnson, R W., Karr, M E., Burden, A R., and Baker, J G.: Daylight visible/NIR whole sky imagers for cloud and radiance monitoring in support of UV research programs, Proc. SPIE, 5156, 155–166, 2003. Singh, M. and Glennen, M.: Automated ground-based cloud recognition, Pattern Anal. Appl., 8, 258–271, 2005. Souza-Echer, M P., Pereira, E B., Bins, L S., and Andrade, M. A R.: A Simple Method for the Assessment of the Cloud Cover State in High-Latitude Regions by a Ground-Based Digital Camera, J. Atmos. Oceanic Technol., 23, 437–447, 2006. Tag, P M., Bankert, R L., and Brody, L R.: An AVHRR multiple cloud-type classification package, J. Appl. Meteorol., 39, 125–134, 2000. Vincent, P. and Bengio, Y.: K-Local Hyperplane and Convex Distance Nearest Neighbor Algorithms, Tech. rep., Dept. IRO, Université de Montréal, 2001.