Optimization of an Instance-Based GOES Cloud Classification Algorithm

Abstract An instance-based nearest-neighbor algorithm was developed for a Geostationary Operational Environmental Satellite (GOES) cloud classifier. Expert-labeled samples serve as the training sets for the various GOES image classification scenes. The initial implementation of the classifier using the complete set of available training samples has proven to be an inefficient method for real-time image classifications, requiring long computational run times and significant computer resources. A variety of training-set reduction methods were examined to find smaller training sets that provide quicker classifier run times with minimal reduction in classifier testing set accuracy. General differences within real-time image classifications as a result of using the various reduction methods were also analyzed. The fast condensed nearest-neighbor (FCNN) method reduced the size of the individual training sets by 68.3% (fourfold cross-validation testing average) while the average overall accuracy of the testing s...

[1]  R. Welch,et al.  Automated Cloud Classification of Global AVHRR Data Using a Fuzzy Logic Approach , 1997 .

[2]  Hugh G. Lewis,et al.  Determination of spatial and temporal characteristics as an aid to neural network cloud classification , 1997 .

[3]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[4]  David W. Aha,et al.  Improvement to a Neural Network Cloud Classifier , 1996 .

[5]  Mahmood R. Azimi-Sadjadi,et al.  A study of cloud classification with neural networks using spectral and textural features , 1999, IEEE Trans. Neural Networks.

[6]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[7]  William J. Emery,et al.  An Automated Neural Network Cloud Classifier for Use over Land and Ocean Surfaces , 1997 .

[8]  W. Paul Menzel,et al.  High-Spatial-Resolution Surface and Cloud-Type Classification from MODIS Multispectral Band Measurements , 2003 .

[9]  G S Pankiewicz,et al.  Pattern recognition techniques for the identification of cloud and cloud systems , 2007 .

[10]  Steven A. Ackerman,et al.  Cloud Classification of Satellite Radiance Data by Multicategory Support Vector Machines , 2004, Journal of Atmospheric and Oceanic Technology.

[11]  Y. Hong,et al.  Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System , 2004 .

[12]  Paul M. Tag,et al.  An AVHRR Multiple Cloud-Type Classification Package , 2000 .

[13]  Peter E. Hart,et al.  The condensed nearest neighbor rule (Corresp.) , 1968, IEEE Trans. Inf. Theory.

[14]  Fabrizio Angiulli,et al.  Fast condensed nearest neighbor rule , 2005, ICML.

[15]  Ronald M. Welch,et al.  Polar Cloud and Surface Classification Using AVHRR Imagery: An Intercomparison of Methods , 1992 .

[16]  Judith A. Curry,et al.  Classification of clouds over the western equatorial Pacific Ocean using combined infrared and microwave satellite data , 1995 .

[17]  Michael Uddstrom,et al.  Satellite Cloud Classification and Rain-Rate Estimation Using Multispectral Radiances and Measures of Spatial Texture , 1996 .

[18]  Taneil Uttal,et al.  Daytime Global Cloud Typing from AVHRR and VIIRS: Algorithm Description, Validation, and Comparisons , 2005 .

[19]  Tony R. Martinez,et al.  Reduction Techniques for Instance-Based Learning Algorithms , 2000, Machine Learning.