Search Results

You are looking at 1 - 2 of 2 items for :

  • Author or Editor: Morton Glass x
  • Journal of Atmospheric and Oceanic Technology x
  • Refine by Access: All Content x
Clear All Modify Search
Rosemary M. Dyer, Morton Glass, and Herbert E. Hunter


A major impediment to the development of computer algorithms for the automatic classification of ice particle types found in the atmosphere as measured by a Particle Measuring System two-dimensional probe is the difficulty of obtaining training data. This is especially true when, as is usually the case, the particle shapes do not correspond to any of the pure crystal types found in textbooks.

This paper presents the results of testing such a training set. Sources of bias among human observers include the effect of training and previous familiarity with the data, fatigue, and particle orientation, as well as subjective differences among observers. The deviation of individual human observers from the classifications arrived at by consensus indicates an upper bound to the accuracy possible in automated classification schemes.

Full access
Herbert E. Hunter, Rosemary M. Dyer, and Morton Glass


Classification algorithms have been developed to distinguish six categories of cloud ice particles. These algorithms have been incorporated in schema which, when applied to shadowgraph images produced by the Precision Measurement System laser scanning device, have demonstrated the capability of classifying with more consistency than human classifiers, and with almost no sensitivity to particle orientation.

The data used to derive the algorithms consisted of observations obtained on four separate aircraft flights. Two human classifiers, interacting with a preliminary machine classification, defined the correct answers for this training data set. The algorithms were then tested against arbitrarily selected segments from two additional flights. The ADAPT Service Corporations eigenvector, or empirical orthogonal function (EOF) technique, defined the features objectively, and the ADAPT independent eigenscreening algorithm development program related these features to the particle type.

Analysis of the performance suggests that considerable variation is to be expected, based on the set-to-set variation of the distribution of particle types between real data sets. The classification schema have been developed to allow the user to change key parameters in order to compensate for this variation.

It was concluded that the machine classification was superior to manual classification for the identification of large numbers of particles in terms of speed and consistency.

Full access