Paper
27 December 1995 Development of an automated classification scheme for detection of polar stratospheric clouds over Antarctica using AVHRR imagery
Patricia S. Foschi, Kathy L. Pagan, Oswaldo Garcia, Deborah K. Smith, Steven E. Gaines, R. Stephen Hipskind
Author Affiliations +
Abstract
Although polar stratospheric clouds (PSCs) are a critical component in the ozone depletion process, their timing, duration, geographic extent, and annual variability are not well understood. The goal of this study is the development of an automated classification scheme for detecting PSCs using NOAA AVHRR data. Visual interpretation, density slicing, and standard multispectral classification detect most optically thick PSCs, but only some thin PSCs. Two types of automated techniques for detecting thin PSCs are being investigated: namely, multispectral classification methods, including the use of texture and other imagederived features, and back-propagation neural networks, including the use of hyperspatial and hypertemporal data. UARS CLAES temperature and aerosol extinction coefficient data are being used as a verification dataset. If successful, this classification scheme will be used to process the entire record of AVHRR data in order to assemble a long-term PSC climatology.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Patricia S. Foschi, Kathy L. Pagan, Oswaldo Garcia, Deborah K. Smith, Steven E. Gaines, and R. Stephen Hipskind "Development of an automated classification scheme for detection of polar stratospheric clouds over Antarctica using AVHRR imagery", Proc. SPIE 2578, Passive Infrared Remote Sensing of Clouds and the Atmosphere III, (27 December 1995); https://doi.org/10.1117/12.228960
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Clouds

Cryogenic limb array etalon spectrometers

Neural networks

Climatology

Aerosols

Image classification

Algorithm development

Back to Top