Remote discrimination of clouds using a neural network

Stephen R. Yool; M. Brandley; C. Kern; Francis W. Gerlach; Ken L. Rhodes

Remote discrimination of clouds using a neural network

Stephen R. Yool, M. Brandley, C. Kern, Francis W. Gerlach, Ken L. Rhodes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Cloud classification is a key input to global climate models. Cloud spectra are typically mixed, however, thus difficult to classify using the maximum likelihood rule. In contrast to maximum likelihood, a densely interconnected, trained neural network can form powerful generalizations that distinguish unique statistical trends among otherwise ambiguous spectral response patterns. Accordingly, cloud classification accuracies produced by a neural network can exceed accuracies produced using the maximum likelihood criterion.

Original language	English (US)
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Publisher	Publ by Int Soc for Optical Engineering
Pages	497-503
Number of pages	7
ISBN (Print)	0819409391
State	Published - 1992
Externally published	Yes
Event	Neural and Stochastic Methods in Image and Signal Processing - San Diego, CA, USA Duration: Jul 20 1992 → Jul 23 1992

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1766
ISSN (Print)	0277-786X

Other

Other	Neural and Stochastic Methods in Image and Signal Processing
City	San Diego, CA, USA
Period	7/20/92 → 7/23/92

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Cite this

Remote discrimination of clouds using a neural network. / Yool, Stephen R.; Brandley, M.; Kern, C. et al.
Proceedings of SPIE - The International Society for Optical Engineering. Publ by Int Soc for Optical Engineering, 1992. p. 497-503 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1766).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yool, SR, Brandley, M, Kern, C, Gerlach, FW & Rhodes, KL 1992, Remote discrimination of clouds using a neural network. in Proceedings of SPIE - The International Society for Optical Engineering. Proceedings of SPIE - The International Society for Optical Engineering, vol. 1766, Publ by Int Soc for Optical Engineering, pp. 497-503, Neural and Stochastic Methods in Image and Signal Processing, San Diego, CA, USA, 7/20/92.

@inproceedings{499146045bb9450bb5d25ae3c1a6611a,

title = "Remote discrimination of clouds using a neural network",

abstract = "Cloud classification is a key input to global climate models. Cloud spectra are typically mixed, however, thus difficult to classify using the maximum likelihood rule. In contrast to maximum likelihood, a densely interconnected, trained neural network can form powerful generalizations that distinguish unique statistical trends among otherwise ambiguous spectral response patterns. Accordingly, cloud classification accuracies produced by a neural network can exceed accuracies produced using the maximum likelihood criterion.",

author = "Yool, {Stephen R.} and M. Brandley and C. Kern and Gerlach, {Francis W.} and Rhodes, {Ken L.}",

year = "1992",

language = "English (US)",

isbn = "0819409391",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "Publ by Int Soc for Optical Engineering",

pages = "497--503",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Neural and Stochastic Methods in Image and Signal Processing ; Conference date: 20-07-1992 Through 23-07-1992",

}

TY - GEN

T1 - Remote discrimination of clouds using a neural network

AU - Yool, Stephen R.

AU - Brandley, M.

AU - Kern, C.

AU - Gerlach, Francis W.

AU - Rhodes, Ken L.

PY - 1992

Y1 - 1992

N2 - Cloud classification is a key input to global climate models. Cloud spectra are typically mixed, however, thus difficult to classify using the maximum likelihood rule. In contrast to maximum likelihood, a densely interconnected, trained neural network can form powerful generalizations that distinguish unique statistical trends among otherwise ambiguous spectral response patterns. Accordingly, cloud classification accuracies produced by a neural network can exceed accuracies produced using the maximum likelihood criterion.

AB - Cloud classification is a key input to global climate models. Cloud spectra are typically mixed, however, thus difficult to classify using the maximum likelihood rule. In contrast to maximum likelihood, a densely interconnected, trained neural network can form powerful generalizations that distinguish unique statistical trends among otherwise ambiguous spectral response patterns. Accordingly, cloud classification accuracies produced by a neural network can exceed accuracies produced using the maximum likelihood criterion.

UR - http://www.scopus.com/inward/record.url?scp=0026997841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026997841&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026997841

SN - 0819409391

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 497

EP - 503

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Publ by Int Soc for Optical Engineering

T2 - Neural and Stochastic Methods in Image and Signal Processing

Y2 - 20 July 1992 through 23 July 1992

ER -

Remote discrimination of clouds using a neural network

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this