Cloud Data Set for Neural Network Classification Studies

reportActive / Technical Report | Accession Number: ADA256181 | Open PDF

Abstract:

A large set of GOES imagery has been analyzed to generate a cloud data set for neural network classification studies. The classification scheme uses 13 classes of clouds. The cloud data base is large enough to allow cross- validation tests of automated cloud classification techniques. The methods used to acquire the data on cloud type and a brief overview of the planned automated classification experiments are presented. The appendix contains an inventory of the cloud data set.

Author(s):
Hawkins, Rupert S. ; Heideman, K. F. ; Smotroff, Ira G.
Author Organization(s):
PHILLIPS LAB HANSCOM AFB MA
Descriptive Note:
Final rept.
Supplementary Note:
Prepared in cooperation with MITRE Corporation, Bedford, MA. DOI: 10.21236/ADA256181
Pagination:
0023

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
PL-TR-92-2027, ERP-1097
Task Number(s):
17
Project Number(s):
6670
Monitor Series:
PL*
 Subject Terms
Joint Capability Areas:
JCA_5_Command and Control; JCA_5.3_Planning; JCA_5.2.2_Develop Knowledge and Situational Awareness; JCA_5.2_Understand; JCA_1.2.1_Training; JCA_1.2.7_Experimentation; JCA_5.5.2_Task; JCA_5.5_Direct
Modernization Areas:
Space
Communities of Interest:
Space
Descriptor(s):
*CLOUDS, *NETWORKS, *CLOUD PHYSICS, DATA BASES, SCIENTIFIC SATELLITES, METEOROLOGICAL SATELLITES, INFRARED IMAGES, IMAGES
Field(s)/Group(s):
Meteorology
Keyword(s):
CLOUD ANALYSIS, SATELLITE IMAGERY, CLOUD CLASSIFICATION, CLOUD TYPING, VISIBLE IMAGES, GOES (GEOSTATIONARY OPERATIONAL ENVIRONMENTAL SATELLITE), SBI1, FISCAL YEAR 1992, PE62101F, WUPL66701712
Report Date:
1992 Jan 23