TY - JOUR
T1 - Neural net classifier for satellite imageries
AU - Hung, S. L.
AU - Cheng, Andrew Y. S.
AU - Lee, Victor C. S.
N1 - Publication information for this record has been verified with the author(s) concerned.
PY - 1992/9/16
Y1 - 1992/9/16
N2 - Accurate identification of cloud type is an important aspect of weather forecasting. One of the primary application of the remotely sensed cloud cover data is to provide synoptic cloud cover information over extensive data-sparse regions; particularly the oceans and deserts. In south-east Asia, information on cloud cover data are obtained from the infrared and visible channels of Geostationary Meterological Satellite. These imageries contain data of clouds. By extracting the textural features embedded in the images, information on cloud types can be derived and mapped spatially. An artificial neural network is used as a classifier to identify different cloud types through comprehensive training cycles. The architecture of the network used in the present study is multi-layered with feedforward and backpropagation. The study makes use of a classification scheme based on the SYNOP code of the World Meterological Organization (WMO). The average cloud classification accuracy obtained in this study is 40%.
AB - Accurate identification of cloud type is an important aspect of weather forecasting. One of the primary application of the remotely sensed cloud cover data is to provide synoptic cloud cover information over extensive data-sparse regions; particularly the oceans and deserts. In south-east Asia, information on cloud cover data are obtained from the infrared and visible channels of Geostationary Meterological Satellite. These imageries contain data of clouds. By extracting the textural features embedded in the images, information on cloud types can be derived and mapped spatially. An artificial neural network is used as a classifier to identify different cloud types through comprehensive training cycles. The architecture of the network used in the present study is multi-layered with feedforward and backpropagation. The study makes use of a classification scheme based on the SYNOP code of the World Meterological Organization (WMO). The average cloud classification accuracy obtained in this study is 40%.
UR - http://www.scopus.com/inward/record.url?scp=0037605543&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0037605543&origin=recordpage
U2 - 10.1117/12.140005
DO - 10.1117/12.140005
M3 - RGC 21 - Publication in refereed journal
VL - 1709
SP - 269
EP - 274
JO - Society of Photo-Optical Instrumentation Engineers (SPIE)
JF - Society of Photo-Optical Instrumentation Engineers (SPIE)
T2 - Applications of Artificial Neural Networks III 1992
Y2 - 20 April 1992
ER -