Title :
Intelligent storm identification system using a hierarchical neural network
Author :
Langi, A. ; Ferens, K. ; Kinsner, W. ; Kect, T. ; Sawatzky, G.
Author_Institution :
Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada
Abstract :
The paper presents a system to detect severe storm events from non-Doppler radar data using a hierarchical artificial neural network (HANN). The system incorporates three levels of data processing: (i) dimensionality reduction (by data slicing, fragmentation, and preprocessing), (ii) feature extraction in the form of codebooks, and (iii) pattern recognition and classification. We study various schemes of such a processing structure. In one scheme, the first level processing slices the volumetric radar data into a set of images representing radar echo intensity at constant altitudes and fragments the images into image blocks. The second level processing extracts features from the image blocks using a self-organizing feature map (SOFM) neural network. It results in a set of codebooks, which is used by a back propagation (BP) neural network at the third level processing for classification. We have used a limited set of 22 known storm events for our experiments and system development. Preliminary results show 100% correct classification of the storm set. The scheme has been implemented in an X-windows environment, which has been installed in the Atmospheric Environment Services, Winnipeg, Canada, for field tests
Keywords :
backpropagation; feature extraction; geophysical signal processing; hierarchical systems; image classification; image recognition; knowledge based systems; radar cross-sections; radar imaging; self-organising feature maps; storms; weather forecasting; X-windows environment; back propagation neural network; codebooks; data processing; data slicing; dimensionality reduction; feature extraction; fragmentation; hierarchical neural network; image blocks; intelligent storm identification system; nonDoppler radar data; pattern classification; pattern recognition; preprocessing; radar echo intensity; self-organizing feature map; severe storm events; volumetric radar data; Backpropagation; Feature extraction; Geophysical signal processing; Hierarchical systems; Image classification; Intelligent systems; Knowledge based systems; Neural network applications; Pattern recognition; Radar cross sections; Radar imaging/mapping; Self-organizing feature maps; Weather forecasting;
Conference_Titel :
Electrical and Computer Engineering, 1994. Conference Proceedings. 1994 Canadian Conference on
Conference_Location :
Halifax, NS
Print_ISBN :
0-7803-2416-1
DOI :
10.1109/CCECE.1994.405798