Paper:
Language: English:

Classification of Volumetric Storm Cell Patterns

M. Alexiuk^*, N. Pizzi^**, P C. Li^* and W. Pedrycz^***

Department of Electrical and Computer Engineering, University of Manitoba Winnipeg, Manitoba R3T 5V6 Institute of Biodiagnostics, National Research Council 435 Ellice Avenue Winnipeg, Manitoba R3B 1Y6 Department of Electrical and Computer Engineering, University of Alberta Edmonton, Alberta T6G 2G7

Received: March 12, 2000

Accepted: May 20, 2000

Keywords: Storm forecasting, Neural networks, Classification, Clustering, Fuzzy set theory

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.4, No.3 pp. 206-211, 2000

Abstract

Meteorological volumetric radar data may be used to detect thunderstorms, storm events responsible for nearly all severe summer weather Discriminating between different types of thunderstorms is a difficult problem due to the high dimensionality of the data, and the imprecision and incompleteness of the data. Several artificial neural network and fuzzy set theoretic classification strategies and preprocessing techniques are tested to determine their usefulness in the discrimination of four types of storm events: tornado, wind, hail and heavy rain.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: