Accession Number:

ADD019017

Title:

Neural Network Hurricane Tracker

Descriptive Note:

Patent application, Filed 27 May 98

Corporate Author:

DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s):

Report Date:

1998-05-27

Pagination or Media Count:

16.0

Abstract:

The present invention relates to a method and a system for predicting the path of a hurricane. The system includes sensors for gathering real-time data about the hurricane and supplying the data to a trained neural network for yielding a predicted path for the hurricane. The system further includes a device for displaying the predicted path of the hurricane. A method for using and training the neural network in the system is described. In the method, the neural network is trained using information about hurricanes in a specific geographical area maintained in a database. The training involves inputting a plurality of parameters about at least one historical hurricane track and producing an output signal representative of a predicted hurricane path. An error is calculated between the output signal and the actual track and the internal weights of the neural network are adjusted to reduce the error.

Subject Categories:

  • Meteorology
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE