Investigation of the Prediction of Lightning Strikes Using Neural Networks
Abstract
A neural network is being trained to predict lightning at Cape Canaveral for periods up to two hours in advance. Inputs consists of ground based field mill data, meteorological tower data, lightning location data and radiosonde and rapid changes in the field mill data, offset in time, provide the 'forecasts' or 'desired output values' used to train the neural network through back propagation. Examples of input data are shown and an example of data compression using a hidden layer in the neural network is discussed. (kr)
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 11, 1990
- Accession Number
- ADA229042
Entities
People
- Arnold A. Barnes Jr.
- Donald S. Frankel
Organizations
- Air Force Systems Command