Philip Gabriel of the CSU Department of Atmospheric Sciences at Colorado State University has written a fortran model of the atmosphere. Given parameters representing the properties of clouds in various layers of the atmosphere, Philip’s model produces an expected power spectrum of the light received by a satellite. To determine the atmosphere properties from an observed power spectrum, this model must be effectively inverted.
Andrew Grauch, an undergraduate computer science major at CSU, investigated the use of artificial neural networks to learn this inverse mapping. His results are described in
– a final report, Experiments Using Neural Networks to Invert the Public1 Model, by Andrew Grauch, May 7, 2001.
– and slides from Andrew’s presentation.
