Temperature Profiling with Neural Network Inversion of Microwave Radiometer Data

James H. Churnside NOAA Wave Propagation Laboratory, Boulder, Colorado

Search for other papers by James H. Churnside in
Current site
Google Scholar
PubMed
Close
,
Thomas A. Stermitz NOAA Wave Propagation Laboratory, Boulder, Colorado

Search for other papers by Thomas A. Stermitz in
Current site
Google Scholar
PubMed
Close
, and
Judith A. Schroeder NOAA Wave Propagation Laboratory, Boulder, Colorado

Search for other papers by Judith A. Schroeder in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

A neural network is used to obtain vertical profiles of temperature from microwave radiometer data. The overall rms error in the retrieved profiles of a test dataset was only about 8% worse than the overall error using an optimized statistical retrieval. In certain cases, such as one with a large temperature inversion, the neural network produced better reproductions of the profiles than did the statistical inversion.

Abstract

A neural network is used to obtain vertical profiles of temperature from microwave radiometer data. The overall rms error in the retrieved profiles of a test dataset was only about 8% worse than the overall error using an optimized statistical retrieval. In certain cases, such as one with a large temperature inversion, the neural network produced better reproductions of the profiles than did the statistical inversion.

Save