Neural network and classical least squares methods for quantitative analysis in remote sensing FTIR systems

C. David Wang; William T. Walter; Robert H. Kagann

doi:10.1117/12.205566

10 February 1995 Neural network and classical least squares methods for quantitative analysis in remote sensing FTIR systems

C. David Wang, William T. Walter, Robert H. Kagann

Author Affiliations +

Proceedings Volume 2366, Optical Instrumentation for Gas Emissions Monitoring and Atmospheric Measurements; (1995) https://doi.org/10.1117/12.205566
Event: Optical Sensing for Environmental and Process Monitoring, 1994, McLean, VA, United States

Abstract

Remote monitoring of molecular species in the atmosphere is accomplished using a Fourier transform infrared (FTIR) spectrometer. Advanced processing algorithms utilized by AIL Systems include the classical least squares (CLS) technique as well as a more recently developed approach which combines digital finite impulse response filtering, adaptive sampling, and artificial neural networks (ANN) to improve detection sensitivity and estimation accuracy. This paper presents a comparison between the CLS and the ANN methods in estimating concentrations of multicomponent mixtures. Detection improvement of ANN over CLS has been demonstrated by examining SF₆ in a stack plume and toluene in a laboratory experiment.

Citation Download Citation

C. David Wang, William T. Walter, and Robert H. Kagann "Neural network and classical least squares methods for quantitative analysis in remote sensing FTIR systems", Proc. SPIE 2366, Optical Instrumentation for Gas Emissions Monitoring and Atmospheric Measurements, (10 February 1995); https://doi.org/10.1117/12.205566

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available