17 May 2016 Development of a real-time neural network estimator to improve defense capabilities of HEO satellites
Author Affiliations +
Abstract
The need to observe thermal targets from space is crucial for monitoring both natural events and hostile threats1. Satellite design must balance high spatial resolution with high sensitivity and multiple spectral channels2. Defense satellites ultimately choose high sensitivity with a small number of spectral channels. This limitation makes atmospheric contamination due to water vapor a significant problem that cannot be determined from the satellite itself. Using a neural network (NN) approach in conjunction with real time measurements or model predictions of sounding data, we show that an accurate estimation of band radiation and band transmission can be computed in near real time. To demonstrate accuracy, we compare the neural network outputs to both model atmospheres as well as the Modis data for a suitable water vapor band.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Samuel Lightstone, Samuel Lightstone, Moshe Fink, Moshe Fink, Fred Moshary, Fred Moshary, Barry Gross, Barry Gross, } "Development of a real-time neural network estimator to improve defense capabilities of HEO satellites", Proc. SPIE 9828, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications XIII, 98280G (17 May 2016); doi: 10.1117/12.2220073; https://doi.org/10.1117/12.2220073
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT


Back to Top