Share Email Print
cover

Proceedings Paper • new

A machine learning approach for predicting atmospheric aerosol size distributions
Author(s): Joshua J. Rudiger; Kevin Book; John Stephen deGrassie; Stephen Hammel; Brooke Baker
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

An accurate model and parameterization of aerosol concentration is needed to predict the performance of electro-optical imaging systems. Current models have been shown to vary widely in their ability to accurately predict aerosol size distributions and subsequent scattering properties of the atmosphere. One of the more prevalent methods for modeling particle size spectra consists of fitting a modified gamma function to measurement data, however this limits the distribution to a single mode. Machine learning models have been shown to predict complex multimodal aerosol particle size spectra. Here we establish an empirical model for predicting aerosol size spectra using machine learning techniques. This is accomplished through measurements of aerosols size distributions over the course of eight months. The machine learning models are shown to extend the functionality of Advanced Navy Aerosol Model (ANAM), developed to model the size distribution of aerosols in the maritime environment.

Paper Details

Date Published: 18 September 2017
PDF: 11 pages
Proc. SPIE 10408, Laser Communication and Propagation through the Atmosphere and Oceans VI, 104080Q (18 September 2017); doi: 10.1117/12.2276717
Show Author Affiliations
Joshua J. Rudiger, SPAWAR Systems Ctr. Pacific (United States)
Kevin Book, SPAWAR Systems Ctr. Pacific (United States)
John Stephen deGrassie, SPAWAR Systems Ctr. Pacific (United States)
Stephen Hammel, SPAWAR Systems Ctr. Pacific (United States)
Brooke Baker, SPAWAR Systems Ctr. Atlantic (United States)


Published in SPIE Proceedings Vol. 10408:
Laser Communication and Propagation through the Atmosphere and Oceans VI
Jeremy P. Bos; Alexander M. J. van Eijk; Stephen M. Hammel, Editor(s)

© SPIE. Terms of Use
Back to Top