Abstract
Ongoing research at Los Alamos National Laboratory studies the Earth’s radio frequency (RF) background utilizing satellite-based RF observations of terrestrial lightning. Such impulsive events occur in the presence of additive noise and structured clutter and appear as broadband nonlinear chirps at a receiver on-orbit due to ionospheric dispersion. The Fast On-orbit Recording of Transient Events (FORTE) satellite provided a rich RF lightning database. Application of modern pattern recognition techniques to this database may further lightning research and potentially improve event discrimination capabilities for future satellite payloads. We extend two established dictionary learning algorithms, K-SVD and Hebbian, for use in classification of satellite RF data. Both algorithms allow us to learn features without relying on analytical constraints or additional knowledge about the expected signal characteristics. We use a pursuit search over the learned dictionaries to generate sparse classification features and discuss performance in terms of event classification using a nearest subspace classifier. We show a use of the two dictionary types in a mixed implementation to showcase algorithm distinctions in extracting discriminative information. We use principal component analysis to analyze and compare the learned dictionary spaces to the real data space, and we discuss some aspects of computational complexity and implementation.
Highlights
Ongoing research at Los Alamos National Laboratory (LANL) studies the Earth’s radio frequency (RF) background utilizing satellite-based RF observations of terrestrial lightning
Los Alamos Portable Pulser (LAPP) shots represent a small percentage of total Fast On-orbit Recording of Transient Events (FORTE) records (
This paper extends two established dictionary learning techniques to satellite RF lightning classification using FORTE recordings
Summary
Ongoing research at Los Alamos National Laboratory (LANL) studies the Earth’s radio frequency (RF) background utilizing satellite-based RF observations of terrestrial lightning. We examine two previously developed supervised dictionary learning methods, the K-SVD algorithm[6] and the Hebbian learning algorithm,[8] and compare their classification performance on real lightning data using Skretting and Husøy’s minimum residual (MR) classifier, originally introduced for image texture classification.[14] We use subspace analysis based on principal component decomposition in a novel way to illustrate the different ways in which the two dictionary learning methods capture entropy in training data, and to discuss their classification performance Part of this manuscript was recently published as an SPIE conference proceeding,[15] and it is being republished here with some revisions given its potential to significantly impact the classification of remotely sensed time series data.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have