Remote Detection of Heated Ethanol Plumes by Airborne Passive Fourier Transform Infrared Spectrometry

Abstract

Methodology is developed for the automated detection of heated plumes of ethanol vapor with airborne passive Fourier transform infrared spectrometry. Positioned in a fixed-wing aircraft in a downward-looking mode, the spectrometer is used to detect ground sources of ethanol vapor from an altitude of 2000-3000 ft. Challenges to the use of this approach for the routine detection of chemical plumes include (1) the presence of a constantly changing background radiance as the aircraft flies, (2) the cost and complexity of collecting the data needed to train the classification algorithms used in implementing the plume detection, and (3) the need for rapid interferogram scans to minimize the ground area viewed per scan. To address these challenges, this work couples a novel ground-based data collection and training protocol with the use of signal processing and pattern recognition methods based on short sections of the interferogram data collected by the spectrometer. In the data collection, heated plumes of ethanol vapor are released from a portable emission stack and viewed by the spectrometer from ground level against a synthetic background designed to simulate a terrestrial radiance source. Classifiers trained with these data are subsequently tested with airborne data collected over a period of 2.5 years. Two classifier architectures are compared in this work: support vector machines (SVM) and piecewise linear discriminant analysis (PLDA). When applied to the airborne test data, the SVM classifiers perform best, failing to detect ethanol in only 8% of the cases in which it is present. False detections occur at a rate of less than 0.5%. The classifier performs well in spite of differences between the backgrounds associated with the ground-based and airborne data collections and the instrumental drift arising from the long time span of the data collection. Further improvements in classification performance are judged to require increased sophistication in the ground-based data collection in order to provide a better match to the infrared backgrounds observed from the air.

Beyond the adaptive matched filter: nonlinear detectors for weak signals in high-dimensional clutter

“…The appeal of machine learning methods, such as the support vector machine, for hyperspectral detection 25 and classification 26,27 problems, is that it draws detection contours in a manner that is driven more by the data than the model. This is particularly attractive when the clutter is known to be structured, but that structure is not known a priori.…”

“…(25), and the solution can be expressed in the two-dimensional space of the MFR plot, as seen in Fig. 5.…”

Signal processing and pattern recognition methods for the remote, airborne detection of radioisotopes by gamma-ray spectroscopy

“…This second set of patterns should be characteristically similar to the training patterns, in order to assess in a controlled environment whether the discriminant optimization was isolated to the training set alone or can be applied to multiple sets of data. 36,77,83 By defining the classes as active and inactive, similar to the training set, the discriminants can be applied to the new set of monitoring data. By assessing how the discriminants separate the classes, the performance of the simplex optimization can be determined.…”

“…[30][31][32][33][34][35] Previous work done by this laboratory involves the pattern recognition of FT-IR interferograms collected during passive infrared remote sensing measurements. 30,[35][36][37][38] The work described in this dissertation focuses on the use of piecewise linear discriminant analysis (PLDA) or linear discriminant analysis (LDA). [39][40][41][42][43] These methods will be described in Chapter 3.…”

“…When dealing with gamma-ray detections, the further the detector is from the analyte the more suppressed the target signal will become due to the various gamma-ray interactions described in Chapter 2. 30,36,38,[60][61] Background or interfering signals can make these detections more difficult by further suppressing or interfering with the analyte signal. 62 Because of the inherent S/N difficulties, the spectra obtained for remote detection purposes frequently require preprocessing before they can be used effectively with pattern recognition algorithms.…”