Discerning molecular transitions using adaptive Savitzy-Golay filtering and ML-based classification in mid-infrared sensing

Al Alexis; Ryan Bischoff; Mohammad A. Khan

doi:10.1117/12.3013755

7 June 2024 Discerning molecular transitions using adaptive Savitzy-Golay filtering and ML-based classification in mid-infrared sensing

Al Alexis, Ryan Bischoff, Mohammad A. Khan

Author Affiliations +

Proceedings Volume 13056, Chemical, Biological, Radiological, Nuclear, and Explosives (CBRNE) Sensing XXV; 130561J (2024) https://doi.org/10.1117/12.3013755
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Conference Poster

Abstract

Mid-infrared sensing in the broadband spectral region of 5 – 11 𝜇m is suitable for detecting and quantifying multiple trace species. However, the challenge in detection is precise discrimination due to the broad linewidth of molecular transitions of species like methane, nitrous oxide, and other volatile organic compounds. In addition, isotopic transitions are generally weaker, with significant overlap with the neighboring abundant molecular transitions. This paper shows broadband detection of multiple species using an external cavity laser operation in 6 to 11 𝜇m spectral region. We use a combination of Savitzy-Golay filtering and machine learning-based classification to discern weaker rotational vibrational transitions. The proposed scheme is used to denoise and discriminate molecular transition in mid-infrared absorption spectroscopy. We show that an optimized S-G framework can be used by choosing a selected frame length determined by the adaptive learning outcome with low loss. We show that an ML-based adaptive SV filter can effectively suppress mod-hop (or any other instrumental-related effects and drifts). This is achieved by appropriately training the absorption spectroscopy signals with a calibrated reference in a (gaussian or thermal) noisy environment.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Al Alexis, Ryan Bischoff, and Mohammad A. Khan "Discerning molecular transitions using adaptive Savitzy-Golay filtering and ML-based classification in mid-infrared sensing", Proc. SPIE 13056, Chemical, Biological, Radiological, Nuclear, and Explosives (CBRNE) Sensing XXV, 130561J (7 June 2024); https://doi.org/10.1117/12.3013755

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