Retrieval of carbon dioxide concentrations using Tm-doped laser with deep learning algorithm

Hui Yin; Kun Liu

doi:10.1117/12.2692273

27 September 2023 Retrieval of carbon dioxide concentrations using Tm-doped laser with deep learning algorithm

Hui Yin, Kun Liu

Proceedings Volume 12813, Asia-Pacific Optical Sensors Conference (APOS 2023); 128130G (2023) https://doi.org/10.1117/12.2692273
Event: Asia Pacific Optical Sensors Conference 2023, 2023, Tianjin, China

Abstract

Sensitive detection of CO₂ concentrations is exceedingly significant for ecological environmental protection and people's production safety. The convolutional layer of convolutional neural network (CNN) can automatically extract features, which greatly saves the cost of manual processing. In this paper, we build a gas sensing system based on thulium-doped ring laser to obtain CO₂ absorption spectral data. A one-dimensional CNN model was proposed to process the data and achieve accurate prediction of CO₂ concentrations. The prediction of the test set data resulted in a regression coefficient R² of 99.58% and MSE of 0.010, which meets the gas detection requirements. The combination of deep learning algorithm and gas absorption spectroscopy provides new ideas for absorption spectroscopy-based gas sensing technology.

Citation Download Citation

Hui Yin and Kun Liu "Retrieval of carbon dioxide concentrations using Tm-doped laser with deep learning algorithm", Proc. SPIE 12813, Asia-Pacific Optical Sensors Conference (APOS 2023), 128130G (27 September 2023); https://doi.org/10.1117/12.2692273

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