{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T06:35:52Z","timestamp":1778999752448,"version":"3.51.4"},"reference-count":41,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:00:00Z","timestamp":1710374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning methods, a powerful form of artificial intelligence, have been applied in a number of spectroscopy and gas sensing applications. However, the speciation of multi-component gas mixtures from infrared (IR) absorption spectra using deep learning remains to be explored. Here, we propose a one-dimensional deep convolutional neural network gas classification model for the identification of small molecules of interest based on IR absorption spectra in flexible user-defined frequency ranges. The molecules considered include ten that are of interest in the atmosphere or in industrial and environmental processes: water vapor, carbon dioxide, ozone, nitrous oxide, carbon monoxide, methane, nitric oxide, sulfur dioxide, nitrogen dioxide, and ammonia. A simulated dataset of IR absorption spectra for mixtures of these molecules diluted in air was generated and used to train a deep learning model. The model was tested against simulated spectra containing noise and was found to provide speciation predictions with accuracy from 82 to 97%. The internal operation of the model was investigated using class activation maps that illustrate how the model prioritizes spectral information for classification. Finally, the model was demonstrated for the prediction of speciation for two synthetic experimental mixture spectra. The proposed model and the dataset generation strategies are generalized and can be implemented for other gases, different frequency ranges, and spectroscopy types. The multi-component speciation method developed herein is the first application of a convolutional neural network model, trained on HITRAN-based simulations, for spectral identification.<\/jats:p>","DOI":"10.3390\/s24061873","type":"journal-article","created":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T04:47:05Z","timestamp":1710478025000},"page":"1873","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Deep Learning for Gas Sensing via Infrared Spectroscopy"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9759-5295","authenticated-orcid":false,"given":"M. Arshad Zahangir","family":"Chowdhury","sequence":"first","affiliation":[{"name":"Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute, 110 Eighth St., Troy, NY 12180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3174-9615","authenticated-orcid":false,"given":"Matthew A.","family":"Oehlschlaeger","sequence":"additional","affiliation":[{"name":"Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute, 110 Eighth St., Troy, NY 12180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.jqsrt.2017.06.038","article-title":"The HITRAN2016 molecular spectroscopic database","volume":"203","author":"Gordon","year":"2017","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_2","unstructured":"Sathyanarayana, D.N. (2004). Vibrational Spectroscopy: Theory and Applications, New Age International."},{"key":"ref_3","unstructured":"Bernath, P.F. (2020). Spectra of Atoms and Molecules, Oxford University Press."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.optlaseng.2005.04.015","article-title":"Near-and mid-infrared laser monitoring of industrial processes, environment and security applications","volume":"44","author":"Willer","year":"2006","journal-title":"Opt. Lasers Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"031003","DOI":"10.1088\/2515-7647\/ac0542","article-title":"Ultra-broadband infrared gas sensor for pollution detection: The TRIAGE project","volume":"3","author":"Napier","year":"2021","journal-title":"J. Phys. Photonics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.pecs.2016.12.002","article-title":"Infrared laser-absorption sensing for combustion gases","volume":"60","author":"Goldenstein","year":"2017","journal-title":"Prog. Energy Combust. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.rse.2015.12.045","article-title":"Advances in 3-D infrared remote sensing gas monitoring. Application to an urban atmospheric environment","volume":"175","author":"Barres","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yu, C., Zhang, W., Zheng, W., Wang, H., Lei, Z., and Zhang, P. (2019, January 7\u20139). Remote sense for environment pollution gases in wide infrared spectral range. Proceedings of the AOPC 2019: Optical Spectroscopy and Imaging, Beijing, China.","DOI":"10.1117\/12.2547867"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6716","DOI":"10.1364\/AO.48.006716","article-title":"Thermal and near infrared sensor for carbon observation Fourier-transform spectrometer on the Greenhouse Gases Observing Satellite for greenhouse gases monitoring","volume":"48","author":"Kuze","year":"2009","journal-title":"Appl. Opt."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5199","DOI":"10.5194\/amt-11-5199-2018","article-title":"GreenHouse gas Observations of the Stratosphere and Troposphere (GHOST): An airborne shortwave-infrared spectrometer for remote sensing of greenhouse gases","volume":"11","author":"Humpage","year":"2018","journal-title":"Atmos. Meas. Tech."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Popa, D., and Udrea, F. (2019). Towards integrated mid-infrared gas sensors. Sensors, 19.","DOI":"10.3390\/s19092076"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/j.snb.2016.03.040","article-title":"A review on non-dispersive infrared gas sensors: Improvement of sensor detection limit and interference correction","volume":"231","author":"Dinh","year":"2016","journal-title":"Sens. Actuators B Chem."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"128414","DOI":"10.1016\/j.snb.2020.128414","article-title":"A grey-box machine learning based model of an electrochemical gas sensor","volume":"321","author":"Aliramezani","year":"2020","journal-title":"Sens. Actuators B Chem."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s00340-021-07582-0","article-title":"Evaluation of machine learning methods for classification of rotational absorption spectra for gases in the 220\u2013330 GHz range","volume":"127","author":"Chowdhury","year":"2021","journal-title":"Appl. Phys. B"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s00340-022-07879-8","article-title":"A support vector machines framework for identification of infrared spectra","volume":"128","author":"Chowdhury","year":"2022","journal-title":"Appl. Phys. B"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2200016","DOI":"10.1002\/aisy.202200016","article-title":"Machine learning-enabled smart gas sensing platform for identification of industrial gases","volume":"4","author":"Huang","year":"2022","journal-title":"Adv. Intell. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.1021\/acssensors.2c02615","article-title":"TSMC-Net: Deep-Learning Multigas Classification Using THz Absorption Spectra","volume":"8","author":"Chowdhury","year":"2023","journal-title":"ACS Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"135230","DOI":"10.1016\/j.snb.2023.135230","article-title":"Local dynamic neural network for quantitative analysis of mixed gases","volume":"404","author":"Li","year":"2024","journal-title":"Sens. Actuators B Chem."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1021\/acs.jcim.3c01633","article-title":"Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview","volume":"64","author":"Nicolle","year":"2024","journal-title":"J. Chem. Inf. Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1038\/s44172-023-00105-z","article-title":"Gas phase multicomponent detection and analysis combining broadband dual-frequency comb absorption spectroscopy and deep learning","volume":"2","author":"Tian","year":"2023","journal-title":"Comms. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"113392","DOI":"10.1016\/j.sna.2022.113392","article-title":"Co-training neural network-based infrared sensor array for natural gas monitoring","volume":"335","author":"Wang","year":"2022","journal-title":"Sens. Actuators A Phys."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chowdhury, M.A.Z., Rice, T.E., and Oehlschlaeger, M.A. (2022). VOC-Net: A Deep Learning Model for the Automated Classification of Rotational THz Spectra of Volatile Organic Compounds. Appl. Sci., 12.","DOI":"10.3390\/app12178447"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3342","DOI":"10.1109\/JSEN.2023.3234194","article-title":"E-Nose System Based on Fourier Series for Gases Identification and Concentration Estimation From Food Spoilage","volume":"23","author":"Luo","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"106558","DOI":"10.1016\/j.rinp.2023.106558","article-title":"Identifying gas mixtures based on acoustic relaxation spectroscopy and attention recurrent neural network","volume":"50","author":"Liu","year":"2023","journal-title":"Results Phys."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108918","DOI":"10.1016\/j.optlastec.2022.108918","article-title":"A novel breath molecule sensing system based on deep neural network employing multiple-line direct absorption spectroscopy","volume":"158","author":"Bayrakli","year":"2023","journal-title":"Opt. Lasers Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, J., Niu, X., Zheng, L., Zheng, C., and Wang, Y. (2016). Wireless mid-infrared spectroscopy sensor network for automatic carbon dioxide fertilization in a greenhouse environment. Sensors, 16.","DOI":"10.3390\/s16111941"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3709","DOI":"10.1016\/j.matpr.2020.10.161","article-title":"Study of gas sensor detection for NOX Gas: A review","volume":"37","author":"Srivastava","year":"2021","journal-title":"Mater. Today Proc."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kwa\u015bny, M., and Bombalska, A. (2023). Optical methods of methane detection. Sensors, 23.","DOI":"10.3390\/s23052834"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2557","DOI":"10.5194\/amt-15-2557-2022","article-title":"Improved ozone monitoring by ground-based FTIR spectrometry","volume":"15","author":"Schneider","year":"2022","journal-title":"Atmos. Meas. Tech."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wu, P., Shan, C., Liu, C., Xie, Y., Wang, W., Zhu, Q., Zeng, X., and Liang, B. (2023). Ground-Based Remote Sensing of Atmospheric Water Vapor Using High-Resolution FTIR Spectrometry. Remote Sens., 15.","DOI":"10.3390\/rs15143484"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1016\/j.talanta.2019.06.034","article-title":"Ammonia gas sensors: A comprehensive review","volume":"204","author":"Kwak","year":"2019","journal-title":"Talanta"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1016\/j.snb.2004.11.054","article-title":"Ammonia sensors and their applications\u2014A review","volume":"107","author":"Timmer","year":"2005","journal-title":"Sens. Actuators B Chem."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"117215","DOI":"10.1016\/j.eswa.2022.117215","article-title":"Comprehensive comparative study of multi-label classification methods","volume":"203","author":"Bogatinovski","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_37","unstructured":"Dumoulin, V., and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv."},{"key":"ref_38","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.jqsrt.2016.03.005","article-title":"HITRAN Application Programming Interface (HAPI): A comprehensive approach to working with spectroscopic data","volume":"177","author":"Kochanov","year":"2016","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"59","DOI":"10.6028\/jres.104.004","article-title":"The NIST quantitative infrared database","volume":"104","author":"Chu","year":"1999","journal-title":"J. Res. Natl. Inst. Stand. Technol."},{"key":"ref_41","unstructured":"Lee, S.A. (1982). The Coblentz Society Desk Book, The Coblentz Scoeity."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/6\/1873\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:13:40Z","timestamp":1760105620000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/6\/1873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,14]]},"references-count":41,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["s24061873"],"URL":"https:\/\/doi.org\/10.3390\/s24061873","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,14]]}}}