{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T15:54:30Z","timestamp":1789142070159,"version":"build-2803163510"},"reference-count":40,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T00:00:00Z","timestamp":1780099200000},"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>Accurate monitoring of nitrogen oxides (NOx) is essential due to their adverse effects on environmental quality and public health. To address the spectral overlap between NO and NO2 in ultraviolet differential optical absorption spectroscopy (UV-DOAS), we propose a multi-scale dual-branch interaction attention network (MDIAN) for simultaneous concentration retrieval in gas mixtures. The model employs a dual-branch multi-scale convolutional architecture to extract local narrow-band absorption details and broad spectral profile features. A cross-attention mechanism is introduced to enable feature interaction between the NO and NO2 branches. A bidirectional long short-term memory (Bi-LSTM) network is further incorporated to model contextual dependencies along the wavelength dimension, enabling joint regression of both target gases. Experimental results show that the proposed model achieves mean absolute errors (MAE) of 0.076 ppm for NO and 0.062 ppm for NO2, with coefficients of determination (R2) of 0.9998 for both gases, outperforming traditional regression methods and baseline deep learning models. The uncertainties are 0.69% and 0.76%, respectively, and the inference time per sample ranges from 48.9 to 74.5 ms. These results indicate that MDIAN achieves a favorable balance among accuracy, stability, and real-time performance, offering a promising approach for intelligent monitoring of complex gas mixtures using UV-DOAS.<\/jats:p>","DOI":"10.3390\/s26113461","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:11:01Z","timestamp":1780333861000},"page":"3461","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A UV-DOAS-Based Multi-Scale Interaction Attention Network for Simultaneous Retrieval of NO and NO2 in Gas Mixtures"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0436-0804","authenticated-orcid":false,"given":"Yuwei","family":"Mu","sequence":"first","affiliation":[{"name":"Purification Equipment Research Institute of CSSC, Handan 056000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Wen","sequence":"additional","affiliation":[{"name":"Purification Equipment Research Institute of CSSC, Handan 056000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1038\/nature04092","article-title":"Increase in tropospheric nitrogen dioxide over China observed from space","volume":"437","author":"Richter","year":"2005","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"eadm8680","DOI":"10.1126\/sciadv.adm8680","article-title":"Nitrogen dioxide exposure, health outcomes, and associated demographic disparities due to gas and propane combustion by US stoves","volume":"10","author":"Kashtan","year":"2024","journal-title":"Sci. Adv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2063","DOI":"10.1016\/S1352-2310(99)00460-4","article-title":"Atmospheric chemistry of VOCs and NOx","volume":"34","author":"Atkinson","year":"2000","journal-title":"Atmos. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e1047","DOI":"10.1016\/S2468-2667(24)00264-0","article-title":"Associations of long-term nitrogen dioxide exposure with wide spectrum of diseases: A prospective cohort study of 0.5 million Chinese adults","volume":"9","author":"Xia","year":"2024","journal-title":"Lancet Public Health"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"743","DOI":"10.3109\/10408440903294945","article-title":"Critical review of the human data on short-term nitrogen dioxide (NO2) exposures: Evidence for NO2 no-effect levels","volume":"39","author":"Hesterberg","year":"2009","journal-title":"Crit. Rev. Toxicol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kwoka, M., and Szuber, J. (2020). Studies of NO2 Gas-Sensing Characteristics of a Novel Room-Temperature Surface-Photovoltage Gas Sensor Device. Sensors, 20.","DOI":"10.3390\/s20020408"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10643380490265117","article-title":"A review of instrumentation and measurement techniques for ground-based and airborne field studies of gas-phase tropospheric chemistry","volume":"34","author":"Clemitshaw","year":"2004","journal-title":"Crit. Rev. Environ. Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108423","DOI":"10.1016\/j.jvolgeores.2025.108423","article-title":"Ultraviolet and visible remote sensing of volcanic gas emissions","volume":"468","author":"Kern","year":"2025","journal-title":"J. Volcanol. Geotherm. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/0022-4073(96)00042-8","article-title":"DOAS for flue gas monitoring\u2014I. Temperature effects in the UV\/visible absorption spectra of NO, NO2, SO2 and NH3","volume":"56","author":"Mellqvist","year":"1996","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/0022-4073(96)00043-X","article-title":"DOAS for flue gas monitoring\u2014II. Deviations from the Beer-Lambert law for the UV\/visible absorption spectra of NO, NO2, SO2 and NH3","volume":"56","author":"Mellqvist","year":"1996","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6041","DOI":"10.1364\/AO.35.006041","article-title":"Numerical analysis and estimation of the statistical error of differential optical absorption spectroscopy measurements with least-squares methods","volume":"35","author":"Stutz","year":"1996","journal-title":"Appl. Opt."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, M., Yin, X., Zhang, J., Meijering, E., and Hu, J. (2023). Deep Learning in Diverse Intelligent Sensor Based Systems. Sensors, 23.","DOI":"10.3390\/s23010062"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xi, M., Dai, H., Wen, J., and Yang, J. (2024). Z-Score Experience Replay in Off-Policy Deep Reinforcement Learning. Sensors, 24.","DOI":"10.3390\/s24237746"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Guo, Y., Sun, X., Li, L., Shi, Y., Cheng, W., and Pan, L. (2025). Deep-Learning-Based Analysis of Electronic Skin Sensing Data. Sensors, 25.","DOI":"10.3390\/s25051615"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"137285","DOI":"10.1016\/j.snb.2025.137285","article-title":"Multi-component gas sensing via spectral feature engineering","volume":"430","author":"Sy","year":"2025","journal-title":"Sens. Actuators B Chem."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"106207","DOI":"10.1016\/j.infrared.2025.106207","article-title":"Ambient noise filtering in methane laser absorption spectroscopy detection using fully connected neural networks","volume":"152","author":"Zhou","year":"2026","journal-title":"Infrared Phys. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"124267","DOI":"10.1016\/j.saa.2024.124267","article-title":"Application of bi-directional long short-term memory in separating NO and SO2 ultraviolet differential absorption spectrum signals","volume":"315","author":"Peng","year":"2024","journal-title":"Spectrochim. Acta A Mol. Biomol. Spectrosc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"23312","DOI":"10.1021\/acs.analchem.5c03975","article-title":"Robust Identification of Gas Mixtures from FTIR Spectra using Attention Mechanism to Mitigate Instrument Line Shape Variations","volume":"97","author":"Xu","year":"2025","journal-title":"Anal. Chem."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"48406","DOI":"10.1364\/OE.543450","article-title":"Qualitative identification of passive Fourier transform infrared spectra via an attention mechanism based deep learning approach","volume":"32","author":"Zhang","year":"2024","journal-title":"Opt. Express"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"138057","DOI":"10.1016\/j.snb.2025.138057","article-title":"An online trace gas detection system for multi-component atmospheric pollutants based on ultraviolet differential optical absorption spectroscopy combined with convolutional attention neural network","volume":"441","author":"Gao","year":"2025","journal-title":"Sens. Actuators B Chem."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"112057","DOI":"10.1016\/j.jms.2025.112057","article-title":"Study on two-stage concentration detection algorithm based on UV-DOAS: For mixed gas of NO and SO2","volume":"413","author":"Peng","year":"2025","journal-title":"J. Mol. Spectrosc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"132965","DOI":"10.1016\/j.fuel.2024.132965","article-title":"Detection of ultra-low concentration NH3, SO2, and NO using UV-DOAS combined with multidimensional spectral fusion","volume":"378","author":"Xie","year":"2024","journal-title":"Fuel"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1021\/ed074p744.3","article-title":"Beer-Lambert law","volume":"74","author":"Calloway","year":"1997","journal-title":"J. Chem. Educ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100901","DOI":"10.1117\/1.JBO.26.10.100901","article-title":"Beer-Lambert law for optical tissue diagnostics: Current state of the art and the main limitations","volume":"26","author":"Oshina","year":"2021","journal-title":"J. Biomed. Opt."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"631","DOI":"10.5194\/amt-3-631-2010","article-title":"Extending differential optical absorption spectroscopy for limb measurements in the UV","volume":"3","author":"Pukite","year":"2010","journal-title":"Atmos. Meas. Tech."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.1021\/ed074p1459","article-title":"Illustration deviations in the Beer-Lambert law in an instrumental analysis laboratory: Measuring atmospheric pollutants by differential optical absorption spectrometry","volume":"74","author":"Allen","year":"1997","journal-title":"J. Chem. Educ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.snb.2016.10.055","article-title":"Optical sulfur dioxide sensor based on broadband absorption spectroscopy in the wavelength range of 198\u2013222 nm","volume":"241","author":"Wang","year":"2017","journal-title":"Sens. Actuators B Chem."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Van Roozendael, M., Hendrick, F., Friedrich, M., Fayt, C., Bais, A., Beirle, S., B\u00f6sch, T., and Comas, M. (2024). Fiducial Reference Measurements for Air Quality Monitoring Using Ground-Based MAX-DOAS Instruments (FRM4DOAS). Remote Sens., 16.","DOI":"10.3390\/rs16234523"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"9515308","DOI":"10.1109\/TIM.2024.3450069","article-title":"Ultrasensitive NO Monitoring System Based on Fourier Transform Ultraviolet Differential Optical Absorption Spectrum","volume":"73","author":"Peng","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1959","DOI":"10.5194\/amt-6-1959-2013","article-title":"Regularisation model study for the least-squares retrieval of aerosol extinction time series from UV\/VIS MAX-DOAS observations for a ground layer profile parameterisation","volume":"6","author":"Hartl","year":"2013","journal-title":"Atmos. Meas. Tech."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"127268","DOI":"10.1016\/j.saa.2025.127268","article-title":"Adversarial unpaired disentanglement network (AUDNet): Precise analysis of severely overlapping CS2\/SO2 signals in UV-DOAS","volume":"349","author":"Du","year":"2026","journal-title":"Spectrochim. Acta A Mol. Biomol. Spectrosc."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"132323","DOI":"10.1016\/j.optcom.2025.132323","article-title":"Development of an ultrawide-band modeless Ce:LiCAF ultraviolet laser for SO2 detection using differential optical absorption spectroscopy","volume":"594","author":"Le","year":"2025","journal-title":"Opt. Commun."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"114303","DOI":"10.1016\/j.optlastec.2025.114303","article-title":"An easy-to-maintain optical gas temperature sensing system based on the regional temperature effect of UV-DOAS","volume":"193","author":"Li","year":"2026","journal-title":"Opt. Laser Technol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"19149","DOI":"10.1039\/D3RA01512B","article-title":"Study on the concentration retrieval of SO2 and NO2 in mixed gases based on the improved DOAS method","volume":"13","author":"Yang","year":"2023","journal-title":"RSC Adv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"587","DOI":"10.3934\/ipi.2014.8.587","article-title":"A semi-blind source separation method for differential optical absorption spectroscopy of atmospheric gas mixtures","volume":"8","author":"Sun","year":"2014","journal-title":"Inverse Probl. Imaging"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Chen, S., Tian, X., Mu, T., Yuan, J., Cao, X., and Cheng, G. (2025). Enhancement of Methane Detection in Tunable Diode Laser Absorption Spectroscopy Using Savitzky\u2013Golay Filtering. Photonics, 12.","DOI":"10.3390\/photonics12010002"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"129913","DOI":"10.1016\/j.neucom.2025.129913","article-title":"DACFusion: Dual Asymmetric Cross-Attention guided feature fusion for multispectral object detection","volume":"635","author":"Qian","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_39","first-page":"2447","article-title":"Study on the Selection of Parameters for Evaluating Drug NIR Universal Quantitative Models","volume":"36","author":"Feng","year":"2016","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1039\/C9JA00090A","article-title":"Direct determination of soil texture using laser-induced breakdown spectroscopy and multivariate linear regressions","volume":"34","author":"Goueguel","year":"2019","journal-title":"J. Anal. At. Spectrom."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3461\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:12:49Z","timestamp":1780333969000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":40,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26113461"],"URL":"https:\/\/doi.org\/10.3390\/s26113461","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,30]]}}}