{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:55:00Z","timestamp":1785434100620,"version":"3.56.0"},"reference-count":42,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["RS-2022-00144110"],"award-info":[{"award-number":["RS-2022-00144110"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"award":["RS-2022-00144110"],"award-info":[{"award-number":["RS-2022-00144110"]}],"id":[{"id":"https:\/\/ror.org\/013aysd81","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Distributed acoustic sensing (DAS) systems capture complex, nonlinear wave propagation across fiber-optic cables. Conventional event classification architectures, constrained by static physical topologies or isolated spatial grids, fail to effectively adapt to the dynamic feature relationships associated with such events, particularly when modeling complex spatiotemporal interactions across sensor arrays. To resolve these structural limitations, we introduce the Spectro-Spatial Dynamic Graph Neural Network (S2-DyGNN), whose architecture couples a two-dimensional frequency\u2013time convolutional front-end with a dual-matrix graph neural network (GNN). First, the convolutional module extracts spectro-temporal features, explicitly capturing localized acoustic dynamics independent of inter-sensor interference. Subsequently, the graph module constructs a dual-matrix topology, fusing a static physical distance prior with a data-driven adjacency matrix that recalculates spatial connections frame by frame from input signals. When evaluated on a highly skewed nine-class DAS field dataset, S2-DyGNN outperformed other conventional models by achieving a peak macro-averaged F1-score of 86.6% and an overall accuracy of 94.0%. The dual-matrix graph topology prevented dominant background features from washing out sparse transient events, improving the minority \u201copenclose\u201d class F1-score to 55.7% compared to the 48.0% ceiling of a static graph topology. These results demonstrate that explicitly coupling localized spectro-temporal representations with physically anchored spatial topologies consistently outperforms models that process these domains in isolation, providing a highly robust and scalable solution for real-world continuous monitoring systems.<\/jats:p>","DOI":"10.3390\/s26144417","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:05:31Z","timestamp":1783929931000},"page":"4417","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["S2-DyGNN: A Spectro-Spatial Dynamic Graph Neural Network for Acoustic Event Classification in Distributed Acoustic Sensing"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3892-9886","authenticated-orcid":false,"given":"Seunghun","family":"Jeong","sequence":"first","affiliation":[{"name":"Department of AI Convergence, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7180-9309","authenticated-orcid":false,"given":"Huioon","family":"Kim","sequence":"additional","affiliation":[{"name":"Optical Precision Measurement Research Center, Korea Photonic Technology Institute, Gwangju 61007, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9805-567X","authenticated-orcid":false,"given":"Young Ho","family":"Kim","sequence":"additional","affiliation":[{"name":"Optical Precision Measurement Research Center, Korea Photonic Technology Institute, Gwangju 61007, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7978-0454","authenticated-orcid":false,"given":"Hyoyoung","family":"Jung","sequence":"additional","affiliation":[{"name":"Optical Precision Measurement Research Center, Korea Photonic Technology Institute, Gwangju 61007, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0105-6693","authenticated-orcid":false,"given":"Hong Kook","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of AI Convergence, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea"},{"name":"Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Gorshkov, B.G., Y\u00fcksel, K., Fotiadi, A.A., Wuilpart, M., Korobko, D.A., Zhirnov, A.A., Stepanov, K.V., Turov, A.T., Konstantinov, Y.A., and Lobach, I.A. (2022). Scientific applications of distributed acoustic sensing: State-of-the-art review and perspective. Sensors, 22.","DOI":"10.3390\/s22031033"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3671","DOI":"10.1109\/JLT.2021.3059771","article-title":"Optical fiber distributed acoustic sensors: A review","volume":"39","author":"He","year":"2021","journal-title":"J. Lightw. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Tejedor, J., Macias-Guarasa, J., Martins, H.F., Pastor-Graells, J., Corredera, P., and Martin-Lopez, S. (2017). Machine learning methods for pipeline surveillance systems based on distributed acoustic sensing: A review. Appl. Sci., 7.","DOI":"10.3390\/app7080841"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1093\/gji\/ggae382","article-title":"A real scale application of a novel set of spatial and similarity features for detection and classification of natural seismic sources from distributed acoustic sensing data","volume":"240","author":"Huynh","year":"2025","journal-title":"Geophys. J. Int."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pedersen, H.B., Heiselberg, P., Heiselberg, H., Simonsen, A., and S\u00f8rensen, K.A. (2025). A feasibility study of automated detection and classification of signals in distributed acoustic sensing. Sensors, 25.","DOI":"10.3390\/s25175445"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s43074-025-00160-z","article-title":"Artificial intelligence-driven distributed acoustic sensing technology and engineering application","volume":"6","author":"Shao","year":"2025","journal-title":"PhotoniX"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1515\/teme-2022-0098","article-title":"A collection of machine learning assisted distributed fiber optic sensors for infrastructure monitoring","volume":"90","author":"Karapanagiotis","year":"2023","journal-title":"TM-Tech. Mess."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103911","DOI":"10.1016\/j.yofte.2024.103911","article-title":"State-of-the-art application and challenges of optical fibre distributed acoustic sensing in civil engineering","volume":"87","author":"Ghazali","year":"2024","journal-title":"Opt. Fiber Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bublin, M. (2021). Event detection for distributed acoustic sensing: Combining knowledge-based, classical machine learning, and deep learning approaches. Sensors, 21.","DOI":"10.3390\/s21227527"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1007\/s13320-017-0360-1","article-title":"Feature extraction and identification in distributed optical-fiber vibration sensing system for oil pipeline safety monitoring","volume":"7","author":"Wu","year":"2017","journal-title":"Photonic Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"11983","DOI":"10.1109\/JSEN.2021.3066037","article-title":"Pattern recognition for distributed optical fiber vibration sensing: A review","volume":"21","author":"Li","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1109\/TVT.2019.2962334","article-title":"Vehicle detection and classification using distributed fiber optic acoustic sensing","volume":"69","author":"Li","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"100152","DOI":"10.1109\/ACCESS.2020.2997941","article-title":"Variational mode decomposition-based threat classification for fiber optic distributed acoustic sensing","volume":"8","author":"Abufana","year":"2020","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1109\/JLT.2023.3308173","article-title":"Fast and storage-optimized compressed domain vibration detection and classification for distributed acoustic sensing","volume":"42","author":"Shen","year":"2023","journal-title":"J. Lightw. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1007\/s10462-024-10998-7","article-title":"A survey on feature extraction and learning techniques for link prediction in homogeneous and heterogeneous complex networks","volume":"57","author":"Kapoor","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gu, X., Collet, O., Tertyshnikov, K., and Pevzner, R. (2024). Removing instrumental noise in distributed acoustic sensing data: A comparison between two deep learning approaches. Remote Sens., 16.","DOI":"10.3390\/rs16224150"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1093\/gji\/ggad460","article-title":"DAS-N2N: Machine learning distributed acoustic sensing (DAS) signal denoising without clean data","volume":"236","author":"Lapins","year":"2024","journal-title":"Geophys. J. Int."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"31293","DOI":"10.1109\/ACCESS.2023.3260780","article-title":"Distributed acoustic sensor systems for vehicle detection and classification","volume":"11","author":"Chiang","year":"2023","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1111\/1365-2478.13199","article-title":"Convolutional neural network-based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data","volume":"70","author":"Liu","year":"2022","journal-title":"Geophys. Prospect."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ma, Y., Eaton, D., Igonin, N., and Wang, C. (2023). Machine learning-assisted processing workflow for multi-fiber DAS microseismic data. Front. Earth Sci., 11.","DOI":"10.3389\/feart.2023.1096212"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wamriew, D., Pevzner, R., Maltsev, E., and Pissarenko, D. (2021). Deep neural networks for detection and location of microseismic events and velocity model inversion from microseismic data acquired by distributed acoustic sensing array. Sensors, 21.","DOI":"10.3390\/s21196627"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1364\/OSAC.1.000963","article-title":"Identification and observation of the phase fading effect in phase-sensitive OTDR","volume":"1","author":"He","year":"2018","journal-title":"OSA Contin."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"18642","DOI":"10.1364\/OE.555768","article-title":"Fading suppression method based on redundant data within the spatial resolution and deep learning for a \u03a6-OTDR system","volume":"33","author":"Pan","year":"2025","journal-title":"Opt. Express"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1007\/s12596-023-01212-y","article-title":"Multi-dimensional feature extraction method for distributed optical fiber sensing signals","volume":"53","author":"Zhan","year":"2023","journal-title":"J. Opt."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"170380","DOI":"10.1016\/j.ijleo.2022.170380","article-title":"\u03a6-OTDR pattern recognition based on CNN-LSTM","volume":"272","author":"Wang","year":"2023","journal-title":"Optik"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1364\/AO.481757","article-title":"Intensity and phase stacked analysis of a \u03a6-OTDR system using deep transfer learning and recurrent neural networks","volume":"62","author":"Kayan","year":"2023","journal-title":"Appl. Opt."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jeong, S., Kim, H., Kim, Y.H., Park, C.-S., Jung, H., and Kim, H.K. (2025). Spatiotemporal anomaly detection in distributed acoustic sensing using a GraphDiffusion model. Sensors, 25.","DOI":"10.3390\/s25165157"},{"key":"ref_28","unstructured":"Shahabudin, M.S.B., Jaafar, J., Bencheva, N., Paputungan, I.V., and Krishnan, N.F.B.M. (2024, January 20\u201322). Graph neural networks for microseismic event detection: Focusing on distributed acoustic sensing data. Proceedings of the 2024 5th International Conference on Communications, Information, Electronic and Energy Systems (CIEES), Ruse, Bulgaria."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"200078","DOI":"10.29026\/oea.2022.200078","article-title":"Advances in phase-sensitive optical time-domain reflectometry","volume":"5","author":"Liu","year":"2022","journal-title":"Opto-Electron. Adv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1038\/s41597-025-05088-4","article-title":"Comprehensive dataset for event classification using distributed acoustic sensing (DAS) systems","volume":"12","author":"Tomasov","year":"2025","journal-title":"Sci. Data"},{"key":"ref_31","unstructured":"ITU-T Recommendation G.652 (2016). Characteristics of a Single-Mode Optical Fibre and Cable, International Telecommunication Union."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Munoz, F., Urricelqui, J., Soto, M.A., and Jimenez-Rodriguez, M. (2023). Finding well-coupled optical fiber locations for railway monitoring using distributed acoustic sensing. Sensors, 23.","DOI":"10.3390\/s23146599"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"105464","DOI":"10.1016\/j.jappgeo.2024.105464","article-title":"Multiple noise reduction for distributed acoustic sensing data processing through densely connected residual convolutional networks","volume":"228","author":"Huang","year":"2024","journal-title":"J. Appl. Geophys."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3112","DOI":"10.1785\/0220240222","article-title":"Acoustic events detection and classification for urban DAS data with supervised learning","volume":"96","author":"Zhong","year":"2025","journal-title":"Seismol. Res. Lett."},{"key":"ref_35","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 7\u20139). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning (PMLR), Lille, France."},{"key":"ref_36","unstructured":"Agarap, A.F. (2018). Deep learning using rectified linear units (ReLU). arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_38","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_39","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"6486","DOI":"10.1109\/TPAMI.2024.3382294","article-title":"Towards understanding convergence and generalization of AdamW","volume":"46","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2925","DOI":"10.1364\/OE.28.002925","article-title":"Fiber distributed acoustic sensing using convolutional long short-term memory network: A field test on high-speed railway intrusion detection","volume":"28","author":"Li","year":"2020","journal-title":"Opt. Express"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"100372","DOI":"10.1016\/j.rio.2023.100372","article-title":"An open dataset of \u03c6-OTDR events with two classification models as baselines","volume":"10","author":"Cao","year":"2023","journal-title":"Results Opt."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4417\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T04:15:25Z","timestamp":1784002525000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"references-count":42,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144417"],"URL":"https:\/\/doi.org\/10.3390\/s26144417","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]}}}