{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:42:46Z","timestamp":1775083366569,"version":"3.50.1"},"reference-count":29,"publisher":"Society of Exploration Geophysicists","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42074154"],"award-info":[{"award-number":["42074154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42130805"],"award-info":[{"award-number":["42130805"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42074154"],"award-info":[{"award-number":["42074154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42130805"],"award-info":[{"award-number":["42130805"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["library.seg.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The location of passive seismic events is essential for seismic activity studies. Deep learning models have shown promising results in localizing source locations from seismic waveforms. However, these methods suffer from deficiencies in generalization and interpretability. These well-trained models may only be well adapted to the region where the training data are located. Here, we propose a passive seismic source localization method based on knowledge-augmented deep learning (KADL). The proposed method integrates the scientific knowledge of time-reversal imaging into the deep learning model at the data level and architecture level, respectively. We design a physics guidance module for the effective integration of knowledge and data. The introduction of scientific knowledge provides guidance and constraints for the training of the model, helping it to focus more efficiently on key features related to passive seismic source localization. The experiment results show that the integration of scientific knowledge and deep learning can achieve better generalization. Especially in the application scenarios across different datasets, the accuracy of source location is significantly improved. The KADL model has the potential to be generalized to different regions. We also use explainable artificial intelligence to analyze the importance of data and knowledge, providing valuable insights into the decision-making process of the KADL model.<\/jats:p>","DOI":"10.1190\/geo2025-0002","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T21:48:41Z","timestamp":1758836921000},"page":"L1-L11","update-policy":"https:\/\/doi.org\/10.1190\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-augmented deep learning for passive seismic event localization"],"prefix":"10.1190","volume":"91","author":[{"given":"Qiang","family":"Feng","sequence":"first","affiliation":[{"name":"Yangtze University 1 , , Wuhan , . Email: fengqiang@yangtzeu.edu.cn (corresponding author).","place":["China"]},{"name":"School of Geophysics and Petroleum Resources 1 , , Wuhan , . Email: fengqiang@yangtzeu.edu.cn (corresponding author).","place":["China"]}]},{"given":"Liguo","family":"Han","sequence":"additional","affiliation":[{"name":"Jilin University 2 , , Changchun . Email: hanliguo@jlu.edu.cn ."},{"name":"College of Geoexploration Science and Technology 2 , , Changchun . Email: hanliguo@jlu.edu.cn ."}]}],"member":"186","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"issue":"2","key":"2026040117154076100_R1","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1190\/1.1437283","article-title":"Three dimensional SEG\/EAEG models \u2014 an update","volume":"15","author":"Aminzadeh","year":"1996","journal-title":"The Leading Edge"},{"issue":"5","key":"2026040117154076100_R2","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1111\/j.1365-2478.2010.00911.x","article-title":"Source location using time-reverse imaging","volume":"58","author":"Artman","year":"2010","journal-title":"Geophysical Prospecting"},{"issue":"3","key":"2026040117154076100_R3","doi-asserted-by":"crossref","first-page":"SE161","DOI":"10.1190\/INT-2018-0236.1","article-title":"Prestack and poststack inversion using a physics-guided convolutional neural network","volume":"7","author":"Biswas","year":"2019","journal-title":"Interpretation"},{"issue":"3","key":"2026040117154076100_R5","article-title":"3D Microseismic Monitoring Using Machine Learning","volume":"127","author":"Chen","year":"2022","journal-title":"Journal of Geophysical Research"},{"key":"2026040117154076100_R4","first-page":"1","article-title":"RFloc3D: A machine-learning method for 3-d microseismic source location using p- and s-wave arrivals","volume":"61","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"2026040117154076100_R6","article-title":"Knowledge-augmented deep learning and its applications: A survey","author":"Cui","year":"2022","journal-title":"Arxiv Preprint Arxiv"},{"issue":"5","key":"2026040117154076100_R8","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1007\/s10712-024-09846-8","article-title":"High-precision microseismic source localization using a fusion network combining convolutional neural network and transformer","volume":"45","author":"Feng","year":"2024","journal-title":"Surveys in Geophysics"},{"issue":"4","key":"2026040117154076100_R9","doi-asserted-by":"crossref","first-page":"SI151","DOI":"10.1190\/1.2215356","article-title":"Time-reversal acoustics in complex environments","volume":"71","author":"Fink","year":"2006","journal-title":"Geophysics"},{"issue":"2\u20133","key":"2026040117154076100_R7","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.jog.2010.02.007","article-title":"Seismotectonic of Southern Apennines from recent passive seismic experiments","volume":"51","author":"Frepoli","year":"2011","journal-title":"Journal of Geodynamics"},{"key":"2026040117154076100_R10","first-page":"4700","article-title":"Densely Connected Convolutional Networks","author":"Huang"},{"issue":"6","key":"2026040117154076100_R11","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed machine learning","volume":"3","author":"Karniadakis","year":"2021","journal-title":"Nature Reviews Physics"},{"issue":"13","key":"2026040117154076100_R12","doi-asserted-by":"crossref","DOI":"10.1029\/2022GL098645","article-title":"Combining deep learning with physics based features in explosion-earthquake discrimination","volume":"49","author":"Kong","year":"2022","journal-title":"Geophysical Research Letters"},{"issue":"3","key":"2026040117154076100_R13","doi-asserted-by":"crossref","first-page":"2168","DOI":"10.1093\/gji\/ggad350","article-title":"A novel deep-learning image condition for locating earthquake","volume":"235","author":"Kuang","year":"2023","journal-title":"Geophysical Journal International"},{"key":"2026040117154076100_R14","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"issue":"11","key":"2026040117154076100_R15","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"2026040117154076100_R16","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11004-019-09832-6","article-title":"Stochastic seismic waveform inversion using generative adversarial networks as a geological prior","volume":"52","author":"Mosser","year":"2020","journal-title":"Mathematical Geosciences"},{"issue":"6607","key":"2026040117154076100_R17","doi-asserted-by":"crossref","DOI":"10.1126\/science.abm4470","article-title":"Deep-learning seismology","volume":"377","author":"Mousavi","year":"2022","journal-title":"Science (New York, N.Y.)"},{"issue":"2","key":"2026040117154076100_R18","doi-asserted-by":"crossref","first-page":"KS51","DOI":"10.1190\/geo2015-0278.1","article-title":"Reverse time migration for microseismic sources using the geometric mean as an imaging condition","volume":"81","author":"Nakata","year":"2016","journal-title":"Geophysics"},{"issue":"1","key":"2026040117154076100_R19","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1071\/EG10039","article-title":"Acceleration of computation speed for elastic wave simulation using a Graphic Processing Unit","volume":"42","author":"Nakata","year":"2011","journal-title":"Exploration Geophysics"},{"issue":"2","key":"2026040117154076100_R20","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.1700578","article-title":"Convolutional neural network for earthquake detection and location","volume":"4","author":"Perol","year":"2018","journal-title":"Science Advances"},{"issue":"1","key":"2026040117154076100_R21","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s13202-011-0005-7","article-title":"Micro-earthquake monitoring with sparsely sampled data","volume":"1","author":"Sava","year":"2011","journal-title":"Journal of Petroleum Exploration and Production Technology"},{"issue":"2","key":"2026040117154076100_R22","doi-asserted-by":"crossref","first-page":"R87","DOI":"10.1190\/geo2019-0138.1","article-title":"A theory-guided deep-learning formulation and optimization of seismic waveform inversion","volume":"85","author":"Sun","year":"2020","journal-title":"Geophysics"},{"issue":"24","key":"2026040117154076100_R23","doi-asserted-by":"crossref","DOI":"10.1029\/2023GL106434","article-title":"Phase neural operator for multi-station picking of seismic arrivals","volume":"50","author":"Sun","year":"2023","journal-title":"Geophysical Research Letters"},{"issue":"6","key":"2026040117154076100_R24","doi-asserted-by":"crossref","first-page":"KS109","DOI":"10.1190\/geo2020-0636.1","article-title":"Direct microseismic event location and characterization from passive seismic data using convolutional neural networks","volume":"86","author":"Wang","year":"2021","journal-title":"Geophysics"},{"key":"2026040117154076100_R25","first-page":"1","article-title":"Data-driven microseismic event localization: An application to the Oklahoma Arkoma basin hydraulic fracturing data","volume":"60","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"2026040117154076100_R26","first-page":"1451","article-title":"Understanding convolution for semantic segmentation","author":"Wang"},{"issue":"11","key":"2026040117154076100_R27","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2118\/118537-JPT","article-title":"Microseismic Monitoring: Inside and Out","volume":"61","author":"Warpinski","year":"2009","journal-title":"Journal of Petroleum Technology"},{"key":"2026040117154076100_R28","first-page":"3057","author":"Zhang","year":"2018","journal-title":"Automatic microseismic detection and location via the deep-convolutional neural network"},{"issue":"1","key":"2026040117154076100_R29","article-title":"Locating induced earthquakes with a network of seismic stations in Oklahoma via a deep learning method","volume":"10","author":"Zhang","year":"2020","journal-title":"Scientific Reports"}],"container-title":["Geophysics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.geoscienceworld.org\/seg\/geophysics\/article-pdf\/91\/1\/L1\/7455590\/geo-2025-0002.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.geoscienceworld.org\/seg\/geophysics\/article-pdf\/91\/1\/L1\/7455590\/geo-2025-0002.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T21:15:55Z","timestamp":1775078155000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.geoscienceworld.org\/geophysics\/article\/91\/1\/L1\/670102\/Knowledge-augmented-deep-learning-for-passive"},"secondary":[{"URL":"https:\/\/pubs.geoscienceworld.org\/geophysics\/article\/doi\/10.1190\/geo2025-0002\/670102\/knowledge-augmented-deep-learning-for-passive","label":"geoscienceworld"}]},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,1]]}},"URL":"https:\/\/doi.org\/10.1190\/geo2025-0002","relation":{},"ISSN":["0016-8033","1942-2156"],"issn-type":[{"value":"0016-8033","type":"print"},{"value":"1942-2156","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2026,1,1]]},"assertion":[{"value":"2025-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}