[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127581-en":3,"doc-seo-127581-105":31,"detail-sidebar-cat-0-en-105":96},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127581,549768064622,"Anda","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Event recognition in marine seismological data using Random Forest machine learning classifier","Automatic detection of seismic events in ocean bottom seismometer (OBS) records is challenging because marine data contain higher noise and more signal types than land seismicity. Deep learning methods trained for earthquakes on land often underperform in marine settings, mainly due to the lack of very large labeled catalogs for OBS. This work presents an automated workflow combining STA/LTA picking refined by a kurtosis-based picker and a Random Forest supervised classifier using waveform, frequency, and spectrum features. Training uses a manually selected subset, iteratively refined across multiple OBS stations in the eastern Fram Strait.","Geophys. J. Int. (2023) 235, 589–609 [https://doi.org/10.1093/gji/ggad244](https://doi.org/10.1093/gji/ggad244)  \nAdvance Access publication 2023 June 16 GJI Applied and Marine Geophysics  \nEvent recognition in marine seismological data using Random Forest machine learning classifier  \nPrzemyslaw Domel  , 1 Clment Hibert  ,2 Vera Schlindwein3,4 and Andreia Plaza-Faverola 1  \n1 Department of Geosciences, UiT The Arctic University of Norway, Dramsvegen 201, 9010 Tromsø, [Norway. E-mail:](Norway. E-mail: przemyslaw.domel@uit.no)[ przemyslaw.domel@uit.no](Norway. E-mail: przemyslaw.domel@uit.no)  \n[2](2 ITES/Institut Terre et Environnement de Strasbourg)[ ITES/Institut Terre et Environnement de Strasbourg](2 ITES/Institut Terre et Environnement de Strasbourg), CNRS UMR7063 CNRS – Universit´e de Strasbourg, 5 rue Descartes, F-67084 Strasbourg, France  \n3Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research, Am Alten Hafen 26, 27568 Bremerhaven, Germany  \n4Faculty of Geosciences, University of Bremen, Klagenfurter Straße 2-4, 28359 Bremen, Germany  \nAccepted 2023 June 9. Received 2023 June 5; in original form 2023 February 20  \nSUMMARY  \nAutomatic detection of seismic events in ocean bottom seismometer (OBS) data is difficult due to elevated levels of noise compared to the recordings from land. Popular deep-learning approaches that work well with earthquakes recorded on land perform poorly in a marine setting. Their adaptation to OBS data requires catalogues containing hundreds of thousands of labelled event examples that currently do not exist, especially for signals different than earthquakes. Therefore, the usual routine involves standard amplitude-based detection methods and manual processing to obtain events of interest. We present here the first attempt to utilize a Random Forest supervised machine learning classifier on marine seismological data to automate catalogue screening and event recognition among different signals [i.e. earthquakes, short duration events (SDE) and marine noise sources] . The detection approach uses the short-term average/long-term average method, enhanced by a kurtosis-based picker for a more precise recognition of the onset of events. The subsequent machine learning method uses a previously published set of signal features (waveform-, frequency- and spectrum-based), applied successfully in recognition of different classes of events in land seismological data. Our workflow uses a small subset of manually selected signals for the initial training procedure and we then iteratively evaluate andrefine the model using subsequent OBS stations within one single deployment in the eastern Fram Strait, between Greenland and Svalbard. We find that the used set of features is well suited for the discrimination of different classes of events during the training step. During the manual verification of the automatic detection results, we find that the produced catalogue of earthquakes contains a large number of noise examples, but almost all events of interest are properly captured. By providing increasingly larger sets of noise examples we see an improvement in the quality of the obtained catalogues. Our final model reaches an average accuracy of 87 per cent in recognition between the classes, comparable toclassification results for data from land. We find that, from the used set of features, the most important in separating the different classes of events are related to the kurtosis ofthe envelope of the signal in different frequencies, the frequency with the highest energy and overall signal duration. We illustrate the implementation of the approach by using the temporal and spatial distribution of SDEs as a case study. We used recordings from six OBSs deployed between 2019 and 2020 off the west-Svalbard coast to investigate the potential link of SDEs to fluid dynamics and discuss the robustness of the approach by analysing SDE intensity, periodicity and distance to seepage sites in relation to other publis","cbCaitNInys33jMV","https://ap.wps.com/l/cbCaitNInys33jMV","pdf",2669135,2,1,21,"English","en",105,"# Introduction\n## Challenges in OBS-based seismic detection\n# Methodology\n## STA/LTA picking with kurtosis-based onset picker\n## Random Forest supervised classification and feature set\n## Training workflow and iterative refinement\n# Results and validation\n## Event catalog quality and noise discrimination\n## Classification accuracy and feature importance\n# Case study: SDEs\n## Temporal-spatial distribution and scientific implications\n## Robustness assessment using intensity, periodicity, and proximity to seepage sites","[{\"question\":\"Why are seismic event detections harder in ocean bottom seismometer (OBS) data than on land?\",\"answer\":\"Marine recordings have higher ambient noise and include additional signal types not common on land, such as ship noise, mammal calls, and ocean current tremor. These factors make reliable detection and labeling more difficult.\"},{\"question\":\"What detection approach is proposed before machine learning classification?\",\"answer\":\"The workflow uses the short-term average/long-term average (STA/LTA) method, enhanced by a kurtosis-based picker to more precisely identify event onsets. This prepares candidate event segments for classification.\"},{\"question\":\"How does the Random Forest classifier distinguish among different event classes?\",\"answer\":\"It uses previously published signal features based on waveform, frequency, and spectrum properties. The study finds kurtosis of the signal envelope in different frequencies, the frequency with the highest energy, and overall duration are especially important for separating classes.\"},{\"question\":\"How is the approach evaluated and what is the reported performance?\",\"answer\":\"The model is trained on a manually selected subset and iteratively evaluated and refined using data from subsequent OBS stations within one deployment in the eastern Fram Strait. Manual verification shows events of interest are captured while catalog noise can be reduced by adding larger noise examples, and the final model achieves about 87% average accuracy across classes.\"}]","Event recognition in marine seismological data using Random Forest machine learning classifier | PDF",1785940092,53,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":91,"head_meta":93,"extra_data":95,"updated_unix":29},"event-recognition-in-marine-seismological-data-using-random-forest-machine-learning-classifier","",{"@graph":37,"@context":90},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/event-recognition-in-marine-seismological-data-using-random-forest-machine-learning-classifier/127581/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"Why are seismic event detections harder in ocean bottom seismometer (OBS) data than on land?","Question",{"text":76,"@type":77},"Marine recordings have higher ambient noise and include additional signal types not common on land, such as ship noise, mammal calls, and ocean current tremor. These factors make reliable detection and labeling more difficult.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What detection approach is proposed before machine learning classification?",{"text":81,"@type":77},"The workflow uses the short-term average/long-term average (STA/LTA) method, enhanced by a kurtosis-based picker to more precisely identify event onsets. This prepares candidate event segments for classification.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the Random Forest classifier distinguish among different event classes?",{"text":85,"@type":77},"It uses previously published signal features based on waveform, frequency, and spectrum properties. The study finds kurtosis of the signal envelope in different frequencies, the frequency with the highest energy, and overall duration are especially important for separating classes.",{"name":87,"@type":74,"acceptedAnswer":88},"How is the approach evaluated and what is the reported performance?",{"text":89,"@type":77},"The model is trained on a manually selected subset and iteratively evaluated and refined using data from subsequent OBS stations within one deployment in the eastern Fram Strait. Manual verification shows events of interest are captured while catalog noise can be reduced by adding larger noise examples, and the final model achieves about 87% average accuracy across classes.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,125,128,133,136,140],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":47,"category_name":142,"show_sort_weight":111,"slug":143},19,"General","general"]