[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124722-en":3,"doc-seo-124722-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124722,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Explainable machine learning for labquake prediction using catalog-driven features","Machine learning methods support laboratory earthquake (labquake) prediction, including time-to-failure (TTF) forecasting from acoustic emission (AE) records. This work develops an ML framework that extracts 47 catalog-driven seismo-mechanical and statistical features from three Westerly granite stick-slip experiments with naturally fractured rough faults, and predicts TTF using a regression voting ensemble of LSTM networks with R² = 0.70 on the test set. Feature importance indicates AE rate, correlation integral, event proximity, and focal-mechanism-based features dominate, while highly correlated inputs may appear less influential. The results motivate using catalog-driven constraints for TTF of complex heterogeneous rough faults.","Contents lists available at ScienceDirect  \nEarth and Planetary Science Letters  \njournal [homepage:](homepage: www.elsevier.com/locate/epsl)[ www.elsevier.com/locate/epsl](homepage: www.elsevier.com/locate/epsl)  \nExplainable machine learning for labquake prediction using catalog-driven features  \nSadegh Karimpouli a,∗ , Danu Causb,c,d , Harsh Grover b,c,d , Patricia Martínez-Garzón a , Marco Bohnhoffa,e , Gregory C. Berozaf, Georg Dresen a,g , Thomas Goebel h ,  \nTobias Weigelb,c,d , Grzegorz Kwiatek a  \na Helmholtz Centre Potsdam, GFZ German Research Centrefor Geosciences, Potsdam, Germany  \nb DKRZ German Climate Computing Center, Hamburg, Germany c Helmholtz Center Hereon, Geesthacht, Germany d Helmholtz AI, Germany  \ne Department of Earth Sciences, Free University Berlin, Berlin, Germany f Department of Geophysics, Stanford University, Stanford, CA, USA  \ng Institute of Earth and Environmental Sciences, Universität Potsdam, Potsdam, Germany h Centerfor Earthquake Research and Information, University of Memphis, Memphis, USA  \n\n| a r t i c l e i n f o | a b s t r a c t\u003Cbr>Recently, Machine learning (ML) has been widely utilized for laboratory earthquake (labquake) prediction using various types of data. This study pioneers in time to failure (TTF) prediction based on ML using acoustic emission (AE) records from three laboratory stick-slip experiments performed on Westerly granite samples with naturally fractured rough faults, more similar to the heterogeneous fault structures in the nature. 47 catalog-driven seismo-mechanical and statistical features are extracted introducing some new features based on focal mechanism. A regression voting ensemble of Long-Short Term Memory (LSTM) networks predicts TTF with a coefficient of determination (R 2 ) of 70% on the test dataset. Feature importance analysis revealed that AE rate, correlation integral, event proximity, and focal mechanismbased features are the most important features for TTF prediction. Results reveal that the network uses all information among the features for prediction, including general trends in high correlated features as well as fine details about local variations and fault evolution involved in low correlated features. Therefore, some highly correlated and physically meaningful features may be considered less important for TTF prediction due to their correlation with other important features. Our study provides a ground for applying catalog-driven to constrain TTF of complex heterogeneous rough faults, which is capable tobe developed for real application.\u003Cbr>© 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC license ([http://creativecommons.org/licenses/by-nc/4.0/](http://creativecommons.org/licenses/by-nc/4.0/)). |\n| --- | --- |\n| Article history:\u003Cbr>Received 6 June 2023\u003Cbr>Received in revised form 21 August 2023 Accepted 5 September 2023\u003Cbr>Available online 11 October 2023\u003Cbr>Editor: R. Bendick |  |\n| Keywords:\u003Cbr>labquake prediction explainable ML catalog-driven features time to failure |  |\n\n1. Introduction  \nEarthquake forecasting and improvement of probabilistic seismic hazard assessment are persistent and challenging problems in geoscience, primarily due to the complexity of deformation processes, evolving fault structure and varying mechanical behavior of geomaterials. Recent advances in machine learning (ML) algorithmsand hardware provided new perspectives and tools to the seismology community (Johnson et al., 2021). Basic signal processing analysis is within the scope of ML applications, including earthquake event detection (Mousavi et al., 2020), phase picking (Zhu et al.,  \n* Corresponding author.  \nE-mail address: sadegh.karimpouli@gfz-potsdam.de (S. Karimpouli).  \n2019) and association (McBrearty et al., 2019), as well as hypocenter determination (Mousavi and Beroza, 2020), among others (as reviewed by Ren et al. (2020)). At the same time, data-driven ML-based approaches were applied to predict the t","cbCailDW9G31xmN0","https://ap.wps.com/l/cbCailDW9G31xmN0","pdf",2234687,1,11,"English","en",105,"# Introduction\n## Labquake prediction with machine learning\n## Feature categories for TTF forecasting\n# Methods and feature engineering\n## Catalog-driven feature extraction\n# Model training and explainability\n## LSTM regression voting ensemble\n## Feature importance and interpretation\n# Results and implications\n## Prediction performance\n## Physical meaning and correlation effects","[{\"question\":\"What prediction target does the study focus on for labquakes?\",\"answer\":\"The study focuses on time-to-failure (TTF) prediction for laboratory earthquake experiments.\"},{\"question\":\"Which input type is central to the proposed approach?\",\"answer\":\"The approach uses catalog-driven features, derived from earthquake or seismicity catalogs, combined with seismo-mechanical and statistical descriptors.\"},{\"question\":\"How is model explainability assessed, and what features are most important?\",\"answer\":\"Feature importance analysis highlights AE rate, correlation integral, event proximity, and focal mechanism-based features as the most influential for TTF prediction.\"}]","Explainable machine learning for labquake prediction using catalog-driven features | PDF",1785894110,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"explainable-machine-learning-for-labquake-prediction-using-catalog-driven-features","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/explainable-machine-learning-for-labquake-prediction-using-catalog-driven-features/124722/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What prediction target does the study focus on for labquakes?","Question",{"text":75,"@type":76},"The study focuses on time-to-failure (TTF) prediction for laboratory earthquake experiments.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which input type is central to the proposed approach?",{"text":80,"@type":76},"The approach uses catalog-driven features, derived from earthquake or seismicity catalogs, combined with seismo-mechanical and statistical descriptors.",{"name":82,"@type":73,"acceptedAnswer":83},"How is model explainability assessed, and what features are most important?",{"text":84,"@type":76},"Feature importance analysis highlights AE rate, correlation integral, event proximity, and focal mechanism-based features as the most influential for TTF prediction.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]