[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128497-en":3,"doc-seo-128497-105":31,"detail-sidebar-cat-0-en-105":92},{"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},128497,687207017582,"Himbo","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Machine Learning for Seismic Data Analysis and Processing","Machine learning drives advances in seismic data analysis by enabling near-automatic extraction of meaningful information from complex datasets. The work highlights dictionary learning and neural networks for capturing embedded structures and patterns, and presents residual dictionary denoising to reduce acquisition footprint in 3D seismic data. It also demonstrates a deep neural network for seismic moment tensor inversion in well-monitoring scenarios, complemented by global optimization methods such as simulated annealing and differential evolution for automating velocity analysis and well-tying.","MACHINE LEARNING FOR SEISMIC DATA ANALYSIS AND PROCESSING  \nDanilo R. Velis 1, Julián L. Gómez 1,2, Gabriel R. Gelpi 3, Germán I. Brunini 1, Daniel O. Pérez1,  \nJuan I. Sabbione1  \n1Facultad de Ciencias Astronómicas y Geofísicas, Universidad Nacional de La Plata, y CONICET,  \nLa Plata, Argentina  \n2 YPF Tecnología S.A., Berisso, Argentina  \n3Facultad de Ciencias Astronómicas y Geofísicas, Universidad Nacional de La Plata, La Plata,  \nArgentina  \nContact: [velis@fcaglp.unlp.edu.ar](velis@fcaglp.unlp.edu.ar)  \nRESUMEN  \nEl aprendizaje automático está marcando el ritmo del avance del análisis de datos en muchos campos de la ciencia, la tecnología y la industria. En este contexto, el procesamiento y la inversiónde datos sísmicos se abordan mediante estrategias que extraen la información relevante de los datos de forma casi automática. El “dictionary learning” y las Redes Neuronales son dosejemplos comunes de algoritmos capaces de capturar las estructuras y patrones complejos incrustados en los datos e inferir o predecir cierta información de interés a partir de ellos. Utilizamos la técnica de “residual dictionary denoising” para atenuar la huella de adquisición en los datos sísmicos 3D. Además, demostramos algunos avances en el uso de una red neuronal profunda para invertir el tensor de momento sísmico en escenarios de monitorización de pozos. Elaprendizaje automático también incluye técnicas de optimización global, como el recocido simulado y la evolución diferencial. Exploramos cómo estos dos algoritmos pueden automatizar procesos en la exploración sísmica, como el análisis de la velocidad y el “well-tying” que convencionalmente se hacen a mano y, por lo tanto, son susceptibles de la subjetividad y la experiencia del usuario.  \nPALABRAS CLAVES: EXPLORACION SISMICA; VELOCIDADES; REDES NEURONALES  \nABSTRACT  \nMachine learning is setting the pace in the advancement of data analysis in many fields of science, technology, and industry. In this context, seismic data processing and inversion are approached by strategies that extract the relevant information from the data almost automatically. Dictionary learning and neural networks are two common examples of algorithms capable of capturing the complex structures and patterns embedded in data and inferring or predicting certain information of interest from them. We use a residual dictionary denoising technique to attenuate the acquisition footprint in 3D seismic data. Besides, we demonstrate some progress in using a deep neural network to invert the seismic moment tensor in well-monitoring scenarios. Machine learning also includes global optimization techniques, such as simulated annealing and differential evolution. We explore how these two algorithms can automate processes in seismic exploration such as velocity analysis and well-tying, which are conventionally done by hand and are thus susceptible to user subjectivity and experience.  \nKEY WORDS: SEISMIC EXPLORATION; VELOCITIES; NEURAL NETWORKS  \nINTRODUCTION  \nMachine learning (ML) are algorithms and strategies devised for making predictions from data without the use of explicit deterministic coding/modeling. It is difficult to pinpoint when ML first appeared, but one of the key works that put on the table the idea of a computer learning to \"think\"like a human was in the late 1950s (Samuel 1959) . Since then, the number of developments and applications has increased dramatically. ML algorithms, such as artificial neural networks (ANN), are useful for extracting information from large datasets associated with complex systems when a deterministic approach/model is unavailable (e.g. , predicting which movie a given streaming service subscriber would like to watch (Bennett, Lanning, and others 2007)) .  \nDeep neural networks (DNN), convolutional neural networks (CNN), and supervised or unsupervised NN are ANN examples. DNN is an acronym for NN with multiple layers. In the simplest of settings, each layer of a DNN contains affine transfo","cbCaiaVMROpR4m7O","https://ap.wps.com/l/cbCaiaVMROpR4m7O","pdf",1109855,2,1,23,"English","en",105,"# Introduction\n## Machine learning fundamentals\n## Neural network types and learning modes\n## Dictionary learning and global optimization methods\n## Seismic applications and related tasks\n## METIS group applications","[{\"question\":\"What is the main goal of using machine learning in seismic data analysis?\",\"answer\":\"To extract relevant information from seismic data in an almost automatic way using learning-based algorithms rather than explicit deterministic modeling.\"},{\"question\":\"How does residual dictionary denoising improve 3D seismic data?\",\"answer\":\"It attenuates the acquisition footprint present in 3D seismic data by leveraging dictionary learning and sparse representations.\"},{\"question\":\"Which optimization techniques are discussed alongside neural approaches?\",\"answer\":\"Simulated annealing and differential evolution are presented as global optimization methods that can automate parts of seismic exploration such as velocity analysis and well-tying.\"}]","Machine Learning for Seismic Data Analysis and Processing | PDF",1786001394,58,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-for-seismic-data-analysis-and-processing","",{"@graph":37,"@context":86},[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/machine-learning-for-seismic-data-analysis-and-processing/128497/",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","2026-08-24","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main goal of using machine learning in seismic data analysis?","Question",{"text":76,"@type":77},"To extract relevant information from seismic data in an almost automatic way using learning-based algorithms rather than explicit deterministic modeling.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does residual dictionary denoising improve 3D seismic data?",{"text":81,"@type":77},"It attenuates the acquisition footprint present in 3D seismic data by leveraging dictionary learning and sparse representations.",{"name":83,"@type":74,"acceptedAnswer":84},"Which optimization techniques are discussed alongside neural approaches?",{"text":85,"@type":77},"Simulated annealing and differential evolution are presented as global optimization methods that can automate parts of seismic exploration such as velocity analysis and well-tying.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]