[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118591-en":3,"doc-seo-118591-105":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},118591,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Advancements in Seismic Data Collection and Analysis Through Machine Learning - Deep Learning for Earthquake Detection","Seismic stations continuously record high-frequency signals that mix seismic and non-seismic information, creating both an operational need and a technical challenge for early, reliable detection. Prior pipelines converted SEED data to CSV and used PCA for feature extraction, then applied machine learning to classify events. This work advances the approach with deep learning using DNN and an LSTM+DNN hybrid model, improving test accuracy to 99.24% versus 97.80% with traditional methods, enabling more accurate real-time earthquake monitoring.","Advancements in seismic data collection and analysis through  \nmachine learning  \nSujata Kulkarni1, Malay Phadke1, Ashwini Sawant2, Neel Patel1, Om Patil1  \n1Department of Electronics and Telecommunication Engineering, Sardar Patel Institute of Technology, Andheri, India 2Department of Electronics and Telecommunication Engineering, Vivekanand Education Society’s Institute of Technology,  \nChembur, India  \nArticle history:  \nReceived Jul 15, 2024 Revised Oct 10, 2024 Accepted Oct 28, 2024  \nKeywords:  \nDeep learning Earthquake detection Feature extraction Long short-term memory Real time dataset  \nCorresponding Author:  \nThe evolution of seismic data collection has been driven by the need for stations to capture large volumes of high-frequency signals continuously. These signals typically contain both seismic and non-seismic information. Previous research converted SEED data into CSV format and used principal component analysis (PCA) for feature extraction from the seismic dataset. Machine learning models were then employed, showing an improvement in identifying seismic and non-seismic events. This paper focuses on applying deep learning methods, specifically deep neural networks (DNN) and a hybrid model combining long short-term memory (LSTM) networks with DNN (LSTM+DNN) . The proposed deep learning models demonstrate a notable improvement over traditional machine learning technique. Experimental results show a test accuracy of 99.24% using deep learning, compared to an average of 97.80% achieved with machine learning models, indicating a 1.46% enhancement in detection accuracy. This underscores the potential of deep learning in accurately detecting seismic events in real-time monitoring systems.  \nThis is an open access article under the CC BY-SA license.  \nSujata Kulkarni  \nDepartment of Electronics and Telecommunication Engineering, Sardar Patel Institute of Technology Andheri, India  \nEmail: [sujata_kulkarni@spit.ac.in](sujata_kulkarni@spit.ac.in)  \nArticle Info ABSTRACT  \n1. INTRODUCTION  \nEarly detection of earthquakes is essential for reducing damage and saving lives [1] . Earthquakes are typically caused by plate tectonics and the sudden release of elastic energy stored in geological faults, resulting in the shaking of the Earth's surface. This energy release generates seismic waves, and the magnitude of an earthquake is proportional to the logarithm of the energy released. Technological developments have greatly increased the knowledge of the interior structure and dynamic processes of the Earth. One example is the better recording of seismic waves using sensitive sensors such as seismographs. These developments are essential to increasing the capacity to anticipate and lessen the effects of earthquakes, which are among the most [2] .  \nManaging the large volumes of data generated by seismic stations, which continually record signals at high sample frequencies, is challenging but crucial for understanding seismic activity. Seismographs, derived from ground motion data recorded by accelerographs, are used by researchers and seismologists to determine key parameters such as wavelength, frequency, magnitude, and timing of seismic signals [3], [4] .  \nIdentifying the primary (P-wave) and secondary (S-wave) waves in these signals is crucial as they frequently contain both seismic and non-seismic data as shown in Figure 1. S-waves follow P-waves during an earthquake, which are the fastest seismic waves but are hard to detect because of their low frequency [5] .  \nFurthermore, as illustrated in Figure 2, three-component seismogram data that record ground motion in vertical, north-south, and east-west directions, along with information from Love and Rayleigh waves [6], offer a full picture of seismic occurrences. The understanding of seismic activity and the capacity to identify and respond to earthquakes will both benefit from this thorough examination.  \nFigure 1. Earthquake with P-wave and S-wave arrivals [7]  \nFigure 2. T","cbCaibTSRzv2KSw2","https://ap.wps.com/l/cbCaibTSRzv2KSw2","pdf",893489,1,11,"English","en",105,"# Introduction\n## Seismic signal sources and P/S wave identification\n## Seismic data volume and preprocessing pipeline\n# Deep learning for seismic event detection\n## DNN capabilities and seismology applications","[{\"question\":\"Why is managing large seismic data volumes important?\",\"answer\":\"Seismic stations record continuous high-sample-frequency signals, producing large datasets that must be handled efficiently to support seismic understanding and accurate event detection.\"},{\"question\":\"What limitations of earlier methods does this paper address?\",\"answer\":\"Earlier approaches converted SEED to CSV and used PCA for feature extraction followed by traditional machine learning, and the study aims to improve detection accuracy using deep learning.\"},{\"question\":\"How do the proposed DNN and LSTM+DNN models improve earthquake detection?\",\"answer\":\"The deep learning models achieve a test accuracy of 99.24%, outperforming traditional machine learning models with an average accuracy of 97.80%, improving detection accuracy by 1.46% for real-time monitoring.\"}]","Advancements in Seismic Data Collection and Analysis Through Machine Learning - Deep Learning for Earthquake Detection | PDF",1785684417,28,{"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},"advancements-in-seismic-data-collection-and-analysis-through-machine-learning-deep-learning-for-earthquake-detection","",{"@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/advancements-in-seismic-data-collection-and-analysis-through-machine-learning-deep-learning-for-earthquake-detection/118591/",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","2026-08-02",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},"Why is managing large seismic data volumes important?","Question",{"text":75,"@type":76},"Seismic stations record continuous high-sample-frequency signals, producing large datasets that must be handled efficiently to support seismic understanding and accurate event detection.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitations of earlier methods does this paper address?",{"text":80,"@type":76},"Earlier approaches converted SEED to CSV and used PCA for feature extraction followed by traditional machine learning, and the study aims to improve detection accuracy using deep learning.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the proposed DNN and LSTM+DNN models improve earthquake detection?",{"text":84,"@type":76},"The deep learning models achieve a test accuracy of 99.24%, outperforming traditional machine learning models with an average accuracy of 97.80%, improving detection accuracy by 1.46% for real-time monitoring.","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"]