[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122605-en":3,"doc-seo-122605-105":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},122605,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Fast imaging for the 3D density structures by machine learning approach","Residual Bouguer gravity anomaly inversion enables imaging of local density structures and interpretation of near-surface anomalous mass distribution, but realistic results depend critically on appropriate prior information. Traditional model-driven methods embed prior constraints or multidisciplinary regularization in an objective function and then rely on optimization, making inversion slow. This work introduces GV-Net, a U-net-inspired gravity voxels inversion network using convolutional neural networks to accelerate inversion. The study evaluates loss functions, tests robustness under varying noise, and validates performance in a real application scenario.","TYPE Original Research PUBLISHED 06 January 2023 DOI 10.3389/feart.2022.1028399  \nOPEN ACCESS  \nEDITED BY  \nJiefu Chen,  \nUniversity of Houston, United States  \nREVIEWED BY  \nQiang Guo,  \nChina University of Mining and Technology, China  \nXiaoyun Wan,  \nChina University of Geosciences, China  \n*CORRESPONDENCE  \nShi Chen,  \n [chenshi@cea-igp.ac.cn](chenshi@cea-igp.ac.cn)  \nSPECIALTY SECTION  \nThis article was submitted to Solid Earth  \nGeophysics, a section of the journal  \nFrontiers in Earth Science  \nRECEIVED 26 August 2022  \nACCEPTED 12 December 2022  \nPUBLISHED 06 January 2023  \nCITATION  \nLi Y, Chen S, Zhang B and Li H (2023),  \nFast imaging for the 3D density structures by machine learning approach.  \nFront. Earth Sci. 10:1028399 .  \ndoi: 10.3389/feart.2022.1028399  \nCOPYRIGHT  \n© 2023 Li, Chen, Zhang and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nFast imaging for the 3D density structures by machine learning approach  \nYongbo Li 1,2, Shi Chen 1,2,3*, Bei Zhang 1,2 and Honglei Li 1,2  \n1Institute of Geophysics, China Earthquake Administration, Beijing, China, 2Beijing Baijiatuan Earth Science National Observation and Research Station, Beijing, China, 3National Engineering Research Center of Offshore Oil and Gas Exploration, Beijing, China  \nResidual Bouguer gravity anomaly inversion can be used to imaging for local density structures or to interpret near-surface anomalous mass distribution. The reasonable prior information is the crucial recipe for obtaining a realistic geological inversion result, especially for the ill-posed geophysical inversion problem. The conventional strategies introduce the prior constraints or joint multidisciplinary information in object function as regularization, and then use some optimization algorithm to minimize the object function. This process is called model-driven approach and is usually time-consuming. In recent years, the rapid development of machine learning technology has provided new solutions for solving geophysical inversion problems. Machine learning methods can reduce the dependence on prior information in the inversion process through setting special training datasets, and the time consumption of an inversion process executed by the trained model can be shortened by several orders of magnitude, which is conducive to fast inversion for the same type of application scenarios. In this study, we were inspired by the U-net model and develops the GV-Net (Gravity voxels inversion network) model using the convolutional neural network for the inversion of residual gravity anomalies. We first discussed the effects of different loss functions on the convergence speed of model training and prediction accuracy. Then, we analyzed the robustness of our model by changing noise levels of the datasets. At last, we employed this model in a real scenario. The results have demonstrated that the GV-Net model has the ability to deal with specific inverse problems by predefined training datasets.  \nKEYWORDS  \ngravity inversion, convolutional neural network, machine learning, ore body identification, fast inversion, bouguer gravity anomaly  \n1 Introduction  \nGravity method as one of multidisciplinary geophysics methods is sensitive to density distribution, which can be used to imaging for the density structure of the shallow Earth (Wang et al., 2014; Honglei et al., 2021) . In general, different sort of gravity anomaly exist their own special geophysical meaning (Johannes and Smilde, 2009). The Bouguer gravity anomaly can be divided into regional and residual parts according to the characteristics of","cbCain9b52yL7Hu9","https://ap.wps.com/l/cbCain9b52yL7Hu9","pdf",7961258,1,17,"English","en",105,"# Introduction\n## Gravity inversion and the role of prior information\n## Model-driven approaches and their limitations\n# GV-Net method\n## Network design inspired by U-net\n## Training loss functions for convergence and accuracy\n# Robustness analysis\n## Influence of noise levels on performance\n# Real-world application\n## Imaging results for residual Bouguer gravity anomalies","[{\"question\":\"Why is prior information crucial for residual Bouguer gravity anomaly inversion?\",\"answer\":\"Because gravity inversion is ill-posed and non-unique, prior constraints are needed to obtain realistic geological results. Selecting inappropriate priors can introduce spurious features.\"},{\"question\":\"What is GV-Net and how does it improve inversion speed?\",\"answer\":\"GV-Net is a U-net-inspired convolutional neural network that learns from special training datasets. After training, it produces predictions much faster than traditional optimization-based model-driven inversion.\"},{\"question\":\"How was GV-Net evaluated in the study?\",\"answer\":\"The study compares different loss functions for training convergence and prediction accuracy, tests robustness by changing noise levels in datasets, and applies the model to a real scenario to demonstrate capability for the targeted inverse problem.\"}]","Fast imaging for the 3D density structures by machine learning approach | PDF",1785811694,43,{"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},"fast-imaging-for-the-3d-density-structures-by-machine-learning-approach","",{"@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/fast-imaging-for-the-3d-density-structures-by-machine-learning-approach/122605/",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","2026-08-04",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 prior information crucial for residual Bouguer gravity anomaly inversion?","Question",{"text":75,"@type":76},"Because gravity inversion is ill-posed and non-unique, prior constraints are needed to obtain realistic geological results. Selecting inappropriate priors can introduce spurious features.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is GV-Net and how does it improve inversion speed?",{"text":80,"@type":76},"GV-Net is a U-net-inspired convolutional neural network that learns from special training datasets. After training, it produces predictions much faster than traditional optimization-based model-driven inversion.",{"name":82,"@type":73,"acceptedAnswer":83},"How was GV-Net evaluated in the study?",{"text":84,"@type":76},"The study compares different loss functions for training convergence and prediction accuracy, tests robustness by changing noise levels in datasets, and applies the model to a real scenario to demonstrate capability for the targeted inverse problem.","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"]