[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85458-en":3,"doc-seo-85458-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},85458,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","OpenEM Large-scale Multi-structural 3D Datasets for Electromagnetic Methods","Electromagnetic (EM) methods are widely used in geological exploration but traditional data processing and inversion remain time-consuming and labor-intensive. Deep learning can alleviate these limitations, yet model effectiveness depends heavily on dataset quality. Existing datasets often use random or structurally simple 3D models and lack standardized, publicly available 3D geoelectric resources. OpenEM delivers a large-scale, multi-structural 3D geoelectric dataset with controllable generation for common EM exploration systems.","arXiv :2510 .2 1859v 3 [ cs .LG] 10 Jul 2026  \nOpenEM: Large-scale multi-structural 3D datasets for electromagnetic methods  \nShuang Wang 1,2 , Xuben Wang 1,2 , Fei Deng3 , Peifan Jiang 1,4 , Jian Chen5 , and Gianluca Fiandaca5  \n1 Key Laboratory of Earth Exploration and Information Techniques of Ministry of Education, Chengdu University of Technology, Chengdu, China.  \n2 College of Geophysics, Chengdu University of Technology, Chengdu, China.  \n3 College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, China.  \n4Faculty of Geo-Information Science and Earth Observation, University of Twente, Enschede, Netherlands  \n5The EEM Team for Hydro and eXploration, Department of Earth Sciences “Ardito Desio”, University of Milano, Milano, Italy  \nCorrespondence: Xuben Wang ([wxb@cdut.edu.cn](wxb@cdut.edu.cn))  \nAbstract. Electromagnetic (EM) methods, owing to their efficiency and non-invasive nature, have become one of the most widely used techniques in geological exploration. Nevertheless, data processing for these methods remains highly timeconsuming and labor-intensive. With the remarkable success of deep learning, applying such techniques to EM methods has emerged as a promising research direction to overcome the limitations of conventional approaches. The effectiveness of deep learning methods depends heavily on the quality of datasets, which directly influences model performance and generalization ability. Existing application studies often construct datasets from random one-dimensional or structurally simple threedimensional (3D) models, which fail to represent the complexity of real geological environments. Furthermore, the absence of standardized, publicly available 3D geoelectric datasets continues to hinder progress in deep learning–based EM exploration. To address these limitations, we present OpenEM, a large-scale, multi-structural 3D geoelectric dataset that encompasses abroad range of geologically plausible subsurface structures. OpenEM consists of nine categories of geoelectric models, spanning from simple configurations with anomalous bodies in half-space to more complex structures such as flat layers, folded layers, flat faults, curved faults and their corresponding variants with anomalous bodies. In addition, we provide a 3D model generator that enables fully controllable 3D model construction, allowing flexible and extensible augmentation of OpenEM. OpenEM provides a unified, comprehensive, and large-scale dataset for common EM exploration systems to accelerate the application of deep learning in electromagnetic methods. The complete dataset and 3D model generator is publicly available at [https://doi.org/10.5281/zenodo.17141981](https://doi.org/10.5281/zenodo.17141981) (Wang et al., 2025b).  \n1 Introduction  \nElectromagnetic (EM) methods are widely employed in geophysical exploration and remain a central focus of research in the geological exploration industry. A variety of EM systems have been developed, including ground-based, airborne, semiairborne, time-domain and frequency-domain electromagnetic systems. These systems have been extensively applied to geological hazard assessment (Damhuis et al., 2020; Malehmir et al., 2016), groundwater detection (Ball et al., 2020; Minsley  \net al., 2021), mineral resource exploration (Koné et al., 2021; Okada, 2021), and geological mapping (Dzikunoo et al., 2020; Wong et al., 2020) .  \nThe extraction of geoelectric structural information from EM data primarily involves two processes: data processing and inversion (Wu et al., 2022b) . Apart from correcting for system response effects, the core task of data processing is denoising. Conventional denoising methods generally depend on empirically chosen parameters, which place heavy demands on the operator’s expertise (Wu et al., 2019, 2020) . Inversion provides direct insights into the geoelectric structure, however, conventional approaches require iterative corrections through forward modeling, ","cbCaikf3YIXeMTAA","https://ap.wps.com/l/cbCaikf3YIXeMTAA","pdf",5421781,1,17,"English","en",105,"# Introduction","[{\"question\":\"What problem does OpenEM aim to address in EM-based geological exploration?\",\"answer\":\"OpenEM targets the lack of standardized, publicly available 3D geoelectric datasets and the limitations of existing datasets that use random or structurally simple models, which reduces deep learning effectiveness and generalization.\"},{\"question\":\"How is the OpenEM dataset structured?\",\"answer\":\"OpenEM contains nine categories of geoelectric models, ranging from simple half-space configurations with anomalous bodies to more complex structures such as flat layers, folded layers, flat faults, and curved faults with variants including anomalous bodies.\"},{\"question\":\"What additional tool does OpenEM provide beyond the dataset itself?\",\"answer\":\"OpenEM includes a 3D model generator that enables fully controllable 3D model construction, supporting flexible and extensible augmentation of the dataset.\"}]",1784203702,43,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"openem-large-scale-multi-structural-3d-datasets-for-electromagnetic-methods","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/openem-large-scale-multi-structural-3d-datasets-for-electromagnetic-methods/85458/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does OpenEM aim to address in EM-based geological exploration?","Question",{"text":74,"@type":75},"OpenEM targets the lack of standardized, publicly available 3D geoelectric datasets and the limitations of existing datasets that use random or structurally simple models, which reduces deep learning effectiveness and generalization.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How is the OpenEM dataset structured?",{"text":79,"@type":75},"OpenEM contains nine categories of geoelectric models, ranging from simple half-space configurations with anomalous bodies to more complex structures such as flat layers, folded layers, flat faults, and curved faults with variants including anomalous bodies.",{"name":81,"@type":72,"acceptedAnswer":82},"What additional tool does OpenEM provide beyond the dataset itself?",{"text":83,"@type":75},"OpenEM includes a 3D model generator that enables fully controllable 3D model construction, supporting flexible and extensible augmentation of the dataset.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]