[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82254-en":3,"doc-seo-82254-105":29,"detail-sidebar-cat-0-en-105":83},{"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":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},82254,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Joint-Embedding Predictive Architecture for Solar PV Panel Fault Classification","Rapid growth of solar photovoltaic (PV) deployments increases the demand for reliable, scalable fault classification, yet manual inspection does not scale and conventional monitoring is limited. Thermal infrared imaging enables non-contact detection, but accuracy is hindered by class imbalance, weak texture cues, and subtle thermal differences. The study evaluates Joint-Embedding Predictive Architecture (JEPA) for thermal IR PV fault classification and introduces JEFFNet (JEPA-EfficientNet), combining JEPA self-supervised semantic representations with EfficientNetV2-S supervised convolutional features, achieving strong accuracy and F1 on PVF-10 and InfraredSolarModules.","Joint-Embedding Predictive Architecture for Solar PV Panel Fault Classification  \nSeyyedhamid Azimidokht, Mehdi Monemi, Abdelhak Kharbouch, Farid Hamzehaghdam, Mehdi Rasti, Jamshid  \nAghaei and Emil Kurvinen  \narXiv :2607 .09205v1 [ ee ss .IV] 10 Jul 2026  \nAbstract—The rapid expansion of solar photovoltaic (PV) systems has increased the need for reliable and scalable fault classification, as manual inspection is impractical at scale. Thermal infrared (IR) imaging provides a non-contact solution for identifying PV faults; however, accurate classification remains challenging due to class imbalance, limited texture information, and subtle thermal differences. In this work, we investigate the applicability of Joint-Embedding Predictive Architecture (JEPA) for thermal IR PV fault classification across various scenarios and propose JEFFNet (JEPA-EFFicientNet), a multibranch architecture that combines JEPA-based self-supervised representation learning with EfficientNetV2-S-based supervised convolutional feature extraction. JEFFNet fuses semantic representations from a JEPA-pretrained Vision Transformer with convolutional features from EfficientNetV2-S, enabling complementary feature learning. JEFFNet is evaluated on two public thermal IR datasets, PVF- 10 and InfraredSolarModules (ISM), for both multiclass and derived binary (healthy/faulty) classification. On PVF-10, JEFFNet achieves an F1-score of 93.21 and an accuracy of 94.33 in the 10-class task, and an F1-score of 97.53 and an accuracy of 96.41 in the derived 2-class task. On ISM, JEFFNet achieves an F1-score of 72.60 and an accuracy of 83.88 in the 12-class task, and an F1-score of 94.69 and an accuracy of 94.78 in the derived 2-class task. JEFFNet also uses only 108.6M parameters versus 205.91M for GEPFNet, a 47.2% reduction. These results demonstrate that combining self-supervised semantic and supervised convolutional features provides an effective, parameter-efficient solution for thermal IR PV fault classification. 1  \nIndex Terms—Joint-Embedding Predictive Architecture (JEPA), photovoltaic (PV) panel, fault classification, infrared thermography, EfficientNetV2, self-supervised learning, solar PV inspection.  \nI. Introduction  \nGlobal renewable electricity capacity is projected to grow rapidly between 2025 and 2030, with solar photovoltaic (PV) systems expected to drive most of this expansion [1] . As PV deployment increases at large scale, traditional manual inspection and conventional monitoring become insufficient for ensuring reliability, performance, and safety. Recent reports by the IEA and IEA-PVPS highlight that AI-and ML-based methods can improve fault detection, predictive maintenance, and operational efficiency, helping reduce outages and maintenance costs [2], [3] . In parallel, IEC standards such as IEC  \nSeyyedhamid Azimidokht, Mehdi Monemi, Abdelhak Kharbouch, Farid Hamzehaghdam, Mehdi Rasti, and Emil Kurvinen are with the University of Oulu, Oulu, Finland. E-mails: {seyyedhamid.azimidokht, mehdi.monemi, abdelhak.kharbouch, farid.hamzehaghdam, mehdi.rasti, [emil.kurvinen](emil.kurvinen}@oulu.fi)[}](emil.kurvinen}@oulu.fi)[@oulu.fi](emil.kurvinen}@oulu.fi). Jamshid Aghaei is with Central Queensland University, Australia. E-mail: [j.aghaei@cqu.edu.au](j.aghaei@cqu.edu.au).  \n1 The source code is publicly available at [https://github.com/Azimi2kht/](https://github.com/Azimi2kht/)[ ](https://github.com/Azimi2kht/)JEFFNet  \nTS 62446-3:2017 provide important imaging protocols for PV inspection and support the development of automated computer vision pipelines [4], [5] .  \nPV farms are exposed to harsh environmental conditions, including high irradiation, temperature variations, humidity, and mechanical stress, all of which contribute to degradation and diverse fault types over time [6] . Early fault detection is therefore essential, since undetected failures can reduce power generation, accelerate degradation, and create safety risks atthe module and string level","cbCaioNCahTRmq3j","https://ap.wps.com/l/cbCaioNCahTRmq3j","pdf",2204803,1,12,"English","en",105,"# Abstract\n# Index Terms\n# Introduction","[{\"question\":\"How does JEFFNet improve fault classification accuracy?\",\"answer\":\"JEFFNet fuses JEPA-pretrained Vision Transformer semantic representations with supervised convolutional features extracted by EfficientNetV2-S. This complementary learning leverages both semantic and detailed visual cues in a parameter-efficient multibranch design.\"}]",1784179183,30,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":27},"joint-embedding-predictive-architecture-for-solar-pv-panel-fault-classification","",{"@graph":35,"@context":77},[36,53,68],{"@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/joint-embedding-predictive-architecture-for-solar-pv-panel-fault-classification/82254/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How does JEFFNet improve fault classification accuracy?","Question",{"text":75,"@type":76},"JEFFNet fuses JEPA-pretrained Vision Transformer semantic representations with supervised convolutional features extracted by EfficientNetV2-S. This complementary learning leverages both semantic and detailed visual cues in a parameter-efficient multibranch design.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":45,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":45,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":113},"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]