[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123723-en":3,"doc-seo-123723-105":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},123723,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Gamma-ray Blazar Classification using Machine Learning with Advanced Weight Initialization and Self-Supervised Learning Techniques","Machine learning has become a key approach in gamma-ray astrophysics, enabling separation of source types such as blazars and pulsars and supporting discovery of new high-energy insights. Using Fermi-LAT observations, the work targets a mostly blazar sample where many objects remain of uncertain type or lack a clear low-energy counterpart. Multiple ML methods are applied with smart weight initialization and self-supervised learning to classify BL Lacertae objects (BL Lac/BLL) versus flat spectrum radio quasars (FSRQ). The proposed model stays simple with few features and deploys easily while improving inference speed by at least 7x. Results indicate that 820 of 1115 uncertain 4FGL-DR3 sources are BL Lacs and 295 are FSRQs.","arXiv :2310 .06095v2 [ astro-ph .HE] 3 Jan 2024  \nGamma-ray Blazar Classification using Machine Learning with Advanced Weight Initialization and Self-Supervised Learning Techniques  \nGopal Bhatta, 1 ★ Sarvesh Gharat,2 † Abhimanyu Borthakur3 and Aman Kumar4  \n1 Janusz Gil Institute of Astronomy, University of Zielona Góra, ul. Szafrana 2, 65-516 Zielona Góra, Poland  \n2 Centre for Machine Intelligence and Data Science, Indian Institute of Technology Bombay, 400076, Mumbai, India  \n3 Department of Electronics and Communication Engineering, Manipal Institute of Technology, 576104, Karnataka, India  \n4 Tezpur University, Tezpur, Assam 784028, India.  \nAccepted XXX. Received YYY; in original form ZZZ  \nABSTRACT  \nMachine learning has emerged as a powerful tool in the field of gamma-ray astrophysics. The algorithms can distinguish between different source types, such as blazars and pulsars, and help uncover new insights into the high-energy universe. The Large Area Telescope on-board the Fermi Gamma-ray telescope has significantly advanced our understanding of the Universe. The instrument has detected a large number of gamma-ray emitting sources, among which a significant number of objects have been identified as active galactic nuclei. The sample is primarily composed of blazars; however, more than one-third of these sources are either of an unknown class or lack a definite association with a low-energy counterpart. In this work, we employ multiple machine learning algorithms to classify the sources based on their other physical properties. In particular, we utilized smart initialisation techniques and self-supervised learning for classifying blazars into BL Lacertae objects (BL Lac, also BLL) and flat spectrum radio quasars (FSRQ) . The core advantage of the algorithm is its simplicity, usage of minimum number of features and easy deployment due to lesser number of parameters without compromising on the performance along with increase in inference speed (at least 7 times more than existing algorithms) . As a result, the best performing model is deployed on multiple platforms so that any user irrespective of their coding background can use the tool. The model predicts that out of the 1115 sources of uncertain type in the 4FGL-DR3 catalog, 820 can be classified as BL Lacs, and 295 can be classified as FSRQs.  \nKey words: radiation mechanisms: non-thermal – methods: observational – methods: statistical – BL Lacertae objects: general–  \nquasars: supermassive black holes–galaxies: active  \n1 INTRODUCTION  \nBlazars, belonging to the class of active galactic nuclei (AGNs), stand out as some of the most luminous and exceptionally variable sources in the Universe. These sources are recognized for their high luminosity, broad-spectrum emissions, and significant rapid variability across a wide range of the electromagnetic spectrum (see e.g., Bhatta 2021; Bhatta & Dhital 2020; Bhatta et al. 2018) . These exceptional characteristics are frequently associated with the emission boosted by Doppler effects from the relativistic outflows originating near the central engine (Urry & Padovani 1995; Jorstad et al. 2017) . Conventionally, these objects are typically divided into two main groups: BL Lacs and FSRQ.  \nThe primary distinction between these two categories lies in the fact that BL Lacs typically display either no or very faint emission line spectra, whereas FSRQs commonly exhibit broad emission lines and and their synchrotron peak is at lower frequencies. While FSRQs are more powerful sources, BL Lacs belong to an extreme class characterized by an excess of high-energy emissions, ranging from hard X-rays to TeV energies. In leptonic models of blazar, this ex-  \n★ [g.bhatta@ia.uz.zgora.pl](g.bhatta@ia.uz.zgora.pl)[ ](g.bhatta@ia.uz.zgora.pl)† [sarveshgharat19@gmail.com](sarveshgharat19@gmail.com)  \n© 2023 The Authors  \ncess arises from synchrotron and inverse-Compton (IC) processes. Their seemingly low luminosity may be attributed to the absen","cbCaisdkchcZs2U7","https://ap.wps.com/l/cbCaisdkchcZs2U7","pdf",1406888,1,11,"English","en",105,"# Abstract\n# Introduction\n## Blazars as active galactic nuclei\n## BL Lac vs FSRQ characteristics\n## Spectral energy distributions and emission peaks\n## Synchrotron-peaked blazar subclasses and blazar sequence\n## Fermi Large Area Telescope overview","[{\"question\":\"What classification task does the paper focus on?\",\"answer\":\"It classifies gamma-ray blazar sources into BL Lacertae objects (BL Lac/BLL) and flat spectrum radio quasars (FSRQ) based on their physical properties.\"},{\"question\":\"Why is self-supervised learning used in this work?\",\"answer\":\"Self-supervised learning supports effective model training for distinguishing uncertain blazar types when clear associations with low-energy counterparts are missing.\"},{\"question\":\"What performance and deployment advantages does the proposed method claim?\",\"answer\":\"The method is designed to be simple, uses a minimum number of features, and has easy deployment due to fewer parameters, while improving inference speed by at least 7 times.\"}]","Gamma-ray Blazar Classification using Machine Learning with Advanced Weight Initialization and Self-Supervised Learning Techniques | PDF",1785818198,28,{"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},"gamma-ray-blazar-classification-using-machine-learning-with-advanced-weight-initialization-and-self-supervised-learning-techniques","",{"@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/gamma-ray-blazar-classification-using-machine-learning-with-advanced-weight-initialization-and-self-supervised-learning-techniques/123723/",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},"What classification task does the paper focus on?","Question",{"text":75,"@type":76},"It classifies gamma-ray blazar sources into BL Lacertae objects (BL Lac/BLL) and flat spectrum radio quasars (FSRQ) based on their physical properties.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is self-supervised learning used in this work?",{"text":80,"@type":76},"Self-supervised learning supports effective model training for distinguishing uncertain blazar types when clear associations with low-energy counterparts are missing.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance and deployment advantages does the proposed method claim?",{"text":84,"@type":76},"The method is designed to be simple, uses a minimum number of features, and has easy deployment due to fewer parameters, while improving inference speed by at least 7 times.","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"]