[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118122-en":3,"doc-seo-118122-105":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},118122,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Microlensing signatures of extended dark objects using machine learning","A machine learning approach detects distinctive gravitational microlensing signatures produced by extended dark matter objects, including boson stars, axion miniclusters, and subhalos. The method adapts MicroLIA to handle low-cadence microlensing survey data by training on simulated light curves generated using realistic observational timestamps. Classifiers distinguish microlensing from point-like lenses versus extended lenses and separate additional variable-magnitude object classes. Results emphasize confident identification of boson stars over 0.8≲r/rE≲3 and show that sharply peaked NFW subhalos can be recognized from point-lens events under regular cadence. Code and dataset are provided.","IPPP/24/02  \nMicrolensing signatures of extended dark objects using machine learning  \nMiguel Crispim Romao 1, ∗ and Djuna Croon 1,†  \n1 Institute for Particle Physics Phenomenology, Department of Physics, Durham University, Durham DH1 3LE, U. K.  \n(Dated: March 10, 2025)  \narXiv :2402 .00107v2 [ astro-ph .CO] 7 Mar 2025  \nThis paper presents a machine learning-based method for the detection of the unique gravitational microlensing signatures of extended dark objects, such as boson stars, axion miniclusters and subhalos. We adapt MicroLIA, a machine learning-based package tailored to handle the challenges posed by low-cadence data in microlensing surveys. Using realistic observational timestamps, our models are trained on simulated light curves to distinguish between microlensing by point-like and extended lenses, as well as from other object classes which give a variable magnitude. We focus on boson stars and NFW-subhalos and show that the former, which are examples of objects with a relatively flat mass distribution, can be confidently identified for 0 .8 ≲ r/rE ≲ 3. Intriguingly, we also find that more sharply peaked structures, such as NFW-subhalos, can be distinctly recognized from point-lenses under regular observation cadence. Our findings significantly advance the potential of microlensing data in uncovering the elusive nature of extended dark objects. The code and dataset used are also provided.  \nI. INTRODUCTION  \nMacroscopic dark matter candidates, with masses ranging from large asteroids (∼ 10 −15M⊙ ) to stars (∼ M⊙ ), offer compelling alternatives to the traditional particle-based theories. These celestial objects, potentially formed in the early universe, are primarily detectable via their gravitational effects: gravitational lensing (e.g. [1–4]) and gravitational waves (e.g. [5–12]) . Indeed, gravitational microlensing is one of the most important ways of probing compact objects such as “machos”or primordial black holes (PBHs), a dark matter (DM) candidate consisting of compact objects formed in the early Universe. Through surveys of a range of sources, microlensing of such point-like lenses has been used to constrain the fraction of DM such objects can comprise in a wide range of masses (see e.g. [4]) .  \nIt has also been proposed that dark matter can instead be comprised of extended objects, such as boson stars (e.g. [13–16]), axion miniclusters [17], and subhalos [18–22] . Like compact objects, such objects can also bend the light of distant stars. Whether this effect can be probed by a microlensing survey depends on the comparison between the object radius and the Einstein radius – the characteristic length scale which is a function of the mass of the dark matter lens and the distance to the light source. The effectiveness of (micro-)lensing then depends on the size of the object compared to the Einstein radius: dilute dark objects, which are transparent to light, are ineffective lenses. Using conservative assumptions about the number of events observed, Refs.[23, 24] derived modified constraints on extended dark matter objects.  \nInterestingly, structures with radii close to the Einstein radius may give distinct microlensing signatures. How the mass is spread within these structures affects  \n∗ [miguel.romao@durham.ac.uk](miguel.romao@durham.ac.uk)[ ](miguel.romao@durham.ac.uk)† [djuna.l.croon@durham.ac.uk](djuna.l.croon@durham.ac.uk)  \nNormal ised Magnitude  \n10 Most Distinctive Boson Star Light Curves w/ OGLE-II Timestamps  \n􀀀100 􀀀75 􀀀50 􀀀25 0 25 50 75 100 Timestamp 􀀀 t0 (days)  \nFIG. 1. The 10 most distinctive Boson Star light curves, using the dataset generated with OGLE-II timestamps..  \nthe lensing effect. This was demonstrated explicitly for microlensing of various dark matter structures in [23–25] . In objects with a flatter density profile, such as boson stars, the microlensing magnification time series can deviate significantly from that expected from a point-like lens such as a PBH, for example f","cbCaipQZt5rPIdXW","https://ap.wps.com/l/cbCaipQZt5rPIdXW","pdf",2915014,1,12,"English","en",105,"# Introduction\n## Macroscopic dark matter candidates and microlensing\n## Extended dark matter objects and Einstein radius comparison\n# Microlensing signatures of extended lenses\n## Microlensing geometry and parameters\n## Lens equation and surface mass density","[{\"question\":\"What problem does the paper address in microlensing surveys?\",\"answer\":\"How to identify microlensing signatures caused by extended dark matter objects using time-series data, despite the challenges of low-cadence observations.\"},{\"question\":\"How does the proposed machine learning method distinguish point-like from extended lenses?\",\"answer\":\"It trains models on simulated light curves using realistic observational timestamps, learning characteristic differences in magnification time series driven by how mass is distributed within the lens.\"},{\"question\":\"What are the key identification results for boson stars and NFW subhalos?\",\"answer\":\"Boson stars with relatively flat mass distributions can be confidently identified for about 0.8≲r/rE≲3, while sharply peaked NFW subhalos can be distinctly recognized from point-lenses under regular observation cadence.\"}]","Microlensing signatures of extended dark objects using machine learning | PDF",1785681714,30,{"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},"microlensing-signatures-of-extended-dark-objects-using-machine-learning","",{"@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/microlensing-signatures-of-extended-dark-objects-using-machine-learning/118122/",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},"What problem does the paper address in microlensing surveys?","Question",{"text":75,"@type":76},"How to identify microlensing signatures caused by extended dark matter objects using time-series data, despite the challenges of low-cadence observations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed machine learning method distinguish point-like from extended lenses?",{"text":80,"@type":76},"It trains models on simulated light curves using realistic observational timestamps, learning characteristic differences in magnification time series driven by how mass is distributed within the lens.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the key identification results for boson stars and NFW subhalos?",{"text":84,"@type":76},"Boson stars with relatively flat mass distributions can be confidently identified for about 0.8≲r/rE≲3, while sharply peaked NFW subhalos can be distinctly recognized from point-lenses under regular observation cadence.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]