[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127168-en":3,"doc-seo-127168-105":30,"detail-sidebar-cat-0-en-105":92},{"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":27,"seo_description":14,"update_tm":28,"read_time":29},127168,3985741905716,"Rowan","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","A Machine Learning Method for Monte Carlo Calculations of Radiative Processes","Radiative processes such as synchrotron radiation and Compton scattering are central to high-energy astrophysics, yet their inherently stochastic nature makes them computationally expensive to model. Monte Carlo methods require sampling from complex probability distributions to derive radiation angular distributions, spectra, and polarization. This work presents a machine learning approach for efficient sampling from arbitrary known distributions, accelerating Monte Carlo calculations in astrophysical scenarios. Applied to inverse Compton radiation, the method achieves up to an order-of-magnitude speedup over traditional sampling techniques.","arXiv :2406 . 19385v1 [ astro-ph .HE] 27 Jun 2024  \nDraft version June 28, 2024  \nTypeset using LATEX preprint2 style in AASTeX631  \nA Machine Learning Method for Monte Carlo Calculations of Radiative Processes  \nWilliam Charles 1 and Alexander Y. Chen 1  \n1 Physics Department and McDonnell Center for the Space Sciences, Washington University in St. Louis, St. Louis,  \nMO 63130, USA  \nABSTRACT  \nRadiative processes such as synchrotron radiation and Compton scattering play an important role in astrophysics. Radiative processes are fundamentally stochastic in nature, and the best tools currently used for resolving these processes computationally are Monte Carlo (MC) methods. These methods typically draw a large number of samples from a complex distribution such as the differential cross section for electron-photon scattering, and then use these samples to compute the radiation properties such as angular distribution, spectrum, and polarization. In this work we propose a machine learning (ML) technique for efficient sampling from arbitrary known probability distributions that can be used to accelerate Monte Carlo calculation of radiative processes in astrophysical scenarios. In particular, we apply our technique to inverse Compton radiation and find that our ML method can be up to an order of magnitude faster than traditional methods currently in use.  \nKeywords: Radiative Processes—High Energy Astrophysics Phenomena—Numerical Methods—Plasma Physics  \n1. INTRODUCTION  \nRadiative processes play a central role in astrophysics, as electromagnetic radiation remained the only means we can use to observe the universe until the recent successes of gravitational wave and neutrino detectors in the last few years (e.g. Abbott et al. 2024; Abbasi et al. 2024) . Theoretical models, in order to make connection to observational data, must rigorously carry out the radiative transfer calculations at the source, as well as along the propagation path before the signals reach us. A successful example is the recent Event Horizon Telescope (EHT) simulation campaign (e.g. Event Horizon Telescope Collaboration et al. 2019 , 2021) where sophisticated general-relativistic ray-tracing calculations were performed on nu-  \nmerical GRMHD models to produce radiation signatures that can be directly compared with the EHT observations.  \nIn some physical systems, e.g. when the optical depth is order unity or above, radiation may also feedback onto the dynamics of the plasma emitting the radiation, through radiation energy loss as well as photon scattering. For some systems, the radiation may even produce e± pairs in the system, thus creating a channel for plasma supply. It is therefore necessary to incorporate the effect of radiative processes into first principles numerical simulations when the radiation feedback is important. In recent years, first-principles Particlein-Cell (PIC) simulations with self-consistent radiation feedback or even pair production be-  \n2  \ncame possible, and they have been used to study plasma physics in extreme environments such as near black holes or neutron stars (e.g. Hakobyanet al. 2019; Werner et al. 2019; Cruz et al. 2021; Mehlhaff et al. 2024) .  \nDue to the stochastic nature of radiative processes, they are most commonly calculated using a Monte Carlo approach, where the photon field is represented by a large number of photon packets, and their emission and scattering are individually computed using the corresponding cross sections. The central problem with modeling radiative processes is therefore the general problem of sampling from complicated probability distributions for the energy and direction of outgoing photons. Some of the most wellknown and commonly used existing methods for doing such sampling are inverse transform sampling and rejection sampling, which can involve using approximate forms of the original distribution or resorting to a large look-up table. An efficient general method for sampling from arbitrary pro","cbCaisKi0Avs7wXJ","https://ap.wps.com/l/cbCaisKi0Avs7wXJ","pdf",964693,1,15,"English","en",105,"# Abstract\n# Introduction\n## Radiative transfer and the role of Monte Carlo\n## Stochastic sampling from probability distributions\n## Neural networks and sampling from distributions","[{\"question\":\"Why do radiative processes often require Monte Carlo methods?\",\"answer\":\"Because radiative processes like synchrotron radiation and Compton scattering are fundamentally stochastic, Monte Carlo methods approximate the outgoing photon properties by sampling many realizations from complex distributions.\"},{\"question\":\"What problem does the paper address in Monte Carlo radiative calculations?\",\"answer\":\"The key challenge is efficiently sampling from complicated probability distributions for the energy and direction of emitted photons, which dominates computational cost.\"},{\"question\":\"How does the proposed machine learning method improve sampling efficiency?\",\"answer\":\"It uses a machine learning technique that enables efficient sampling from arbitrary known probability distributions, and for inverse Compton radiation it can be up to an order of magnitude faster than traditional methods.\"}]","A Machine Learning Method for Monte Carlo Calculations of Radiative Processes | PDF",1785937300,38,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"a-machine-learning-method-for-monte-carlo-calculations-of-radiative-processes","",{"@graph":36,"@context":86},[37,54,69],{"@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/a-machine-learning-method-for-monte-carlo-calculations-of-radiative-processes/127168/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why do radiative processes often require Monte Carlo methods?","Question",{"text":76,"@type":77},"Because radiative processes like synchrotron radiation and Compton scattering are fundamentally stochastic, Monte Carlo methods approximate the outgoing photon properties by sampling many realizations from complex distributions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What problem does the paper address in Monte Carlo radiative calculations?",{"text":81,"@type":77},"The key challenge is efficiently sampling from complicated probability distributions for the energy and direction of emitted photons, which dominates computational cost.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed machine learning method improve sampling efficiency?",{"text":85,"@type":77},"It uses a machine learning technique that enables efficient sampling from arbitrary known probability distributions, and for inverse Compton radiation it can be up to an order of magnitude faster than traditional methods.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]