[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85891-en":3,"doc-seo-85891-105":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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85891,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","A Hyperbolic Neural Closure for M1 Radiation Transfer","In radiation transfer simulations, the M1 method reduces cost by replacing the full angular transport equation with a low-order moment system, but the truncation requires a closure for higher-order moments. While machine learning closures can outperform classical analytic models, unconstrained learning may break hyperbolicity by yielding non-real characteristic speeds and cause numerical solver failure. A hyperbolic neural closure is proposed by parameterizing the M1 Jacobian using two neural networks: a symmetric matrix network and a strictly convex entropy network whose Hessian provides a positive-definite symmetrizer. The closure is reconstructed by integrating the learned Jacobian field along an integration path, improving accuracy and stability in discontinuous Galerkin simulations.","arXiv :2607 . 10364v 1 [ cs .LG] 11 Jul 2026  \nA Hyperbolic Neural Closure for M1 Radiation Transfer  \nBongseok Kima, Jiahao Zhangb , Johannes Krotzc , Dinshaw Balsarad,e , Ryan  \nMcClarrenc, Guang Lina,b,∗  \na School of Mechanical Engineering, Purdue University, West Lafayette, IN, USA b Department of Mathematics, Purdue University, West Lafayette, IN, USAc Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame,  \nIN, USA  \nd Department of Physics and Astronomy, University of Notre Dame, Notre Dame, IN, USA e Department of Applied and Computational Mathematics and Statistics, University of Notre  \nDame, Notre Dame, IN, USA  \nAbstract  \nIn radiation transfer simulations, an M1 method achieves substantial computational savings by replacing the full angular transport equation with a low-order moment system. Because this reduced system is not closed, a closure model is required to represent the unknown higher-order moments using lower-order moments. While machine learning (ML)-based closures can improve accuracy beyond classical analytic closures, unconstrained learned closures may produce non-real characteristic speedsand consequently cause numerical solver breakdown. To guarantee real eigenvalues of the Jacobian associated with ML closures, we propose a hyperbolic neural closure for the M1 radiative transfer system. Rather than directly predicting closure terms, we parameterize the Jacobian through two neural networks: (i) a symmetric matrix network and (ii) a strictly convex entropy network whose Hessian defines a positive definite symmetrizer. These components are combined to yield a Jacobian that is similar to a symmetric matrix, thereby ensuring real eigenvalues. The closure is then reconstructed by numerical integration of the learned Jacobian field along a prescribed integration path. Numerical experiments show that the proposed closure not only achieves higher closure accuracy than classical analytic closures, but also improves solution accuracy and remains stable in discontinuous Galerkin simulations for radiative transfer problems.  \nKeywords: Radiation transfer, M1 method, Moment closure, Deep learning,  \n∗ Corresponding author.  \nEmail address: [guanglin@purdue.edu](guanglin@purdue.edu) (Guang Lin)  \nPreprint submitted to arXiv July 14, 2026  \nDiscontinuous Galerkin method, Hyperbolicity  \n1. Introduction  \nRadiative transfer arises in diverse physical phenomena, including astrophysics [1], plasma physics [2], atmospheric science [3], biomedical optics [4], and heat transfer [5] . The radiative transfer equation (RTE) is a kinetic transport equation whose direct numerical simulation is computationally expensive because the solution depends on spatial, angular, frequency, and temporal variables. Moment methods [6] reduce computational complexity by replacing the full angular transport equation with a finite hierarchy of moment equations. Among these formulations, the M1 method [7, 8] truncates the hierarchy at second order, leading to a hyperbolic system for radiation energy density and radiation flux together with a closure relation for the radiation pressure tensor. The remaining difficulty is the closure problem: the moment system contains more unknowns than governing equations, leaving the radiation pressure tensor unspecified. A widely used approach to address the closure problem is to use analytic closure models for the radiation pressure tensor, such asthe Levermore closure [8], the Minerbo closure [9], and several related formulations surveyed in [7] . However, classical closure models can become restrictive in strongly anisotropic transport regimes [10, 11] and struggle to represent complex angular radiation distributions [11] .  \nAs an alternative to classical closure models, machine learning (ML)-based closures may offer a promising approach for constructing more accurate closure relations for M1 radiative transfer. However, the ML-based closure can violate hyperbolicity of","cbCaihrdgol1bGJz","https://ap.wps.com/l/cbCaihrdgol1bGJz","pdf",7133473,3,1,43,"English","en",105,"# Introduction\n## Radiation transfer and moment methods\n## The closure problem in the M1 method\n## Limitations of classical analytic closures\n## ML-based closures and the need for hyperbolicity\n## Related work on hyperbolic and entropy-based closures","[{\"question\":\"Why does the M1 method need a closure model?\",\"answer\":\"The M1 method truncates the moment hierarchy at second order, which leaves more unknowns than governing equations. The radiation pressure tensor is not fully specified, so a closure relation is required.\"},{\"question\":\"What problem can occur with unconstrained machine-learning closures for M1?\",\"answer\":\"Learned closures can violate hyperbolicity, producing non-real characteristic speeds. This can cause numerical solver breakdown because wave propagation becomes physically inconsistent.\"},{\"question\":\"How does the proposed hyperbolic neural closure ensure real eigenvalues?\",\"answer\":\"The approach parameterizes the M1 Jacobian using a symmetric matrix network and a strictly convex entropy network whose Hessian defines a positive-definite symmetrizer. The resulting Jacobian is constructed so it is similar to a symmetric matrix, guaranteeing real eigenvalues.\"}]",1784206991,108,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-hyperbolic-neural-closure-for-m1-radiation-transfer","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/a-hyperbolic-neural-closure-for-m1-radiation-transfer/85891/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does the M1 method need a closure model?","Question",{"text":75,"@type":76},"The M1 method truncates the moment hierarchy at second order, which leaves more unknowns than governing equations. The radiation pressure tensor is not fully specified, so a closure relation is required.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem can occur with unconstrained machine-learning closures for M1?",{"text":80,"@type":76},"Learned closures can violate hyperbolicity, producing non-real characteristic speeds. This can cause numerical solver breakdown because wave propagation becomes physically inconsistent.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed hyperbolic neural closure ensure real eigenvalues?",{"text":84,"@type":76},"The approach parameterizes the M1 Jacobian using a symmetric matrix network and a strictly convex entropy network whose Hessian defines a positive-definite symmetrizer. The resulting Jacobian is constructed so it is similar to a symmetric matrix, guaranteeing real eigenvalues.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"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":52,"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"]