[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121053-en":3,"doc-seo-121053-105":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},121053,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Machine Learning for Infinite Neutron Matter at Finite Temperatures","Machine learning is applied to model the imaginary part of the neutron self-energy in a neutron-star binary system, approximated as infinite neutron matter at finite temperature. Model quality is assessed through computed physical observables, including the momentum distribution and the total energy per particle. The study demonstrates strong agreement with theoretical reference values. The approach combines a finite-temperature many-body framework with supervised neural-network modeling to enable accurate interpolation and controlled extrapolation.","Machine Learning for Infinite Neutron Matter at Finite Temperatures  \nAuthor: Alba Mart´ınez Marimon  \nFacultat de F´ısica, Universitat de Barcelona, Diagonal 645, 08028 Barcelona, Spain.  \nAdvisors: Arnau Rios Huguet and Javier Rozal´en Sarmiento  \nAbstract: In this paper, machine learning is used to model the imaginary part of the self-energy of a neutron-star binary system, which is approximated as infinite neutron matter. The performance of the model is evaluated by computing physical properties such as the momentum distribution and the total energy. The results obtained with the model show a high degree of accuracy when compared to theoretical values.  \nI. INTRODUCTION  \nWith the recent detection of gravitational waves originated from the merging of a neutron-star (NS) binary system [1], the need for accurate modeling of neutron star matter has increased. NS binaries represent some of the most extreme environments in the universe, with temperatures of tens of MeV [2] . NSs are formed from the remnants of Type II supernovae, caused by the gravitational collapse of the core of a star with a mass M  8M⊙ . The mass of NSs typically ranges from 0.1M⊙ to about 3 M⊙ , with their radii being approximately 10–15 kilometers [3] .  \nThe study of NS binaries is key to a better understanding of nuclear matter, as some regions show similar physical conditions to those observed in atomic nuclei. This resemblance has led to a growing interest in infinite neutron matter modeling, with the proposal of new, realistic nucleon-nucleon potentials [4] .  \nGiven the complexity of modeling such systems, Artificial Neural Networks (ANNs) can be a powerful tool. ANNs are computational models inspired by the neural networks of the human brain, which use interconnected hidden nodes (neurons) to learn patterns within data. Specifically, in this project ANNs are used as a supervised machine learning technique, meaning they learn from labeled data and manage to predict unseen data. The interest in modelling with ANNs is that they require significantly less memory than the entire dataset, since only the parameters of the model need to be stored. Furthermore, they enable inference instead of a simple interpolation, due to their ability to learn patterns and handling high-dimensional data. Inference grants predictions on unseen data points outside the range of training data, which can lead to interesting extrapolations for T = 0 MeV when only finite temperature data is available. These kinds of generalizations are very useful for real-world applications, where future data may differ from past data [5] .  \nThis document is structured as follows. In section II, we provide the necessary physical background, followed by the theoretical computational framework in section III, where we briefly introduce ANNs. In section IV, we provide a more in-depth explanation of the model building process. Finally, section V compares the results  \nof the physical values obtained with the original dataset and those obtained with the ANN.  \nII. THEORETICAL FRAMEWORK  \nPhysical systems of neutron matter at non-zero temperatures, such as binary neutron star systems or neutron stars in the early stages of their evolution, exhibit complex many-body correlations that complicate their modeling. An approach to tackle this problem is the Self-Consistent Green’s Function (SCGF) method [6] .  \nThe SCGF formalism is based on Green’s functions or propagators, which are mathematical objects that represent the dynamics of particles and their interactions, and are often depicted using Feynman diagrams. We can characterize very different systems, like neutron stars and nuclei, with the same formalism [7] . Besides all these advantages, perhaps the most important in the context of astrophysics and infinite neutron matter is that SCGF methods can be formulated consistently at non-zero temperature [8] .  \nAnother key benefit of these propagators is that a number of observables can be easily deriv","cbCaif9fKva6O43P","https://ap.wps.com/l/cbCaif9fKva6O43P","pdf",531949,1,5,"English","en",105,"# Introduction\n## Motivation from neutron-star binaries and gravitational-wave observations\n## Neural-network modeling for many-body systems\n# Theoretical framework\n## Self-consistent Green’s function at non-zero temperature\n## Green’s functions, spectral function, and derived observables","[{\"question\":\"What physical quantity is modeled with machine learning in this work?\",\"answer\":\"The model targets the imaginary part of the neutron-star matter self-energy, using infinite neutron matter as the approximation.\"},{\"question\":\"How are the model results evaluated?\",\"answer\":\"Performance is evaluated by computing observables such as the momentum distribution and the total energy, then comparing them with theoretical values.\"},{\"question\":\"Why are neural networks suitable for this modeling task?\",\"answer\":\"Supervised neural networks can learn patterns from labeled data, require storing only model parameters instead of the full dataset, and provide inference that supports generalization beyond interpolation.\"}]","Machine Learning for Infinite Neutron Matter at Finite Temperatures | PDF",1785733500,13,{"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},"machine-learning-for-infinite-neutron-matter-at-finite-temperatures","",{"@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/machine-learning-for-infinite-neutron-matter-at-finite-temperatures/121053/",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","2026-08-04","2026-08-03",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},"What physical quantity is modeled with machine learning in this work?","Question",{"text":76,"@type":77},"The model targets the imaginary part of the neutron-star matter self-energy, using infinite neutron matter as the approximation.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are the model results evaluated?",{"text":81,"@type":77},"Performance is evaluated by computing observables such as the momentum distribution and the total energy, then comparing them with theoretical values.",{"name":83,"@type":74,"acceptedAnswer":84},"Why are neural networks suitable for this modeling task?",{"text":85,"@type":77},"Supervised neural networks can learn patterns from labeled data, require storing only model parameters instead of the full dataset, and provide inference that supports generalization beyond interpolation.","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},[94,98,102,106,110,115,120,123,128,131,135],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"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":21,"slug":138},19,"General","general"]