[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127399-en":3,"doc-seo-127399-105":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},127399,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Disk2Planet - A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems","Disk2Planet is a machine learning tool designed to infer key parameters in disk-planet systems from observed protoplanetary disk structures. It uses two-dimensional density and velocity maps as input and outputs disk and planet properties, including the Shakura–Sunyaev viscosity, disk aspect ratio, planet–star mass ratio, and the planet’s radius and azimuth. The method combines CMA-ES and PPDONet, achieving automated retrieval in about three minutes on an Nvidia A100 and percent-level accuracy with support for missing data and unknown noise.","arXiv :2409 . 17228v1 [ astro-ph .EP] 25 Sep 2024  \nDraft version September 27, 2024  \nTypeset using LATEX twocolumn style in AASTeX631  \nDisk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in  \nDisk-Planet Systems  \nShunyuan Mao (毛顺元) ,1 Ruobing Dong (董若冰) ,2, 3 Kwang Moo Yi ,4 Lu Lu ,5 Sifan Wang,6, 7 and  \nParis Perdikaris8  \n1 Department of Physics and Astronomy, University of Victoria, Victoria, BC V8P 5C2, Canada, [symao@uvic.ca](symao@uvic.ca)  \n2 Department of Physics and Astronomy, University of Victoria, Victoria, BC V8P 5C2, Canada  \n3 Kavli Institute for Astronomy and Astrophysics, Peking University, Beijing 100871, People’s Republic of China, [rbdong@pku.edu.cn](rbdong@pku.edu.cn)[ ](rbdong@pku.edu.cn)4 Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada  \n5 Department of Statistics and Data Science, Yale University, New Haven, CT 06511, USA  \n6 Graduate Group in Applied Mathematics and Computational Science, University of Pennsylvania, Philadelphia, PA 19104, USA  \n7 Institute for Foundations of Data Science, Yale University, New Haven, CT 06520, USA  \n8 Department of Mechanical Engineering and Applied Mechanics, University of Pennsylvania, Philadelphia, PA 19104, USA  \nABSTRACT  \nWe introduce Disk2Planet, a machine learning-based tool to infer key parameters in disk-planet systems from observed protoplanetary disk structures. Disk2Planet takes as input the disk structures in the form of two-dimensional density and velocity maps, and outputs disk and planet properties, that is, the Shakura–Sunyaev viscosity, the disk aspect ratio, the planet–star mass ratio, and the planet’s radius and azimuth. We integrate the Covariance Matrix Adaptation Evolution Strategy (CMA– ES), an evolutionary algorithm tailored for complex optimization problems, and the Protoplanetary Disk Operator Network (PPDONet), a neural network designed to predict solutions of disk–planet interactions. Our tool is fully automated and can retrieve parameters in one system in three minutes on an Nvidia A100 graphics processing unit. We empirically demonstrate that our tool achieves percent-level or higher accuracy, and is able to handle missing data and unknown levels of noise.  \nKeywords: Protoplanetary disks (1300)– Planetary-disk interactions (2204)– Hydrodynamical simulations (767)– Neural networks (1933)– Open source software (1866)  \n1. INTRODUCTION  \nPlanets form in protoplanetary disks: flattened, gaseous disks surrounding newborn stars (Andrews 2020) . To study planet formation in the outer disk beyond the snowline, a straightforward approach is to directly image the forming planets in these disks (e.g. , Keppler et al. 2018; M¨uller et al. 2018; Wagner et al. 2018; Christiaens et al. 2019; Haffert et al. 2019; Hashimoto et al. 2020; Wang et al. 2020; Currie et al. 2022; Zhou et al. 2022; Wagner et al. 2023) . Successful detections can provide critical information about the process, such as the mass and orbit of the forming planets. However, this approach is challenging with current observational techniques as the signals from the stars and disks overwhelm those from the planets (Currie et al. 2022) . These factors severely limit our understanding of how planets form.  \nTo detect young planets embedded in protoplanetary disks, an alternative method is to infer their presence  \nand constrain their parameters from observations of large-scale disk structures produced by disk-planet interactions (Paardekooper et al. 2022) . The morphology of these structures, such as gaps (e.g. , Paardekooper & Mellema 2006; Rosotti et al. 2016; Dipierro & Laibe 2017), spiral arms (e.g. , Bae & Zhu 2018; Dong et al. 2015a), vortices (e.g. , Zhu et al. 2014), and kinematic perturbations (e.g. , Pinte et al. 2018; Teague et al. 2018; Izquierdo et al. 2021; Rabago & Zhu 2021), depends on the properties of the disk and the planets, such as the viscosity and aspect ratio of the disk, and the mass","cbCaisYsQmYaU4cX","https://ap.wps.com/l/cbCaisYsQmYaU4cX","pdf",2520373,1,11,"English","en",105,"# Abstract\n# Introduction\n## Planet formation in protoplanetary disks\n## Inverse problem for disk-planet parameter inference\n## Limitations of conventional inverse problem solvers\n# Proposed approach: automated machine learning inference","[{\"question\":\"What inputs does Disk2Planet require to infer parameters?\",\"answer\":\"Disk2Planet takes observed disk structures in the form of two-dimensional density and velocity maps.\"},{\"question\":\"What parameter outputs are produced by the tool?\",\"answer\":\"It outputs disk and planet properties, including the Shakura–Sunyaev viscosity, disk aspect ratio, planet–star mass ratio, and the planet’s radius and azimuth.\"},{\"question\":\"How does Disk2Planet achieve automation and speed?\",\"answer\":\"It integrates CMA-ES with a neural network (PPDONet) and performs fully automated parameter retrieval in about three minutes on an Nvidia A100 GPU.\"}]","Disk2Planet - A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems | PDF",1785938684,28,{"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},"disk2planet-a-robust-and-automated-machine-learning-tool-for-parameter-inference-in-disk-planet-systems","",{"@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/disk2planet-a-robust-and-automated-machine-learning-tool-for-parameter-inference-in-disk-planet-systems/127399/",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","2026-08-05",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 inputs does Disk2Planet require to infer parameters?","Question",{"text":75,"@type":76},"Disk2Planet takes observed disk structures in the form of two-dimensional density and velocity maps.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What parameter outputs are produced by the tool?",{"text":80,"@type":76},"It outputs disk and planet properties, including the Shakura–Sunyaev viscosity, disk aspect ratio, planet–star mass ratio, and the planet’s radius and azimuth.",{"name":82,"@type":73,"acceptedAnswer":83},"How does Disk2Planet achieve automation and speed?",{"text":84,"@type":76},"It integrates CMA-ES with a neural network (PPDONet) and performs fully automated parameter retrieval in about three minutes on an Nvidia A100 GPU.","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"]