[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290813-105":59,"doc-detail-290813-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","accelerating-giant-impact-simulations-with-machine-learning-290813","Accelerating Giant Impact Simulations with Machine Learning","","Constraining planet formation models from the observed exoplanet population requires generating large synthetic sets of planetary systems, often restricted by computational expense. A major bottleneck is the giant impact phase, where planetary embryos gravitationally evolve and merge, with subsequent collisions possible. This work introduces a machine learning approach for predicting collisional outcomes in multiplanet systems. Trained on over 500,000 N-body simulations of three-planet systems, the model predicts which two planets collide and the post-collision planetary state from short integrations, outperforming non-ML baselines and enabling an ML giant impact emulator with up to ~10,000x speedup.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/accelerating-giant-impact-simulations-with-machine-learning-290813/290813/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/accelerating-giant-impact-simulations-with-machine-learning-290813/290813.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-18","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why are giant impact simulations computationally expensive?","Question",{"text":113,"@type":114},"They require large samples of synthetic planetary systems and detailed N-body evolution, with many chaotic realizations needed to obtain statistically meaningful collision outcomes.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the machine learning model accelerate giant impact simulations?",{"text":118,"@type":114},"The model predicts which planet pair will collide and the resulting post-collision planetary state from short integrations of initial conditions, reducing the need for full long-term N-body runs.",{"name":120,"@type":111,"acceptedAnswer":121},"What training data is used to build the ML collision outcome predictor?",{"text":122,"@type":114},"The model is trained on more than 500,000 N-body simulations of three-planet systems.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290813,1789642613,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","arXiv :2408 .08873v2 [ astro-ph .EP] 25 Sep 2024  \nDraft version September 27, 2024  \nTypeset using LATEX twocolumn style in AASTeX631  \nAccelerating Giant Impact Simulations with Machine Learning  \nCaleb Lammers  ,1 Miles Cranmer  ,2, 3, 4 Sam Hadden  ,5 Shirley Ho  ,6, 1, 7 Norman Murray  ,5, 8 and  \nDaniel Tamayo 9  \n1 Department of Astrophysical Sciences, Princeton University, 4 Ivy Lane, Princeton, NJ 08544, USA  \n2 Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Wilberforce Road, Cambridge, CB3 0WA, UK  \n3 Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge, CB3 0HA, UK  \n4 Kavli Institute for Cosmology, University of Cambridge, Madingley Road, Cambridge, CB3 0HA, UK  \n5 Canadian Institute for Theoretical Astrophysics, University of Toronto, 60 St. George Street, Toronto, ON M5S 3H8, Canada  \n6 Center for Computational Astrophysics, Flatiron Institute, New York, NY 10010, USA  \n7 Department of Physics & Center for Data Science, New York University, 726 Broadway, New York, NY 10003, USA  \n8 Department of Physics, University of Toronto, 60 St. George Street, Toronto, ON M5S 1A7, Canada  \n9 Department of Physics, Harvey Mudd College, Claremont, CA 91711, USA  \nABSTRACT  \nConstraining planet formation models based on the observed exoplanet population requires generating large samples of synthetic planetary systems, which can be computationally prohibitive. A significant bottleneck is simulating the giant impact phase, during which planetary embryos evolve gravitationally and combine to form planets, which may themselves experience later collisions. To accelerate giant impact simulations, we present a machine learning (ML) approach to predicting collisional outcomes in multiplanet systems. Trained on more than 500,000 N-body simulations of three-planet systems, we develop an ML model that can accurately predict which two planets will experience a collision, along with the state of the post-collision planets, from a short integration of the system’s initial conditions. Our model greatly improves on non-ML baselines that rely on metrics from dynamics theory, which struggle to accurately predict which pair of planets will experience a collision. By combining with a model for predicting long-term stability, we create an ML-based giant impact emulator, which can predict the outcomes of giant impact simulations with reasonable accuracy anda speedup of up to four orders of magnitude. We expect our model to enable analyses that would not otherwise be computationally feasible. As such, we release our training code, along with an easy-to-use API for our collision outcome model and giant impact emulator. a)  \nKeywords: exoplanets—extrasolar rocky planets—planet formation—planetary dynamics  \n1. INTRODUCTION  \nThe nebular hypothesis, initially proposed by Immanuel Kant (Kant 1755) and later built upon by Pierre Laplace (Laplace 1796), remains the leading explanation for the formation of planetary systems. In the modern picture, terrestrial planets form out of a protoplanetary disk before experiencing a phase of giant impacts in which planets grow via collisions (see, e.g. , Lissauer 1993) . Giant impacts are therefore believed to play an important role in shaping the orbital configuration of planetary systems, and there has been significant effort to simulate this process (e.g. , Kokubo & Ida 1998;  \na) [https://github.com/dtamayo/spock](https://github.com/dtamayo/spock)  \nChambers & Wetherill 1998; Agnor et al. 1999; Chambers 2001; Raymond et al. 2005; Kokubo et al. 2006; Raymond et al. 2008; Hansen & Murray 2012) .  \nInterest in terrestrial planet formation has been reinvigorated by the discovery, due to NASA’s Kepler mission, that compact multiplanet systems are remarkably common in the galactic neighbourhood (Borucki et al. 2011; Lissauer et al. 2011; Fressin et al. 2013; Fabryckyet al. 2014; Zhu et al. 2018) . Planets in these systems typically possess short periods, sub-Nep","cbCaioVNTBNMc9LJ","https://ap.wps.com/l/cbCaioVNTBNMc9LJ","pdf",4527100,15,"English","# Abstract\n# Introduction\n## Nebular hypothesis and terrestrial planet formation\n## Giant impacts and dynamical instabilities\n## Numerical simulations and computational bottlenecks","[{\"question\":\"Why are giant impact simulations computationally expensive?\",\"answer\":\"They require large samples of synthetic planetary systems and detailed N-body evolution, with many chaotic realizations needed to obtain statistically meaningful collision outcomes.\"},{\"question\":\"How does the machine learning model accelerate giant impact simulations?\",\"answer\":\"The model predicts which planet pair will collide and the resulting post-collision planetary state from short integrations of initial conditions, reducing the need for full long-term N-body runs.\"},{\"question\":\"What training data is used to build the ML collision outcome predictor?\",\"answer\":\"The model is trained on more than 500,000 N-body simulations of three-planet systems.\"}]","Accelerating Giant Impact Simulations with Machine Learning | PDF",38]