[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120670-en":3,"doc-seo-120670-105":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},120670,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Estimating spectroscopic ages of red-giant stars using machine learning","The study estimates spectroscopic stellar ages for 197,000 red-giant stars observed by the APOGEE survey, building on the empirical link between stellar age and elemental abundances known as chemical tagging. Supervised machine learning is used, training an XGBoost model on 3,314 stars with asteroseismic ages from APOGEE–Kepler overlap. Predicted ages are then validated by analyzing the chemical, kinematic, and spatial relationships with respect to stellar age.","Estimating spectroscopic ages of red-giant stars using machine learning  \nAuthor: Pol Gispert Latorre  \nFacultat de F´ısica, Universitat de Barcelona, Diagonal 645, 08028 Barcelona, Spain.  \nAdvisor: Friedrich Anders  \nAbstract: Over the last few years, many studies have found an empirical relation between the abundance of a star and its age, rather well known as chemical tagging. Here we estimate spectroscopic stellar ages for 197.000 stars observed by the APOGEE survey. To this end, we use the supervised machine learning technique XGBoost, trained on a set of 3314 stars with asteroseismic ages observed by both APOGEE and Kepler (Miglio et al. 2021) . Eventually, to verify the obtained age estimates, we investigated the chemical, kinematic and positional relationship of the stars in respect to their age.  \nI. INTRODUCTION  \nFrequently, isochrone matching is used to determine stellar ages of the main sequence turn off and sub-giant branch. Another well-tested (but also model-dependent) method to estimate ages for field stars is asteroseismology. The main problem of these methods remains on the fact that they are not feasible nor accurate for an enormous sample of stars, just usable for a limited group of them. Therefore, for large-scale spectroscopic surveys like GALAH, other methods are necessary in order to know their age.  \nHere is where a recent study [1] comes into play, as it confirms an obvious relation between the age and abundances in field stars from the GALAH survey. This work hint at the possibility of Weak Chemical Tagging: the abundances of a star can be enough to determine its birth time, and possibly also its approximate birth position. In this way, we can study the kinematic and spatial structure of the galaxy (Galactic Archaeology), as it will be shown in this paper.  \nIn addition to that, some authors [2] [3] have also considered the possibility of Strong Chemical Tagging: the idea to link the abundance pattern of a star directly with its birth cluster or association.  \nA recent study [4] shows that this is not realistic. This research explains that it is not clear if each cluster just has one chemical signature, if this one can be different from the neighbour clusters (overlapping chemical signatures) or even if these signatures evolve over time. In this study it has been found that more of the 70% of groups of stars marked by the chemical signature actually belonged to groups created statistically from stars pertaining to different real clusters. It is therefore unlikely to recover most birth clusters. Hence, dismissing the Strong Chemical Tagging, the Weak Chemical Tagging is used in our research.  \nAnother study [5] found that approximately 30 elements (from the totality of those he resolved to study) show significant trends with age, a fact that suggests/ shows the path to follow. Thus, if abundances can be measured accurately, it is potentially possible to estimate the stars’ age.  \nA similar procedure to the one used in [1] will be carried out, in which if the same algorithm is used, it studies different types of stars. This research will use the data test of Kepler field and will extrapolate the agechemistry relations to the wider galaxy. Moreover, while [1] has utilised main-sequence turn-off stars, ours will be red-giant stars.  \nSo, the objectives of this work is reproducing the cinematic and spatial measures with the predicted chemical ages. These chemical ages will be predicted with an algorithm of Extreme Gradient Boosting using as training the data from Kepler field and extrapolating the model to new zones of the galaxy.  \nII. EXPERIMENTAL  \nA. Machine Learning basics  \nA brief introduction about the basic functioning of a machine learning model will be shown in the following lines. A machine learning model is a mathematical representation of a system which learns about the introduced data. This models are used to predict outcomes based on an introduced input (a feature) . The features are the","cbCaibdHuqPubiPr","https://ap.wps.com/l/cbCaibdHuqPubiPr","pdf",2114898,1,5,"English","en",105,"# Introduction\n## Chemical tagging: weak vs strong\n## Motivation and objectives\n# Experimental\n## Machine Learning basics\n## XGB Algorithm\n## Optimization objective","[{\"question\":\"What data and method are used to estimate spectroscopic stellar ages?\",\"answer\":\"The work estimates ages for 197,000 APOGEE red-giant stars using supervised machine learning with an XGBoost model trained on 3,314 APOGEE–Kepler stars that have asteroseismic ages.\"},{\"question\":\"How does the study relate chemical tagging to stellar age estimation?\",\"answer\":\"It leverages the empirical relation between stellar age and elemental abundances (chemical tagging), focusing on Weak Chemical Tagging as abundances can help infer birth time and possibly birth position.\"},{\"question\":\"How are the predicted ages verified after the model produces estimates?\",\"answer\":\"The study investigates how the estimated ages relate to the stars’ chemical properties, kinematics, and positional/spatial relationships, checking consistency with age-dependent trends.\"}]","Estimating spectroscopic ages of red-giant stars using machine learning | PDF",1785731266,13,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"estimating-spectroscopic-ages-of-red-giant-stars-using-machine-learning","",{"@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/estimating-spectroscopic-ages-of-red-giant-stars-using-machine-learning/120670/",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","2026-08-03",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 data and method are used to estimate spectroscopic stellar ages?","Question",{"text":75,"@type":76},"The work estimates ages for 197,000 APOGEE red-giant stars using supervised machine learning with an XGBoost model trained on 3,314 APOGEE–Kepler stars that have asteroseismic ages.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study relate chemical tagging to stellar age estimation?",{"text":80,"@type":76},"It leverages the empirical relation between stellar age and elemental abundances (chemical tagging), focusing on Weak Chemical Tagging as abundances can help infer birth time and possibly birth position.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the predicted ages verified after the model produces estimates?",{"text":84,"@type":76},"The study investigates how the estimated ages relate to the stars’ chemical properties, kinematics, and positional/spatial relationships, checking consistency with age-dependent trends.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]