[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118314-en":3,"doc-seo-118314-105":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},118314,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Leveraging Machine Learning for Photometric Redshift Estimation of JWST Galaxies","JWST开启后，天文观测数据的规模与复杂度持续上升，未来还将伴随SKA、Euclid等任务带来更大挑战。该研究基于机器学习开展光度红移（zphot）预测，采用核化局部线性回归模型，并使用4605个星系的光谱数据训练。模型在偏差σdz=0.018与灾难性离群率foutlier=3.5%方面表现出较高精度，同时具备良好的计算效率。结果表明，机器学习能为大规模巡天的天文数据分析提供可扩展且降低偏差的解决思路。","Leveraging Machine Learning for Photometric Redshift Estimation of JWST  \nGalaxies  \nJulie Kalná∗1 , Ryan Begley†1 , Callum Donnan 1  1 School of Physics and Astronomy, University of Edinburgh  \nOpen Access  \nReceived  \n20 Sep 2024  \nRevised  \n16 Oct 2024  \nAccepted  \n21 Oct 2024  \nPublished  \n24 Oct 2024  \nAbstract  \nWith the launch of JWST, the volume and complexity of astronomical data are increasing, a trend that will continue with future instruments such as SKA and Euclid. It is inevitable that data-driven methods will become more prominent alongside model-driven analysis. This research utilises machine learning, specifically a kernelised local linear regression model, in photometric redshift predictions of galaxies observed with JWST. With a spectroscopic dataset of 4605 galaxies, we trained the model and achieved a deviation of σdz = 0 .018 anda catastrophic outlier rate of foutlier = 3 .5% . These results demonstrate high accuracy and computational efficiency, highlighting the potential of machine learning for astronomical data analysis, in particular for large-scale surveys. DOI: 10.2218/esjs.9996 ISSN 3049-7930  \nIntroduction  \nAstronomical redshift measures the shift in light wavelengths due to the expansion of the universe, providing key information about galaxy distances and recession velocities, as well as insight into the evolution and large-scale structure of the universe. There are two primary approaches taken for measuring redshift: spectroscopic redshift (zspec ) and photometric redshift (zphot ) . Spectroscopic redshifts are obtained by taking the explicit spectrum of light from an object and comparing prominent emission lines in the spectrum to known rest-frame wavelengths. These measurements are very precise with small uncertainties (e.g. , δz ⪅ 0.01); however, they can be time-consuming and resource-intensive, especially with large-scale surveys. On the other hand, photometric techniques simply require measurements of an object’s flux taken through multiple broadband filters. Some common methods used for photometric redshift estimations are spectral energy distribution (SED) fitting (Brammer et al. 2008) and the Lymanbreak technique (Dunlop 2012) . These techniques enable efficient measurements on large sets of data, often used to compile samples of galaxies for spectroscopic follow-up observations.  \nThe James Webb Space Telescope (JWST) has provided data that looks further back in time than previously possible, allowing some of the fundamental questions about the universe to be addressed. By operating primarily in the infrared, objects from the early universe whose light has been reddened due to cosmological expansion are now detectable. JWST also offers enhanced resolution and sensitivity, enabling deeper observations of fainter, distant objects (McElwain et al. 2023; Wang 2024) . JWSTis providing vast sets of high-quality data ready to be analysed, for which machine learning can offer insights into complicated patterns that may be hard to identify otherwise (Baron 2019) .  \nThis research focuses on the implementation of a supervised machine learning model to allow scalability of zphot measurements for galaxies observed by JWST. The goal is to develop a data-driven approach that is efficient and accurate in handling large datasets as well as free from model-dependent biases (Hainline et al. 2024) . This research demonstrates the potential for enhancing and accelerating data analysis methods during the big data era of astronomy (Zhang et al. 2015) .  \nIn this work, we first provide a brief background on machine learning and its applications in redshift  \nastronomy. We then describe the observational data and the machine learning model used in this study ∗ Student Author  \n†Corresponding academic contact: [rbeg@roe.ac.uk](rbeg@roe.ac.uk)  \nbefore presenting and discussing the results.  \nMachine Learning Background  \nThe central idea in supervised machine learning involves a mapping function, f, that rel","cbCaig15s7cmRDjq","https://ap.wps.com/l/cbCaig15s7cmRDjq","pdf",517620,1,6,"English","en",105,"# Abstract\n# Introduction\n## Redshift measurement methods\n## Role of JWST\n## Study objective\n# Machine Learning Background\n## Supervised learning formulation\n## Objective function and generalisation\n## Previous redshift estimation approaches\n# Results and discussion","[{\"question\":\"为什么需要用机器学习来估计JWST星系的光度红移？\",\"answer\":\"JWST及未来巡天会产生更大规模、更高复杂度的数据，使得数据驱动方法需与模型驱动分析并行。该研究旨在提升zphot测量的可扩展性，同时降低模型依赖偏差。\"},{\"question\":\"本研究使用的机器学习模型是什么？\",\"answer\":\"采用核化（kernelised）的局部线性回归模型，用于根据光度观测信息预测星系红移。\"},{\"question\":\"模型的关键性能指标有哪些？\",\"answer\":\"基于4605个星系的光谱数据训练后，偏差达到σdz=0.018，灾难性离群率为foutlier=3.5%，并体现出较高精度与计算效率。\"}]","Leveraging Machine Learning for Photometric Redshift Estimation of JWST Galaxies | PDF",1785682992,15,{"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},"leveraging-machine-learning-for-photometric-redshift-estimation-of-jwst-galaxies","",{"@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/leveraging-machine-learning-for-photometric-redshift-estimation-of-jwst-galaxies/118314/",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","2026-08-02",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},"为什么需要用机器学习来估计JWST星系的光度红移？","Question",{"text":75,"@type":76},"JWST及未来巡天会产生更大规模、更高复杂度的数据，使得数据驱动方法需与模型驱动分析并行。该研究旨在提升zphot测量的可扩展性，同时降低模型依赖偏差。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"本研究使用的机器学习模型是什么？",{"text":80,"@type":76},"采用核化（kernelised）的局部线性回归模型，用于根据光度观测信息预测星系红移。",{"name":82,"@type":73,"acceptedAnswer":83},"模型的关键性能指标有哪些？",{"text":84,"@type":76},"基于4605个星系的光谱数据训练后，偏差达到σdz=0.018，灾难性离群率为foutlier=3.5%，并体现出较高精度与计算效率。","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"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":106,"slug":137},19,"General","general"]