[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117229-en":3,"doc-seo-117229-105":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},117229,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Detecting Moving Objects With Machine Learning - Chapter 9 - scientific study and machine learning methods","Minor bodies in the Solar System are discovered by searching astronomical imagery for objects that change position over time. This chapter reviews machine learning methods used to find both natural and artificial moving objects in images, contrasting them with classical non-ML approaches. The review organizes ML work into streak detection, detection of moving point sources in image sequences, and detection in shift-and-stack searches, highlighting the common use of convolutional neural networks. Two example networks are presented, and major pitfalls including overfitting are discussed with best practices for robust training, validation, and generalization.","arXiv :2405 .06148v1 [ astro-ph .EP] 10 May 2024  \nChapter 9  \nDetecting Moving Objects With Machine Learning  \nAuthor: Wesley C. Fraser (Herzberg Astronomy and Astrophysics Research Centre)  \nABSTRACT  \nThe scientific study of the Solar System’s minor bodies ultimately starts with a search for those bodies. This chapter presents a review of the use of machine learning techniques to find moving objects, both natural and artificial, in astronomical imagery. After a short review of the classical non-machine learning techniques that are historically used, I review the relatively nascent machine learning literature, which can broadly be summarized into three categories: streak detection, detection of moving point sources in image sequences, and detection of moving sources in shift and stack searches. In most cases, convolutional neural networks are utilized, which is the obvious choice given the imagery nature of the inputs. In this chapter I present two example networks: a Residual Network I designed which is in use in various shift and stack searches, and a convolutional neural network that was designed for prediction of source brightnesses and their uncertainties in those same shift-stacks. In discussion of the literature and example networks, I discuss various pitfalls with the use of machine learning techniques, including a discussion on the important issue of overfitting. I discuss various pitfall associated with the use of machine learning techniques, and what I consider best practices to follow in the application of machine learning to a new problem, including methods for the creation of robust training sets, validation, and training to avoid overfitting.  \nKEYWORDS  \nminor body, moving object, convolutional neural network, machine learning, photometry, digital tracking  \n9.1 INTRODUCTION  \nThe study of natural moving objects such as the asteroids or comets has a fruitful history, which has enabled significant insights into the physical and chemical structure of the early protoplanetary disk, the formation processes responsible for the growth of planetesimals and planets, and the delivery of water, organics, and other materials important for the formation of life on the Earth, to name a few topics. The discussion of these topics is beyond the scope of this chapter, but we point the novice reader to review texts such as Asteroids IV (Michel et al., 2015), the Trans-Neptunian Solar System (Prialnik et al., 2019), Protostars and  \n2  \nPlanets VII (ppv, 2023), and the chapters of the upcoming Comets III which are avialable on the arxiv.1 The focus of this chapter is the – often arduous – task of searching for new minor bodies, a requisite first step in the study of these populations, either as a bulk population, or individually. In this chapter, I first summarize various flavours of classic search techniques which have enabled the current research into minor bodies. I then move on to discussing the nascent field of utilizing machine learning to assist in the search for minor bodies. These techniques are sometimes employed to assist with the most difficult steps in the search process, or to enable new techniques entirely. Hereafter when the distinction matters, I refer to natural Solar System objects as minor bodies to distinguish them from artificial satellites and other spacecraft.  \nThe later half of this chapter is dedicated to a discussion of the use of a convolutional neural network (CNN) that I developed to perform source classification in a circumstance that classically requires significant human effort to perform. The CNN I introduce was relatively straight forward to develop, and has been used quite successfully in numerous recent surveys for minor bodies. I use this as an easy to understand example of machine learning (ML), and to discuss some of the pitfalls and best practices in developing an ML tool.  \n9.2 INTRODUCTION TO THE DETECTION OF MOVING OBJECTS IN ASTRONOMICAL IMAGERY  \nIn this section I first introduce c","cbCaie9nfHbmXZni","https://ap.wps.com/l/cbCaie9nfHbmXZni","pdf",4387435,1,39,"English","en",105,"# 9.1 Introduction\n## 9.1.1 Background and motivation\n# 9.2 Introduction to the Detection of Moving Objects in Astronomical Imagery\n## 9.2.1 The Image Search\n## 9.2.2 Linking detections into arcs\n## 9.2.3 Shift-and-stack digital tracking","[{\"question\":\"What problem does Chapter 9 address in the search for minor bodies?\",\"answer\":\"It focuses on the task of finding new minor bodies by detecting sources that are not stationary in astronomical imagery and confirming their motion.\"},{\"question\":\"How does the chapter categorize machine learning approaches for moving object detection?\",\"answer\":\"It groups machine learning literature into streak detection, detection of moving point sources in image sequences, and detection of moving sources in shift-and-stack searches.\"},{\"question\":\"Why is overfitting emphasized, and what best practices are recommended?\",\"answer\":\"Overfitting is highlighted as a major pitfall when applying machine learning to new problems. The chapter recommends creating robust training sets, using validation, and training strategies aimed at avoiding overfitting.\"}]","Detecting Moving Objects With Machine Learning - Chapter 9 - scientific study and machine learning methods | PDF",1785674566,98,{"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},"detecting-moving-objects-with-machine-learning-chapter-9-scientific-study-and-machine-learning-methods","",{"@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/detecting-moving-objects-with-machine-learning-chapter-9-scientific-study-and-machine-learning-methods/117229/",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},"What problem does Chapter 9 address in the search for minor bodies?","Question",{"text":75,"@type":76},"It focuses on the task of finding new minor bodies by detecting sources that are not stationary in astronomical imagery and confirming their motion.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the chapter categorize machine learning approaches for moving object detection?",{"text":80,"@type":76},"It groups machine learning literature into streak detection, detection of moving point sources in image sequences, and detection of moving sources in shift-and-stack searches.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is overfitting emphasized, and what best practices are recommended?",{"text":84,"@type":76},"Overfitting is highlighted as a major pitfall when applying machine learning to new problems. The chapter recommends creating robust training sets, using validation, and training strategies aimed at avoiding overfitting.","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"]