[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121898-en":3,"doc-seo-121898-105":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},121898,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Mapping Planetary Surface Ages at Ultimate Resolutions with Machine Learning - The Moon - Thesis Abstract","The Moon’s lack of atmosphere and limited erosion make it an effective archive of impact craters for estimating surface ages. Conventional crater-age methods depend on complete detection and measurement of craters above a chosen size, a process usually carried out manually and hindered by the presence of thousands of craters. This thesis introduces a Crater Detection Algorithm (CDA) that automatically identifies impact craters down to 10 pixels on high-resolution imagery. The work develops, evaluates, and applies the CDA in three phases: building and validating the framework, deriving model ages for young craters and mare surfaces, and quantifying crater production over the last ~3 Ga by dating 211 lunar impact craters. Evaluation shows true positive rates of 93% for LRO-NAC images and 98% for Kaguya TC images, with CDA-derived ages matching manually derived results while stressing careful CDA application. Findings reveal non-constant crater production with notable fluctuations around ~500 Ma within the large-impactor population.","School of Earth and Planetary Sciences  \nMapping Planetary Surface Ages at Ultimate  \nResolutions with Machine Learning: The Moon  \nJohn Hugh Fairweather  \n0000-0002-3854-6311  \nThis thesis is presented for the Degree of  \nDoctor of Philosophy-Applied Geology  \nof  \nCurtin University  \nSeptember 2023  \nDeclaration  \nTo the best of my knowledge and belief this thesis contains no material previously published by any other person except where due acknowledgement has been made.  \nThis thesis contains no material which has been accepted for the award of any other degree or diploma in any university.  \nSignature: ………………………………………….  \n28/03/2024  \nDate:    \nAbstract  \nThe Moon's absence of an atmosphere and significant erosional mechanisms make it an ideal celestial body for preserving impact craters. When using a known crater accumulation rate, the number of impact craters across a given surface can be used to estimate a celestial surface’s age. However, this method requires all craters above a specific size to be recorded and measured – a task typically accomplished by hand. Manual counting methodologies can be tedious as craters can number in the thousands across any surface. Therefore, a Crater Detection Algorithm (CDA) was developed to efficiently identify and record impact craters down to 10 pixels in size on high-resolution images. This thesis presents the development, evaluation, and use of the lunar CDA with three key phases. (1) The development and showcase of the CDA framework, which involves model training and evaluation. The overall evaluation results (True Positive rate) for the presented CDA are 93% and 98% for the Lunar Reconnaissance Orbiter-Narrow Angle Camera (LRO-NAC) images and Kaguya Terrain Camera (TC) images, respectively. (2) Using the CDA to derive model ages for young lunar craters and mare surfaces. It was shown that our CDAderived ages are equivalent to published manually-derived ages while also emphasising the need to apply a CDA carefully. (3) Investigating the crater production over the last ~3 Ga. Here, we date 211 lunar impact craters and infer shifts in the crater production – highlighting that the crater production for impact craters may not be as constant as initially thought, wherein we see significant fluctuations within the large impactor population at ~500 Ma. Overall, this PhD project has emphasised the significance and challenges of high-resolution automated crater mapping while also opening the door to in-depth global lunar analysis, all of which aids in our understanding of the temporal evolution of our solar system.  \nThe Acknowledgements  \nBefore reading into all the aspects of teaching a stubborn computer algorithm to identify millions of small impact craters on the Moon, I would first like to thank and acknowledge some important people.  \nI would first like to thank my two supervisors. To Anthony, thank you for your unwavering ability to help in any number of ways throughout this PhD. I am honoured to be your first PhD student, which must have been a learning curve for us both, one for which I am eternally grateful. To Gretchen, thank you for the supervision throughout and the ability to pursue a PhD in a field of earth sciences that few can experience. From a small database volunteer to a complete PhD project, I am grateful for such an opportunity. Finally, I would like to thank Kosta. Though not an official supervisor, you were someone who helped me become semi-adept in the art of the Unix command line, script files, and probably much more.  \nIt cannot be overstated how much I need to thank the Pit Crew, mainly Seamus and Hely, but also those who left, Andrea, Patrick, Tanja, and those who arrived, Ash, Sophie, Dale, and Ola. The dynamic in our office was much appreciated, and I hope it continues.  \nUltimately, I thank my family (i.e., Mum) the most – without their (her) ongoing support, I would have happily become a garbageman.  \nAcknowledgement of Country  \nIt is with my deepest res","cbCaitaMUxVIbSLN","https://ap.wps.com/l/cbCaitaMUxVIbSLN","pdf",18982912,1,243,"English","en",105,"# Chapter 1: Introduction\n## 1.1 The Moon\n## 1.2 Impact Craters\n### 1.2.1 Types of Impact Craters\n### 1.2.2 Impact Crater Formation\n### 1.2.3 Impact Crater Morphology\n### 1.2.4 Impactors\n## 1.3 The Lunar Geological Timescale\n## 1.4 The Moon as a Celestial Record\n## 1.5 The Importance of Impact Crater Statistics\n## 1.6 The Advent of Machine","[{\"question\":\"Why is the Moon suitable for estimating planetary surface ages from impact craters?\",\"answer\":\"The Moon’s absence of atmosphere and significant erosional processes help preserve impact craters over long timescales, enabling crater counts to be used for age estimation.\"},{\"question\":\"What problem does the Crater Detection Algorithm (CDA) address in crater mapping?\",\"answer\":\"Manual crater counting is slow and burdensome because surfaces can contain thousands of craters, and complete detection and measurement above a size threshold is required.\"},{\"question\":\"How well does the lunar CDA perform on different image datasets?\",\"answer\":\"The reported evaluation true positive rates are 93% for LRO-NAC images and 98% for Kaguya Terrain Camera (TC) images, supporting accurate automated crater identification.\"}]","Mapping Planetary Surface Ages at Ultimate Resolutions with Machine Learning - The Moon - Thesis Abstract | PDF",1785807638,612,{"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},"mapping-planetary-surface-ages-at-ultimate-resolutions-with-machine-learning-the-moon-thesis-abstract","",{"@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/mapping-planetary-surface-ages-at-ultimate-resolutions-with-machine-learning-the-moon-thesis-abstract/121898/",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","2026-08-04",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},"Why is the Moon suitable for estimating planetary surface ages from impact craters?","Question",{"text":75,"@type":76},"The Moon’s absence of atmosphere and significant erosional processes help preserve impact craters over long timescales, enabling crater counts to be used for age estimation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem does the Crater Detection Algorithm (CDA) address in crater mapping?",{"text":80,"@type":76},"Manual crater counting is slow and burdensome because surfaces can contain thousands of craters, and complete detection and measurement above a size threshold is required.",{"name":82,"@type":73,"acceptedAnswer":83},"How well does the lunar CDA perform on different image datasets?",{"text":84,"@type":76},"The reported evaluation true positive rates are 93% for LRO-NAC images and 98% for Kaguya Terrain Camera (TC) images, supporting accurate automated crater identification.","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"]