[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118183-en":3,"doc-seo-118183-105":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},118183,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Automated Scanning Probe Tip State Classification without Machine Learning - article","Manual identification and in situ correction of scanning probe tip states is a time-consuming, tedious step in atomic-resolution scanning probe microscopy because tip structures vary randomly at the atomic level and operators must inspect topographical images after each probe change. Prior automation efforts rely on machine learning models trained with large labeled datasets for each studied surface, which are expensive and often unavailable for new substrates or adsorbate systems. Template matching using a single surface image plus limited prior knowledge enables comparable accuracy and precision to machine learning, and is demonstrated with both ML-trained comparisons and application to systems where supervised training was not feasible, also assessing transfer to literature surfaces.","This article is licensed under CC-BY 4.0   \n[www.acsnano.org](www.acsnano.org)  \nAutomated Scanning Probe Tip State Classification without Machine Learning  \nDylan Stewart Barker, * Philip James Blowey, Timothy Brown, and Adam Sweetman*  \n Cite This: ACS Nano 2024, 18, 2384−2394  \nRead Online  \nDownloaded via UNIV OF LEEDS on February 5, 2024 at 16:06:21 (UTC) . See [https://pubs.acs.org/sharingguidelines](https://pubs.acs.org/sharingguidelines) for options on how to legitimately share published articles.  \nACCESS  \n Metrics & More  \n Article Recommendations  \n*sı   \nSupporting Information  \nABSTRACT: The manual identification and in situ correction of the state of the scanning probe tip is one of the most timeconsuming and tedious processes in atomic-resolution scanning probe microscopy. This is due to the random nature of the probe tip on the atomic level, and the requirement for a human operator to compare the probe quality via manual inspection of the topographical images after any change in the probe. Previous attempts to automate the classification of the scanning probe state have focused on the use of machine learning techniques, but the training of these models relies on large, labeled data sets for each surface being studied. These data sets are extremely time-consuming to create and are not always available, especially when considering a new substrate or  \nadsorbate system. In this paper, we show that the problem of tip classification from a topographical image can be solved by using only a single image of the surface along with a small amount of prior knowledge of the appearance of the system in question with a method utilizing template matching (TM). We find that by using these TM methods, comparable accuracy and precision can be achieved to values obtained with the use of machine learning. We demonstrate the efficacy of this technique by training a machine learning-based classifier and comparing the classifications with the TM classifier for two prototypical silicon-based surfaces. We also apply the TM classifier to a number of other systems where supervised machine learning-based training was not possible due to the nature of the training data sets. Finally, the applicability of the TM method to surfaces used in the literature, which have been classified using machine learning-based methods, is considered.  \nKEYWORDS: scanning tunneling microscopy (STM), scanning probe microscopy (SPM), atomic resolution, machine learning, in situ tip conditioning, cross-correlation, automation  \nINTRODUCTION  \nAtomic-resolution scanning probe microscopy (SPM) has revolutionized our ability to investigate nanoscale phenomena 1−3 and manipulate matter with exceptional precision.4−8 Central to the success of SPM techniques is the quality and sharpness of the probe tip, which directly influences theresolution, sensitivity, and reliability of measurements. The manual in situ preparation of probe tips is a labor-intensive and time-consuming process, which poses a challenge to the efficiency and reproducibiltiy of SPM experiments, making it difficult to meet the growing demand for high-throughput SPM experiments. The ability to automate tip preparation is therefore desirable, as it would allow for operators to use their time elsewhere or assist in fully autonomous experimentation.  \nThe main hurdle to overcome in producing a system for the automatic in situ preparation of tips is the classification of the state of the tip itself. This is usually carried out by an operator through comparisons between the expected surface structure  \nand a few lines of a topograph while scanning, with the final decision being entirely based on the operator’s experience. It is also possible to use “inverse imaging” to characterize a tip, whereby the tip is scanned over a high aspect ratio surface feature, such as an adsorbed carbon monoxide (CO) molecule9 or a surface adatom, 10 to image the shape of the probe apex. This difficulty in classification is sp","cbCaikRIpyUtC7Vf","https://ap.wps.com/l/cbCaikRIpyUtC7Vf","pdf",9761167,1,11,"English","en",105,"# Abstract\n## Introduction\n## Automated Tip State Classification Approach\n## Evaluation Against Machine Learning\n## Applicability to Other Surfaces\n## Key Concepts and Keywords","[{\"question\":\"Why is manual scanning probe tip state identification so time-consuming?\",\"answer\":\"Tip structures vary randomly at the atomic level, and operators must manually inspect topographical images after probe changes to decide the tip state.\"},{\"question\":\"What replaces machine learning in this method?\",\"answer\":\"The approach uses template matching (TM) with only a single image of the surface plus a small amount of prior knowledge about the system’s appearance.\"},{\"question\":\"How does the TM classifier’s performance compare with machine learning?\",\"answer\":\"Template matching achieves comparable accuracy and precision to values obtained with machine learning. The paper also demonstrates effectiveness by training an ML-based classifier and comparing classifications for prototypical silicon-based surfaces.\"}]","Automated Scanning Probe Tip State Classification without Machine Learning - article | PDF",1785682069,28,{"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},"automated-scanning-probe-tip-state-classification-without-machine-learning-article","",{"@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/automated-scanning-probe-tip-state-classification-without-machine-learning-article/118183/",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},"Why is manual scanning probe tip state identification so time-consuming?","Question",{"text":75,"@type":76},"Tip structures vary randomly at the atomic level, and operators must manually inspect topographical images after probe changes to decide the tip state.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What replaces machine learning in this method?",{"text":80,"@type":76},"The approach uses template matching (TM) with only a single image of the surface plus a small amount of prior knowledge about the system’s appearance.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the TM classifier’s performance compare with machine learning?",{"text":84,"@type":76},"Template matching achieves comparable accuracy and precision to values obtained with machine learning. The paper also demonstrates effectiveness by training an ML-based classifier and comparing classifications for prototypical silicon-based surfaces.","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"]