[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118960-en":3,"doc-seo-118960-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},118960,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Automatic Identification of 2D Materials Based on Machine Learning Method","Two-dimensional (2D) materials enable low-dimensional quantum properties, yet accurate layer number and material identification from optical microscopy (OM) remains time-consuming and labor-intensive. This thesis develops a rapid, accurate identification pipeline using Mask R-CNN, trained on datasets of 2D materials images with optimized hyperparameters to maximize evaluation performance. The resulting models predict OM images by generating bounding boxes, segmentations, and layer categories (monolayer, few-layers, thick-layers). A software system and an integrated machine-learning-based transfer system support real-time processing of large image batches and precise motorized stage control, with upgrade paths for datasets and scanning and future model architectures.","Automatic Identification of 2D Materials Based on Machine Learning Method  \nby  \nQuanjin Wang  \nDepartment of Physics Bachelor of Arts University of Colorado Boulder  \nCommittee Members:  \nDr. Daniel Dessau-Thesis Advisor  \nDepartment of Physics  \nDr. John Cumalat-Honors Council Representative Department of Physics  \nDr. Sean Shaheen-Outside Reader  \nDepartment of Electrical, Computer & Energy Engineering  \nApril 8, 2024  \nii  \nAbstract  \nAs highly anticipated quantum materials of low dimensionality, 2D materials have recently seen significant advances in their fabrication, characterization, modification, and application in research. The research on 2D materials is fascinating, and one of the most attractive directions relates to the creation of heterostructures with on-demand and unique quantum properties through the stacking of various 2D materials. However, finding and identification of 2D materials are challenging as the essential part of 2D material research. Although we can artificially estimate the number of 2D materials layers based on optical microscopy (OM), looking for sufficient and suitable 2D materials for further research is still time-consuming and labor-intensive. Given the excellent performance of machine learning in the field of computer vision, we design a method to rapidly and accurately identify 2D materials upon OM. We utilize the architecture of the Mask Region-Based Convolutional Neural Network (Mask R-CNN) to complete the model training with datasets of 2D materials images. Additionally, we optimize hyperparameters to maximize the evaluation results of the trained models. Subsequently, we successfully apply the trained models to predict optical images of 2D materials, outputting the prediction image with bounding boxes (position), segmentations (shape), and categories (monolayer, few-layers, and thick-layers) . Based on the feasibility of models and algorithms, we program software for 2D materials identification for universal and convenient usage. Finally, we design a Machine-Learning-Based 2D Material Transfer System with a system software, that  \niii  \nsuccessfully achieves real-time identification of 2D materials, processes large batches of images, and realizes precise control of the motorized stage through simple usage of the system software. This thesis is upgradeable; we also discuss potential development directions in datasets, the function of 2D materials auto scanning, and different architectures of machine learning.  \niv  \nAcknowledgments  \nFirstly, I would like to thank Professor Daniel Dessau for his kindness, patience, and invaluable assistance as my advisor for 3 years. I deeply appreciate his willingness to provide me with the opportunity to obtain a position in the research and offer strong academic support.  \nI also wish to thank the members of the Dessau’s Group, with a special mention of Mr. Zack Sierzega. Zack has offered many valuable suggestions and guidance throughout this thesis and has become a good friend in my life.  \nI would like to express my deep gratitude to my parents, whose support, enlightenment, and upbringing have been foundational to my life and academic journey. Their endless dedication has fueled my pursuit of dreams, and I am eternally grateful for everything they have done.  \nFinally, I profoundly appreciate Yanyun, my beloved, whose unwavering encouragement and hope have been power for me to move forward. I am immensely thankful for her irreplaceable tenderness and love, which complete my life and make me shine.  \nv  \nContents  \n1 Introduction 1  \n1.1 Microscopy in 2D Materials Research ································································2  \n1.2 2D Materials Transfer System··········································································6  \n1.3 Machine Learning ························································································7  \n1.3.1 Convolutional Neural Network ······················································","cbCaiaNfznMWZjjN","https://ap.wps.com/l/cbCaiaNfznMWZjjN","pdf",3096172,1,57,"English","en",105,"# Introduction\n## Microscopy in 2D Materials Research\n## 2D Materials Transfer System\n## Machine Learning\n## Convolutional Neural Network\n## Mask Region-Based Convolutional Neural Network\n# Data and Evaluation\n## Common Objects in Context\n## Evaluation\n## Training Loss\n## Mean Average Precision\n# Methodology\n## Training Strategies\n## Hyperparameters and Evaluation Plots\n# Results and Applications\n## Predictions in Optical Images of 2D Materials\n## 2D Materials Identification Software\n## Software for Machine-Learning-based 2D Materials Transfer System\n# Conclusion\n## Future Work\n## Improvement of Datasets\n## Automatic Scanning of 2D materials\n## Vision Transformer","[{\"question\":\"Why is identifying 2D materials from optical microscopy challenging?\",\"answer\":\"OM can estimate the number of layers, but finding and selecting sufficient and suitable 2D materials for further research is still time-consuming and labor-intensive.\"},{\"question\":\"Which machine learning model is used for 2D materials identification?\",\"answer\":\"The method uses Mask Region-Based Convolutional Neural Network (Mask R-CNN) trained on datasets of 2D materials images.\"},{\"question\":\"What outputs does the trained model provide when predicting optical images?\",\"answer\":\"It outputs prediction images with bounding boxes (position), segmentations (shape), and category labels for monolayer, few-layers, and thick-layers.\"}]","Automatic Identification of 2D Materials Based on Machine Learning Method | PDF",1785721221,144,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"automatic-identification-of-2d-materials-based-on-machine-learning-method","",{"@graph":36,"@context":86},[37,54,69],{"@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/automatic-identification-of-2d-materials-based-on-machine-learning-method/118960/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is identifying 2D materials from optical microscopy challenging?","Question",{"text":76,"@type":77},"OM can estimate the number of layers, but finding and selecting sufficient and suitable 2D materials for further research is still time-consuming and labor-intensive.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning model is used for 2D materials identification?",{"text":81,"@type":77},"The method uses Mask Region-Based Convolutional Neural Network (Mask R-CNN) trained on datasets of 2D materials images.",{"name":83,"@type":74,"acceptedAnswer":84},"What outputs does the trained model provide when predicting optical images?",{"text":85,"@type":77},"It outputs prediction images with bounding boxes (position), segmentations (shape), and category labels for monolayer, few-layers, and thick-layers.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]