[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123966-en":3,"doc-seo-123966-105":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},123966,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Transforming the Synthesis of Carbon Nanotubes with Machine Learning Models and Automation","Carbon-based nanomaterials (CBNs) hold strong promise for electronics, energy, and mechanics, yet practical deployment is constrained by synthesis difficulties such as structural control, large-area uniformity, and high yield. Existing approaches struggle to capture the multi-variable, coupled interactions that govern CBN production. Machine learning can manage these complexities, and its pairing with automated synthesis platforms can accelerate chemical discovery. Here, CARCO integrates transformer models for carbon materials with robotic CVD and data-driven learning to enable rapid, experimentally validated improvements, including catalyst prediction and high-precision nanotube array synthesis.","Transforming the Synthesis of Carbon Nanotubes with Machine Learning Models and Automation  \nYue Li, 1, 2 § Shurui Wang, 1, 3 § Zhou Lv, 1 Zhaoji Wang,4 Yunbiao Zhao,2 Ying Xie, 1 Yang Xu,2 Liu Qian, 1 * Yaodong Yang,4 * Ziqiang Zhao, 1, 2 * Jin Zhang 1, 3 *  \n1 School of Materials Science and Engineering, Peking University, Beijing, 100871, China.  \n2 State Key Laboratory of Nuclear Physics and Technology, School of Physics, Peking University, Beijing 100871, P. R. China.  \n3 Beijing Science and Engineering Center for Nanocarbons, Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University, Beijing, 100871, China.  \n4 Institute for AI, Peking University, Beijing 100871, China.  \n§These authors contributed equally to this work: Yue Li and Shurui Wang.  \nE-mail: [j](jinzhang@pku.edu.cn)[inzhang@pku.edu.cn](jinzhang@pku.edu.cn) ; [zqzhao@pku.edu.cn](zqzhao@pku.edu.cn) ; [yaodong.yang@pku.edu.cn](yaodong.yang@pku.edu.cn); qianliu[cnc@pku.edu.cn](cnc@pku.edu.cn)  \nAbstract  \nCarbon-based nanomaterials (CBNs) are showing significant potential in various fields, such as electronics, energy, and mechanics 1–3. However, their practical applications face synthesis challenges stemming from the complexities of structural control, large-area uniformity, and high yield. Current research methodologies fall short in addressing the multi-variable, coupled interactions inherent to CBNs production. Machine learning methods excel at navigating such complexities. Their integration with automated synthesis platforms has demonstrated remarkable potential in accelerating chemical synthesis research4, but remains underexplored in the nanomaterial domain. Here we  \nintroduce Carbon Copilot (CARCO), an artificial intelligence (AI)-driven platform that  \nintegrates transformer-based language models tailored for carbon materials, robotic chemical vapor deposition (CVD), and data-driven machine learning models,  \nempowering accelerated research of CBNs synthesis. Employing CARCO, we  \ndemonstrate innovative catalyst discovery by predicting a superior Titanium-Platinum bimetallic catalyst for high-density horizontally aligned carbon nanotube (HACNT)  \narray synthesis, validated through over 500 experiments. Furthermore, with the  \nassistance of millions of virtual experiments, we achieved an unprecedented 56.25% precision in synthesizing HACNT arrays with predetermined densities in the real world.  \nAll were accomplished within just 43 days. This work not only advances the field of HACNT arrays but also exemplifies the integration of AI with human expertise to  \novercome the limitations of traditional experimental approaches, marking a paradigm shift in nanomaterials research and paving the way for broader applications.  \n0. Introduction  \nCarbon-based nanomaterials (CBNs), such as carbon nanotubes (CNTs) and graphene, have revolutionized material science with their exceptional electrical, mechanical, and thermal properties5,6 . From facilitating the fabrication of electronics that surpass the limits of Moore's Law 1, to upgrading the performance of lightweight and high-strength structural-materials3, to enhancing the efficiency of energy storage2, CBNs have embarked on a significant journey in advanced materials. However, the full potential of CBNs is often hindered by challenges in synthesizing products with controllable  \nstructures, large-area uniformity, and high yield, which are critical for their transition from laboratory research to industrial applications.  \nThis conundrum is a microcosm of the intrinsic challenges prevalent in the development of nanomaterials. Essentially, the journey from atomic assembly to waferscale production spans numerous dimensions, exposing the limitations of traditional research methodologies when confronted with such complex systems. Within the conventional scientific paradigm, innovation is often driven by hypothesis-deductive reasoning or analogical reasoning.","cbCaig7wEqxxF7Jm","https://ap.wps.com/l/cbCaig7wEqxxF7Jm","pdf",5196256,1,51,"English","en",105,"# Introduction","[{\"question\":\"What synthesis challenges limit carbon-based nanomaterials in real applications?\",\"answer\":\"Key challenges include achieving controllable structures, maintaining large-area uniformity, and producing high yields. Multi-variable coupled interactions further complicate synthesis recipe optimization.\"},{\"question\":\"How does machine learning contribute to carbon nanotube and related nanomaterial synthesis?\",\"answer\":\"Machine learning helps navigate nonlinear, highly coupled systems by learning relationships among multiple synthesis variables. This enables more effective exploration than traditional single-factor strategies.\"},{\"question\":\"What is CARCO and what does it integrate to accelerate research?\",\"answer\":\"CARCO is an AI-driven platform that combines transformer-based language models tailored for carbon materials, robotic chemical vapor deposition (CVD), and data-driven machine learning models. It supports accelerated discovery through prediction and automated experimentation.\"}]","Transforming the Synthesis of Carbon Nanotubes with Machine Learning Models and Automation | PDF",1785819476,129,{"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},"transforming-the-synthesis-of-carbon-nanotubes-with-machine-learning-models-and-automation","",{"@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/transforming-the-synthesis-of-carbon-nanotubes-with-machine-learning-models-and-automation/123966/",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},"What synthesis challenges limit carbon-based nanomaterials in real applications?","Question",{"text":75,"@type":76},"Key challenges include achieving controllable structures, maintaining large-area uniformity, and producing high yields. Multi-variable coupled interactions further complicate synthesis recipe optimization.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does machine learning contribute to carbon nanotube and related nanomaterial synthesis?",{"text":80,"@type":76},"Machine learning helps navigate nonlinear, highly coupled systems by learning relationships among multiple synthesis variables. This enables more effective exploration than traditional single-factor strategies.",{"name":82,"@type":73,"acceptedAnswer":83},"What is CARCO and what does it integrate to accelerate research?",{"text":84,"@type":76},"CARCO is an AI-driven platform that combines transformer-based language models tailored for carbon materials, robotic chemical vapor deposition (CVD), and data-driven machine learning models. It supports accelerated discovery through prediction and automated experimentation.","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"]