[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119704-en":3,"doc-seo-119704-105":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},119704,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",6,"Technology","TBMaLT - a flexible toolkit for combining tight-binding and machine learning","Tight-binding approaches, including Density Functional Tight-Binding (DFTB) and extended tight-binding schemes, provide efficient quantum simulations for large systems and long-time scales by applying pragmatic approximations to density functional theory. Accuracy is enhanced by learning empirical parameters from machine learning, particularly when local atomic environments are represented. By fitting only short-range corrections, the workflow is typically shorter and more transferable than direct quantum-property prediction. The framework enables computing derived quantum quantities directly from tight-binding without additional learning. The open-source toolkit includes DFTB layers and an interface to the GFN1-xTB Hamiltonian, with a modular structure supporting new atom-based schemes.","TBMaLT, a flexible toolkit for combining tight-binding and machine learning  \n\n| Cite as: J. Chem. Phys. 158, 034801 (2023); [https://doi.org/10.1063/5.0132892](https://doi.org/10.1063/5.0132892)\u003Cbr>Submitted: 31 October 2022 • Accepted: 02 January 2023 • Accepted Manuscript Online: 02 January 2023 • Published Online: 18 January 2023 |  |  |  |\n| --- | --- | --- | --- |\n|  A. McSloy,  G. Fan,  W. Sun, et al. |  |  |  |\n| COLLECTIONS\u003Cbr>Paper published as part of the special topic on Modern Semiempirical Electronic Structure Methods |  |  |  |\n|  |  |  |  |\n\nARTICLES YOU MAY BE INTERESTED IN  \nωB97X-3c: A composite range-separated hybrid DFT method with a molecule-optimized polarized valence double-ζ basis set  \nThe Journal of Chemical Physics 158, 014103 (2023); [https://doi.org/10.1063/5.0133026](https://doi.org/10.1063/5.0133026)  \nDFTB+, a software package for efficient approximate density functional theory based atomistic simulations  \nThe Journal of Chemical Physics 152, 124101 (2020); [https://doi.org/10.1063/1.5143190](https://doi.org/10.1063/1.5143190)  \nr2SCAN-3c: A “Swiss army knife” composite electronic-structure method  \nThe Journal of Chemical Physics 154, 064103 (2021); [https://doi.org/10.1063/5.0040021](https://doi.org/10.1063/5.0040021)  \nJ. Chem. Phys. 158, 034801 (2023); [https://doi.org/10.1063/5.0132892](https://doi.org/10.1063/5.0132892) 158, 034801 © 2023 Author(s) .  \nThe Journal  \nof Chemical Physics  \nARTICLE  \n[scitation.org/journal/jcp](scitation.org/journal/jcp)  \nTBMaLT, a flexible toolkit for combining tight-binding and machine learning  \n\n| Cite as: J. Chem. Phys. 158, 034801 (2023); doi: 10. 1063/5.0132892 Submitted: 31 October 2022 • Accepted: 2 January 2023 •\u003Cbr>Published Online: 18 January 2023 |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- |\n| A. McSloy,1, a)  G. Fan,2  W. Sun,2  C. Hölzer,3 \u003Cbr>S. Grimme,3  T. Frauenheim,2 , 5 and B. Aradi2, b)  | M. Friede,3  | S. Ehlert,3 , 4  | N. -E. Schütte,2  |  |  |\n| AFFILIATIONS\u003Cbr>1 Warwick Centre for Predictive Modelling, School of Engineering, University of Warwick, Coventry CV4 7AL, United Kingdom\u003Cbr>2 Bremen Center of Computational Materials Science, University of Bremen, 28359 Bremen, Germany\u003Cbr>3 Mulliken Center for Theoretical Chemistry, University of Bonn, 53115 Bonn, Germany\u003Cbr>4 Microsoft Research AI4Science, 1118 CZ Schiphol, Netherlands\u003Cbr>5 Computational Science Research Center (CSRC) Beijing and Computational Science Applied Research (CSAR) Institute Shenzhen, Shenzhen, China\u003Cbr>Note: This paper is part of the JCP Special Topic on Modern Semiempirical Electronic Structure Methods.\u003Cbr>a)Electronic mail: [adam.mcsloy@warwick.ac.uk](adam.mcsloy@warwick.ac.uk)\u003Cbr>b)Author to whom correspondence should be addressed: [aradi@uni-bremen.de](aradi@uni-bremen.de) |  |  |  |  |  |\n| ABSTRACT\u003Cbr>Tight-binding approaches, especially the Density Functional Tight-Binding (DFTB) and the extended tight-binding schemes, allow for efficient quantum mechanical simulations of large systems and long-time scales. They are derived from ab initio density functional theory using pragmatic approximations and some empirical terms, ensuring a fine balance between speed and accuracy. Their accuracy can be improved by tuning the empirical parameters using machine learning techniques, especially when information about the local environment of the atoms is incorporated. As the significant quantum mechanical contributions are still provided by the tight-binding models, and only short-ranged corrections are fitted, the learning procedure is typically shorter and more transferable as it were with predicting the quantum mechanical properties directly with machine learning without an underlying physically motivated model. As a further advantage, derived quantum mechanical quantities can be calculated based on the tight-binding model without the need for additional learning. We have developed the open-source framework—Tight-Binding Machine Learning Toolkit—which al","cbCaiexG8YpEHd7Z","https://ap.wps.com/l/cbCaiexG8YpEHd7Z","pdf",5389933,1,10,"English","en",105,"# Abstract\n# Introduction\n## Motivation: functional materials and simulation challenges\n## Cost barriers of ab initio DFT\n## Limitations of classical force fields\n## Role of semi-empirical “bridging” methods","[{\"question\":\"What problem does TBMaLT address in computational materials simulation?\",\"answer\":\"TBMaLT targets the challenge of balancing efficiency and accuracy when simulating large systems and long-time scales, where ab initio methods are too expensive and classical force fields may miss electronic-structure complexity.\"},{\"question\":\"How does machine learning improve tight-binding accuracy in this approach?\",\"answer\":\"Machine learning tunes empirical parameters using information about the local atomic environment, fitting short-range corrections while retaining the physically motivated tight-binding quantum contributions.\"},{\"question\":\"What does the open-source TBMaLT toolkit provide?\",\"answer\":\"The toolkit offers an open-source framework with layers for the DFTB method and an interface to the GFN1-xTB Hamiltonian, designed with modular structure and defined interfaces to support additional atom-based schemes.\"}]","TBMaLT - a flexible toolkit for combining tight-binding and machine learning | PDF",1785725874,25,{"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},"tbmalt-a-flexible-toolkit-for-combining-tight-binding-and-machine-learning","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/tbmalt-a-flexible-toolkit-for-combining-tight-binding-and-machine-learning/119704/",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","2026-08-04","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},"What problem does TBMaLT address in computational materials simulation?","Question",{"text":76,"@type":77},"TBMaLT targets the challenge of balancing efficiency and accuracy when simulating large systems and long-time scales, where ab initio methods are too expensive and classical force fields may miss electronic-structure complexity.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does machine learning improve tight-binding accuracy in this approach?",{"text":81,"@type":77},"Machine learning tunes empirical parameters using information about the local atomic environment, fitting short-range corrections while retaining the physically motivated tight-binding quantum contributions.",{"name":83,"@type":74,"acceptedAnswer":84},"What does the open-source TBMaLT toolkit provide?",{"text":85,"@type":77},"The toolkit offers an open-source framework with layers for the DFTB method and an interface to the GFN1-xTB Hamiltonian, designed with modular structure and defined interfaces to support additional atom-based schemes.","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},[94,98,102,106,111,114,119,124,129,132,135],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},8,"Research & Report",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":21,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":21,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]