[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117548-en":3,"doc-seo-117548-105":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},117548,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Advancing Computational Quantum Chemistry with Machine Learning - Dissertation","This thesis advances computational quantum chemistry through machine learning. A comprehensive lanthanoid dataset, LnQM, is generated, enabling systematic benchmarking across the lanthanoid series with geometric, energetic, molecular, and electronic properties. Conformer ranking is improved using a pairwise-trained machine learning approach, where a DimeNet++-based model increases relative energy prediction accuracy by 29% on benchmark conformational subsets. An efficient, fully differentiable extended tight-binding framework is introduced via a PyTorch dxTB implementation, enabling end-to-end parameter optimization through backpropagation and delivering major computational speed-ups.","Advancing Computational Quantum Chemistry with Machine Learning  \nDissertation  \nzur  \nErlangung des Doktorgrades (Dr. rer. nat.)  \nder  \nMathematisch-Naturwissenschaftlichen Fakultät  \nder  \nRheinischen Friedrich-Wilhelms-Universität Bonn  \nvon  \nChristian Hölzer  \naus  \nKöln  \nBonn, 2025  \nAngefertigt mit Genehmigung der Mathematisch-Naturwissenschaftlichen Fakultät der Rheinischen Friedrich-Wilhelms-Universität Bonn  \nGutachter / Betreuer: Prof. Dr. Stefan Grimme  \nGutachter: Prof. Dr. Thomas Bredow  \nTag der Promotion: 05.06.2025  \nErscheinungsjahr: 2025  \nDedicated to the Prüfungsbüro.  \nDa steh ich nun, ich promovierter Tor,  \nBin jedenfalls ein bisschen klüger als wie zuvor!  \nadapted from Goethe, Faust I  \nv  \nAbstract  \nThis thesis focuses on advancing quantum chemistry using machine learning methods. For this purpose, a dataset for the lanthanoid elements is generated, conformer ranking is addressed leveraging novel machine learning architectures and the widely used extended tight-binding model is enhanced with automatic differentiation.  \nThe LnQM dataset, a comprehensive benchmark of 17 269 mono-lanthanoid complexes optimized at PBE0-D4/def2-SVP level, enables systematic evaluations of quantum chemical and machine learning methods across the lanthanoid series. It features geometric, energetic, molecular and electronic properties at lB97M-V/def2-SVPD level, granting insights into lanthanoid chemistry and highlighting limitations of current atomic charge models.  \nThe ConfRank ansatz improves conformer ranking through pairwise training of state-of-the-art machine learning models. Utilizing the DimeNet++ architecture, the accuracy of relative energy prediction on GMKTN55 conformational subsets is improved by 29 % on average. Moreover, a considerable 100-fold computational speed-up compared to the currently used GFN2-xTB method is achieved using GPU infrastructure.  \nThe dxTB model, a PyTorch implementation of GFN-xTB, demonstrates a novel integration of quantum chemical algorithms into machine learning frameworks. It allows for differentiation of any input parameters to arbitrary order, achieving similar runtimes as the original Fortran implementation, which in turn lacks automatic differentiation. Moreover, parameter optimization can now be conducted using backpropagation, harnessing the extensive existing machine learning infrastructure, opening up possibilities to investigate new functional forms of internal xTB procedures and to develop individual, problem-specific GFN parametrizations.  \nTogether, these contributions chart new directions across different dimensions of computational research, ranging from data science aspects to model development. This thesis conduces to the ongoing advancement of machine learning in the domain of computational quantum chemistry and aims to offer a valuable contribution on the path to improved material sciences, healthcare and beyond.  \nContents  \n1 Introduction 1  \n2 Theoretical background 3  \n2.1 Quantum Chemistry ................................... 3  \n2.1.1 Wavefunction Theory .............................. 5  \n2.1.2 Density Functional Theory ........................... 13  \n2.1.3 Semiempirical Quantum Mechanical Methods ................. 18  \n2.2 Machine Learning .................................... 23  \n2.2.1 Fundamentals and Key Concepts ........................ 24  \n2.2.2 Molecular Representations and Descriptors .................. 29  \n2.2.3 Supervised Learning Approaches in Quantum Chemistry ........... 32  \n2.2.4 Graph Neural Networks ............................ 35  \n3 Hybrid DFT Geometries and Properties for 17k Lanthanoid Complexes 41  \n4 Improving GFN-FF Conformer Ranking with Pairwise Training 45  \n5 An Efficient And Fully Differentiable Framework For Extended Tight-Binding 49  \n6 Summary and Outlook 53  \nA Hybrid DFT Geometries and Properties for 17k Lanthanoid Complexes – The LnQM Dataset 59  \nA. 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .","cbCait5mWcBlbxRA","https://ap.wps.com/l/cbCait5mWcBlbxRA","pdf",27399106,1,165,"English","en",105,"# 1 Introduction\n# 2 Theoretical background\n## 2.1 Quantum Chemistry\n## 2.2 Machine Learning\n# 3 Hybrid DFT Geometries and Properties for 17k Lanthanoid Complexes\n# 4 Improving GFN-FF Conformer Ranking with Pairwise Training\n# 5 An Efficient And Fully Differentiable Framework For Extended Tight-Binding\n# 6 Summary and Outlook\n# A Hybrid DFT Geometries and Properties for 17k Lanthanoid Complexes – The LnQM Dataset\n# B ConfRank: Improving GFN-FF Conformer Ranking with Pairwise Training\n# C dxtb – An Efficient And Fully Differentiable Framework For Extended Tight-Binding","[{\"question\":\"What is the main goal of this dissertation?\",\"answer\":\"The dissertation aims to advance computational quantum chemistry by integrating machine learning methods for improved data generation, property prediction, and model efficiency.\"},{\"question\":\"What is the LnQM dataset and how is it used?\",\"answer\":\"LnQM is a benchmark dataset of mono-lanthanoid complexes, optimized at a defined quantum-chemical level and enriched with properties evaluated at another level, supporting systematic evaluations across the lanthanoid series.\"},{\"question\":\"How does the ConfRank approach improve conformer ranking?\",\"answer\":\"ConfRank improves conformer ranking through pairwise training of modern machine learning models, using a DimeNet++ architecture to enhance relative energy prediction accuracy and reduce computation time compared with an existing baseline.\"}]","Advancing Computational Quantum Chemistry with Machine Learning - Dissertation | PDF",1785676911,416,{"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},"advancing-computational-quantum-chemistry-with-machine-learning-dissertation","",{"@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/advancing-computational-quantum-chemistry-with-machine-learning-dissertation/117548/",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},"What is the main goal of this dissertation?","Question",{"text":75,"@type":76},"The dissertation aims to advance computational quantum chemistry by integrating machine learning methods for improved data generation, property prediction, and model efficiency.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the LnQM dataset and how is it used?",{"text":80,"@type":76},"LnQM is a benchmark dataset of mono-lanthanoid complexes, optimized at a defined quantum-chemical level and enriched with properties evaluated at another level, supporting systematic evaluations across the lanthanoid series.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the ConfRank approach improve conformer ranking?",{"text":84,"@type":76},"ConfRank improves conformer ranking through pairwise training of modern machine learning models, using a DimeNet++ architecture to enhance relative energy prediction accuracy and reduce computation time compared with an existing baseline.","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"]