[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118607-en":3,"doc-seo-118607-105":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},118607,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning for Atomistic Modeling - Representations and Thermal Transport - Dissertation","Computer simulations of molecules and materials are essential tools in physics, chemistry, and materials science, spanning first-principles electronic structure methods with high accuracy but heavy computational cost and forcefields with low cost but requiring parametrization and explicit interaction models. This thesis uses machine learning to bridge these extremes by training regression models on quantum-mechanical reference data and employing them as surrogate models in simulation workflows. It addresses representation learning for atomistic systems and applies machine-learning potentials to thermal transport simulations.","Machine Learning for Atomistic Modeling:  \nRepresentations and Thermal Transport  \nvorgelegt von  \nM. Sc .  \nMarcel F. Langer ORCID:0000-0002-1270-3016  \nan der Fakultät IV-Elektrotechnik und Informatik der Technischen Universität Berlin zur Erlangung des akademischen Grades Doktor der Naturwissenschaften  \n– Dr. rer. nat.–  \ngenehmigte Dissertation  \nPromotionsausschuss:  \nVorsitzender Gutachter  \nGutachter  \nGutachter  \nGutachter  \nProf. Dr. Wojciech Samek  \nProf. Dr. Klaus-Robert Müller  \nProf. Dr. Matthias Scheffler  \nProf. Dr. Alexandre Tkatchenko Dr. Matthias Rupp  \nTag der wissenschaftlichen Aussprache: 7 . Juli 2023  \nBerlin 2023  \n3  \nAbstract  \nComputer simulations of molecules and materials are an indispensable tool for physics, chemistry, and materials science. A wide range of methods are available for this task: On one end, first-principles electronic structure approaches, which numerically solve the Schrödinger equation, obtain high accuracy at high computational cost. On the other end, forcefields, simple analytical approximations, are fast to evaluate, but require parametrisation and an explicit model of desired physical interactions. Machine learning is increasingly used to bridge the gap between these two extremes, aiming to combine high accuracy with computational efficiency. To this end, regression models are trained on quantum-mechanical reference calculations and then used as surrogate model during simulations.  \nThis thesis considers two topics related to such models: Representations of atomistic systems, and the application of machine-learning potentials to thermal transport simulations.  \nEfficient learning in this setting requires models, and therefore input features, that respect fundamental symmetries. We comprehensively review and discuss such representations and relations between them. For selected representations, we compare energy predictions for a range of datasets in numerical experiments controlled for data distribution, regression method, and hyperparameter optimisation.  \nThe Green-Kubo method is a rigorous framework for thermal transport simulations in materials. It is based on equilibrium molecular dynamics simulations, requiring both an accurate description of the potential energy surface and careful consideration of convergence in simulation duration and size. In this context, machine-learning potentials trained with first-principles data promise the ability to reach convergence at a fraction of the computational cost. This thesis adapts the implementation of the Green-Kubo approach to the recently developed class of message-passing machine-learning potentials, which iteratively consider semi-local interactions beyond the initial interaction cutoff. We derive an adapted heat flux formulation for such potentials that can be implemented using automatic differentiation without compromising computational efficiency. The approach is validated by computing the thermal conductivity of zirconia, tin selenide, and silicon with message-passing neural networks.  \n4  \nZusammenfassung  \nComputersimulationen von MolekülenundMaterialien sind einwichtiges Werkzeug für Chemie, Physik, und Materialwissenschaft. Es stehen dazu ein Spektrum an Methoden zur Verfügung: Auf der einen Seite stehen quantenmechanische Ansätze, die numerisch die Schrödingergleichung lösen und somit unter großem Rechenaufwand genaue Ergebnisse erzielen können. Auf der anderen Seite stehen einfache analytischeNäherungen, sogenannte Kraftfelder, die sehr effizientsind, jedoch für neue Probleme parametrisiert werden müssen, und bei denen physikalische Wechselwirkungen explizit modelliert werden müssen. Methoden aus dem maschinellen Lernen werden zunehmend dazu verwendet, diese Extreme zusammenzuführen und Genauigkeit mit Effizienz zu vereinbaren. Dabei werden Regressionsmodelle auf Referenzrechnungen trainiert und dann als Ersatz für quantenmechanische Rechnungen in Simulationen verwendet.  \nDiese Arbeit setzt sich mit der Konstrukti","cbCaibHjAJ54yf4K","https://ap.wps.com/l/cbCaibHjAJ54yf4K","pdf",12032840,1,216,"English","en",105,"# Abstract\n## Problem setup: bridging accuracy and efficiency\n## Representations for atomistic systems\n## Thermal transport via machine-learning potentials\n## Validation on material systems\n# Zusammenfassung\n## Motivation and methodology","[{\"question\":\"How does the thesis use machine learning to connect first-principles and forcefield methods?\",\"answer\":\"Regression models are trained on quantum-mechanical reference calculations and then used as surrogate models during molecular simulations to combine high accuracy with better computational efficiency.\"},{\"question\":\"What is the role of symmetry in learning atomistic representations?\",\"answer\":\"Efficient learning requires input features that respect fundamental symmetries, and the thesis reviews representations and compares energy predictions across datasets under controlled conditions.\"},{\"question\":\"How is the Green-Kubo method adapted for message-passing machine-learning potentials?\",\"answer\":\"The work adapts the Green-Kubo implementation to message-passing potentials by deriving an adapted heat-flux formulation that can be implemented with automatic differentiation while preserving computational efficiency.\"}]","Machine Learning for Atomistic Modeling - Representations and Thermal Transport - Dissertation | PDF",1785684482,544,{"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},"machine-learning-for-atomistic-modeling-representations-and-thermal-transport-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/machine-learning-for-atomistic-modeling-representations-and-thermal-transport-dissertation/118607/",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},"How does the thesis use machine learning to connect first-principles and forcefield methods?","Question",{"text":75,"@type":76},"Regression models are trained on quantum-mechanical reference calculations and then used as surrogate models during molecular simulations to combine high accuracy with better computational efficiency.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the role of symmetry in learning atomistic representations?",{"text":80,"@type":76},"Efficient learning requires input features that respect fundamental symmetries, and the thesis reviews representations and compares energy predictions across datasets under controlled conditions.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the Green-Kubo method adapted for message-passing machine-learning potentials?",{"text":84,"@type":76},"The work adapts the Green-Kubo implementation to message-passing potentials by deriving an adapted heat-flux formulation that can be implemented with automatic differentiation while preserving computational efficiency.","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"]