[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118030-en":3,"doc-seo-118030-105":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},118030,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Applications of Machine Learning for Atomistic Modeling in Catalysis Informatics - Dissertation","Applications of machine learning for atomistic modeling in catalysis informatics are developed through a dissertation focused on constructing practical ML-based models and evaluating their performance on chemically relevant systems. The work reviews descriptor and feature transformations for atomistic data, establishes ML and deep learning foundations, and formulates machine learning force fields. Case studies include ML models for high-entropy alloy catalysts, ML potentials for fluxional zeolite-confined Au nanoclusters, and size-extensive multiobjective deep neural networks for partial charge prediction, emphasizing accuracy, transferability, stability, and predictive usability.","UC Davis  \nUC Davis Electronic Theses and Dissertations  \nTitle  \nApplications of Machine Learning for Atomistic Modeling in Catalysis Informatics  \nPermalink  \n[https://escholarship.org/uc/item/4c30p2fx](https://escholarship.org/uc/item/4c30p2fx)  \nAuthor  \nSun, Chenghan  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nApplications of Machine Learning for Atomistic Modeling in Catalysis  \nInformatics  \nBy  \nChenghan Sun  \nDissertation  \nSubmitted in partial satisfaction of the requirements for the degree of  \nDoctor of Philosophy  \nin  \nChemical Engineering  \nin the  \nOffice of Graduate Studies  \nof the  \nUniversity of California  \nDavis  \nApproved:  \n\n| Ambarish Kulkarni, Chair |\n| --- |\n| Surl-Hee (Shirley) Ahn |\n\nAhmet Palazoglu Committee in Charge  \n2023  \nCopyright © 2023 by Chenghan Sun All rights reserved.  \nTo my Grandmother.  \nTo all the people who are not that lucky in their life.  \nKnow that I stand by you.  \nContents  \nList [of Figures .................................... vi](of Figures .................................... vi)  \n[List of Tables ...................................](List of Tables ...................................). xix  \nAbstract ....................................... xx  \nAcknowledgments .................................. xxi  \n1 Introduction and Methods 1  \n1.1 Overview .................................... 1  \n1.2 Atomistic Simulation Methods in Computational Catalysis ........ 13  \n1.2.1 Density Functional Theory (DFT) .................. 14  \n1.2.2 Climbing Image Nudge Elastic Band (CI-NEB) .......... 18  \n1.2.3 Ab Initio Molecular Dynamics (AIMD) ............... 20  \n1.2.4 Metadynamics (MetaD) ....................... 22  \n1.3 Descriptors and Feature Transformations (A Practical Review) ...... 26  \n1.3.1 Atom-centered Symmetry Functions (ACSF) ............ 26  \n1.3.2 Smooth Overlap of Atomic Positions (SOAP) ........... 28  \n1.3.3 Many-body Tensor Representation (MBTR) ............ 30  \n1.3.4 Generalized Coordination Number (GCN) ............. 31  \n1.3.5 Generalized Local Structure-sensitive Descriptor (GLaSS) ..... 32  \n1.4 Machine Learning (ML) and Deep Learning (DL) Foundations ...... 34  \n1.4.1 Machine Learning Methods ..................... 35  \n1.4.2 Deep Learning Methods ....................... 40  \n1.5 Machine Learning Force Fields (MLFFs) .................. 45  \n1.5.1 The Conceptual Framework ..................... 45  \n1.5.2 Practical Software Packages ..................... 47  \n1.5.3 MLFFs Development Best Practices ................. 52  \n1.6 The Outline of My PhD Projects ...................... 55  \n1.7 References ................................... 56  \n2 Developing Cheap but Useful Machine Learning based Models for Investigating High-Entropy Alloy Catalysts 75  \n2.1 Abstract .................................... 75  \n2.2 Introduction .................................. 76  \n2.3 Methods .................................... 80  \n2.3.1 DFT Calculations ........................... 80  \n2.3.2 ML-FF training ............................ 81  \n2.3.3 XGBoost and Optuna ........................ 83  \n2.4 Results and Discussion ............................ 84  \n2.5 Conclusion ................................... 96  \n2.6 Supporting Information ............................ 98  \n2.7 References ................................... 109  \n3 Elucidating the Fluxionality and Dynamics of Zeolite-Confined Au Nanoclusters Using Machine Learning Potentials 116  \n3.1 Abstract .................................... 116  \n3.2 Introduction .................................. 117  \n3.3 Methods .................................... 120  \n3.3.1 Dataset Generation for MLP Training ............... 120  \n3.3.2 Training of Polarizable Atom interaction Neural Network (PaiNN) Model ................................. 122  \n3.3.3 Training of Neuroevolution Potential Model with Active Learning 124  \n3.3.4 C","cbCaiuW7ThSMtlos","https://ap.wps.com/l/cbCaiuW7ThSMtlos","pdf",35137378,1,243,"English","en",105,"# 1 Introduction and Methods\n## 1.1 Overview\n## 1.2 Atomistic Simulation Methods in Computational Catalysis\n## 1.3 Descriptors and Feature Transformations (A Practical Review)\n## 1.4 Machine Learning (ML) and Deep Learning (DL) Foundations\n## 1.5 Machine Learning Force Fields (MLFFs)\n## 1.6 The Outline of My PhD Projects\n## 1.7 References\n# 2 Developing Cheap but Useful Machine Learning based Models for Investigating High-Entropy Alloy Catalysts\n## 2.1 Abstract\n## 2.2 Introduction\n## 2.3 Methods\n## 2.4 Results and Discussion\n## 2.5 Conclusion\n## 2.6 Supporting Information\n## 2.7 References\n# 3 Elucidating the Fluxionality and Dynamics of Zeolite-Confined Au Nanoclusters Using Machine Learning Potentials\n## 3.1 Abstract\n## 3.2 Introduction\n## 3.3 Methods\n## 3.4 Results and Discussion\n## 3.5 Conclusion\n## 3.6 Supporting Information\n## 3.7 References\n# 4 Efficient Prediction of Partial Charges with a Size Extensive Multiobjective Deep Neural Network\n## 4.1 Abstract\n## 4.2 Introduction\n## 4.3 Methods\n## 4.4 Results and Discussion\n## 4.5 Conclusion\n## 4.6 Supporting Information\n## 4.7 References\n# 5 Summary and Future Directions\n## 5.1 Summary of Past Research\n## 5.2 Prospects and Aspirations for Future Research\n## 5.3 References","[{\"question\":\"What core topics does the dissertation cover about atomistic catalysis modeling?\",\"answer\":\"It reviews atomistic simulation methods, descriptor/feature transformations, and ML/DL foundations, then develops machine learning force fields. It connects these to practical modeling tasks in catalysis informatics.\"},{\"question\":\"How are machine learning models applied to high-entropy alloy catalysts?\",\"answer\":\"The work develops cheap but useful ML-based models using DFT calculations and ML-FF training. It uses methods such as XGBoost and Optuna, followed by results and discussion of predictive performance.\"},{\"question\":\"How are partial charges predicted, and what is special about the neural network approach?\",\"answer\":\"Partial charges are predicted using a size-extensive multiobjective deep neural network. The method includes curated datasets, SOAP descriptors, and a charge-balance scheme with considerations such as dipole moments.\"}]","Applications of Machine Learning for Atomistic Modeling in Catalysis Informatics - Dissertation | PDF",1785680856,612,{"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},"applications-of-machine-learning-for-atomistic-modeling-in-catalysis-informatics-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/applications-of-machine-learning-for-atomistic-modeling-in-catalysis-informatics-dissertation/118030/",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 core topics does the dissertation cover about atomistic catalysis modeling?","Question",{"text":75,"@type":76},"It reviews atomistic simulation methods, descriptor/feature transformations, and ML/DL foundations, then develops machine learning force fields. It connects these to practical modeling tasks in catalysis informatics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are machine learning models applied to high-entropy alloy catalysts?",{"text":80,"@type":76},"The work develops cheap but useful ML-based models using DFT calculations and ML-FF training. It uses methods such as XGBoost and Optuna, followed by results and discussion of predictive performance.",{"name":82,"@type":73,"acceptedAnswer":83},"How are partial charges predicted, and what is special about the neural network approach?",{"text":84,"@type":76},"Partial charges are predicted using a size-extensive multiobjective deep neural network. The method includes curated datasets, SOAP descriptors, and a charge-balance scheme with considerations such as dipole moments.","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"]