[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290414-105":59,"doc-detail-290414-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","identifying-local-structures-in-dipolar-colloid-polymer-mixtures-using-machine-learning-thesis","Identifying Local Structures in Dipolar Colloid-Polymer Mixtures using Machine Learning - Thesis","","A colloid-polymer mixture subjected to an external electric field experiences induced dipole-dipole interactions alongside polymer-driven depletion forces. Varying polymer concentrations and field strengths yield multiple structural arrangements with distinct local ordering. The work studies these local structures using molecular dynamics and computes bond order parameters from simulation outputs. A multi-step unsupervised machine learning pipeline combining autoencoders, Gaussian mixture models, and a cluster merging strategy identifies local atomic clusters consistent with the proposed system understanding.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/identifying-local-structures-in-dipolar-colloid-polymer-mixtures-using-machine-learning-thesis/290414/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/identifying-local-structures-in-dipolar-colloid-polymer-mixtures-using-machine-learning-thesis/290414.png","ImageObject",300,407,{"name":92,"@type":93},"Eliana","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What forces govern structure formation in the dipolar colloid-polymer system?","Question",{"text":112,"@type":113},"The system is driven by induced dipole-dipole interactions and depletion forces caused by the polymer. Their combined effect, under different polymer concentrations and electric fields, leads to different local structures.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are local structures investigated beyond direct simulation observation?",{"text":117,"@type":113},"Molecular dynamics simulations are used to compute particle features such as bond order parameters. These features are then analyzed with an unsupervised machine learning pipeline.",{"name":119,"@type":110,"acceptedAnswer":120},"What machine learning methods are used to identify local atomic clusters?",{"text":121,"@type":113},"The thesis applies a multi-step unsupervised approach that combines autoencoders, Gaussian mixture models, and a cluster merging technique to identify different local structures from simulation outputs.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},290414,1789641643,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","Identifying Local Structures in Dipolar Colloid-Polymer Mixtures using Machine Learning  \nby  \n􀀍c Vahid Sheigani  \nA thesis submitted in partial ful􀀌llment of the re  \nquirements for the degree of Bachelor of Science.  \nDepartment of Physics and Physical Oceanography Memorial University  \nOctober 2023  \nSt. John's, Newfoundland and Labrador, Canada  \nAbstract  \nA colloid-polymer mixture with an applied electric 􀀌eld is subject to two categories of forces, the induced dipole-dipole interactions and depletion forces due to the polymer. The combination of these forces with di􀀋erent polymer concentrations and external electric 􀀌elds results in the formation of various structures with di􀀋erent local orders. To study these structures in more detail, the colloid-polymer system can be replicated computationally using the molecular dynamics method which enables us to calculate particle features such as bond order parameters computationally and further investigate these features using advanced methods such as machine learning. In this thesis, we apply a multi-step machine learning algorithm to dipolar-depletion systems and identify the local structure of atoms in the simulation box using the algorithm. The machine learning algorithm is a combination of multiple cutting-edge machine learning techniques including autoencoders, Gaussian mixture models, and a cluster merging technique. These algorithms are combined to create a multi-step process that can identify di􀀋erent structures of matter in any molecular dynamics simulation output. This algorithm utilizes unsupervised machine learning which does not require labeled data and is applicable to known and unknown local structures. The machine learning model can identify di􀀋erent local structures in colloid-polymer systems and the identi􀀌ed clusters of atoms in the systems is in complete agreement with our understanding of the systems.  \nAcknowledgements  \nI would like to thank my supervisor Dr. Ivan Saika-Voivod for introducing me to the 􀀌eld of condensed matter physics and for his invaluable insights into molecular dynamics simulations and for his guidance through conducting this research. I would also like to thank Cassandra Clowe-Coish for providing the LAMMPS con􀀌gurations that became the basis for my MD simulations. I would also like to thank Drs. Anand Yethiraj and Shivani Semwal for providing insight into the colloid-polymer mixture experiment.  \nTable of contents  \nTitle page i  \nAbstract ii  \nAcknowledgements iii  \nTable of contents iv  \nList of 􀀌gures vi  \n1 Introduction 1  \n1.1 Overview ................................... 1  \n1.2 Dipolar Depletion Systems ......................... 2  \n1.3 Molecular Dynamics Simulation ...................... 5  \n1.4 LAMMPS .................................. 6  \n1.4.1 LAMMPS Con􀀌guration ...................... 6  \n1.5 Bond Order Parameters .......................... 8  \n1.5.1 Averaged Bond Order Parameters ................. 9  \n1.5.2 Determining the cuto􀀋 distance .................. 9  \n2 Machine Learning 12  \n2.1 Overview ................................... 12  \n2.2 Neural Networks .............................. 13  \n2.2.1 The Perceptron ........................... 14  \n2.2.2 Gradient Descent Backpropagation ................ 15  \n2.3 Autoencoders ................................ 18  \n2.3.1 Undercomplete Autoencoders ................... 18  \n2.3.2 Regularized Autoencoders ..................... 19  \n2.3.3 Weight Decay Regularization ................... 20  \n2.4 Gaussian Mixture Models ......................... 21  \n2.5 Bayesian Information Criterion (BIC) ................... 22  \n2.6 Merging Algorithm ............................. 23  \n2.7 Illustrative Case ............................... 24  \n3 Results 38  \n4 Discussion and Future Work 50  \nA Source Codes 53  \nA.1 Bond Order Parameters .......................... 53  \nA.2 Autoencoder ................................. 54  \nA.3 Autoencoder Feature Importance ..................... 56  \nA.4 Gaussian Mix","cbCaihG6hhTu8Lnt","https://ap.wps.com/l/cbCaihG6hhTu8Lnt","pdf",17234900,71,"English","# 1 Introduction\n## 1.1 Overview\n## 1.2 Dipolar Depletion Systems\n## 1.3 Molecular Dynamics Simulation\n## 1.4 LAMMPS\n## 1.5 Bond Order Parameters\n# 2 Machine Learning\n## 2.1 Overview\n## 2.2 Neural Networks\n## 2.3 Autoencoders\n## 2.4 Gaussian Mixture Models\n## 2.5 Bayesian Information Criterion (BIC)\n## 2.6 Merging Algorithm\n## 2.7 Illustrative Case\n# 3 Results\n# 4 Discussion and Future Work\n# A Source Codes\n## A.1 Bond Order Parameters\n## A.2 Autoencoder\n## A.3 Autoencoder Feature Importance\n## A.4 Gaussian Mixture Model\n## A.5 Merging Algorithm\n## A.6 Particle System Visualization using Ovito","[{\"question\":\"What forces govern structure formation in the dipolar colloid-polymer system?\",\"answer\":\"The system is driven by induced dipole-dipole interactions and depletion forces caused by the polymer. Their combined effect, under different polymer concentrations and electric fields, leads to different local structures.\"},{\"question\":\"How are local structures investigated beyond direct simulation observation?\",\"answer\":\"Molecular dynamics simulations are used to compute particle features such as bond order parameters. These features are then analyzed with an unsupervised machine learning pipeline.\"},{\"question\":\"What machine learning methods are used to identify local atomic clusters?\",\"answer\":\"The thesis applies a multi-step unsupervised approach that combines autoencoders, Gaussian mixture models, and a cluster merging technique to identify different local structures from simulation outputs.\"}]","Identifying Local Structures in Dipolar Colloid-Polymer Mixtures using Machine Learning - Thesis | PDF",179]