[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128224-en":3,"doc-seo-128224-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128224,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","Transferable User-Friendly Machine Learning for Normal Boiling Point Prediction - Thesis","Normal boiling point (NBP) estimation is essential for material science and process design, serving as a widely documented baseline property for predicting many related thermophysical characteristics. When experimental NBP data are unavailable, model-based prediction becomes critical. This thesis evaluates multiple machine learning and deep learning strategies, focusing on feature selection and representation, including functional group moieties, molecular descriptors, SMILES enumeration, and molecular graphs with graph neural networks (GNNs). Results show GNN-based molecular graphs provide the best accuracy, with an average error rate of about 2.5% across tested compounds. The work supports improved predictions for solid and temperature-dependent properties and proposes a user-friendly online tool.","Brigham Young University  \nBYU ScholarsArchive  \nTheses and Dissertations  \n2024-04-22  \nTransferable User-Friendly Machine Learning for Normal Boiling Point Prediction  \nFrank Tafadzwa Mtetwa Brigham Young University  \nFollow this and additional works at: [https://scholarsarchive.byu.edu/etd](https://scholarsarchive.byu.edu/etd)  \n Part of the Engineering Commons  \nBYU ScholarsArchive Citation  \nMtetwa, Frank Tafadzwa, \"Transferable User-Friendly Machine Learning for Normal Boiling Point Prediction\" (2024) . Theses and Dissertations. 10837.  \n[https://scholarsarchive.byu.edu/etd/10837](https://scholarsarchive.byu.edu/etd/10837)  \nThis Thesis is brought to you for free and open access by BYU ScholarsArchive. It has been accepted for inclusion in Theses and Dissertations by an authorized administrator of BYU ScholarsArchive. For more information, please [contact](contact ellen_amatangelo@byu.edu)[ ellen_amatangelo@byu.edu](contact ellen_amatangelo@byu.edu).  \nTransferable User-Friendly Machine Learning for Normal Boiling Point  \nPrediction  \nFrank T. Mtetwa  \nA thesis submitted to the faculty of Brigham Young University  \nin partial fulfillment of the requirements for the degree of  \nMaster of Science  \nThomas A. Knotts IV, Chair  \nW.Vincent Wilding  \nJohn D. Hedengren  \nDepartment of Chemical Engineering Brigham Young University  \nCopyright © 2024 Frank T. Mtetwa All Rights Reserved  \nTransferable User-Friendly Machine Learning for Normal Boiling Point Prediction  \nFrank T. Mtetwa  \nDepartment of Chemical Engineering Master of Science  \nAbstract  \nThe estimation of thermophysical properties of chemical compounds holds considerable importance across a multitude of fields, ranging from material science to process design. Among these properties, the normal boiling point (NBP) stands out as a pivotal parameter in scientific and engineering contexts, as it elucidates the state of a substance under standard conditions commonly encountered in nature. Additionally, NBP is extensively documented in various reference materials and databases. Given its paramount importance and widespread availability, prediction methodologies for other properties such as critical temperature, liquid density, vapor pressure, surface tension, liquid viscosity, liquid thermal conductivity, and flash point often rely on NBP as a foundational metric. Accurate prediction of NBP becomes imperative when experimental data are lacking. Consequently, several prediction techniques have been proposed. These approaches encompass group contribution methodologies, which analyze chemical moieties within molecules, and quantitative structure-property relationships (QSPR), which aim to correlate molecular descriptors with various features of the substance. Although in recent years, Machine Learning (ML) and Deep Learning (DL) techniques have gained traction for predicting molecular properties, determining the optimal strategies for feature selection, feature vectorization, and algorithm choice remains an ongoing challenge. In this study, multiple feature selection methods were explored and evaluated alongside various ML/DL algorithms. Specifically, four techniques were assessed namely functional group moieties, molecular descriptors, SMILES enumeration, and molecular graphs (GNNs) . The findings suggest that the utilization of molecular graphs, particularly employing GNNs, yields superior prediction capabilities compared to alternative methods and traditional non-machinelearning approaches, average an average error rate of 2.5% on the tested compounds. Also, the findings of this work will be useful in improving the prediction of solid as well as temperature dependent thermophysical properties. To enhance accessibility, a user-friendly online tool based on GNNs, making this technique readily accessible to the broader scientific community.  \nKeywords: Machine Learning, Deep Learning, normal boiling point prediction, organic compounds  \nAcknowledgments  \nI would like to ackno","cbCaibCcyeSe5k23","https://ap.wps.com/l/cbCaibCcyeSe5k23","pdf",8570148,5,1,75,"English","en",105,"# 1 Introduction\n# 2 A Review of Normal Boiling Point Prediction Methods in Literature\n## 2.1 Introduction\n## 2.2 Group Contribution methods\n## 2.3 Comparison of GC methods\n## 2.4 QSPR Models\n## 2.5 Summary\n# 3 Machine Learning and Deep Learning\n## 3.1 Introduction\n## 3.2 Machine Learning and Deep Learning\n## 3.3 Featurization and Molecular Representation\n## 3.4 Graph Neural Networks\n## 3.5 Recurrent Neural Networks\n# 4 Molecule Representation and Modeling\n## 4.1 Introduction\n## 4.2 Methods\n## 4.3 Data set splitting\n## 4.4 Modeling\n# 5 Results and Discussion\n## 5.1 Introduction\n## 5.2 Model performance\n## 5.3 Comparison of current prediction methods and GNN method\n## 5.4 Outlier analysis of GNN predictions\n## 5.5 Effects of varying dataset size of ML model accuracy\n# 6 Model Deployment\n## 6.1 Introduction\n# 7 Conclusions and Future Work\n## 7.1 Conclusions\n## 7.2 Future Work","[{\"question\":\"Why is normal boiling point (NBP) prediction important in chemical engineering and materials science?\",\"answer\":\"NBP is a key thermophysical property that is widely used as a reference for understanding and predicting other substance behaviors. Accurate NBP prediction is especially important when experimental data are missing.\"},{\"question\":\"Which feature selection and representation methods are evaluated for NBP prediction?\",\"answer\":\"The thesis evaluates functional group moieties, molecular descriptors, SMILES enumeration, and molecular graphs using graph neural networks (GNNs). These approaches determine how molecular information is converted into model inputs.\"},{\"question\":\"What model approach performs best according to the thesis results?\",\"answer\":\"Using molecular graphs with GNNs delivers the strongest prediction performance, achieving an average error rate of about 2.5% on the tested compounds. The findings also indicate the approach can support improved predictions for solid and temperature-dependent thermophysical properties.\"}]","Transferable User-Friendly Machine Learning for Normal Boiling Point Prediction - Thesis | PDF",1785945819,189,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"transferable-user-friendly-machine-learning-for-normal-boiling-point-prediction-thesis","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/transferable-user-friendly-machine-learning-for-normal-boiling-point-prediction-thesis/128224/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-29","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why is normal boiling point (NBP) prediction important in chemical engineering and materials science?","Question",{"text":77,"@type":78},"NBP is a key thermophysical property that is widely used as a reference for understanding and predicting other substance behaviors. Accurate NBP prediction is especially important when experimental data are missing.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which feature selection and representation methods are evaluated for NBP prediction?",{"text":82,"@type":78},"The thesis evaluates functional group moieties, molecular descriptors, SMILES enumeration, and molecular graphs using graph neural networks (GNNs). These approaches determine how molecular information is converted into model inputs.",{"name":84,"@type":75,"acceptedAnswer":85},"What model approach performs best according to the thesis results?",{"text":86,"@type":78},"Using molecular graphs with GNNs delivers the strongest prediction performance, achieving an average error rate of about 2.5% on the tested compounds. The findings also indicate the approach can support improved predictions for solid and temperature-dependent thermophysical properties.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]