[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122562-en":3,"doc-seo-122562-105":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},122562,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Accelerating Zero-Carbon Fuel Combustion Modelling with Machine Learning - Doctoral Thesis","This thesis tackles computational difficulties in simulating reacting flows of low- and zero-carbon fuels by developing machine learning models that predict essential combustion properties. It targets laminar burning velocity (LBV) prediction and chemical source term integration, building ML models for NH3/H2/air and NH3/H2/CH4/air mixtures across diverse conditions. Reported results show up to 27,000x acceleration (R2>0.99) while preserving accuracy. The work addresses limited data for novel blends and extreme regimes using systematic data analysis, preprocessing, and validated chemical-kinetic mechanisms to generate synthetic data. It introduces the first systematic ML framework for LBV of ternary NH3/H2/CH4/air via ensemble learning. Two probabilistic integration frameworks are proposed: a Gaussian Process method validated on H2/air autoignition (up to 2.1x speed-up) and a scalable Deep Ensemble validated on H2/air and NH3/H2/air autoignition (up to 9.4x speed-up), both enabling uncertainty quantification. Physics-informed loss functions and data-generation strategy design support reliability across mechanisms and operating conditions.","Accelerating Zero-Carbon Fuel Combustion Modelling with Machine Learning  \nCihat Emre st¨un  \nSubmitted in partial fulfillment of the requirements of the Degree of Doctor of Philosophy  \nSchool of Engineering and Material Science  \nQueen Mary University of London  \nJanuary 2025  \nStatement of originality  \nI, Cihat Emre st¨un, confirm that the research included within this thesis is my own work or that where it has been carried out in collaboration with, or supported by others, that this is duly acknowledged below and my contribution indicated. Previously published material is also acknowledged below.  \nI attest that I have exercised reasonable care to ensure that the work is original, and does not to the best of my knowledge break any UK law, infringe any third party’s copyright or other Intellectual Property Right, or contain any confidential material.  \nI accept that the College has the right to use plagiarism detection software to check the electronic version of the thesis.  \nI confirm that this thesis has not been previously submitted for the award of a degree by this or any other university.  \nThe copyright of this thesis rests with the author and no quotation from it or information derived from it may be published without the prior written consent of the author.  \nSignature: Cihat Emre st¨un  \nDate: 13.01.2025  \nAbstract  \nThis thesis addresses computational challenges in simulating the reacting flows of low- and zero-carbon fuels, focusing on developing machine learning (ML) models to predict key combustion properties. The work aims to accelerate two critical aspects: laminar burning velocity (LBV) prediction and chemical source term integration. Machine learning models were developed for NH3 /H2 /air and NH3 /H2 /CH4 /air mixtures across various conditions, achieving remarkable computational efficiency (up to 27,000x speedup) while maintaining high accuracy (coefficient of determination: R2 > 0.99) . Through systematic data analysis and preprocessing, the research combines experimental data with synthetic data generation through validated chemical kinetic mechanisms to address limited data availability for novel fuel blends and extreme operating conditions while creating fast and accurate predictive tools. The work also presents the first systematic ML framework for the LBV prediction of ternary NH3 /H2 /CH4 /air mixtures, addressing multi-component complexity through ensemble learning. For chemical source term integration, two probabilistic frameworks are introduced: a Gaussian Process-based approach validated on H2 /air autoignition, achieving up to 2.1x speed-up compared to direct integration while demonstrating the feasibility of uncertainty-aware predictions, and a scalable Deep Ensemble framework validated on both H2 /air and NH3 /H2 /air autoignition problems, achieving up to 9.4x speed-up while providing crucial uncertainty quantification. These frameworks maintain calibrated uncertainty estimates  \nduring recursive predictions and enable dynamic switching between MLand traditional solvers based on confidence levels. The implementation of physics-informed loss functions and careful consideration of data generation strategies ensured the frameworks’ reliability across different chemical mechanisms and operating conditions. Key insights include the effectiveness of physics-informed approaches through loss functions and data-generation strategies, the importance of ensemble learning for complex multi-component systems, and the crucial role of uncertainty quantification in ensuring reliable combustion simulations. The methodologies developed contribute to enabling efficient, high-fidelity simulations of novel combustion systems and supporting the transition to sustainable energy systems.  \nANNEM, BABAM ve LAYDA’YA...  \nAcknowledgements  \nFirst and foremost, I would like to thank my supervisor, Dr. Amin Paykani, for believing in me in the first place and making this journey easier throughout.  \nI am deeply grateful","cbCaieTjhbeuf68E","https://ap.wps.com/l/cbCaieTjhbeuf68E","pdf",26125012,1,219,"English","en",105,"# Abstract\n## Laminar burning velocity (LBV) prediction\n## Chemical source term integration\n## Data generation, uncertainty quantification, and reliability","[{\"question\":\"What combustion problems does the thesis address?\",\"answer\":\"The thesis addresses computational challenges in simulating reacting flows for low- and zero-carbon fuels, focusing on predicting laminar burning velocity and integrating chemical source terms.\"},{\"question\":\"How are the machine learning models validated and what performance is reported?\",\"answer\":\"ML models are developed for NH3/H2/air and NH3/H2/CH4/air mixtures across various conditions, showing major computational efficiency gains (up to 27,000x speedup) with high accuracy (R2 \\u003e 0.99).\"},{\"question\":\"What methods are proposed for chemical source term integration and how is uncertainty handled?\",\"answer\":\"Two probabilistic frameworks are introduced: a Gaussian Process-based approach and a Deep Ensemble framework. Both are designed to provide uncertainty quantification with calibrated uncertainty estimates during recursive predictions.\"}]","Accelerating Zero-Carbon Fuel Combustion Modelling with Machine Learning - Doctoral Thesis | PDF",1785811322,552,{"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},"accelerating-zero-carbon-fuel-combustion-modelling-with-machine-learning-doctoral-thesis","",{"@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/accelerating-zero-carbon-fuel-combustion-modelling-with-machine-learning-doctoral-thesis/122562/",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","2026-08-04",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 combustion problems does the thesis address?","Question",{"text":75,"@type":76},"The thesis addresses computational challenges in simulating reacting flows for low- and zero-carbon fuels, focusing on predicting laminar burning velocity and integrating chemical source terms.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the machine learning models validated and what performance is reported?",{"text":80,"@type":76},"ML models are developed for NH3/H2/air and NH3/H2/CH4/air mixtures across various conditions, showing major computational efficiency gains (up to 27,000x speedup) with high accuracy (R2 > 0.99).",{"name":82,"@type":73,"acceptedAnswer":83},"What methods are proposed for chemical source term integration and how is uncertainty handled?",{"text":84,"@type":76},"Two probabilistic frameworks are introduced: a Gaussian Process-based approach and a Deep Ensemble framework. Both are designed to provide uncertainty quantification with calibrated uncertainty estimates during recursive predictions.","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"]