[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123410-en":3,"doc-seo-123410-105":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},123410,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Hybrid Pathways for Methane Production - Merging Thermodynamic Insights with Machine Learning","A comprehensive thermodynamic and data-driven framework was developed to optimize CH4 production via CO and CO2 methanation using blast furnace gas and basic oxygen furnace gas. Gibbs free energy equilibrium modeling located optimal conditions at moderate temperatures (150–250 °C) and higher pressures, yielding over 98% CO2 conversion with under 1 wt% carbon formation. Parallel machine learning models trained on 2777 experimental observations used atomic-level descriptors for catalyst, promoters, and supports, achieving R2 > 0.93. SHAP and partial dependence linked stability and textural properties to performance, enabling catalyst and operating-limit guidance for high-efficiency industrial methanation.","Journal of Cleaner Production 526 (2025) 146662  \nContents lists available at ScienceDirect Journal of Cleaner Production  \njournal [homepage: www.elsevier.com/locate/jclepro](homepage: www.elsevier.com/locate/jclepro)  \n| Hybrid pathways for methane production: Merging thermodynamic insights with machine learning\u003Cbr>Azita Etminana,* , Peter J. Hollimana, Peyman Karimib , Majid Majdb, Ian Mabbetta ,\u003Cbr>Mary Larimia, Ciaran Martin c , Anna RL. Carter d \u003Cbr>a Swansea University, Faculty of Science and Engineering, Bay Campus, Swansea, SA1 8EN, UK\u003Cbr>b Arak University, Faculty of Engineering, Department of Mechanical Engineering, Arak, 38156-88349, Iran c Tata Steel UK, Port Talbot, UK\u003Cbr>d School of Computer and Information Sciences, Northumbria University, Newcastle Upon Tyne, UK |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Thermodynamic analysis Catalyst selection Machine learning\u003Cbr>CO2 Methanation\u003Cbr>Energy and Exergy Analysis |  | A comprehensive study was conducted to simultaneously simulate thermodynamic behavior and predict catalyst performance for CH4 production via CO and CO2 methanation, using blast furnace gas (BFG) and basic oxygen furnace gas (BOFG) as feedstocks. Thermodynamic equilibrium simulations based on Gibbs free energy minimization identified optimal reaction conditions at moderate temperatures (150–250 ◦ C) and elevated pressures, achieving over 98 % CO2 conversion with less than 1 wt% carbon formation. In parallel, machine learning models were developed using an augmented dataset of 2777 experimental observations. Atomic-level structural and electronic descriptors were incorporated into the dataset, including unit cell density and formation energy for active metals, promoters, and supports. Feature selection through Pearson correlation and RFECV identified active phase weight, support density, and reduction conditions as the most influential variables. Among all tested algorithms, XGBoost and CatBoost demonstrated the highest accuracy, with R2 values exceeding 0.93 for predicting CH4 yield, selectivity, and CO2 conversion. SHAP and partial dependence analyses showed that catalyst stability and textural properties govern overall performance. This integrated thermodynamic and machine learning approach defines the operating limits for high-efficiency methanation and provides a data-driven framework for catalyst optimization in industrial applications. |\n\nNomenclature  \nSymbols and Terms  \nΔ rG0 (T)  \nΔ rH0 (T)  \nΔ rS0 (T)  \nCp,m  \nR  \nη Total,En, H,Reactant  \nH,Product Qheat  \nStandard Gibbs free energy change of reaction at temperature T (kJ/mol) Standard enthalpy change of reaction at temperature T (kJ/mol)  \nStandard entropy changes of reaction at temperature T (kJ/mol⋅K)  \nMolar heat capacity at constant pressure (kJ/mol⋅K)  \nUniversal gas constant (8.314 J/mol⋅K) Overall energy efficiency (%)  \nTotal enthalpy of the reactants (kJ) Total enthalpy of the products (kJ) Net heat released by the methanation reaction (MJ)  \n(continued on next column)  \n(continued )  \nEn,out  \nEn,in  \nLHV,CH4  \nLHV,H2  \nni ղ, Total, Ex Ex, out  \nEx, in Ex Ch  \nEx, Ph  \nTotal useful energy output from the system (MJ/h)  \nTotal energy input supplied to the system (MJ/h)  \nLower heating value of methane (MJ/ Kmol)  \nLower heating value of hydrogen (MJ/ Kmol)  \nMolar flow rate of species i (Kmol/h) Total exergy efficiency (%)  \nExergy recovered from the process (MJ/h) Exergy supplied to the process(MJ/h) Standard chemical exergy of pure substances (MJ/Kmol)  \nStandard physical exergy of pure substances (MJ/Kmol)  \n(continued on next page)  \n* Corresponding author.  \nE-mail address: [2157090@swansea.ac.uk](2157090@swansea.ac.uk) (A. Etminan).  \n[https://doi.org/10.1016/j.jclepro.2025.146662](https://doi.org/10.1016/j.jclepro.2025.146662)  \nReceived 19 April 2025; Received in revised form 4 September 2025; Accepted 13 September 2025 Available online 17 September 2025  \n0959-6526/© 2025 T","cbCaipqMbcEmoIgW","https://ap.wps.com/l/cbCaipqMbcEmoIgW","pdf",18367363,1,20,"English","en",105,"# Introduction\n# Nomenclature\n## Symbols and Terms","[{\"question\":\"How were optimal methanation reaction conditions determined for CO and CO2 pathways?\",\"answer\":\"Equilibrium thermodynamic simulations based on Gibbs free energy minimization were used to identify conditions at moderate temperatures (150–250 °C) and elevated pressures.\"},{\"question\":\"What approach was used to predict methane yield, selectivity, and CO2 conversion?\",\"answer\":\"Machine learning models were trained on an augmented dataset of 2777 experimental observations using atomic-level structural and electronic descriptors and feature selection methods.\"},{\"question\":\"Which machine learning algorithms performed best and how were key drivers interpreted?\",\"answer\":\"XGBoost and CatBoost achieved the highest accuracy with R2 values exceeding 0.93. SHAP and partial dependence analyses indicated that catalyst stability and textural properties govern overall performance.\"}]","Hybrid Pathways for Methane Production - Merging Thermodynamic Insights with Machine Learning | PDF",1785816330,50,{"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},"hybrid-pathways-for-methane-production-merging-thermodynamic-insights-with-machine-learning","",{"@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/hybrid-pathways-for-methane-production-merging-thermodynamic-insights-with-machine-learning/123410/",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},"How were optimal methanation reaction conditions determined for CO and CO2 pathways?","Question",{"text":75,"@type":76},"Equilibrium thermodynamic simulations based on Gibbs free energy minimization were used to identify conditions at moderate temperatures (150–250 °C) and elevated pressures.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What approach was used to predict methane yield, selectivity, and CO2 conversion?",{"text":80,"@type":76},"Machine learning models were trained on an augmented dataset of 2777 experimental observations using atomic-level structural and electronic descriptors and feature selection methods.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning algorithms performed best and how were key drivers interpreted?",{"text":84,"@type":76},"XGBoost and CatBoost achieved the highest accuracy with R2 values exceeding 0.93. SHAP and partial dependence analyses indicated that catalyst stability and textural properties govern overall performance.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]