[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127385-en":3,"doc-seo-127385-105":30,"detail-sidebar-cat-0-en-105":92},{"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":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},127385,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning for Chemistry Reduction in N2-H2 Low-Temperature Plasmas - Paper","Low-temperature plasmas are partially ionized gases where ions and neutrals coexist, producing complex and highly reactive plasma chemistry that is difficult to interpret using conventional analysis. The work develops a machine learning model that learns reaction importance from initial and final species distributions, producing reaction weights that enable reduction of large chemical schemes. The method is applied to N2–H2 plasmas formed by electrical discharge at low pressure, targeting NH3 production, and reveals dominant chemical pathways across volume and surface reactions.","Machine Learning for Chemistry Reduction in N2–H2 Low-Temperature Plasmas  \narXiv :2409 .05914v2 [physics .plasm-ph] 12 Sep 2024  \nDiogo R. Ferreira 1 , Alexandre Lança 1 , and Luís Lemos Alves2  \n1 Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal  \n2 Instituto de Plasmas e Fusão Nuclear (IPFN), Instituto Superior Técnico,  \nUniversidade de Lisboa, 1049-001 Lisboa, Portugal [diogo.ferreira@tecnico.ulisboa.pt](diogo.ferreira@tecnico.ulisboa.pt)  \nAbstract. Low-temperature plasmas are partially ionized gases, where ions and neutrals coexist in a highly reactive environment. This creates a rich chemistry, which is often difficult to understand in its full complexity.  \nIn this work, we develop a machine learning model to identify the most important reactions in a given chemical scheme. The training data are an initial distribution of species and a final distribution of species, which can be obtained from either experiments or simulations. The model is trained to provide a set of reaction weights, which become the basis for reducing the chemical scheme. The approach is applied to N2–H2 plasmas, created by an electric discharge at low pressure, where the main goal is to produce NH3 . The interplay of multiple species, as well as of volume and surface reactions, make this chemistry especially challenging to understand. Reducing the chemical scheme via the proposed model helps identify the main chemical pathways.  \nKeywords: Plasma Physics · Plasma Chemistry · Machine Learning.  \n1 Introduction  \nThe production of ammonia (NH3 ) is critically important to a wide range of economic activities in the agricultural and industrial sectors. For example, ammonia is a key ingredient in the manufacturing of fertilizers, pharmaceuticals, plastics, textiles, and other chemicals. For more than a hundred years, the main industrial procedure for the production of ammonia has been the Haber-Bosch process [1] . However, this procedure requires temperatures in the range of 400 to 500 °C and pressures in the range of 150 to 300 atmospheres, which translate into considerable requirements in terms of energy consumption. These conditions are necessary in order to overcome the triple bond of nitrogen molecules (N 2 ), enabling them to react with hydrogen (H2 ), via N2 + 3 H2 → 2 NH3.  \nLow-temperature plasmas have emerged as a more energy efficient and environmentally friendly process for ammonia synthesis [2] . In this case, the process begins by exciting and ionizing a gas mixture of N2 and H2. Several ionization methods are available, but one of the simplest and most direct is to apply an electrical discharge [3] . This brings the gas mixture into a partially ionized state,  \n2 D. R. Ferreira, A. Lança, L. L. Alves  \ncontaining electrons, ions, radicals, and neutral particles. In this plasma state, the triple bonds of N2 and the covalent bonds of H2 can be broken more effectively than in thermal processes, leading to the formation of highly reactive nitrogen and hydrogen species. A vast and complicated series of reactions then unfolds, eventually producing NH3. One of the main goals of this work is to contribute to the understanding of this chain of reactions.  \nStudying the chemistry of ammonia production is important for additional reasons. Ammonia is known to be present in the atmosphere of the gas giants in our solar system, especially in Jupiter, Saturn, and Saturn’s moon Titan [4] . Ammonia has also been detected in interstellar space and in exoplanets [5] . The complex chemistry that takes place in a planetary atmosphere has prompted scientists to carry out laboratory experiments, including plasma discharges, to study the formation of organic molecules and even prebiotic molecules required for the origin of life [6] . Understanding the production of ammonia in those environments, through lab experiments and computer-based simulations, is an integral part of those endeavors. Using machine learning, our goal is to ident","cbCaiobQ7EYnKQtW","https://ap.wps.com/l/cbCaiobQ7EYnKQtW","pdf",525239,1,16,"English","en",105,"# Introduction\n# Chemistry of N2–H2 Plasmas\n# Petri net representation and matrix formulation\n# Machine learning model training\n# Training data and results\n# Main NH3 production pathways","[{\"question\":\"What problem does the machine learning model address in N2–H2 plasma chemistry?\",\"answer\":\"It identifies the most important reactions within a large chemical scheme, making the chemistry easier to interpret and reducing the scheme while preserving key pathways.\"},{\"question\":\"What inputs are used to train the model?\",\"answer\":\"Training relies on an initial distribution of species and a final distribution of species, obtainable from experiments or simulations.\"},{\"question\":\"How is the approach applied in this study?\",\"answer\":\"It is applied to low-pressure N2–H2 plasmas created by electrical discharge to improve understanding of NH3 production, including both volume and surface reactions.\"}]","Machine Learning for Chemistry Reduction in N2-H2 Low-Temperature Plasmas - Paper | PDF",1785938623,40,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-for-chemistry-reduction-in-n2-h2-low-temperature-plasmas-paper","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-for-chemistry-reduction-in-n2-h2-low-temperature-plasmas-paper/127385/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the machine learning model address in N2–H2 plasma chemistry?","Question",{"text":76,"@type":77},"It identifies the most important reactions within a large chemical scheme, making the chemistry easier to interpret and reducing the scheme while preserving key pathways.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What inputs are used to train the model?",{"text":81,"@type":77},"Training relies on an initial distribution of species and a final distribution of species, obtainable from experiments or simulations.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the approach applied in this study?",{"text":85,"@type":77},"It is applied to low-pressure N2–H2 plasmas created by electrical discharge to improve understanding of NH3 production, including both volume and surface reactions.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":29,"slug":119},7,"Healthcare","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":107,"slug":138},19,"General","general"]