[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123648-en":3,"doc-seo-123648-105":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},123648,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","A Data-Driven Machine Learning Approach for Electron-Molecule Ionization Cross Sections","Ionization cross sections are crucial for modeling in multiple applied physics domains, yet accurate estimation for large molecules remains difficult for both experiment and first-principles theory. A data-driven machine learning model is developed to predict ionization cross sections across a broad set of molecular targets, using a 3-layer neural network trained on published experimental datasets. The model requires minimal inputs and achieves prediction errors comparable to experimental uncertainties when trained on as few as 10 molecular datasets, improving further with more training. Predictions span diverse molecule classes including alkanes, alkenes, ring-structured systems, and DNA nucleotide bases.","A Data-Driven Machine Learning Approach for Electron-Molecule Ionization Cross Sections  \nA. L. Harris* and J. Nepomuceno  \nPhysics Department, Illinois State University, Normal, IL, USA 61790  \nAbstract  \nDespite their importance in a wide variety of applications, the estimation of ionization cross sections for large molecules continues to present challenges for both experiment and theory. Machine learning algorithms have been shown to be an effective mechanism for estimating cross section data for atomic targets and a select number of molecular targets. We present an efficient machine learning model for predicting ionization cross sections for a broad array of molecular targets. Our model is a 3-layer neural network that is trained using published experimental datasets. There is minimal input to the network, making it widely applicable. We show that with training on as few as 10 molecular datasets, the network is able to predict the experimental cross sections of additional molecules with an accuracy similar to experimental uncertainties in existing data. As the number of training molecular datasets increased, the network’s predictions became more accurate and, in the worst case, were within 30% of accepted experimental values. In many cases, predictions were within 10% of accepted values. Using a network trained on datasets for 25 different molecules, we present predictions for an additional 27 molecules, including alkanes, alkenes, molecules with ring structures, and DNA nucleotide bases.  \n1. Introduction  \nAtomic and molecular cross sections play a pivotal role in many areas of applied physics, including plasma physics, biophysics, and astrophysics. In these fields, cross sections are essential fundamental inputs for modeling complex problems. The success of models within these fields to understand fundamental physical processes relies, at least in part, on the accuracy and availability of the scattering cross sections. Often, cross sections are required over a wide range of energies, target species, and collision processes. Databases such as the NIST Electron Elastic-Scattering Cross-Section Database [1], LxCat [2], BEAMDB [3], and others [4] have begun to address the need for large amounts of cross section data by compiling available experimental and theoretical datasets into openly accessible repositories. There are also computational methods that have proven to be reliable in predicting cross sections in various energy regimes, and many of these are being made publicly available through resources such as the Atomic, Molecular, and Optical Science Gateway [5] . Despite the increasing availability of cross section databases, in many instances, the necessary data remains inaccessible experimentally or too computationally demanding for ab initio theory. It is therefore impractical to rely exclusively on experiment or computation to obtain all of the needed data.  \nMachine learning (ML) algorithms have proven to be effective tools in many areas of physics. These algorithms utilize data from existing experiment and/or simulation to train a model that is able to accurately predict the data for unknown systems. The use of ML algorithms in the physical sciences has exploded in recent years and is becoming commonplace in many areas of physics, such as high energy physics [6,7], quantum many body problems [8], quantum computing [9], molecular chemistry and material science [10], and countless others. However, these techniques have seen only limited use in atomic and molecular collision physics. Existing applications in collision physics can be sorted into two broad categories that predict atomic and  \nmolecular cross sections: (1) training a ML model using measured or calculated cross sections or (2) using a ML model to solve the inverse swarm problem and predict the cross sections.  \nIn the first category, one of the earliest applications of ML techniques for atomic and molecular cross sections was implemented by El-Bakry and ","cbCaiezrA2fL1dI0","https://ap.wps.com/l/cbCaiezrA2fL1dI0","pdf",931972,1,20,"English","en",105,"# Introduction\n## Cross-section databases and computational limits\n## Machine learning in physics and collision applications\n## Prior machine learning approaches for cross sections","[{\"question\":\"Why are electron-molecule ionization cross sections challenging for large molecules?\",\"answer\":\"Accurate estimation is difficult for both experiment and theory, and the required data can be inaccessible experimentally or computationally demanding for ab initio methods.\"},{\"question\":\"How is the proposed machine learning model constructed?\",\"answer\":\"The approach uses a 3-layer neural network trained on published experimental datasets, designed to require minimal inputs for broad applicability.\"},{\"question\":\"What accuracy is achieved and how does training set size affect it?\",\"answer\":\"Training on as few as 10 molecular datasets yields predictions with accuracy similar to experimental uncertainties. Increasing the number of training datasets improves performance, and in the worst case predictions are within 30% of accepted experimental values, with many within 10%.\"}]","A Data-Driven Machine Learning Approach for Electron-Molecule Ionization Cross Sections | PDF",1785817828,50,{"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},"a-data-driven-machine-learning-approach-for-electron-molecule-ionization-cross-sections","",{"@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/a-data-driven-machine-learning-approach-for-electron-molecule-ionization-cross-sections/123648/",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},"Why are electron-molecule ionization cross sections challenging for large molecules?","Question",{"text":75,"@type":76},"Accurate estimation is difficult for both experiment and theory, and the required data can be inaccessible experimentally or computationally demanding for ab initio methods.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the proposed machine learning model constructed?",{"text":80,"@type":76},"The approach uses a 3-layer neural network trained on published experimental datasets, designed to require minimal inputs for broad applicability.",{"name":82,"@type":73,"acceptedAnswer":83},"What accuracy is achieved and how does training set size affect it?",{"text":84,"@type":76},"Training on as few as 10 molecular datasets yields predictions with accuracy similar to experimental uncertainties. Increasing the number of training datasets improves performance, and in the worst case predictions are within 30% of accepted experimental values, with many within 10%.","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"]