[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119582-en":3,"doc-seo-119582-105":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},119582,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Propellant Discovery For Electrospray Thrusters Using Machine Learning","This study introduces a machine learning framework to predict whether ionic liquids with unknown physical properties can serve as propellants for electrospray thrusters, using molecular structure information. Ionic liquids are labeled as suitable (+1) or unsuitable (-1) based on density, viscosity, and surface tension, forming a supervised training dataset. Molecules are encoded with Mordred-derived molecular descriptors from their structure, and four algorithms are compared, with SVM achieving the best predictive performance. The trained SVM model identifies 193 candidate propellants from a set of unlabeled ionic liquids and uses SHAP to interpret and rank descriptor contributions to individual decisions.","Graphical Abstract  \nPropellant Discovery For Electrospray Thrusters Using Machine Learning  \nRafid Bendimerad, Elaine Petro  \narXiv :2408 . 169 51v2 [phys  \nHighlights  \nPropellant Discovery For Electrospray Thrusters Using Machine Learning  \nRafid Bendimerad, Elaine Petro  \n• This paper introduces a general machine learning framework designed to predict the suitability of ionic liquids with unknown physical properties for specialized applications in engineering.  \n• The utility of this framework is demonstrated for an application in aerospace engineering where ionic liquids with specific physical properties are required to serve as propellants for electrospray thrusters.  \n• This framework produces a classifier that predicts 193 candidate ionic liquids that could potentially be used as propellants for electrospray thrusters.  \nPropellant Discovery For Electrospray Thrusters Using  \nMachine Learning  \nRafid Bendimerada , Elaine Petroa  \na Cornell Sibley School of Mechanical and Aerospace Engineering, 124 Hoy  \nRd, Ithaca, 14850, NY, United States of America  \nAbstract  \nThis study introduces a machine learning framework to predict the suitability of ionic liquids with unknown physical properties as propellants for electrospray thrusters based on their molecular structure. We construct a training dataset by labeling ionic liquids as suitable (+1) or unsuitable (- 1) for electrospray thrusters based on their density, viscosity, and surface tension. The ionic liquids are represented by their molecular descriptors calculated using the Mordred package. We evaluate four machine learning algorithms—Logistic Regression, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost)—with SVM demonstrating superior predictive performance. The SVM predicts 193 candidate propellants from a dataset of ionic liquids with unknown physical properties. Further, we employ Shapley Additive Explanations (SHAP) to assess and rank the impact of individual molecular descriptors on model decisions.  \nKeywords: ionic liquids, new propellants, electrospray thrusters, molecular descriptors, supervised classification  \nPACS: 0000, 1111  \n2000 MSC: 0000, 1111  \n1. Introduction  \nIonic liquids are organic salts composed of cations and anions that exist in a liquid state at room temperatures [1] . Due to their distinctive physicochemical properties, such as low volatility, high thermal stability, and wide electrochemical windows, they garner significant attention in various scientific and industrial applications such as solvents, electrolytes, lubricants, cat  \nPreprint submitted to Elsevier September 17, 2024  \nalysts, drug delivery systems, absorption chillers, and many other applications [2, 3, 4, 5, 6, 7] . Despite their versatility, the applicability of ionic liquids is contingent upon the fulfillment of specific physicochemical criteria required by each application. Therefore, the precise selection of an ionic liquid tailored to meet the demands of a particular application is imperative for ensuring effective and efficient performance.  \nHowever, identifying all the suitable ionic liquid candidates for a specific application is not a simple task as hundreds of ionic liquids are already available commercially, with potentially millions more awaiting synthesis. Given the current advancements in organic synthesis, which present virtually no boundaries, a myriad of ionic liquids can be produced [8] . A comprehensive experimental study examining the effects of the chemical structure of ILs on their pertinent properties is not practically achievable. Therefore, it is essential to exploit the sparse experimental data that are available to extrapolate properties of ILs that have yet to be empirically characterized.  \nFormer studies have utilized the group contribution method (GCM) within a quantitative structure-property relationship (QSPR) framework for estimating density [8], viscosity [9], and surface tension [10] of ionic liquids. T","cbCaiuiFnZLmZ2W8","https://ap.wps.com/l/cbCaiuiFnZLmZ2W8","pdf",2839953,1,30,"English","en",105,"# Highlights\n## Machine learning framework and dataset construction\n## Model training and evaluation\n## Candidate propellant prediction and explainability","[{\"question\":\"How are ionic liquids labeled for training in the proposed framework?\",\"answer\":\"Ionic liquids are labeled as suitable (+1) or unsuitable (-1) for electrospray thrusters based on their density, viscosity, and surface tension.\"},{\"question\":\"Which molecular representation is used to build the model features?\",\"answer\":\"Ionic liquids are represented by molecular descriptors computed with the Mordred package from their molecular structure.\"},{\"question\":\"What method is used to interpret the model’s predictions?\",\"answer\":\"Shapley Additive Explanations (SHAP) is applied to assess and rank the impact of individual molecular descriptors on model decisions.\"}]","Propellant Discovery For Electrospray Thrusters Using Machine Learning | PDF",1785725109,76,{"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},"propellant-discovery-for-electrospray-thrusters-using-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/propellant-discovery-for-electrospray-thrusters-using-machine-learning/119582/",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","2026-08-03",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 are ionic liquids labeled for training in the proposed framework?","Question",{"text":75,"@type":76},"Ionic liquids are labeled as suitable (+1) or unsuitable (-1) for electrospray thrusters based on their density, viscosity, and surface tension.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which molecular representation is used to build the model features?",{"text":80,"@type":76},"Ionic liquids are represented by molecular descriptors computed with the Mordred package from their molecular structure.",{"name":82,"@type":73,"acceptedAnswer":83},"What method is used to interpret the model’s predictions?",{"text":84,"@type":76},"Shapley Additive Explanations (SHAP) is applied to assess and rank the impact of individual molecular descriptors on model decisions.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":21,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]