[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123872-en":3,"doc-seo-123872-105":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},123872,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Prediction of Fishbone Linear Instability in Tokamaks with Machine Learning Methods","A machine learning based surrogate model for fishbone linear instability in tokamaks is constructed using hybrid kinetic-magnetohydrodynamic simulations with the code M3D-K to build a training database. The study scans four physically motivated input parameters controlling fishbone dynamics: central total beta of thermal plasma and fast ions, fast ion pressure fraction, central safety factor value, and the location of the q=1 surface. Linear regression, SVM (linear and nonlinear kernels), and a multi-layer perceptron are used to predict instability, growth rate, real frequency, and mode structure. The nonlinear-kernel SVM achieves about 95% accuracy for instability and about 98% for growth rate, real frequency, and mode structure.","Prediction of Fishbone Linear Instability in Tokamaks with  \nMachine Learning Methods  \nZ.Y. Liu 1, H.R. Qiu 2, G.Y. Fu 2*, Y. Xiao 2, Y.C. Chen 1, Z.J. Wang 1, Y.X. Wei 1†  \n1 Zhejiang Lab, Hangzhou, Zhejiang 311121, People's Republic of China  \n2 Institute for Fusion Theory and Simulation and School of Physics, Zhejiang University,  \nHangzhou, Zhejiang 310027, People's Republic of China  \n* Email address for correspondence: [gyfu@zju.edu.cn](gyfu@zju.edu.cn)  \n† Email address [for correspondence: yx_wei@zhejianglab.com](for correspondence: yx_wei@zhejianglab.com)  \nAbstract  \nA machine learning based surrogate model for fishbone linear instability in tokamaks is constructed. Hybrid simulations with the kinetic-magnetohydrodynamic (MHD) code M3D-K is used to generate the database of fishbone linear instability, through scanning the four key parameters which are thought to determine the fishbone physics. The four key parameters include (1) central total beta of both thermal plasma and fast ions, (2) the fast ion pressure fraction,(3) central value of safety factor 􀝍 and (4) the radius of 􀝍 = 1 surface. Four machine learning methods including linear regression, support vector machines (SVM) with linear kernel, SVM with nonlinear kernel and multi-layer perceptron are used to predict the fishbone instability, growth rate and real frequency, mode structure respectively. Among the four methods, SVM with nonlinear kernel performs very well to predict the linear instability with accuracy ≈ 95%, growth rate and real frequency with 􀜴 2 ≈ 98%, mode structure with 􀜴 2 ≈ 98% .  \n1. Introduction  \nEnergetic particles (EPs) can drive the MHD instabilities via wave-particle resonances intokamaks, these instabilities evolve, then saturate and ultimately lead to EP transport, which is crucial to the performance of burning fusion plasmas [1] . The first observation of EP-driven mode is the fishbone instability in the Poloidal Divertor eXperiment (PDX) [2] . This experimental observation has drawn a lot of attention in the fusion community, because the fishbone instability  \ncan induce dramatic global EP transport [3] . The linear instability of fishbone was successfully explained by the resonant interaction between the 􀝊 = 􀝉 = 1 internal kink mode and the precession and/or transit frequencies of EPs [4-7], where 􀝊/􀝉 represents the toroidal/poloidal number respectively. A number of self-consistent hybrid kinetic-MHD simulations were performed to study the linear and nonlinear physics of fishbone driven by neutral beam injection (NBI) [8-15], alpha particles [16], and energetic electrons [17] . Recently, the formations of internal transport barrier (ITB) accompanied with fishbone activity were studied in experiments [18-21] and simulations [22,23], regarding the shear flow generation through the nonlinear dynamics of fishbone [24,25] .  \nNowadays, machine learning methods show great potential to solve many scientific and engineering problems, with much better performance and efficiency comparing with traditional approaches. This trend is even more obvious as the computing power and capacity of modern computer clusters raise rapidly, especially for the Graphic Process Unit (GPU) development. Various machine learning algorithms have been applied in magnetic confinement fusion research, including the fast equilibrium solution [26-29], safety factor reconstruction [30,31], pedestal density prediction [32,33], plasma control [34-37] and disruption prediction [38-43] . It is also novel to use these new methods to identify and classify MHD instabilities and transport events in experiments [44-52], and to construct surrogate models for the first-principle simulations and transport calculations [53-58] . The machine learning methods can even solve the physical problems with the ability to merge the physical equations into the target loss functions, which are known as physics-informed neural networks (PINNs) [27, 59-63] .  \nThis work is aimed at constructi","cbCaisHtISncIeYU","https://ap.wps.com/l/cbCaisHtISncIeYU","pdf",2179065,1,28,"English","en",105,"# Abstract\n# 1. Introduction\n## Energetic particles and fishbone physics\n## Motivation for machine learning in fusion\n## Objective and reduced parameter setting\n# 2. Method overview (based on available text)","[{\"question\":\"What surrogate model is proposed for fishbone linear instability in tokamaks?\",\"answer\":\"A machine learning based surrogate model is built to predict fishbone linear instability. It is trained using a database generated by hybrid kinetic-MHD simulations with M3D-K.\"},{\"question\":\"Which four parameters are scanned to generate the fishbone instability database?\",\"answer\":\"The inputs are (1) central total beta of thermal plasma and fast ions, (2) fast ion pressure fraction, (3) central safety factor value, and (4) the position of the q=1 surface.\"},{\"question\":\"How well does the best machine learning method perform?\",\"answer\":\"SVM with a nonlinear kernel performs best, with about 95% accuracy for predicting linear instability. It reaches about 98% accuracy for growth rate, real frequency, and mode structure.\"}]","Prediction of Fishbone Linear Instability in Tokamaks with Machine Learning Methods | PDF",1785819001,71,{"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},"prediction-of-fishbone-linear-instability-in-tokamaks-with-machine-learning-methods","",{"@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/prediction-of-fishbone-linear-instability-in-tokamaks-with-machine-learning-methods/123872/",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","2026-08-05","2026-08-04",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 surrogate model is proposed for fishbone linear instability in tokamaks?","Question",{"text":76,"@type":77},"A machine learning based surrogate model is built to predict fishbone linear instability. It is trained using a database generated by hybrid kinetic-MHD simulations with M3D-K.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which four parameters are scanned to generate the fishbone instability database?",{"text":81,"@type":77},"The inputs are (1) central total beta of thermal plasma and fast ions, (2) fast ion pressure fraction, (3) central safety factor value, and (4) the position of the q=1 surface.",{"name":83,"@type":74,"acceptedAnswer":84},"How well does the best machine learning method perform?",{"text":85,"@type":77},"SVM with a nonlinear kernel performs best, with about 95% accuracy for predicting linear instability. It reaches about 98% accuracy for growth rate, real frequency, and mode structure.","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},[94,98,102,106,111,116,121,124,129,132,136],{"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":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]