[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119741-en":3,"doc-seo-119741-105":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},119741,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Machine Learning Models Capture Plasmon Dynamics in Ag Nanoparticles - Abstract and Introduction Summary","Highly energetic electron-hole pairs generated by plasmon decay in metallic nanostructures could enable energy-harvesting devices, yet efficient hot-carrier collection before thermalization remains a major barrier. Achieving the required mechanistic understanding demands detailed atomistic modeling from plasmon excitation through collection at metal-molecule or metal-semiconductor interfaces, but first-principles simulations are prohibitively expensive. A modified HIP-NN model predicts plasmon dynamics in Ag nanoparticles using rt-TDDFT charge history, extending accurate trajectories to larger sizes and providing up to ~200–4000× speedups.","arXiv :2303 .04318v1 [ cond-mat .mes-hall ] 8 Mar 2023  \nMachine Learning Models Capture Plasmon Dynamics in Ag Nanoparticles  \nAdela Habib,􀀃 , y Nicholas Lubbers,z Sergei Tretiak,y ,{ and Benjamin Nebgen􀀃 , y  \ny Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USA zComputer, Computational and Statistical Sciences (CCS) Division, Los Alamos National  \nLaboratory, Los Alamos, NM 87545, USA  \n{Center for Integrated Nanotechnologies Los Alamos National Laboratory, Los Alamos,  \nNM 87545, USA  \nE-mail: [ahabib@lanl.gov](ahabib@lanl.gov) ; [bnebgen@lanl.gov](bnebgen@lanl.gov)  \nAbstract  \nHighly energetic electron-hole pairs (hot carriers) formed from plasmon decay in metallic nanostructures promise sustainable pathways for energy-harvesting devices. However, e􀀎 -cient collection before thermalization remains an obstacle for realization of their full energy generating potential. Addressing this challenge requires detailed understanding of physical processes from plasmon excitation in metal to their collection in a molecule or a semiconductor, where atomistic theoretical investigation may be particularly bene􀀌cial. Unfortunately,􀀌rst-principles theoretical modeling of these processes is extremely costly, preventing a detailed analysis over a large number of potential nanostructures and limiting the analysis to systems with a few 100s of atoms. Recent advances in machine learned interatomic potentials suggest that dynamics can be accelerated with surrogate models which replace the full solution of the Schr􀁿odinger Equation. Here, we modify an existing neural network, Hierarchically Interacting Particle Neural Network (HIP-NN), to predict plasmon dynamics in Ag nanoparticles. The model takes as minimum as three time-steps of the reference real-time time-dependent density functional theory (rt-TDDFT) calculated charges as history and predicts trajectories for 5 femtoseconds in great agreement with the reference simulation. Further, we show that a multi-step training approach in which the loss function includes errors from future time-step predictions, can stabilize the model predictions for the entire simulated trajectory ( 􀀘 25 fs) . This extends the model's capability to accurately predict plasmon dynamics in large nanoparticles of up to 561 atoms, not present in training dataset. More importantly, with machine learning models we gain a speed-up of 􀀘 200 times as compared with the rt-TDDFT calculations when predicting important physical quantities such as dynamic dipole moments in Ag55 and 􀀘 4000 times for extended nanoparticles that are 10 times larger. This underscores the promise of future machine learning accelerated electron/nuclear dynamics simulations for understanding fundamental properties of plasmon-driven hot carrier devices.  \nIntroduction  \nPlasmons are collective oscillations of free electrons in metal nanostructures. Their decay enables formation of highly energetic electrons and holes known as hot carriers. These plas-  \nmonic hot carriers promise useful applications in photodetection, 1 photovoltaics, 2 and photocatalysis. 3,4 However, experimental measurements have shown low photon to carrier conversion e􀀎ciencies in these devices. 5,6 Understanding the root cause of this low rate of carrier col-  \nlection requires scrutinizing various quantummechanical (QM) processes including the excitation of plasmons, plasmonic decay into generating hot carriers, the transport of hot carriers in the metal, and 􀀌nally their collection across the metal-semiconductor or metalmolecule interface. Many factors including geometry, electronic band structure of the system, energy and momentum matching at the interface contribute to these processes. However, studying these processes only by experimental means is limited due to a variety of challenges such as interpretation of experimental data and time/spatial resolution of speci􀀌c experiments. 7,8  \nTheoretical studies of hot carriers have also proven extremel","cbCaijKUmNtsM5jm","https://ap.wps.com/l/cbCaijKUmNtsM5jm","pdf",1244636,1,18,"English","en",105,"# Abstract\n# Introduction\n## Motivation: low carrier-collection efficiency\n## Limits of experimental characterization\n## Challenges of first-principles theory for hot carriers\n## Prior theoretical approaches: jellium and DFT-based methods\n## Geometry-aware simulations: rt-TDDFT and NAMD","[{\"question\":\"What problem does the work address regarding plasmon-driven hot carriers?\",\"answer\":\"The work addresses the difficulty of efficiently collecting hot carriers formed by plasmon decay before they thermalize, limiting energy-harvesting performance.\"},{\"question\":\"Why are first-principles simulations difficult for analyzing plasmon decay and hot-carrier collection?\",\"answer\":\"First-principles (from first principles) modeling is extremely computationally costly, restricting analysis to only small systems and preventing broad exploration of candidate nanostructures.\"},{\"question\":\"How does the proposed machine learning model accelerate plasmon dynamics simulations?\",\"answer\":\"It modifies HIP-NN to predict plasmon trajectories from a minimal history of rt-TDDFT-calculated charges, enabling accurate predictions for longer trajectories and larger nanoparticles while achieving large speedups versus rt-TDDFT.\"}]","Machine Learning Models Capture Plasmon Dynamics in Ag Nanoparticles - Abstract and Introduction Summary | PDF",1785726043,45,{"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},"machine-learning-models-capture-plasmon-dynamics-in-ag-nanoparticles-abstract-and-introduction-summary","",{"@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/machine-learning-models-capture-plasmon-dynamics-in-ag-nanoparticles-abstract-and-introduction-summary/119741/",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},"What problem does the work address regarding plasmon-driven hot carriers?","Question",{"text":75,"@type":76},"The work addresses the difficulty of efficiently collecting hot carriers formed by plasmon decay before they thermalize, limiting energy-harvesting performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why are first-principles simulations difficult for analyzing plasmon decay and hot-carrier collection?",{"text":80,"@type":76},"First-principles (from first principles) modeling is extremely computationally costly, restricting analysis to only small systems and preventing broad exploration of candidate nanostructures.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed machine learning model accelerate plasmon dynamics simulations?",{"text":84,"@type":76},"It modifies HIP-NN to predict plasmon trajectories from a minimal history of rt-TDDFT-calculated charges, enabling accurate predictions for longer trajectories and larger nanoparticles while achieving large speedups versus rt-TDDFT.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":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":106,"slug":138},19,"General","general"]