[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123751-en":3,"doc-seo-123751-105":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},123751,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Integration of machine learning with neutron scattering for the Hamiltonian tuning of spin ice under pressure - Research scheme and experimental pipeline","Quantum materials research demands co-design between theory and experiments, requiring demanding simulations and large-scale data analysis with pattern recognition and clustering. A proposed framework integrates machine learning with high-performance simulations and neutron scattering measurements across a typical experimental pipeline. Nonlinear autoencoders are trained on realistic simulations, alongside a fast surrogate generative model for scattering calculations, enabling guided experiments under hydrostatic pressure. Demonstrated on Dy2Ti2O7, it extracts material parameters and builds a pressure-dependent phase diagram.","ARTICLE  \n [https://doi.org/10.1038/s43246-022-00306-7](https://doi.org/10.1038/s43246-022-00306-7)  OPEN  \nIntegration of machine learning with neutron scattering for the Hamiltonian tuning of spin ice under pressure  \nAnjana Samarakoon  1,2,3, D. Alan Tennant  1,2, Feng Ye  1, Qiang Zhang  1 & Santiago A. Grigera4✉  \nQuantum materials research requires co-design of theory with experiments and involves demanding simulations and the analysis of vast quantities of data, usually including pattern recognition and clustering. Artificial intelligence is a natural route to optimise these processes and bring theory and experiments together. Here, we propose a scheme that integrates machine learning with high-performance simulations and scattering measurements, covering the pipeline of typical neutron experiments. Our approach uses nonlinear autoencoders trained on realistic simulations along with a fast surrogate for the calculation of scattering in the form of a generative model. We demonstrate this approach in a highly frustrated magnet, Dy2Ti2O7, using machine learning predictions to guide the neutron scattering experiment under hydrostatic pressure, extract material parameters and construct a phase diagram. Our scheme provides a comprehensive set of capabilities that allows direct integration of theory along with automated data processing and provides on a rapid timescale direct insight into a challenging condensed matter system.  \n1 Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA. 2 Shull Wol lan Center-A Joint Institute for Neutron Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA. 3 Materials Science Division, Argonne National Laboratory, Argonne, IL, USA. 4 Instituto de Física de Líquidos y Sistemas Biológicos, UNLP-CONICET, La Plata 1900, Argentina. ✉ email: sgrigera@fi[sica.unlp.edu.ar](sica.unlp.edu.ar)  \nCOMMUNICATIONS MATERIALS| (2022)3:84 | [https://doi.org/10.1038/s43246-022-00306-7 |www.nature.com/commsmat](https://doi.org/10.1038/s43246-022-00306-7 |www.nature.com/commsmat) 1  \nA  \nrtificial Intelligence holds the promise of profound and far reaching impact on experimental science by integrating theory and experiment in new ways 1. Neutron scattering  \non quantum materials is an area where much progress can be expected 1–3 which would impact co-design of theory and experiment as well as materials discovery and optimization. To achieve this requires the integration of simulations, data treatment and analysis, and theoretical interpretation3. Data science, and in particular machine learning (ML), have been proposed as ways to integrate scattering experiments with demanding stateof-the art simulations2,4, however effective schemes to do this remain to be demonstrated. Here, we deploy ML across the experimental pipeline, closely integrating theory and experiment in a way that could be used more widely for materials research. We apply it to a highly frustrated magnet that provides challenges representative of current state-of-the-art materials.  \nTraditionally, experiment planning, data treatment, and analysis have taken major efforts involving months of detailed work2,3,5. They have relied on often crude analytic approximations due to the difficulty in matching time consuming and highly specialized simulations with experiment. Recently we have shown that machine learning, and in particular the application of NonLinear Autoencoders (NLAEs) can be used to create automated capabilities for Hamiltonian extraction from diffuse neutron scattering data4,5. Further, this approach was demonstrated to provide robust parameter optimization, automated denoising and data treatment, as well as phase diagram mapping and categorization.  \nHere we show how a complete integration could be achieved and present a scheme that integrates the experiments with theory and modelling on the experiment timescales. The approach in ref. 4 is augmented with generative models to provide fast surrogates f","cbCaikqJpMHUjdjw","https://ap.wps.com/l/cbCaikqJpMHUjdjw","pdf",2101386,1,11,"English","en",105,"# Introduction\n## ML for co-design in neutron scattering\n## Motivation and prior automated Hamiltonian extraction\n# Results\n## Neutron scattering experimental pipeline\n## Machine-learning framework with surrogate generative models","[{\"question\":\"What is the core idea of integrating machine learning with neutron scattering in this work?\",\"answer\":\"The approach combines nonlinear autoencoders trained on realistic simulations with a fast surrogate generative model for scattering calculations, enabling integration of theory and experiment across the neutron-scattering pipeline.\"},{\"question\":\"How does the method help during neutron scattering experiments under pressure?\",\"answer\":\"Machine-learning predictions guide the neutron-scattering experiment under hydrostatic pressure, allowing rapid feedback and enabling extraction of material parameters.\"},{\"question\":\"Which material is used to demonstrate the scheme and what outcomes are shown?\",\"answer\":\"The demonstration targets the highly frustrated magnet Dy2Ti2O7, where the method yields material parameters and constructs a pressure-dependent phase diagram using integrated automated data processing.\"}]","Integration of machine learning with neutron scattering for the Hamiltonian tuning of spin ice under pressure - Research scheme and experimental pipeline | PDF",1785818329,28,{"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},"integration-of-machine-learning-with-neutron-scattering-for-the-hamiltonian-tuning-of-spin-ice-under-pressure-research-scheme-and-experimental-pipeline","",{"@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/integration-of-machine-learning-with-neutron-scattering-for-the-hamiltonian-tuning-of-spin-ice-under-pressure-research-scheme-and-experimental-pipeline/123751/",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},"What is the core idea of integrating machine learning with neutron scattering in this work?","Question",{"text":75,"@type":76},"The approach combines nonlinear autoencoders trained on realistic simulations with a fast surrogate generative model for scattering calculations, enabling integration of theory and experiment across the neutron-scattering pipeline.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the method help during neutron scattering experiments under pressure?",{"text":80,"@type":76},"Machine-learning predictions guide the neutron-scattering experiment under hydrostatic pressure, allowing rapid feedback and enabling extraction of material parameters.",{"name":82,"@type":73,"acceptedAnswer":83},"Which material is used to demonstrate the scheme and what outcomes are shown?",{"text":84,"@type":76},"The demonstration targets the highly frustrated magnet Dy2Ti2O7, where the method yields material parameters and constructs a pressure-dependent phase diagram using integrated automated data processing.","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"]