[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118460-en":3,"doc-seo-118460-105":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},118460,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Accelerating High-Throughput Phonon Calculations via Machine Learning Universal Potentials","Phonons are central to predicting material thermal, mechanical, electrical, and superconducting properties, yet conventional harmonic phonon calculations based on finite-displacement DFT are computationally expensive and limit high-throughput materials screening. The study develops a machine-learning universal potential using MACE, trained on 2,738 crystal structures spanning 77 elements with 15,670 DFT supercell structures. Validation on 384 held-out materials yields low errors and strong dynamical stability classification, with thermodynamic agreement across polymorphic systems.","arXiv :2407 .09674v1 [ cond-mat .mtrl-sci ] 12 Jul 2024  \nAccelerating High-Throughput Phonon Calculations via Machine Learning Universal  \nPotentials  \nHuiju Lee, 1 Vinay I. Hegde,2 Chris Wolverton,2 and Yi Xia 1, ∗  \n1 Department of Mechanical and Materials Engineering, Portland State University, Portland, OR 97201, USA  \n2 Department of Materials Science and Engineering, Northwestern University, Evanston, IL 60208, USA (Dated: July 16, 2024)  \nPhonons play a critical role in determining various material properties, but conventional methods for phonon calculations are computationally intensive, limiting their broad applicability. In this study, we present an approach to accelerate high-throughput harmonic phonon calculations using machine learning universal potentials. We train a state-of-the-art machine learning interatomic potential, based on multi-atomic cluster expansion (MACE), on a comprehensive dataset of 2,738 crystal structures with 77 elements, totaling 15,670 supercell structures, computed using high-fidelity density functional theory (DFT) calculations. Our approach significantly reduces the number of required supercells for phonon calculations while maintaining high accuracy in predicting harmonic phonon properties across diverse materials. The trained model is validated against phonon calculations for a held-out subset of 384 materials, achieving a mean absolute error (MAE) of 0.18 THz for vibrational frequencies from full phonon dispersions, 2.19 meV/atom for Helmholtz vibrational free energies at 300K, as well as a classification accuracy of 86 .2% for dynamical stability of materials. A thermodynamic analysis of polymorphic stability in 126 systems demonstrates good agreement with DFT results at 300 K and 1000 K. In addition, the diverse and extensive high-quality DFT dataset curated in this study serves as a valuable resource for researchers to train and improve other machine learning interatomic potential models.  \nI. INTRODUCTION  \nPhonons, as quasiparticles representing the collective vibrational modes of atoms within a crystalline material, are ubiquitous and play a crucial role in determining various material properties, including thermal conductivity, mechanical behavior, electrical conductivity, and superconductivity [1–3] . Additionally, they are vital in assessing dynamic and thermodynamic stability, as well as phase transitions of crystalline materials. This is particularly significant in materials discovery, where accurately predicting stability is essential for identifying new materials with desired properties [4–6] .  \nOne popular approach for first-principles phonon calculations is the finite-displacement method [7, 8] . In this approach, the equilibrium positions of atoms are perturbed by small displacements, and the resulting changes in energies and forces are calculated to determine the force constants that govern the vibrational modes. However, it is worth noting that this method requires calculations of numerous supercells using density functional theory (DFT) [9, 10] to capture short to long-range interactions and achieve converged results. Consequently, phonon calculations are computationally intensive, especially for large unit cells or complex materials with low symmetry, and the resulting high-quality dataset is available for only a small set of materials [11–13] . Despite the exponential growth of computing power over the decades, traditional methods remain limited in their applicability to a vast array of materials in a high-throughput screening.  \n∗ [yxia@pdx.edu](yxia@pdx.edu); [yimaverickxia@gmail.com](yimaverickxia@gmail.com)  \nIn recent years, machine learning approaches have emerged as a powerful tool for predicting phonon properties and accelerating materials discovery processes. These methods can be broadly categorized into two main strategies. The first strategy is directly predicting phonon properties using machine learning models trained on large datasets of phonon spect","cbCailBCL7wOHgKP","https://ap.wps.com/l/cbCailBCL7wOHgKP","pdf",12366330,1,26,"English","en",105,"# Introduction\n## Phonon role in material properties\n## Finite-displacement phonon calculations and their limitations\n## Machine learning strategies for phonon prediction","[{\"question\":\"Why are conventional phonon calculations computationally intensive for high-throughput screening?\",\"answer\":\"They require many DFT supercell calculations to capture short- to long-range interactions and achieve converged force constants, making them especially costly for large or low-symmetry unit cells.\"},{\"question\":\"How does the proposed method accelerate harmonic phonon calculations?\",\"answer\":\"It trains a machine-learning interatomic potential (MACE) on a large DFT dataset, reducing the number of supercells needed to compute harmonic phonon properties while maintaining accuracy.\"},{\"question\":\"How accurate and reliable is the trained model?\",\"answer\":\"On a held-out set of 384 materials, it achieves a mean absolute error of 0.18 THz for vibrational frequencies, 2.19 meV/atom for Helmholtz vibrational free energies at 300 K, and 86.2% accuracy for dynamical stability classification.\"}]","Accelerating High-Throughput Phonon Calculations via Machine Learning Universal Potentials | PDF",1785683724,66,{"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},"accelerating-high-throughput-phonon-calculations-via-machine-learning-universal-potentials","",{"@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/accelerating-high-throughput-phonon-calculations-via-machine-learning-universal-potentials/118460/",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","2026-08-02",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},"Why are conventional phonon calculations computationally intensive for high-throughput screening?","Question",{"text":76,"@type":77},"They require many DFT supercell calculations to capture short- to long-range interactions and achieve converged force constants, making them especially costly for large or low-symmetry unit cells.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method accelerate harmonic phonon calculations?",{"text":81,"@type":77},"It trains a machine-learning interatomic potential (MACE) on a large DFT dataset, reducing the number of supercells needed to compute harmonic phonon properties while maintaining accuracy.",{"name":83,"@type":74,"acceptedAnswer":84},"How accurate and reliable is the trained model?",{"text":85,"@type":77},"On a held-out set of 384 materials, it achieves a mean absolute error of 0.18 THz for vibrational frequencies, 2.19 meV/atom for Helmholtz vibrational free energies at 300 K, and 86.2% accuracy for dynamical stability classification.","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"]