{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:42:39Z","timestamp":1773139359248,"version":"3.50.1"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007431","name":"NRF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007431","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"publisher","award":["RS-2025-23524569"],"award-info":[{"award-number":["RS-2025-23524569"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Supervised super-resolution methods estimate high-resolution simulation results from low-resolution inputs. These methods typically train the neural networks using pairs of high-resolution data and their downsampled low-resolution counterparts, implicitly assuming the global similarity between the low- and high-resolution models. This assumption, however, often fails as the low-resolution models usually exhibit stiffer behaviour than high-resolution models due to numerical stiffening. This paper proposes a novel supervised super-resolution method to mitigate this problem for linear deformable object simulation. The method constructs training data pairs by matching low- and high-resolution simulation snapshots based on the similarity of the normalized strain energy, the normalized temporal change rate of strain energy, and the modal contributions to the overall strain energy. The loss function also incorporates the equation residuals derived from the finite-element method. The time-integration scheme is selected by examining the eigenvalue distributions of the neural tangent kernel associated with the finite-element residuals. Compared with previous downsampling methods, the proposed method reduces the maximum relative displacement error by 25%, 54%, and 38% for the beam, elephant, and armadillo models, respectively.<\/jats:p>","DOI":"10.1093\/jcde\/qwag015","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T12:24:10Z","timestamp":1771849450000},"page":"69-83","source":"Crossref","is-referenced-by-count":0,"title":["Strain-energy-based training of super-resolution for deformation simulation"],"prefix":"10.1093","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5664-4685","authenticated-orcid":false,"given":"Qiaodi","family":"Yuan","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology Department of Mechanical Engineering, , Yuseong-gu, Daejeon 34141 ,","place":["Republic of Korea"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4769-1331","authenticated-orcid":false,"given":"Doo Yong","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology Department of Mechanical Engineering, , Yuseong-gu, Daejeon 34141 ,","place":["Republic of Korea"]}]}],"member":"286","published-online":{"date-parts":[[2026,2,24]]},"reference":[{"key":"2026030916152416300_bib1","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1109\/AI4S56813.2022.00008","article-title":"PhySRNet: Physics informed super-resolution network for application in computational solid mechanics","volume-title":"Proceedings of 2022 IEEE\/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)","author":"Arora","year":"2022"},{"key":"2026030916152416300_bib2","article-title":"Spatio-temporal super-resolution of dynamical systems using physics-informed deep-learning","volume-title":"Proceedings of AAAI 2023: Workshop on AI to Accelerate Science and Engineering (AI2ASE)","author":"Arora","year":"2022"},{"key":"2026030916152416300_bib3","doi-asserted-by":"publisher","first-page":"84:1","DOI":"10.1145\/3072959.3073669","article-title":"Dynamics-aware numerical coarsening for fabrication design","volume":"36","author":"Chen","year":"2017","journal-title":"ACM Transactions on Graphics"},{"key":"2026030916152416300_bib4","first-page":"73:1","article-title":"Data-driven finite elements for geometry and material design","volume":"37","author":"Chen","year":"2015","journal-title":"ACM Transactions on Graphics"},{"key":"2026030916152416300_bib5","doi-asserted-by":"publisher","first-page":"120:1","DOI":"10.1145\/3197517.3201386","article-title":"Numerical coarsening using discontinuous shape functions","volume":"37","author":"Chen","year":"2018","journal-title":"ACM Transactions on Graphics"},{"key":"2026030916152416300_bib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3309486.3340248","article-title":"EigenFit for consistent elastodynamic simulation across mesh resolution","volume-title":"Proceedings of the 18th Annual ACM SIGGRAPH\/Eurographics Symposium on Computer Animation","author":"Chen","year":"2019"},{"key":"2026030916152416300_bib7","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/2945.764872","article-title":"Real-time elastic deformations of soft tissues for surgery simulation","volume":"5","author":"Cotin","year":"1999","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"2026030916152416300_bib8","first-page":"7264","article-title":"Mitigating propagation failures in physics-informed neural networks using retain-resample-release (r3) sampling","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Daw","year":"2023"},{"key":"2026030916152416300_bib9","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/8415_2012_125","article-title":"SOFA: A Multi-Model Framework for Interactive Physical Simulation","volume-title":"Soft Tissue Biomechanical Modeling for Computer Assisted Surgery","author":"Faure","year":"2012"},{"key":"2026030916152416300_bib10","first-page":"5850","article-title":"Deep learning versus kernel learning: An empirical study of loss landscape geometry and the time evolution of the neural tangent kernel","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Fort","year":"2020"},{"key":"2026030916152416300_bib11","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1017\/jfm.2019.238","article-title":"Super-resolution reconstruction of turbulent flows with machine learning","volume":"870","author":"Fukami","year":"2019","journal-title":"Journal of Fluid Mechanics"},{"key":"2026030916152416300_bib12","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s00162-023-00663-0","article-title":"Super-resolution analysis via machine learning: A survey for fluid flows","volume":"37","author":"Fukami","year":"2023","journal-title":"Theoretical and Computational Fluid Dynamics"},{"key":"2026030916152416300_bib13","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1111\/cgf.13645","article-title":"Latent-space dynamics for reduced deformable simulation","volume":"38","author":"Fulton","year":"2019","journal-title":"Computer Graphics Forum"},{"key":"2026030916152416300_bib14","doi-asserted-by":"publisher","first-page":"073603","DOI":"10.1063\/5.0054312","article-title":"Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels","volume":"33","author":"Gao","year":"2021","journal-title":"Physics of Fluids"},{"key":"2026030916152416300_bib15","doi-asserted-by":"publisher","first-page":"114502","DOI":"10.1016\/j.cma.2021.114502","article-title":"Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems","volume":"390","author":"Gao","year":"2022","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"key":"2026030916152416300_bib16","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics","author":"Glorot","year":"2010"},{"key":"2026030916152416300_bib17","article-title":"NIPS 2016 Tutorial: Generative Adversarial Networks","volume-title":"preprint arXiv:1701.00160","author":"Goodfellow","year":"2017"},{"key":"2026030916152416300_bib18","doi-asserted-by":"publisher","first-page":"116663","DOI":"10.1016\/j.cam.2025.116663","article-title":"Preconditioned FEM-based neural networks for solving incompressible fluid flows and related inverse problems","volume":"469","author":"Griese","year":"2025","journal-title":"Journal of Computational and Applied Mathematics"},{"key":"2026030916152416300_bib19","first-page":"8580","article-title":"Neural tangent kernel: convergence and generalization in neural networks","volume":"31","author":"Jacot","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026030916152416300_bib20","first-page":"1","article-title":"MESHFREEFLOWNET: A physics-constrained deep continuous space-time super-resolution framework","volume-title":"SC20: IEEE-ACM International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Jiang","year":"2020"},{"key":"2026030916152416300_bib21","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657448","article-title":"VR-GS: A physical dynamics-aware interactive Gaussian splatting system in virtual reality","volume-title":"Proceedings of ACM SIGGRAPH 2024","author":"Jiang","year":"2024"},{"key":"2026030916152416300_bib22","doi-asserted-by":"publisher","first-page":"51:1","DOI":"10.1145\/1531326.1531357","article-title":"Numerical coarsening of inhomogeneous elastic materials","volume":"28","author":"Kharevych","year":"2009","journal-title":"ACM Transactions on Graphics"},{"key":"2026030916152416300_bib23","doi-asserted-by":"publisher","first-page":"A29","DOI":"10.1017\/jfm.2020.1028","article-title":"Unsupervised deep learning for super-resolution reconstruction of turbulence","volume":"910","author":"Kim","year":"2021","journal-title":"Journal of Fluid Mechanics"},{"key":"2026030916152416300_bib24","article-title":"Adam: A method for stochastic optimization","volume-title":"preprint arXiv:1412.6980","author":"Kingma","year":"2017"},{"key":"2026030916152416300_bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICOA55659.2022.9934291","article-title":"Mode collapse in generative adversarial networks: An overview","volume-title":"2022 8th International Conference on Optimization and Applications (ICOA)","author":"Kossale","year":"2022"},{"key":"2026030916152416300_bib26","first-page":"26548","article-title":"Characterizing possible failure modes in physics-informed neural networks","volume":"34","author":"Krishnapriyan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026030916152416300_bib27","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","article-title":"Divergence measures based on the Shannon entropy","volume":"37","author":"Lin","year":"1991","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026030916152416300_bib28","article-title":"Preconditioning for physics-informed neural networks","volume-title":"preprint arXiv:2402.00531","author":"Liu","year":"2024"},{"key":"2026030916152416300_bib29","first-page":"17","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Maas","year":"2013"},{"key":"2026030916152416300_bib30","doi-asserted-by":"publisher","DOI":"10.48456\/tr-562","volume-title":"Fast Marching farthest point sampling (No. UCAM-CL-TR-562)","author":"Moenning","year":"2003"},{"key":"2026030916152416300_bib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1576246.1531358","article-title":"Preserving topology and elasticity for embedded deformable models","volume-title":"Proceedings of ACM SIGGRAPH","author":"Nesme","year":"2009"},{"key":"2026030916152416300_bib32","doi-asserted-by":"publisher","first-page":"e14736","DOI":"10.1111\/cgf.14736","article-title":"Numerical coarsening with neural shape functions","volume":"42","author":"Ni","year":"2023","journal-title":"Computer Graphics Forum"},{"key":"2026030916152416300_bib33","doi-asserted-by":"publisher","first-page":"158:1","DOI":"10.1145\/3670687","article-title":"Near-realtime facial animation by deep 3D simulation super-resolution","volume":"43","author":"Park","year":"2024","journal-title":"ACM Transactions on Graphics"},{"key":"2026030916152416300_bib34","article-title":"Challenges in training PINNs: a loss landscape perspective","volume-title":"preprint arXiv:2402.01868","author":"Rathore","year":"2024"},{"key":"2026030916152416300_bib35","doi-asserted-by":"publisher","first-page":"112438","DOI":"10.1016\/j.jcp.2023.112438","article-title":"PhySR: Physics-informed deep super-resolution for spatiotemporal data","volume":"492","author":"Ren","year":"2023","journal-title":"Journal of Computational Physics"},{"key":"2026030916152416300_bib36","article-title":"What is a good linear finite element? interpolation, conditioning, anisotropy, and quality measures","volume-title":"preprint","author":"Shewchuk","year":"2002"},{"key":"2026030916152416300_bib37","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1093\/jcde\/qwaf044","article-title":"Local stress fields prediction using global displacement through Fourier neural operators","volume":"12","author":"Shin","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026030916152416300_bib38","doi-asserted-by":"publisher","first-page":"041303","DOI":"10.1063\/5.0265738","article-title":"A review of deep learning for super-resolution in fluid flows","volume":"37","author":"Sofos","year":"2025","journal-title":"Physics of Fluids"},{"key":"2026030916152416300_bib39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12057-7_15","article-title":"Interactive deformation of heterogeneous volume data","volume-title":"Biomedical Simulation","author":"Torres","year":"2014"},{"key":"2026030916152416300_bib40","doi-asserted-by":"publisher","first-page":"211:1","DOI":"10.1145\/2980179.2982414","article-title":"High-resolution interaction with corotational coarsening models","volume":"35","author":"Torres","year":"2016","journal-title":"ACM Transactions on Graphics"},{"key":"2026030916152416300_bib41","doi-asserted-by":"publisher","first-page":"116813","DOI":"10.1016\/j.cma.2024.116813","article-title":"Respecting causality for training physics-informed neural networks","volume":"421","author":"Wang","year":"2024","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"key":"2026030916152416300_bib42","article-title":"An expert\u2019s guide to training physics-informed neural networks","volume-title":"preprint arXiv:2308.08468","author":"Wang","year":"2023"},{"key":"2026030916152416300_bib43","doi-asserted-by":"publisher","first-page":"A3055","DOI":"10.1137\/20M1318043","article-title":"Understanding and mitigating gradient flow pathologies in physics-informed neural networks","volume":"43","author":"Wang","year":"2021","journal-title":"SIAM Journal on Scientific Computing"},{"key":"2026030916152416300_bib44","doi-asserted-by":"publisher","first-page":"110768","DOI":"10.1016\/j.jcp.2021.110768","article-title":"When and why PINNs fail to train: A neural tangent kernel perspective","volume":"449","author":"Wang","year":"2022","journal-title":"Journal of Computational Physics"},{"key":"2026030916152416300_bib45","doi-asserted-by":"publisher","first-page":"105649","DOI":"10.1016\/j.proci.2024.105649","article-title":"Physics-informed recurrent super-resolution generative reconstruction in rotating detonation combustor","volume":"40","author":"Wang","year":"2024","journal-title":"Proceedings of the Combustion Institute"},{"key":"2026030916152416300_bib46","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TAI.2022.3192362","article-title":"Learning in sinusoidal spaces with physics-informed neural networks","volume":"5","author":"Wong","year":"2024","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"2026030916152416300_bib47","doi-asserted-by":"publisher","first-page":"108597","DOI":"10.1016\/j.buildenv.2021.108597","article-title":"Super-resolution of near-surface temperature utilizing physical quantities for real-time prediction of urban micrometeorology","volume":"209","author":"Yasuda","year":"2022","journal-title":"Building and Environment"},{"key":"2026030916152416300_bib48","doi-asserted-by":"publisher","first-page":"103852","DOI":"10.1016\/j.finel.2022.103852","article-title":"Super-resolving 2D stress tensor field conserving equilibrium constraints using physics-informed U-Net","volume":"213","author":"Yonekura","year":"2023","journal-title":"Finite Elements in Analysis and Design"},{"key":"2026030916152416300_bib49","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.vrih.2021.01.002","article-title":"A homogenization method for nonlinear inhomogeneous elastic materials","volume":"3","author":"Zhao","year":"2021","journal-title":"Virtual Reality & Intelligent Hardware"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwag015\/67091568\/qwag015.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/3\/69\/67091568\/qwag015.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/3\/69\/67091568\/qwag015.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:15:34Z","timestamp":1773087334000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/13\/3\/69\/8496070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2,28]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwag015","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,2,24]]}}}