{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T12:34:31Z","timestamp":1753878871368,"version":"3.41.2"},"reference-count":51,"publisher":"ASME International","issue":"5","license":[{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The presence of gaps and spurious nonphysical artifacts in datasets is a nearly ubiquitous problem in many scientific and engineering domains. In the context of multiphysics numerical models, data gaps may arise from lack of coordination between modeling elements and limitations of the discretization and solver schemes employed. In the case of data derived from physical experiments, the limitations of sensing and data acquisition technologies, as well as myriad sources of experimental noise, may result in the generation of data gaps and artifacts. In the present work, we develop and demonstrate a machine learning (ML) meta-framework for repairing such gaps in multiphysics datasets. A unique \u201ccross-training\u201d methodology is used to ensure that the ML models capture the underlying multiphysics of the input datasets, without requiring training on datasets free of gaps\/artifacts. The general utility of this approach is demonstrated by the repair of gaps in a multiphysics dataset taken from hypervelocity impact simulations. Subsequently, we examine the problem of removing scan artifacts from X-ray computed microtomographic (XCMT) datasets. A unique experimental methodology for acquiring XCMT data, wherein articles are scanned multiple times under different conditions, enables the ready identification of artifacts, their removal from the datasets, and the filling of the resulting gaps using the ML framework. This work concludes with observations regarding the unique features of the developed methodology, and a discussion of potential future developments and applications for this technology.<\/jats:p>","DOI":"10.1115\/1.4064986","type":"journal-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T15:15:53Z","timestamp":1709565353000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":0,"title":["Multiphysics Missing Data Synthesis: A Machine Learning Approach for Mitigating Data Gaps and Artifacts"],"prefix":"10.1115","volume":"24","author":[{"given":"J. C.","family":"Steuben","sequence":"first","affiliation":[{"name":"U.S. Naval Research Laboratory Computational Multiphysics Systems Laboratory, , Washington, DC 20375"}]},{"given":"A. B.","family":"Geltmacher","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/04d23a975","id-type":"ROR","asserted-by":"publisher"}],"name":"United States Naval Research Laboratory Simulations and Imaging Section, Materials Science and Technology Division, , Washington, DC 20375"},{"name":"U.S. Naval Research Laboratory Simulations and Imaging Section, Materials Science and Technology Division, , Washington, DC 20375"}]},{"given":"S. N.","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"U.S. Naval Research Laboratory, Computational Multiphysics Systems Laboratory, Washington, DC 20375"}]},{"given":"B. D.","family":"Graber","sequence":"additional","affiliation":[{"name":"U.S. Naval Research Laboratory, Computational Multiphysics Systems Laboratory, Washington, DC 20375"}]},{"given":"A. P.","family":"Iliopoulos","sequence":"additional","affiliation":[{"name":"U.S. Naval Research Laboratory, Computational Multiphysics Systems Laboratory, Washington, DC 20375"}]},{"given":"J. G.","family":"Michopoulos","sequence":"additional","affiliation":[{"name":"U.S. Naval Research Laboratory Computational Multiphysics Systems Laboratory, , Washington, DC 20375"}]}],"member":"33","published-online":{"date-parts":[[2024,3,27]]},"reference":[{"key":"2024041815241137000_CIT0001","first-page":"V002T02A035","article-title":"X-Ray Marching for the Computational Modeling of Tomographic Systems Applied to Materials Applications","author":"Steuben","year":"2022"},{"key":"2024041815241137000_CIT0002","first-page":"759","article-title":"Selecting an Appropriate Metamodel: The Case for NURBs Metamodels","author":"Turner","year":"2005"},{"key":"2024041815241137000_CIT0003","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2023-115260","article-title":"Multiphysics Missing Data Synthesis (MiDaS): A Machine-Learning Approach for Mitigating Data Gaps and Artifacts","author":"Steuben","year":"2023"},{"key":"2024041815241137000_CIT0004","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00158-001-0160-4","article-title":"Comparative Studies of Metamodelling Techniques Under Multiple Modelling Criteria","volume":"23","author":"Jin","year":"2001","journal-title":"Struct. Multidiscipl. Optim."},{"issue":"1","key":"2024041815241137000_CIT0005","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/S0377-2217(98)00392-0","article-title":"A Methodology for Fitting and Validating Metamodels in Simulation","volume":"120","author":"Kleijnen","year":"2000","journal-title":"Eur. J. Oper. Res."},{"issue":"3","key":"2024041815241137000_CIT0006","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s00163-020-00336-7","article-title":"Managing Computational Complexity Using Surrogate Models: A Critical Review","volume":"31","author":"Alizadeh","year":"2020","journal-title":"Res. Eng. Design"},{"issue":"1","key":"2024041815241137000_CIT0007","doi-asserted-by":"crossref","first-page":"012187","DOI":"10.1088\/1742-6596\/1754\/1\/012187","article-title":"Missing Data Filling Method Based on Linear Interpolation and Lightgbm","volume":"1754","author":"Huang","year":"2021","journal-title":"J. Phys. Conf. Series"},{"volume-title":"Anderson Cook, CM: Response Surface Methodology: Process and Product Optimization Using Designed Experiments","year":"2009","author":"Myers","key":"2024041815241137000_CIT0008"},{"issue":"10","key":"2024041815241137000_CIT0009","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1109\/TPAMI.2002.1039207","article-title":"Reconstructing Surfaces by Volumetric Regularization Using Radial Basis Functions","volume":"24","author":"Dinh","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"2024041815241137000_CIT0010","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/BF00889887","article-title":"The Origins of Kriging","volume":"22","author":"Cressie","year":"1990","journal-title":"Math. Geol."},{"key":"2024041815241137000_CIT0011","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmp.2018.03.001","article-title":"A Tutorial on Gaussian Process Regression: Modelling, Exploring, and Exploiting Functions","volume":"85","author":"Schulz","year":"2018","journal-title":"J. Math. Psychol."},{"issue":"2","key":"2024041815241137000_CIT0012","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1029\/GL014i002p00139","article-title":"Biharmonic Spline Interpolation of GEOS-3 and Seasat Altimeter Data","volume":"14","author":"Sandwell","year":"1987","journal-title":"Geophys. Res. Lett."},{"issue":"1","key":"2024041815241137000_CIT0013","first-page":"1","article-title":"Multivariate Adaptive Regression Splines","volume":"19","author":"Friedman","year":"1991","journal-title":"Ann. Stat."},{"issue":"3","key":"2024041815241137000_CIT0014","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1080\/03052150601077260","article-title":"Global Optimization of Nurbs-Based Metamodels","volume":"39","author":"Turner","year":"2007","journal-title":"Eng. Optim."},{"issue":"6","key":"2024041815241137000_CIT0015","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/72.97934","article-title":"A General Regression Neural Network","volume":"2","author":"Specht","year":"1991","journal-title":"IEEE Trans. Neural Netw."},{"key":"2024041815241137000_CIT0016","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.compchemeng.2014.05.021","article-title":"Adaptive Sequential Sampling for Surrogate Model Generation With Artificial Neural Networks","volume":"68","author":"Eason","year":"2014","journal-title":"Comput. Chem. Eng."},{"issue":"4","key":"2024041815241137000_CIT0017","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","article-title":"Support Vector Machines","volume":"13","author":"Hearst","year":"1998","journal-title":"IEEE Intell. Syst. Appl."},{"key":"2024041815241137000_CIT0018","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/978-1-4302-5990-9_4","volume-title":"Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers","author":"Awad","year":"2015"},{"issue":"1","key":"2024041815241137000_CIT0019","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1145\/234313.234346","article-title":"Learning Decision Tree Classifiers","volume":"28","author":"Quinlan","year":"1996","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"2024041815241137000_CIT0020","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.advengsoft.2016.09.001","article-title":"Gtapprox: Surrogate Modeling for Industrial Design","volume":"102","author":"Belyaev","year":"2016","journal-title":"Adv. Eng. Softw."},{"issue":"5","key":"2024041815241137000_CIT0021","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"issue":"15","key":"2024041815241137000_CIT0022","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.3390\/rs11151796","article-title":"A Decision Tree Approach for Spatially Interpolating Missing Land Cover Data and Classifying Satellite Images","volume":"11","author":"Holloway","year":"2019","journal-title":"Remote Sens."},{"issue":"2","key":"2024041815241137000_CIT0023","first-page":"129","article-title":"The Analysis of Replicated Experiments When the Field Results Are Incomplete","volume":"1","author":"Yates","year":"1933","journal-title":"Empire J. Exp. Agric."},{"issue":"8","key":"2024041815241137000_CIT0024","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1364\/JOSAA.12.001657","article-title":"Karhunen\u2013Loeve Procedure for Gappy Data","volume":"12","author":"Everson","year":"1995","journal-title":"JOSA A"},{"key":"2024041815241137000_CIT0025","doi-asserted-by":"crossref","DOI":"10.1017\/9781009089517","volume-title":"Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control","author":"Brunton","year":"2022"},{"issue":"1","key":"2024041815241137000_CIT0026","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.jcp.2005.06.023","article-title":"Gappy Data: To Krig or Not to Krig?","volume":"212","author":"Gunes","year":"2006","journal-title":"J. Comput. Phys."},{"issue":"8","key":"2024041815241137000_CIT0027","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.2514\/1.2159","article-title":"Aerodynamic Data Reconstruction and Inverse Design Using Proper Orthogonal Decomposition","volume":"42","author":"Bui-Thanh","year":"2004","journal-title":"AIAA J."},{"issue":"9","key":"2024041815241137000_CIT0028","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1002\/nme.4668","article-title":"Dimensional Reduction of Nonlinear Finite Element Dynamic Models With Finite Rotations and Energy-Based Mesh Sampling and Weighting for Computational Efficiency","volume":"98","author":"Farhat","year":"2014","journal-title":"Int. J. Numer. Methods Eng."},{"key":"2024041815241137000_CIT0029","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/j.jcp.2013.02.028","article-title":"The GNAT Method for Nonlinear Model Reduction: Effective Implementation and Application to Computational Fluid Dynamics and Turbulent Flows","volume":"242","author":"Carlberg","year":"2013","journal-title":"J. Comput. Phys."},{"issue":"5","key":"2024041815241137000_CIT0030","doi-asserted-by":"publisher","first-page":"2737","DOI":"10.1137\/090766498","article-title":"Nonlinear Model Reduction via Discrete Empirical Interpolation","volume":"32","author":"Chaturantabut","year":"2010","journal-title":"SIAM J. Sci. Comput."},{"key":"2024041815241137000_CIT0031","doi-asserted-by":"publisher","first-page":"111141","DOI":"10.1016\/j.jcp.2022.111141","article-title":"Projection-Tree Reduced-Order Modeling for Fast n-Body Computations","volume":"459","author":"Rodriguez","year":"2022","journal-title":"J. Comput. Phys."},{"issue":"2","key":"2024041815241137000_CIT0032","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s10915-022-02001-8","article-title":"Deep-hyromnet: A Deep Learning-Based Operator Approximation for Hyper-Reduction of Nonlinear Parametrized PDEs","volume":"93","author":"Cicci","year":"2022","journal-title":"J. Sci. Comput."},{"article-title":"Efficient Nonlinear Manifold Reduced Order Model","year":"2020","author":"Kim","key":"2024041815241137000_CIT0033"},{"key":"2024041815241137000_CIT0034","doi-asserted-by":"publisher","first-page":"111908","DOI":"10.1016\/j.jcp.2023.111908","article-title":"Model Reduction for the Material Point Method via an Implicit Neural Representation of the Deformation Map","volume":"478","author":"Chen","year":"2023","journal-title":"J. Comput. Phys."},{"volume-title":"Computed Tomography: Principles, Design, Artifacts, and Recent Advances","year":"2003","author":"Hsieh","key":"2024041815241137000_CIT0035"},{"issue":"8","key":"2024041815241137000_CIT0036","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1364\/AO.31.001146","article-title":"One-Dimensional Tomography: A Comparison of Abel, Onion-Peeling, and Filtered Backprojection Methods","volume":"31","author":"Dasch","year":"1992","journal-title":"Appl. Opt."},{"issue":"4","key":"2024041815241137000_CIT0037","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1016\/S0196-8858(03)00099-X","article-title":"An Improved Exact Filtered Backprojection Algorithm for Spiral Computed Tomography","volume":"32","author":"Katsevich","year":"2004","journal-title":"Adv. Appl. Math."},{"key":"2024041815241137000_CIT0038","first-page":"1","article-title":"A Method for Simultaneous Image Reconstruction and Beam Hardening Correction","author":"Jin","year":"2013"},{"issue":"3","key":"2024041815241137000_CIT0039","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1148\/radiol.11101782","article-title":"Evaluation of Two Iterative Techniques for Reducing Metal Artifacts in Computed Tomography","volume":"259","author":"Boas","year":"2011","journal-title":"Radiology"},{"issue":"5","key":"2024041815241137000_CIT0040","doi-asserted-by":"publisher","first-page":"050901","DOI":"10.1115\/1.4049760","article-title":"Multiscale Tomographic Wave\u2013Matter Interaction Modeling to Enable Artifact-Free Material Defect Reconstruction","volume":"21","author":"Steuben","year":"2021","journal-title":"J. Comput. Inf. Sci. Eng."},{"key":"2024041815241137000_CIT0041","first-page":"539","article-title":"On Sequential Sampling for Global Metamodeling in Engineering Design","author":"Jin","year":"2002"},{"issue":"5","key":"2024041815241137000_CIT0042","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1007\/s11222-016-9696-4","article-title":"Practical Bayesian Model Evaluation Using Leave-One-Out Cross-Validation and Waic","volume":"27","author":"Vehtari","year":"2017","journal-title":"Stat. Comput."},{"issue":"6","key":"2024041815241137000_CIT0043","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1214\/aos\/1176345632","article-title":"Estimation of the Mean of a Multivariate Normal Distribution","volume":"9","author":"Stein","year":"1981","journal-title":"Ann. Stat."},{"issue":"3","key":"2024041815241137000_CIT0044","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1214\/aoms\/1177696968","article-title":"An Iterative Procedure for Estimation in Contingency Tables","volume":"41","author":"Fienberg","year":"1970","journal-title":"Ann. Math. Stat."},{"issue":"3","key":"2024041815241137000_CIT0045","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1214\/aos\/1176348768","article-title":"Variable Kernel Density Estimation","volume":"20","author":"Terrell","year":"1992","journal-title":"Ann. Stat."},{"key":"2024041815241137000_CIT0046","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/978-0-387-73003-5_196","article-title":"Gaussian Mixture Models","volume":"741","author":"Reynolds","year":"2009","journal-title":"Encyclopedia Biom."},{"issue":"1","key":"2024041815241137000_CIT0047","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","article-title":"A Tutorial on the Cross-Entropy Method","volume":"134","author":"De Boer","year":"2005","journal-title":"Ann. Oper. Res."},{"year":"2022","author":"Wolfram Research Inc.","key":"2024041815241137000_CIT0048"},{"key":"2024041815241137000_CIT0049","doi-asserted-by":"publisher","first-page":"101927","DOI":"10.1016\/j.eml.2022.101927","article-title":"Plasma Formation in Ambient Fluid From Hypervelocity Impacts","volume":"58","author":"Islam","year":"2023","journal-title":"Extreme Mech. Lett."},{"issue":"6","key":"2024041815241137000_CIT0050","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1364\/JOSAA.1.000612","article-title":"Practical Cone-Beam Algorithm","volume":"1","author":"Feldkamp","year":"1984","journal-title":"JOSA A"},{"issue":"8","key":"2024041815241137000_CIT0051","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1021\/ac60214a047","article-title":"Smoothing and Differentiation of Data by Simplified Least Squares Procedures","volume":"36","author":"Savitzky","year":"1964","journal-title":"Anal. Chem."}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/5\/051010\/7323027\/jcise_24_5_051010.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/5\/051010\/7323027\/jcise_24_5_051010.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T15:24:25Z","timestamp":1713453865000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/5\/051009\/1198175\/Multiphysics-Missing-Data-Synthesis-A-Machine"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4064986","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"type":"print","value":"1530-9827"},{"type":"electronic","value":"1944-7078"}],"subject":[],"published":{"date-parts":[[2024,3,27]]},"article-number":"051009"}}