none 10.1177/87552930241231686 Wiley Wiley (John Wiley & Sons) 311 158736711 5867 2026012504074700963 10.1002 2026-01-25T14:14:14Z 2024-03-11T00:07:27Z 9 Earthquake Spectra Earthquake Spectra 8755-2930 1944-8201 05 2024 40 2 Farid Ghahari Civil and Environmental Engineering Department University of California Los Angeles CA USA California Geological Survey Sacramento CA USA http://orcid.org/0000-0002-3847-5277 Daniel Swensen California Geological Survey Sacramento CA USA Hamid Haddadi California Geological Survey Sacramento CA USA Ertugrul Taciroglu Civil and Environmental Engineering Department University of California Los Angeles CA USA http://orcid.org/0000-0001-9618-1210 This study presents a two‐step hybrid (model‐data fusion) method for reconstructing the seismic response of instrumented buildings at their non‐instrumented floors. Over the past couple of decades, seismic data recorded within instrumented buildings have yielded invaluable insights into the behavior of civil structures, which were arguably impossible to obtain through numerical simulations, laboratory‐scale experiments, or even in‐situ testing. Recently, advances in sensing technology have opened new pathways for structural health monitoring (SHM) and rapid post‐earthquake assessment. However, data‐driven techniques tend to lack accuracy when structures have sparse instrumentation. In addition, creating detailed numerical models for the monitored structures is labor‐intensive and time‐consuming, often unsuitable for rapid post‐event assessments. The common approach to address these challenges has been to use simple interpolation techniques over the sparse measurements. However, uncertainties associated with such estimates are usually overlooked, and these methods have certain physical limitations. In this study, we propose a two‐step approach for reconstructing seismic responses. In the initial step, a coupled shear–flexural beam model is calibrated using data collected from instrumented floors. Next, the residual, representing the difference between measurements and the beam model’s predictions, is used to train a Gaussian process regression model. The combination of these two models provides both the mean and variance of the response at the non‐instrumented floors. This new approach is verified by using simulated acceleration responses of a tall building. Validation is attained by using real seismic data recorded in two tall buildings and comparing the method’s predictions with actual measurements on floors not used for training. Finally, data recorded in a 52‐story building during multiple earthquakes are used for demonstrating the practical application of the proposed approach in real‐world scenarios. 05 2024 05 2024 1235 1268 10.1177/87552930241231686 http://onlinelibrary.wiley.com/termsAndConditions#vor http://doi.wiley.com/10.1002/tdm_license_1.1 2 10.1177/sage-journals-update-policy journals.sagepub.com true https://journals.sagepub.com/page/policies/text-and-data-mining-license 10.1177/87552930241231686 https://onlinelibrary.wiley.com/doi/10.1177/87552930241231686 http://sage.cnpereading.com/paragraph/article/?doi=10.1177/87552930241231686 https://onlinelibrary.wiley.com/doi/pdf/10.1177/87552930241231686 https://onlinelibrary.wiley.com/doi/pdf/10.1177/87552930241231686 https://onlinelibrary.wiley.com/doi/full-xml/10.1177/87552930241231686 https://pubs.geoscienceworld.org/earthquake-spectra/article/40/2/1235/639007/a-hybrid-model-data-method-for-seismic-response 10.1002/stc.1513 10.1193/031712EQS093M 10.1061/(ASCE)EM.1943-7889.0000990 10.1193/1.2084232 10.1002/eqe.3915 10.1061/(ASCE)EM.1943-7889.0000851 ATC‐20(2005)Building Safety Evaluation Forms and Placards. Available at:https://www.atcouncil.org/atc‐20 Numerical issues in maximum likelihood parameter estimation for Gaussian Process interpolation (Lecture Notes in Computer Science) Basak S 2022 10.1098/rstl.1763.0053 10.1002/eqe.3636 10.1193/1.2359702 10.1785/0220190220 10.1177/8755293020906836 10.1193/092713EQS260M 10.1193/052114EQS071M 10.1193/122216eqs249m 10.1193/1.1735987 10.1785/0120220005 Dynamics of Structures Clough RW 2013 10.1137/0806023 10.1016/j.engstruct.2018.08.017 10.1007/978-1-4612-6333-3 10.2172/249299 10.3390/buildings13010028 FEMA P‐58(2018)Seismic performance assessment of buildings volume 1—methodology. Technical Report FEMA‐P 58‐1. Available at:https://www.atcouncil.org/docman/fema/246‐fema‐p‐58‐1‐seismic‐performance‐assessment‐of‐buildings‐volume‐1‐methodology‐second‐edition/file Finite Element Model Updating in Structural Dynamics (Solid Mechanics and Its Applications) Friswell MI 1995 Conference of Earthquake Risk and Engineering Towards a Resilient World Gentile R 1 87 2019 Gaussian process regression for seismic fragility assessment of building Portfolios 10.1002/stc.1925 10.1007/s10518-017-0253-0 10.1002/stc.1803 10.1002/eqe.2268 10.1002/stc.1593 10.1785/0120210224 10.3390/s22031278 10.1002/stc.3078 10.1093/biomet/58.2.255 Proceedings ‐ 6th International Conference on New Trends in Information Science, Service Science and Data Mining (NISS, ICMIA and NASNIT), Taipei, 23–25 October Hong S 2012 Strong Motion Instrumentation for Civil Engineering Structures Huang MJ 17 373 2011 Structure instrumentation in the California strong motion instrumentation program 10.1193/1.4000091 10.1002/2475-8876.12155 Journal of Southern African Institute of Mining and Metallurgy Krige DG 4792 52 6 1951 A statistical approach to some basic mine valuation problems on the Witwatersrand 10.1198/004017004000000671 10.1007/s10518-022-01461-5 10.1002/eqe.262 10.1016/j.jsv.2011.06.012 10.1007/978-3-030-13976-6 10.1098/rsta.2006.1932 10.3390/buildings13020420 10.1007/s11222-011-9274-8 10.1193/1.4000151 MartuscelliP MoehleJP(2019)Using CSMIP data to test FEMA P58 methodology and the potential for automated loss estimation. SMIP Seminar. Available at:https://www.semanticscholar.org/paper/USING‐CSMIP‐DATA‐TO‐TEST‐FEMA‐P58‐METHODOLOGY‐AND‐Martuscelli‐Moehle/a085233a0a87cf5799234efc26bb042f08fb33d4 MathWorks(2018).MATLAB version: 9.4.0 (R2018b) Natick Massachusetts: The MathWorks Inc.https://www.mathworks.com. 10.1061/(ASCE)0733-9445(1999)125:4(417) 10.1016/j.ymssp.2010.10.012 10.1002/tal.345 10.1061/(ASCE)ST.1943-541X.0001200 10.1093/biomet/58.3.545 10.1109/MSP.2013.2250352 PorterKA(2003)An overview of PEER’s performance‐based earthquake engineering methodology. In: 9th International Conference on Applications of Statistics and Probability in Civil Engineering San Francisco CA 6–9 July. 10.1002/eqe.3422 10.1016/j.engstruct.2012.07.007 Gaussian Processes for Machine Learning Rasmussen CE 2006 10.1007/BF02162161 10.1007/s13349-020-00416-1 10.1002/stc.2373 10.1061/(ASCE)ST.1943-541X.0003095 10.1016/j.jmp.2018.03.001 10.1061/(ASCE)0733-9399(2000)126:12(1224) 10.1002/stc.2090 10.1002/0470045345 10.1016/j.ymssp.2020.106837 10.1109/TBME.2008.923118 10.1007/978-1-4612-1494-6 10.1193/072215EQS118M 10.1016/j.soildyn.2016.09.041 10.1061/(ASCE)0733-9445(2005)131:2(212) 10.1785/0120210054 10.1111/j.2517-6161.1996.tb02080.x Mathematics of Computation Wahba G 687 57 195 1991 Spline models for observational data 10.1193/1.2923924 10.1785/0120160069 10.1080/13632469.2021.1991860 10.1016/j.soildyn.2021.106961