Gaussian Process Regression-Based Structural Response Model and Its Application to Regional Damage Assessment

Seismic activities are serious disasters that induce natural hazards resulting in an incalculable amount of damage to properties and millions of deaths. Typically, seismic risk assessment can be performed by means of structural damage information computed based on the maximum displacement of the structure. In this study, machine learning models based on GPR are developed in order to estimate the maximum displacement of the structures from seismic activities and then used to construct fragility curves as an application. During construction of the models, 13 features of seismic waves are considered, and six wave features are selected to establish the seismic models with the correlation analysis normalizing the variables with the peak ground acceleration. Two models for six-floor and 13-floor buildings are developed, and a sensitivity analysis is performed to identify the relationship between prediction accuracy and sampling size. A 10-fold cross-validation method is used to evaluate the model performance, using the R-squared, root mean squared error, Nash criterion, and mean bias. Results of the six-parameter-based model apparently indicate a similar performance to that of the 13-parameter-based model for the two types of buildings. The model for the six-floor building affords a steadily enhanced performance by increasing the sampling size, while the model for the 13-floor building shows a significantly improved performance with a sampling size of over 200. The results indicate that the heighted structure requires a larger sampling size because it has more degrees of freedom that can influence the model performance. Finally, the proposed models are successfully constructed to estimate the maximum displacement, and applied to obtain fragility curves with various performance levels. Then, the regional seismic damage is assessed in Gyeonjgu city of South Korea as an application of the developed models. The damage assessment with the fragility curve provides the structural response from the seismic activities, which can assist in minimizing damage.

[1]  O. Bursi,et al.  Seismic vulnerability of above-ground storage tanks with unanchored support conditions for Na-tech risks based on Gaussian process regression , 2020, Bulletin of Earthquake Engineering.

[2]  Arash Akbari Hamed,et al.  Seismic performance evaluation of steel structures equipped with dissipative columns , 2020 .

[3]  Vasant Matsagar,et al.  Uncertainty quantification and seismic fragility of base-isolated liquid storage tanks using response surface models , 2016 .

[4]  Andreas Krause,et al.  A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions , 2016, bioRxiv.

[5]  Phuong H. Hoang,et al.  Kriging Metamodel-Based Seismic Fragility Analysis of Single-Bent Reinforced Concrete Highway Bridges , 2021, Buildings.

[6]  Behrouz Shafei,et al.  A simplified method for collapse capacity assessment of moment-resisting frame and shear wall structural systems , 2011 .

[7]  A. M. Prasad,et al.  Development of fragility curves using high‐dimensional model representation , 2013 .

[8]  Michel Bruneau,et al.  Performance‐based metamodel for healthcare facilities , 2011 .

[9]  Iain Murray,et al.  A framework for evaluating approximation methods for Gaussian process regression , 2012, J. Mach. Learn. Res..

[10]  Zekeriya Polat,et al.  Fragility analysis of mid-rise R/C frame buildings , 2006 .

[11]  Peyman Yariyan,et al.  Earthquake risk assessment using an integrated Fuzzy Analytic Hierarchy Process with Artificial Neural Networks based on GIS: A case study of Sanandaj in Iran , 2020, International Journal of Disaster Risk Reduction.

[12]  João Manuel Carvalho Estevão,et al.  The use of Artificial Neural Networks to estimate seismic damage and derive vulnerability functions for traditional masonry , 2020 .

[13]  Seong-Hoon Hwang,et al.  Machine learning-based approaches for seismic demand and collapse of ductile reinforced concrete building frames , 2020 .

[14]  Armando Calabrese,et al.  Fragility functions of blockwork wharves using artificial neural networks , 2013 .

[15]  G. Candia,et al.  Collapse risk assessment of a Chilean dual wall-frame reinforced concrete office building , 2019, Engineering Structures.

[16]  Rupert G. Miller.  A Trustworthy Jackknife , 1964 .

[17]  E. Park,et al.  Did the 12 September 2016 Gyeongju, South Korea earthquake cause surface deformation? , 2018, Geosciences Journal.

[19]  Michalis Fragiadakis,et al.  Fragility Assessment of Steel Frames Using Neural Networks , 2007 .

[20]  G. R. Toro,et al.  Model of Strong Ground Motions from Earthquakes in Central and Eastern North America: Best Estimates and Uncertainties , 1997 .

[21]  Sashi K. Kunnath,et al.  Modeling and Response Prediction in Performance-Based Seismic Evaluation: Case Studies of Instrumented Steel Moment-Frame Buildings , 2004 .

[22]  M. Noh,et al.  Estimation of Peak Ground Motions in the Southeastern Part of the Korean peninsula (II) : Development of Predictive Equations , 1995 .

[23]  Soyoung Park,et al.  Seismic Vulnerability Assessment and Mapping of Gyeongju, South Korea Using Frequency Ratio, Decision Tree, and Random Forest , 2020, Sustainability.

[24]  Nicola Pedroni,et al.  Seismic fragility analysis with artificial neural networks: Application to nuclear power plant equipment , 2018 .

[25]  Anne S. Kiremidjian,et al.  Assembly-Based Vulnerability of Buildings and Its Use in Performance Evaluation , 2001 .

[26]  Dina D'Ayala,et al.  Development of Bayesian Networks for the multi-hazard fragility assessment of bridge systems , 2016 .

[27]  Anil K. Chopra,et al.  Practical guidelines to select and scale earthquake records for nonlinear response history analysis of structures , 2010 .

[28]  Sashi K. Kunnath,et al.  Effects of Fling Step and Forward Directivity on Seismic Response of Buildings , 2006 .

[29]  Sangki Park,et al.  Development of Models for Prompt Responses from Natural Disasters , 2020, Sustainability.

[30]  George Papazafeiropoulos,et al.  OpenSeismoMatlab: A new open-source software for strong ground motion data processing , 2018, Heliyon.

[31]  조남대,et al.  Estimation of Spectrum Decay Parameter and Stochastic Prediction of Strong Ground Motions in Southeastern Korea , 2003 .

[32]  Fateh Chebana,et al.  Development of regional flood frequency analysis techniques using generalized additive models for Australia , 2017, Stochastic Environmental Research and Risk Assessment.