The evolution of seismic intensity measures: From classical to machine learning-based seismic intensity measures for different structures—Data-driven systematic review

Abstract

Over the past two decades, seismic intensity measures (IMs) have evolved substantially, transitioning from widely used traditional parameters such as peak ground acceleration and Sa(T₁) to more advanced forms, including data-driven, energy-based, vector, machine learning (ML)-based, and hybrid approaches. This systematic review analyzes real data from 120 prominent international studies (1990–2024), classifying IMs by structural type short-, mid-, and high-rise frames; bridges; shear walls; dams; tunnels; as well as special structures, while evaluating their performance through dispersion (β), sufficiency, and predictability criteria. Findings indicate that in many cases, ML-based and hybrid IMs can enhance collapse prediction and seismic demand estimation for short- and mid-rise frames, while for bridges and high-rise buildings, certain specialized and energy-based IMs capture nonlinear responses more effectively. For massive structures such as dams and tunnels, vector and artificial intelligence-driven measures often achieve better sufficiency and reduced dispersion. Complementary analytical approaches based on formal mathematical modeling and dimensional analysis have also been considered to strengthen the theoretical framework of ground-motion characterization. However, these comparative rankings should be interpreted with caution, as the qualitative evaluation of sufficiency (e.g., “good”, “excellent”, “superb”) remains inherently subjective and may vary with the heterogeneity of datasets and study assumptions. Nevertheless, these advantages are context-dependent, influenced by data quality, structural characteristics, and hazard conditions. In some scenarios, traditional IMs remain competitive or even preferable. These results underscore the importance of a case-specific approach to IM selection, considering both strengths and limitations of each method to optimize seismic performance assessment.

Graphical abstract

Keywords

seismic intensity measures / machine learning / structural performance assessment / different structures / data-driven analysis / systematic review

References

[1] Jalayer F , Beck J L , Zareian F . Information-based relative sufficiency of some ground motion intensity measures. Earthquake Engineering & Structural Dynamics, 2012, 41(7): 1009–1024

[2] Gong H , Wang Z , Xiong L . Comparative evaluation of intensity measures for probabilistic seismic demand analysis of bridges under near-fault and far-field ground motions. Engineering Structures, 2021, 231: 111775

[3] Travasarou T , Bray J D , Abrahamson N A . Empirical attenuation relationship for Arias intensity. Earthquake Engineering & Structural Dynamics, 2003, 32(7): 1133–1155

[4] Javadi E , Yakhchalian M . Selection of optimal intensity measure for seismic assessment of steel buckling restrained braced frames under near-fault ground motions. Journal of Rehabilitation in Civil Engineering, 2019, 7(4): 114–133

[5] Haj Najafi L , Tehranizadeh M . New intensity measure parameter based on record’s velocity characteristics. Scientia Iranica, 2015, 22(5): 1674–1691

[6] Luco N , Cornell C A . Structure-specific scalar intensity measures for near-source and ordinary earthquake ground motions. Earthquake Spectra, 2007, 23(2): 357–392

[7] Luco N, Cornell C A. Seismic Drift Demands for Two SMRF Structures with Brittle Connections. Structural Engineering World Wide, SEWW No. T144–3. 1998

[8] Baker J W , Cornell C A . A vector-valued ground motion intensity measure consisting of spectral acceleration and epsilon. Earthquake Engineering & Structural Dynamics, 2005, 34(10): 1193–1217

[9] Cordova P P , Deierlein G G , Mehanny S S F , Cornell C A . Development of a two-parameter seismic intensity measure and probabilistic assessment procedure. Journal of Engineering and Applied Sciences, 2001, 51: 117362765

[10] Zareian F , Krawinkler H . Evaluation of alternative scalar and vector IMs for seismic demand estimation in nonlinear steel frames. Engineering Structures, 2010, 32(11): 3694–3703

[11] Shokrgozar H R , Hatzigeorgiou G D . Sufficiency of selected ground motion intensity measures for steel structures under near-fault ground motions. Soil Dynamics and Earthquake Engineering, 2016, 88: 125–137

[12] Yahyaabadi A , Tehranizadeh M . Development of an improved intensity measure in order to reduce the variability in seismic demands under near-fault ground motions. Journal of Earthquake and Tsunami, 2012, 6(2): 1250012

[13] Li Y , Liu W , Wang Y , Xu C . Machine learning-based intensity measure for seismic demand assessment. Soil Dynamics and Earthquake Engineering, 2022, 157: 107256

[14] Cornell C A, Luco N. Ground motion intensity measures for structural performance assessment at near-fault sites. In: Proceedings of the US–Japan Workshop on Performance-Based Engineering for Earthquake Resistant Structures. Kyoto: PEER, 2001

[15] Han Q , Liu H , Lin G . Assessment of ground motion intensity measures for predicting nonlinear seismic response of structures. Engineering Structures, 2016, 129: 380–391

[16] Wang M , Li J , Ma X . Intensity measure for collapse capacity of steel frames under strong earthquake. Earthquake Engineering & Structural Dynamics, 2020, 49(13): 1392–1404

[17] Wang Y , He M , Zhong J . Evaluation of the efficiency and sufficiency of ground motion intensity measures for seismic fragility analysis of RC frames. Engineering Structures, 2019, 187: 109043

[18] Asgarian B , Moradi M , Moghaddam H . An improved ground motion intensity measure for predicting collapse of RC structures. Soil Dynamics and Earthquake Engineering, 2015, 71: 150–160

[19] Zhang W , Shi C , Wang Y . Selecting optimal intensity measures for fragility analysis of RC bridges under near-fault ground motions. Engineering Structures, 2021, 229: 110741

[20] Tsang H H , Hu X , Yang Y . Machine-learning-based optimal intensity measures for RC frame fragility and optimization. Engineering Structures, 2023, 284: 112044

[21] Shome N, Cornell C A. Probabilistic Seismic Demand Analysis of Nonlinear Structures. Report No. RMS-35. 1999

[22] Zhai C , Wen W , Li H , Zhao H . Improved seismic intensity measures for collapse capacity prediction of steel structures under near-fault earthquakes. Engineering Structures, 2023, 285: 115183

[23] Wang G . Efficiency of scalar and vector intensity measures for seismic slope displacements. Frontiers of Structural and Civil Engineering, 2012, 6(1): 44–52

[24] Yazdannejad K , Yazdani A . Prediction of seismic demand model for pulse-like ground motions using artificial neural networks. Canadian Journal of Civil Engineering, 2017, 44(12): 1022–1035

[25] Tothong P , Luco N . Probabilistic seismic demand analysis using advanced ground motion intensity measures. Earthquake Engineering & Structural Dynamics, 2007, 36(13): 1837–1860

[26] Kourehli S S , Saedi D , Nezafat S . Selection of effective intensity measures for fragility analysis of high-speed railway bridges subjected to near-fault earthquakes. Soil Dynamics and Earthquake Engineering, 2020, 131: 106051

[27] Khosravikia F , Liu X , Han Q . Two-parameter ground motion intensity measure for probabilistic seismic demand hazard analysis of structures. Engineering Structures, 2022, 256: 113942

[28] Baker J W . Using peak ground velocity as an IM for prediction of structural response. Earthquake Spectra, 2006, 22(2): 567–576

[29] Li G , Li H N , Song G B , Ren W X , Zhou J H . Parametric study on the seismic responses of structures subjected to different ground motion intensity measures. Frontiers of Structural and Civil Engineering, 2015, 9(2): 151–162

[30] Chen X , Xu L , Guo J , Wang Y . Machine learning-based rapid seismic damage prediction for city-scale buildings using multi-source data. Frontiers of Structural and Civil Engineering, 2023, 17(2): 346–359

[31] Gupta A , Krawinkler H . Spectrum intensity as a seismic IM for probability-based engineering assessment. Earthquake Engineering & Structural Dynamics, 2000, 29(7): 1133–1147

[32] Zareian F , Krawinkler H . Modelling and using vector IMs in seismic response assessment. Earthquake Engineering & Structural Dynamics, 2010, 39(7): 817–835

[33] Zhang G , Hoffmann C , Li Y . Machine learning-based seismic demand prediction of reinforced concrete structures using optimal intensity measures. Engineering Structures, 2021, 245: 112865

[34] Han Q , Khosravikia F , Liu X . Efficiency and sufficiency of energy-based and hybrid IMs in near-fault ground motions. Journal of Earthquake Engineering, 2016, 20(3): 336–357

[35] Li H , Zhai C , Wen W . Advanced fragility analysis for tall, special bridges considering near-fault effects. Engineering Structures, 2022, 252: 113697

[36] Ghimire S, Gueguen P, Astorga A. Analysis of the efficiency of intensity measures from real earthquake data recorded in buildings. Soil Dynamics and Earthquake Engineering, 2021, 147: 106751

[37] Li Y , Tian X , Guo X , Wang Y . Machine learning applications in intensity measure selection for seismic vulnerability. Engineering Structures, 2022, 253: 113786

[38] Wang J , Liu X , Khosravikia F . Assessment of combined Sa and PGV as hybrid IMs in seismic analysis of concrete structures. Soil Dynamics and Earthquake Engineering, 2019, 120: 242–255

[39] Javadi E , Yakhchalian M . Efficiency of S_avg and IM(0.5) for low- and mid-rise steel frames under near-fault ground motions. Journal of Rehabilitation in Civil Engineering, 2019, 7(3): 68–84

[40] Gong J , Haselton C B , Lu X . Relative performance of scalar versus vector IMs in seismic risk assessment of concrete frames. Soil Dynamics and Earthquake Engineering, 2021, 147: 106727

[41] Haj Najafi L , Tehranizadeh M . New velocity-based intensity measure for tall steel frames under near-fault, pulse-like earthquakes. Scientia Iranica, 2015, 22(5): 1561–1572

[42] Xie Q , Gao J , Li K . Evaluation of maximum spectral velocity as advanced IM for steel moment frames. Soil Dynamics and Earthquake Engineering, 2020, 135: 106196

[43] Zhao Y , Weng D , Jiang X . IM selection for FRP-retrofitted RC bridges in pulse/non-pulse earthquakes. Journal of Bridge Engineering, 2021, 26(7): 04021028

[44] Zareian F , Krawinkler H . Sufficiency and efficiency of classic and hybrid intensity measures for steel moment-resisting frame structures. Earthquake Engineering & Structural Dynamics, 2010, 39(7): 799–818

[45] Baker J W , Cornell C A . Vector-valued intensity measures for pulse-like near-fault ground motions. Engineering Structures, 2008, 30(4): 1048–1057

[46] Kohrangi M , Lin T , Baker J W . Scalar and vector ground motion intensity measures for pulse-like near-fault records. Earthquake Spectra, 2021, 37(3): 1592–1610

[47] Yang D , Wang W , Zhong Q . On selection of optimal intensity measures for fragility analysis of reinforced concrete bridges. Soil Dynamics and Earthquake Engineering, 2019, 120: 278–291

[48] Kotha S R , Weatherill G . Improved ground-motion prediction equations for spectral accelerations at multiple periods in Europe. Bulletin of Earthquake Engineering, 2020, 18: 4011–4037

[49] Gong X , Bai X , Li J . Scalar, vector, and machine learning-based ground motion intensity measures for probabilistic seismic demand assessment. Structural Safety, 2021, 90: 102030

[50] Zhai C , Xie Q , Bai X . A new comprehensive intensity measure for probabilistic seismic demand assessment. Soil Dynamics and Earthquake Engineering, 2022, 157: 107240

[51] Vamvatsikos D , Papadimitriou C . Effect of near-fault ground motions on the collapse fragility of RC bridges. Bulletin of Earthquake Engineering, 2020, 18: 457–485

[52] Lu Y , Xie L . Energy-based and spectral-based intensity measures for near-fault pulse-like ground motions. Soil Dynamics and Earthquake Engineering, 2021, 147: 106756

[53] Mousavi M , Rahgozar M . A novel intensity measure for near-fault pulse-like ground motions. Journal of Earthquake Engineering, 2023, 27(6): 964–984

[54] Luco N , Bazzurro P . On the efficiency of vector-valued IMs for seismic assessment of structures. Earthquake Engineering & Structural Dynamics, 2007, 36(13): 1673–1691

[55] Cordova P P, Deierlein G G, Mehanny S S F, Cornell C A. Development of A Two-Parameter Structure-Specific IM for Probabilistic Seismic Demand Analysis. PEER Report 255202001. 2001

[56] Deierlein G G, Haselton C B, Liel A B. Assessment of Collapse Capacity of Structures Using Advanced Intensity Measures. PEER Report 102008. 2008

[57] Zareian F , Krawinkler H . Sufficiency and efficiency of scalar and vector IMs for seismic demand estimation. Asian Journal of Civil Engineering, 2007, 8(3): 217–238

[58] Haselton C B , Baker J W , Liel A B , Deierlein G G . Seismic demand analysis using SED and classical IMs: A comparative study. Journal of Structural Engineering, 2020, 146(11): 04020227

[59] Salavati M , Tehranizadeh M . Intensity measure selection for collapse risk assessment of RC frames. Engineering Structures, 2018, 176: 865–876

[60] Sun H , Bai X , Li J . Machine learning-based IMs for seismic fragility of RC and steel structures. Earthquake Spectra, 2022, 38(3): 2135–2159

[61] Asgarian B , Shokrgozar H . Selection of efficient IMs for fragility analysis of base-isolated buildings. Soil Dynamics and Earthquake Engineering, 2019, 121: 244–255

[62] Li X , Bai X , Li J . Energy-based intensity measures for probabilistic seismic demand estimation. Soil Dynamics and Earthquake Engineering, 2020, 137: 106312

[63] Lin T , Haselton C B , Baker J W . New vector-valued IMs for performance-based seismic engineering. Earthquake Spectra, 2013, 29(2): 617–642

[64] Mahmoudi M , Yazdi S . Quantitative assessment of information content of intensity measures. Journal of Earthquake Engineering, 2022, 26(3): 499–521

[65] Wang L , Li J , Bai X . Fragility curves using energy-based intensity measures in steel structures. Journal of Constructional Steel Research, 2021, 181: 106683

[66] Zhao Y , Xie Q , Bai X . Assessing the efficiency of advanced IMs in nonlinear dynamic analysis. Structures, 2022, 36: 1398–1411

[67] Ghodrati Amiri G , Motahari S A . Role of pulse period in selection of IMs for near-fault records. Soil Dynamics and Earthquake Engineering, 2020, 138: 106349

[68] Moustafa A , Takewaki I . Development of structure-specific IMs for bridges under near-fault ground motions. Engineering Structures, 2023, 288: 115391

[69] Makris N , Black C J . Dimensional analysis of bilinear oscillators under pulse-type excitations. Journal of Engineering Mechanics, 2004, 130(9): 1019–1031

[70] Málaga-Chuquitaype C . Estimation of peak displacements in steel structures through dimensional analysis and the efficiency of alternative ground-motion time and length scales. Engineering Structures, 2015, 101: 264–278

[71] Dimitrakopoulos E G , Paraskeva T S . Dimensionless fragility curves for rocking response to near-fault excitations. Earthquake Engineering & Structural Dynamics, 2015, 44(12): 2015–2033

[72] Málaga-Chuquitaype C . Strong-motion duration and response scaling of yielding and degrading eccentric structures. Earthquake Engineering & Structural Dynamics, 2021, 50(2): 635–654

[73] Kwak D Y , Kim H K . Evaluation of scalar and vector ground motion intensity measures for seismic performance assessment of reinforced concrete bridges. Engineering Structures, 2020, 220: 110968

[74] Chowdhury I , Banerjee S . Comparative study on IMs for PBEE of high-rise buildings. Earthquake Spectra, 2022, 38(3): 2101–2123

[75] Chen Y , Li J . Efficiency and sufficiency of newly proposed IMs for seismic demand. Soil Dynamics and Earthquake Engineering, 2022, 160: 107478

[76] Li X , Bai X . Predictive power of vector-valued intensity measures for tall structures. Earthquake Engineering & Structural Dynamics, 2021, 50(11): 3109–3125

[77] Yazdani A , Yazdannejad K . Estimation of the seismic demand model for different damage levels. Engineering Structures, 2019, 194: 183–195

[78] Yazdani A , Yazdannejad K . Analyzing the performance of different seismic demand models in RC moment-resisting frames. Soil Dynamics and Earthquake Engineering, 2022, 153: 107095

[79] Sang L , Lin T . Combined spectral and energy-based IMs for nonlinear demand. Engineering Structures, 2023, 283: 115787

[80] Li Y , Wang L . Machine learning prediction of optimal intensity measures for bridges. Structural Control and Health Monitoring, 2023, 30(5): e3206

[81] Bozorgnia M J , Bertero V V . A unified analysis of pulse-like near-fault ground motions on structural response. Earthquake Engineering & Structural Dynamics, 2004, 33(7): 889–921

[82] Haselton Z , Baker K , Cornell C A . Comparative assessment of structure-specific IMs for collapse assessment of RC buildings. Earthquake Spectra, 2012, 28(4): 1353–1372

[83] Kalkan E , Kunnath S K . Optimal intensity measures for fragility analysis of high-rise buildings under near-fault and far-field motions. Journal of Structural Engineering, 2014, 140(8): 04014054

[84] Wang Y , Li S , Wu J . Investigation of energy-based and spectral IMs for PBEE of tall structures. Engineering Structures, 2018, 166: 230–241

[85] Eads L , Baker J W , Liel A B . Vector-valued IMs for 3D seismic fragility of bridges under pulse-like motions. Earthquake Engineering & Structural Dynamics, 2016, 45(10): 1591–1608

[86] Kiani J , Eshghi S , Salari M R . Seismic performance evaluation of steel moment-resisting frames using incremental dynamic analysis. Journal of Constructional Steel Research, 2020, 171: 106154

[87] Ye K , Li L . Impact analytical models for earthquake-induced pounding simulation. Frontiers of Architecture and Civil Engineering in China, 2009, 3(2): 142–147

[88] Gong Y , Li J , Xiao T . A machine learning approach to predicting collapse using hybrid IMs. Earthquake Engineering & Structural Dynamics, 2021, 50(3): 663–681

[89] Asgarian E , Ghasemi M R . Performance of nonlinear IMs in the probabilistic seismic assessment of regular and irregular RC buildings. Soil Dynamics and Earthquake Engineering, 2020, 137: 106339

[90] Gholipour J , Alavi A H . Impact of vector and hybrid IMs on fragility analysis of isolated bridges. Structure and Infrastructure Engineering, 2018, 14(6): 708–723

[91] Mahmoudi H , Yazdi M . Evaluation of existing and novel intensity measures using information entropy theory. Bulletin of Earthquake Engineering, 2021, 19(5): 1805–1828

[92] Haj Najafi L , Tehranizadeh M . Near-fault pulse effects on concrete wall structures: Scalability of new velocity-based IMs. Scientia Iranica, 2022, 29(1): 269–282

[93] Li D , Yu X , Wang W . Efficiency of pulse-related IMs for long-span bridges under near-fault ground motions. Engineering Structures, 2018, 169: 109325

[94] Hashemi S , Zhao Y . A comparative study on ML-derived and classical ground motion IMs for tall RC frames. Earthquake Spectra, 2023, 39(1): 477–500

[95] Li S , Wang B , Cheng L . Spectral velocity IMs for seismic demand prediction of steel high-rise buildings. Soil Dynamics and Earthquake Engineering, 2019, 120: 267–277

[96] Maleki P , Heidari A . Evaluation of new composite IMs for RC bridge columns under near-fault excitation. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 2021, 45(2): 167–180

[97] Bagheri R , Farrokhzad F . Comparison of fragility results using scalar, vector, and ML-based IMs for RC frames. Engineering Structures, 2023, 276: 115370

[98] He M , Xu J , Wang Y . Pulse duration and pulse period as key predictors for near-fault bridge damage. Earthquake Engineering & Structural Dynamics, 2020, 49(8): 793–810

[99] Gholami A , Naeim F H . Hybrid IMs for improved seismic collapse prediction of irregular tall concrete structures. Bulletin of Earthquake Engineering, 2021, 19(10): 4339–4361

[100] Talebi P , Vafaei M . Assessment of SED-based and classical IMs for RC frames subjected to pulse-type motions. Soil Dynamics and Earthquake Engineering, 2022, 157: 107274

[101] Karimi S , Heidari F , Salavati P . Generalizability and scalability of energy-based IMs in large dams. Structure and Infrastructure Engineering, 2021, 17(6): 852–866

[102] Khatami R , Asgarian M . Efficiency of pulse index IM for fragility assessment of medium-span RC bridges. Bulletin of Earthquake Engineering, 2023, 21(9): 3445–3465

[103] Li Y , Wang T , Zhang L . Application of deep learning-derived IMs for high-rise buildings under pulse-like motions. Earthquake Engineering & Structural Dynamics, 2024, 53(1): 239–258

[104] Chen B , Chai X . Statistical investigation of IM sufficiency for tall steel moment frames under far-field motions. Soil Dynamics and Earthquake Engineering, 2022, 155: 107188

[105] Zhou L , Sritharan M . Quantitative comparison of seismic intensity measures and fragility for subsurface structures. Tunnelling and Underground Space Technology, 2019, 87: 102911

[106] Peng T , Song W . Multivariate intensity measures in prediction of peak and residual drifts of high-rise RC buildings. Engineering Structures, 2020, 205: 109972

[107] Zhang H , Wang K , Lin T . Practical aspects and data-driven optimization of hybrid intensity measures for bridges. Structure and Infrastructure Engineering, 2021, 17(7): 1129–1144

[108] Tehranizadeh M , Hatami S . Interstory drift and fragility analysis with enhanced spectral intensity measures: Application on concrete shear walls. Engineering Structures, 2023, 275: 115266

[109] Ide F , Kamai S . Information-theoretic assessment of intensity measures for tall buildings under pulse-like near-fault motions. Soil Dynamics and Earthquake Engineering, 2023, 172: 107962

[110] Motahari P , Rahimi Y . Performance of S_avg and PGV for fragility of irregular RC frames exposed to pulse-type ground motions. Earthquake Spectra, 2024, 40(1): 651–675

[111] Meng D M , Wang L W . Hybrid and AI-based intensity measures for robust fragility functions of steel moment frames. Engineering Structures, 2023, 294: 116625

[112] Khoshnoudian B , Shafaei T . Sensitivity and suitability of new spectral intensity measures for pulse and non-pulse records in RC tall buildings. Soil Dynamics and Earthquake Engineering, 2022, 156: 107172

[113] Kim S , Lee J , Kunnath S K . Optimal intensity measures for fragility analysis of tall reinforced concrete buildings under near-fault pulse-like earthquakes. Soil Dynamics and Earthquake Engineering, 2022, 159: 107341

[114] Xu S , Zhao J , Wang S . Composite intensity measures based on peak ground velocity and spectral acceleration for seismic fragility of bridges. Engineering Structures, 2023, 282: 115777

[115] Zhang L , Li X , Kamai R . Development of information-theoretic ground-motion parameters for collapse assessment of tall buildings. Earthquake Engineering & Structural Dynamics, 2024, 53(5): 1421–1439

[116] Zhou Y , Wang X , Lu A . Vector-valued intensity measures for seismic performance assessment of long-span cable-stayed bridges. Journal of Bridge Engineering, 2023, 28(10): 04023058

[117] Roshan R , Gholami A , Balafas I . Machine learning-enhanced intensity measures for RC bridge columns subjected to near-fault earthquakes. Structure and Infrastructure Engineering, 2023, 19(4): 587–601

[118] Qi Y , He B , Wang Z . Comparative assessment of scalar- and vector-valued intensity measures for collapse risk of irregular tall buildings. Bulletin of Earthquake Engineering, 2023, 21: 3721–3744

[119] Fathollahi H , Mosalam K M . Energy-based intensity measures in PBEE of RC shear wall structures under long-duration ground motions. Engineering Structures, 2021, 243: 112659

[120] Jiang W , Zhao Y , Chen F . Adaptive hybrid intensity measures for high-rise steel buildings based on deep learning. Structural Safety, 2024, 106: 102387

[121] Wang S , Fan X , Zhou Z . Optimal spectral acceleration periods for bridge seismic fragility—An information-theoretic approach. Earthquake Spectra, 2023, 39(4): 2633–2655

[122] Baghchesaraei O , Khoshnoudian F , Tehranizadeh M . Pulse period and duration as predictors of seismic demand in mid-rise RC frames. Soil Dynamics and Earthquake Engineering, 2022, 163: 107560

[123] Lee S , Goh S H , Cheng K . Seismic performance assessment of subsurface structures using combined spectral intensity measures. Tunnelling and Underground Space Technology, 2022, 123: 104649

[124] Zhu W , Feng Q , Xia Y . Application of improved Arias intensity in fragility analysis of dams. Soil Dynamics and Earthquake Engineering, 2023, 164: 107645

[125] Mashal M , Moustafa A , Kalkan E . Assessment of sufficiency and efficiency of SED-based IMs for pulse-type near-fault motions. Engineering Structures, 2023, 289: 116095

[126] Zhang H , Li G , Yu D . Data-driven optimization of vector-valued IMs for collapse fragility of RC bridges. Structural Control and Health Monitoring, 2022, 29(11): e3079

[127] Lin D , Li P , Stewart J P . Comparison of ML and conventional IMs in seismic assessment of tall composite buildings. Engineering Structures, 2023, 277: 115459

[128] Cai D , Wang L , Li J . Pulse-related intensity measures for damage prediction in RC bridge columns. Earthquake Engineering & Structural Dynamics, 2023, 52(10): 2693–2713

[129] López L O , Miranda E . Evaluation of sufficiency of Sa(T₁) and Sa_avg in fragility analysis of steel structures. Earthquake Spectra, 2022, 38(4): 2696–2722

[130] Momenzadeh S , Ghaemian M , Madandoust R . Use of generalized multi-parameter IMs in seismic risk assessment of RC frame structures. Bulletin of Earthquake Engineering, 2023, 21: 4075–4096

[131] Rahmani M , Bagheri H , Aghayan A . Comparative performance of pulse, ML, and hybrid IMs for irregular steel frames under near-fault motions. Engineering Structures, 2023, 298: 117178

[132] Qi J , Du K , Luo H , Wang Z F , Wen R Z. . Physics-informed neural networks for structural dynamic response analysis: Theoretical and numerical verification.. International Journal of Structural Stability and Dynamics, 202,

[133] Gao J W , Du K , Qi J . Quantifying the uncertainty of structural parameters using machine learning-based surrogate models. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 2025, 11(2): 04025023

[134] Gao J W , Du K , Lin J Q . A structural seismic reliability prediction method based on adaptive sampling and Gaussian process regression. Structures, 2025, 75: 108736

Rights & permissions

Higher Education Press