AIM3 - SENSE AND SENSIBILITY OF MACHINE LEARNING IN NATURAL HAZARDS ENGINEERING |
THURSDAY | ||||||||
AMBER 2 | Convenors: N. Bijelic, H. Burton, Y. Xie | ||||||||
09:00 - 09:12 | INTELLIGENT LEARNING PARADIGMS TO ENABLE ADAPTABLE SEISMIC FRAGILITY AND RESTORATION MODELS R. Rincon, J.E. Padgett | |||||||
09:12 - 09:24 | INTEGRATING AUTOMATION AND SURROGATE MODELING FOR HIGH-FIDELITY REGIONAL SEISMIC RISK ASSESSMENT L. Dahal, H. Burton | |||||||
09:24 - 09:36 | ESTIMATING THE DYNAMIC RESPONSE OF STRUCTURES USING RECURRENT NEURAL NETWORKS Z. Kasi, B. Simpson, M. Scott | |||||||
09:36 - 09:48 | DEEP LEARNING FOR GROUND MOTION GENERATION, SEISMIC RESPONSE PREDICTION, AND FRAGILITY ASSESSMENT T. Xie, C. Ning | |||||||
09:48 - 10:00 | HAZARD-CONSISTENT COLLAPSE RISK ASSESSMENT OF STEEL MOMENT RESISTING FRAMES USING SURROGATE MODELS N. Bijelic, A. Skiadopoulos, D. Lignos | |||||||
10:00 - 10:12 | AN END-TO-END DEEP LEARNING VULNERABILITY MODEL FOR SEISMIC RISK ASSESSMENT L. Martins, V. Silva | |||||||
10:12 - 10:15 | DISCUSSION | |||||||
MONITOR 1 | Convenors: N. Bijelic, H. Burton, Y. Xie | ||||||||
10:30 - 10:42 | A FREQUENCY-BASED SITE FORECASTING METHOD USING DEEP LEARNING A. A. Torky, S. Ohno | |||||||
10:42 - 10:54 | PHYSICS-INFORMED NEURAL NETWORKS FOR 1D SITE RESPONSE ANALYSIS Y. Chen, D. Ji, C. Li, W. Wen, C. Zhai | |||||||
10:54 - 11:06 | A RANDOM FOREST-BASED GROUND MOTION MODEL FOR ITALY F. Di Michele, G. Lanzano, S. Sgobba | |||||||
11:06 - 11:18 | MEANET: MAGNITUDE ESTIMATION VIA PHYSICS-BASED FEATURES TIME SERIES, AND NEURAL NETWORKS J. Song, J. Zhu, S. Li, Q. Ma, H. Liu, D. Tao | |||||||
11:18 - 11:30 | ONE-DIMENSIONAL CONVOLUTIONAL NEURAL NETWORK-BASED LIQUEFACTION PREDICTION MODEL X. Long, R. Sun, T. Zheng, Y. Zhang | |||||||
11:30 - 11:42 | SOURCE DEPENDENCY OF SPECTRAL TRANSFER CHARACTERISTICS FOR REALTIME SPECTRAL FORECASTING S. Ohno, A. Torky | |||||||
11:42 - 11:45 | DISCUSSION | |||||||
MONITOR 2 | Convenors: N. Bijelic, H. Burton, Y. Xie | ||||||||
10:30 - 10:42 | BAYESIAN NEURAL NETWORKS BASED STRUCTURAL DEMAND SURROGATE MODELS FOR STEEL MOMENT FRAMES J. Fayaz, A. Zsarnoczay | |||||||
10:42 - 10:54 | ACCELERATING FINITE-ELEMENT STRUCTURAL ELASTIC DYNAMIC ANALYSIS USING GPU COMPUTING G.A. Araújo R., B.G. Simpson, M. Zhu, M.H. Scott | |||||||
10:54 - 11:06 | AN INTERPRETABLE MODEL TO PREDICT THE SEISMIC FAILURE MODE OF RC SHEAR WALLS Z. Tuna Deger, G. Taskin Kaya | |||||||
11:06 - 11:18 | LEVERAGING MACHINE LEARNING ALGORITHMS FOR REGRESSION ANALYSIS IN SHAKE TABLE DATA PROCESSING K. Erler, G. Mosqueda | |||||||
11:18 - 11:30 | STRUCTURAL RESPONSE PREDICTED BY NEURAL NETWORKS AND EXPLAINED BY STRUCTURAL DYNAMICS S. Gunay, I.K. Pang, K. Mosalam | |||||||
11:30 - 11:42 | ENHANCING NONLINEAR MODELING PARAMETERS OF RC COLUMNS USING MACHINE LEARNING TECHNIQUES H. Khodadadi Koodiani, E. Jafari, A. Matamoros | |||||||
11:42 - 11:45 | DISCUSSION |