A neural network-based ground motion model trained on ground motion simulations in NZ (2020)
Type of ContentConference Contributions - Published
Probabilistic seismic hazard analysis (PSHA) based on physics-based simulations offers many advantages compared to more traditional empirical Ground Motion Model (GMM) based PHSA. However when a large number of seismic sources is considered, such as distributed seismicity, simulation based PHSA becomes unfeasible due to the high computational cost associated with simulations. Utilising a surrogate model, such as an artifical neural network, gives the physics-based simulation advantages without the associated computational cost. Additionally it provides an extra avenue for investigating simulation results.
CitationSchill C, Thomson E, Bradley B, Lee R (2020). A neural network-based ground motion model trained on ground motion simulations in NZ. Nelson, New Zealand: QuakeCoRE Annual Meeting.
This citation is automatically generated and may be unreliable. Use as a guide only.
ANZSRC Fields of Research37 - Earth sciences::3706 - Geophysics::370609 - Seismology and seismic exploration
RightsAll rights reserved unless otherwise stated
Showing items related by title, author, creator and subject.
A 3D seismic velocity model for Canterbury, New Zealand for broadband ground motion simulation Lee, R.L.; Bradley, Brendon; Ghisetti, F.; Pettinga, J.R.; Hughes, M.W.; Thomson, E.M. (University of Canterbury. Civil and Natural Resources Engineering, 2014)This poster presents the on-going development of a new 3D seismic velocity model of Canterbury, New Zealand. The intention of the model is to provide the 3D crustal structure in the region at multiple length scales for ...
A neural network for ground motion quality classification from New Zealand earthquakes of variable magnitudes and tectonic types Dupuis M; Schill C; Lee R; Bradley, Brendon (2020)
Modeling nonlinear site effects in physics-based ground motion simulation Bradley, Brendon; de la torre C (2017)This study examines the performance of nonlinear total-stress wave-propagation site response analysis for modelling site effects in physics-based ground motion simulations of the 2010-2011 Canterbury, New Zealand ...