An equation-discovery approach to earthquake-ground-motion prediction

Authors:
ŠTefan Markič;Vlado Stankovski
Affiliations:
Faculty of Civil and Geodetic Engineering, University of Ljubljana, Jamova cesta 2, SI-1000 Ljubljana, Slovenia;Faculty of Civil and Geodetic Engineering, University of Ljubljana, Jamova cesta 2, SI-1000 Ljubljana, Slovenia
Venue:
Engineering Applications of Artificial Intelligence
Year:
2013

Citing 7
Cited 0

Declarative Bias in Equation Discovery

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Using Domain Knowledge on Population Dynamics Modeling for Equation Discovery

EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Grid-enabling data mining applications with DataMiningGrid: An architectural perspective

Future Generation Computer Systems
Digging Deep into the Data Mine with DataMiningGrid

IEEE Internet Computing
A hybrid computational approach to derive new ground-motion prediction equations

Engineering Applications of Artificial Intelligence
Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing

Computers and Structures
Computational Models of Learning

Computational Models of Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In active seismic regions an earthquake's peak ground acceleration (PGA) is required information when designing a building. In this study we employ the state-of-the-art, Lagramge, equation-discovery system to induce an equation that is suitable for modeling the PGA and investigate its applicability. In contrast to traditional modeling techniques the Lagramge system does not presume the structure of the equation and then identify the parameter values; instead, it finds the equation's structure as well. From the large amount of background knowledge on earthquake engineering we formalize a context-free grammar, which is then used as a guideline for the equation-building procedure. The PF-L data set used for the experiments is taken from the study of Perus and Fajfar (2010), which is based on the data sets of Chiou et al. (2008) in the project Next Generation Attenuation of Ground Motion and the study of Akkar and Bommer (2010). The best model derived from the grammar is then quantitatively and qualitatively evaluated and compared. The presented results support the proposal to use an equation-discovery tool as an aid to the PGA modeling work and to potentially contribute new knowledge to the field of earthquake engineering.