prediction of peak ground acceleration by the genetic programming

peak ground acceleration (pga) has still been considered one of the important factor that plays the significant role on the earthquake-induced damageof structures. thus, prediction of the pga and selection of appropriate ground motion models often have become a valuable topic for seismic hazard assessments. with using some strong ground motion from iran prediction of gpa by applying genetic programming is scrutinized in this study. the proposed gp models are based on the most reliable database compiled for earthquakes in silakhor plain, lorestan, iran. in gp modeling processes, frequency and the earthquake source to site distance are considered as inputs and pga values as the output consequently. the results show that, the obtained results represent the appropriate performance genetic programming in the estimation of the pga and the consistency between the observed pga values and the predicted ones by the gp models yield relatively high correlation coefficients (r=0.80).