Application of metaheuristic algorithms in prediction of earthquake peak ground acceleration

The seismic resilience of a structure has been evaluated using peak ground acceleration (PGA). Ground motion parameters such as source characteristics, local site conditions are used to forecast the PGA motion. This paper aims develop an Artificial Neural Network (ANN) based model predict PGA. Here, hypocentral distance ( R h y p o ${R}_{hypo}$ ), shear wave velocity V s 30 ${V}_{s30}$ and moment magnitude M w ${M}_w$ input parameters. uses 12,706 recordings from 283 earthquakes revised NGA-West2 database supplied by Pacific Engineering Research Centre. Among whole data, 70% data is set for training, 15% validation, testing network. value derived dataset 0.952, indicating excellent performance An extensive parametric study conducted with values, results indicate that increases decreases distance. predicted values present comparable those existing relationships in global database. generated ANN further verified comparing recorded actual event.