Empirical Evaluation of Aleatory and Epistemic Uncertainty in Eastern Ground Motions

Horizontal-component response spectra data for ground motions recorded on hard-rock sites in eastern North America (ENA) are used to explore the aleatory and epistemic uncertainty in ground-motion prediction equations (GMPEs). An all-station sigma, expressing the total calculated scatter of values about a GMPE, ranges from 0.25 to 0.29 log(10) unit. Single-station sigmas, in which the scatter is evaluated station by station relative to a regional GMPE, average in the range of 0.23-0.28. The scatter of observations about site-specific GMPEs (GMPEs developed from multiple events recorded at a single station), which comes the closest to measuring the actual aleatory variability, has average values of 0.22-0.26. Overall, aleatory variability of ground motions in ENA is no larger than that for California, at least for moderate events recorded on hard-rock sites. Epistemic uncertainty is considered by looking at the standard deviation of GMPEs developed separately for each station (i.e., the scatter of predictions rather than the scatter of observations). This exercise suggests that the overall epistemic uncertainty in ENA GMPEs should be at least 0.15 log unit (as a standard deviation of the median GMPEs) in the magnitude distance range in which the prediction equations can be anchored by empirical data (magnitude <5.5, distances >50 km). It should be larger than 0.15 unit at large magnitudes and close distances.