Stochastic inversion based on spectral simulation of non-stationary statistical characteristic parameters

Abstract

Abstract The traditional method of constructing the prior model for stochastic inversion mainly uses well-logging data to obtain the stationary range from the variogram to characterize the complex non-stationary spatial tectonic features of the subsurface layers. Unfortunately, it is hard for the stationary range to precisely describe the complex non-stationary spatial tectonic features of the subsurface layers. The established prior model is also difficult to describe the real spatial tectonic features of the subsurface media; thus, it cannot provide reliable prior information for the inversion. Therefore, according to the theory of random media, we extract the non-stationary statistical characteristic parameters that change with spatial coordinates from the known information such as seismic and well-logging data, to accurately and reliably characterize the non-stationary spatial tectonic of the subsurface media. Then, combined with FFT-MA spectral simulation, a spectral simulation method based on non-stationary statistical characteristic parameters is built to construct the spectral simulation results that can more accurately conform to the spatial tectonic features of the subsurface media, to provide reliable and reasonable geostatistical prior information for a better inversion result.