When MCMC methods for Bayesian spatiotemporal modeling are applied to large geostatistical problems, challenges arise as a consequence of memory requirements, computing costs, and convergence monitoring. This article describes the parallelization of a reparametrized and marginalized posterior sampling (RAMPS) algorithm, which is carefully designed to generate posterior samples efficiently. The ...

Reservoir model needs to be constrained by various data, including dynamic production data. Reservoir heterogeneities are usually described using geostatistical approaches. Constraining geologicaljgeostatistical mode! realizations by dynamic data is generally performed through history matching, which is a complex inversion process and requires a parameterization of the geostatistical realizatio...

Being able to provide a quick and accurate pollutant maps from readings at isolated measurement stations is becoming more important today in light of the European norms on air quality and the public’s demand to be informed. Commonly used algorithms for cartography are quick but their accuracy remains to be determined. Firstly, the choice of method is arbitrary and based on user's subjective per...

The development of geostatistics has been mostly accomplished by application-oriented engineers in the past 20 years. The focus on concrete applications gave birth to many algorithms and computer programs designed to address different issues, such as estimating or simulating a variable while possibly accounting for secondary information such as seismic data, or integrating geological and geomet...

One of the most challenging aspects multivariate geostatistics is dealing with complex relationships between variables. Geostatistical co-simulation and spatial decorrelation methods, commonly used for modelling multiple variables, are ineffective in presence complexities. On other hand, multi-Gaussian transforms designed to deal relationships, such as non-linearity, heteroscedasticity geologic...

Two geostatistical methods for history matching are presented. Both rely on the sequential simulation principle for generating geologically sound realizations. The first method relies on perturbing the sequential simulation through the perturbation of the conditional distribution models; the second method relies on the perturbation of random numbers. We show that both approaches are general in ...

Multiple-point statistics are used in geostatistical simulation to improve forecasting of responses that are highly dependent on the reproduction of complex features of the phenomenon that cannot be captured by conventional two-point simulation methods. Inference of multiple-point statistics is often based on a training image that depicts the features that provide the character to the geologica...