Implementation schemes for avoiding artifact discontinuities in simulated annealing

The simulated annealing algorithm has been applied successfully to conditional simulation of categorical variables (e.g., rock or facies units) with the objective of improving the match between measured and modeled spatial variability. In some implementation schemes, however, spurious features termed ''artifact discontinuities'' may occur near conditioning data, especially during the ''zero-temperature'' case referred to as simulated quenching. This paper shows that artifact discontinuities can be avoided by considering the anisotropy of the spatial variability model, reducing the number of lag vectors used in the objective function, and providing a rudimentary initial configuration. Results from several test cases suggest that the artifact discontinuities might be caused by overly precise fitting of measured to modeled spatial variability.