Evaluation of Bio-Inspired Algorithms in Cluster-Based Kriging Optimization

Kriging is one of the most used spatial estimation methods in real-world applications. In kriging estimation, some parameters must be estimated in order to reach a good accuracy in the interpolation process, however, this step is still a challenge. Various optimization methods have been tested to find good parameters to this process, however, in recent years, many authors are using bio-inspired techniques and reaching good results in estimating these parameters. This paper presents a comparison between well-known bio-inspired techniques such as Genetic Algorithms, Differential Evolution and Particle Swarm Optimization in the estimation of the essential kriging parameters: nugget, sill, range, angle, and factor. We also proposed an improved cluster-based kriging method to perform the tests. The results shows that the algorithms have a similar accuracy in estimating these parameters, and the number of clusters have a high impact on the results.