Space Regression Analysis on Geochemical Data by the GEP Evolutionary Model Based on Kriging

Abstract

There are several approaches to handle spatial trends: Kriging, stochastic simulation models, fractal and so on. The paper presents some contemporary approaches to spatial data analysis. The main topics are concentrated on the problems of space regression analysis by geochemical exploration data modeling. The innovative part of the paper presents integrated/hybrid model-combine GEP evolution modeling with spatial structure analysis. The models are based on GEP evolution modeling algorithm. Geostatistical tools on the basis of spatial autocorrelation thesis are used to extract representative data to fully utilize spatial structural information and weaken the influence of noise. Case study from mineral deposits in Gejiu illustrates the performance of the proposed model and BP neural network model is chosen as comparative study. It is shown that the fitting of the model and precision of test, provided by the combination of GEP evolution modeling and geostatistical model based approaches, are obviously improved.KeywordsSpatial DistributionGEPKrigingSpatial Autocorrelation