Question

Geostatistics deviates from classic statistics in that Geostatistics is not tied to a population distribution model that assumes, for example, all samples of a population are normally distributed and independent from one another. Most of the earth science data (e.g., rock properties, contaminant concentrations) often do not satisfy these assumptions as they can be highly skewed and/or possess spatial correlation. a. Illustrate with the aid of diagram how and why any of such Earth Science data obtained from a given field would be skewed and possess spatial correlation. b. How would the spatial correlation property aid the Geostatistician in predicting the values of the unknown data points of a given field?

Answer 1

a)In geostatistics more often the closely spaced samples tend to be similar because each samples will be influenced by similar physical and chemical depositional or transport processes. On the other hand classic statistics examines the statistical distribution of a set of sampled data, geostatistics combines both the statistical distribution of the sample data and the spatial correlation among the sample data. Because of this difference, many earth science problems are more effectively solved using geostatistical methods.

b) Geostatistics predicts the possibliility of the spatial distribution of a given property. Those prediction are in the form of a map or a series of maps. There are two typres of prediction that is estimation and simulation. The estimation is based on both the sample data and also depends on  model that is identified as most accurate in representing the spatial correlation between the sample data. Whereas in simulation, using the model of spatial correlation many equally likely maps of the property distribution are produced.

Geostatistics transforms scattered data set from the field into a spatial map through estimion technique, it helps to create nonuniformity again and it is incorporated into numerical flow and transport modeling. On the other hand, by transforming a scattered data set into multiple spatial maps either through unconditional or conditional simulations techniques, it helps in evaluating the uncertainties on modeling due to the uncertain nature of each map.