- [Voiceover] Let's study geostatistics definition, geostatistics basic contents, geostatistics coverages, and at the end, we'll make a summary. We will go through some selected geostatistics definitions From Wikipedia, "Geostatistics is a branch of statistics "focus on spatial or spatiotemporal datasets. "Developed originally to predict probability distributions "of ore grades for mining operations, "it is currently applied in diverse disciplines "including petroleum geology." From Deutsch, "Geostatistics: a study of phenomena "what vary in space and/or time" From Olea, "Geostatistics can be regarded "as a collection of numerical techniques "that deal with the characterization of spatial attributes, "employing primarily random models in a manner similar "to the way in which time series analysis "characterizes temporal data." From Isaaks and Srivastava, "Geostatistics offers "a way of describing the spatial continuity "of natural phenomena and provides adaptations "of classical regression techniques "to take advantage of this continuity." Geostatistics basic contents include three parts. Variogram analysis, kriging, and stochastic stimulation. Variogram analysis is the characterization of spatial correlation. Kriging is the optimal interpolation. It generates best linear unbiased estimate at each location and employs variogram model. Stochastic stimulation generates multiple equiprobable images of the variable. It also employs variogram model. This is the reservoir model grid and variogram data based on that. So variogram can be computed after interpretating. A mathematical variogram can be obtained. Apply kriging method to the grid. Using data and the variogram model, a map can be generated. Apply sequential Gaussian simulation method to the grid using data on the variogram model. A number of maps can be generated. Here is a example of three maps. Input a data, which include core data, well log data, seismic data, dynamic data, and analog data. And also, input geological reservoir model. Essential statistics concepts will cover population versus sample, variables, univariate analysis, bivariate analysis, Q-Q plot and P-P plot, data transformation, data declustering, histogram and cumulative histogram, probability distribution and cumulative probability distribution, normal distribution, uniform distribution, central limit theory, and Monte Carlo simulation. Analysis of data spatial continuity will cover variogram calculation, variogram interpretation, horizontal variogram, removing data vertical trend, variogram modeling, indicator variogram, cross variogram, and multiple points statistics. Kriging methods will cover simple kriging, ordinary kriging, kriging with trend, kriging with external drift, block kriging, cokriging and collocated cokriging, Bayesian kriging, and indicator kriging. Simulation methods will cover, sequential Gaussian simulation, sequential indicator simulation, unconditional sequential Gaussian simulation, unconditional sequential indicator simulation, truncated Gaussian simulation, P field simulation. Post processing will cover fill property holes, smooth properties, upscale and downscale properties. QC results will cover view models, check assigned data are honored, check input statistics parameters and distribution are honored, check input variogram model is honored, check input bivariate correlation is honored, check vertical summary is honored, check multiple point realizations. This talking about cross validation and jackknife. Uncertainly management will cover uncertainty considerations, number of simulation realizations, summarizing uncertainty, ranking realizations, selecting realizations. Special topics will cover object-based modeling, multipoint geostatistics, simulated annealing, classification, and search strategy. Let's make a summary for this lecture. Geostatistics is a branch of statistics focused on spatial or spatiotemporal datasets. Geostatistics mainly includes variogram, kriging, and simulation. Subtopics which will be addressed in the following lectures are listed in this lecture.