Scribd
Upload
324 views

Geostatistics Lesson 1

The document provides information on geostatistics, including: 1. An outline of topics covered in geostatistics such as univariate statistics, variogram estimation, and kriging. 2. Motivations for learning geostatistics, which is used in mining industry for resource estimation and provides the best weighting for reserve estimation. 3. A definition of geostatistics as the application of probabilistic methods to regionalized variables displayed in real space.

Uploaded by

Budi Pratama
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
324 views

Geostatistics Lesson 1

The document provides information on geostatistics, including: 1. An outline of topics covered in geostatistics such as univariate statistics, variogram estimation, and kriging. 2. Motivations for learning geostatistics, which is used in mining industry for resource estimation and provides the best weighting for reserve estimation. 3. A definition of geostatistics as the application of probabilistic methods to regionalized variables displayed in real space.

Uploaded by

Budi Pratama
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 25

GEOSTATISTICS

C R E D I T: 3

RECIPE FOR SUCCESS GEOSTATISTICS


1.Prepare for lectures
attempt assigned reading before class
be active in class (paying attention to lecture is more
important than taking exacting notes)
2.Come to lecture
Dont late for this class. (only 10-minute delay tolerance)
3.Attendance should be more than 75%
4.Do homework
best way to prepare for exam is by doing problems
5.Discuss and explore material with classmates
6.If you have questions, get them answered
7.Come to office hours when you need help

OUTLINE
Introduction
Univariate Statistics
Bivariate Statistics
Multivariate Statistics
Estimation
Variogram
Kriging, Co-Kriging
Application of Geostatistics in Mineral
Exploration

REFERENCES
1. Edwar H. Isaak dan R. Mohan Srivastava, Applied
Geostatistics, Oxford University Press, 1989
2. Friedrich-Wilhelm Wellmer, Statistical Evaluations
in Exploration for Mineral Deposits, Springer,
1989
3. Ricardo A. Olea, Geostatistics for Engineer and
Earth Scientist, Springer Science+Businees
Media, 1999

ASSESSMENT

Final exam
: 20%
Mid-term exam
: 20%
Quiz + Homework + Presentation
Practicum
: 20%

: 40%

MOTIVATION
WHY LEARN ABOUT GEOSTATISTICS?
Since introduced by D. Krige (1955) and G. Matheron (1960),
geostatistics have been widely used in mining industry for resource
and reserve estimation.
Geostatistical analysis provides a powerful tool for enhancing the
prediction and decision making capabilities of mine planners and
geologists.
The experimental semivariogram provides the only measure of whether
a deposit, or part of a deposit, is best analyzed using geostatistical
methods or whether classical statistics would suffice.
Geostatistics provides the best possible weighting for samples used in
reserve estimation so as to produce the lowest possible error of
estimation.
Computerized simulation of in situ coal quality for improving predictions
of the variability of coal qualities have been identified as the most
significant parameters affecting coal supply (Whateley, 2002).

GEOSTATISTICS???

Prof. Matheron (1960):


Geostatistics has been
defined as "the application
of probabilistic methods to
regionalized variables",
which designate any
function displayed in a real
space.

BASIC STATISTICS
Univariate
Statistics
Analysis on
single variable
without
considering
their location.
The data is
assumed to be
a random
variable.

Bivariate
Statistics

Spatial
Statistics

Analysis on two
different
variables
located in the
same location.

Analysis on a
variable with
considering the
spatial aspect
of data. It can
be applied for
natural
phenomena, by
assuming that
the data is a
random
function

UNIVARIATE STATISTICS
LESSON 1

Frequency
tables &
histograms

Measures
of locations

Box plots
UNIVARIAT
E
STATISTICS

Measures
of shape

Measures
of
dispersion

A POROSITY DATASET

FREQUENCY TABLES & HISTOGRAM

Look for the min & max values


Divide the range of values into certain intervals (bins)
Count the number of data fall within each interval (bin)
Make a frequency table
Make a histogram by plotting the data in the frequency
tables

CUMULATIVE PLOTS
Given a frequency table:
Add the number of data which are smaller than a
given value
Divide the number of data by the total number of data
Make a cumulative frequency table
Make a cumulative histogram

MEASURES OF LOCATIONS

MEASURES OF DISPERSION

The Variance is defined as:


The average of the squared differences
from the Mean.
The Standard Deviation is a
measure of how spread out
numbers are

The coefficient of variation represents the ratio of the standard deviation to the mean,
and it is a useful statistic for comparing the degree of variation from one data series to
another, even if the means are drastically different from each other.

MEASURES OF SHAPE

UNIMODAL VS BIMODAL VS POLYMODAL


Mode is used to describe a local
maximum in a chart. It does not
refer to the most frequently
appearing score (as in the central
tendency mode). Rather, a local
maximum is a high point in a
chart. The local maxima are the
points where the score frequencies
stop increasing and begin
decreasing.
Unimodal distributions have one
peak or mode.
Bimodal distributions have two
modes
Polymodal distributions have
three or more local maxima

SYMMETRIC

SUMMARY STATISTICS

BOX PLOTS
The box plot (box and whisker diagram) is a
standardized way of displaying the distribution of
data based on the five number summary: minimum,
first quartile, median, third quartile, and maximum.

BOX PLOTS

BOX PLOTS: EXAMPLE

EXAMPLE
Draw a boxplot with outliers to show the number of hours spent on a
project by individual students in a particular school.
2 3 4 9 9 13 19 24 27 35 36
37 40 48 56 59 71 76 86 90 92 97
102 102 108 111 146 147 147 166 181 226 264
Solution:
1. The data are already given in order. From this ordered list, find
the median, Q1 and Q3, and hence find the interquartile range.
There are 33 values, so Q1 is halfway between the 8th and 9th
values and Q3 is halfway between the 25th and the 26th values.

EXAMPLE
2. To find the lower limit for outliers, calculate
Q1 1.5 IQR
3. To find the upper limit for outliers, calculate
Q3 + 1.5 IQR
4. Check the data to see if there are any values
outside these limits. If there are then these will be
classified as outliers and will be denoted with
circles in the boxplot.

EXAMPLE
5. Find the largest value which is not an outlier. The
right hand whisker of the boxplot will finish at this
value.
6. The boxplot can now be constructed as shown.

You might also like