Geography 625
Intermediate
Geographic Information Science
Week 13: The Statistics of Fields
Instructor: Changshan Wu
Department of Geography
The University of Wisconsin-Milwaukee
Fall 2006
University of Wisconsin-Milwaukee
Geographic Information Science
Outline
1. Introduction
2. Review of Regression
University of Wisconsin-Milwaukee
Geographic Information Science
1. Introduction
Problems
1) No environmental measurements can be made without error. It is ill-
advised to try to honor all the observed data without recognizing the
inherent variability
University of Wisconsin-Milwaukee
Geographic Information Science
1. Introduction
University of Wisconsin-Milwaukee
Geographic Information Science
1. Introduction
1. Introduction
Kriging (ArcGIS)
University of Wisconsin-Milwaukee
Geographic Information Science
1. Introduction
Kriging (ArcGIS)
University of Wisconsin-Milwaukee
Geographic Information Science
2. Review of Regression
Simple linear regression y
Dependent variable: y
Independent variable: x
yi b0 b1 xi i
i yi y i yi b0 b1 xi
2. Review of Regression
Minimize: ( y b b x )
2
i i 0 1 i
i i
y 2b y 2b x y
2
i 0 i 1 i i nb02 2b0b1 xi b12 xi2
i2
Lagrangian algorithm
i
0
b0
Any statistical software can
i
2
calculate these parameters (e.g.
i
0 SPSS, S-Plus, R, SAS)
b1
University of Wisconsin-Milwaukee
Geographic Information Science
It is an exploratory method to
give a rough idea of the spatial
pattern in a set of observations.
zi f ( si ) f ( xi , yi )
University of Wisconsin-Milwaukee
Geographic Information Science
University of Wisconsin-Milwaukee
Geographic Information Science
i 1 i
n
2
Sum of squared errors
R 1
2
n
i 1
( zi z ) 2
Sum of squared
differences from mean
University of Wisconsin-Milwaukee
Geographic Information Science
Problems
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
Kriging is a statistical interpolation method that is optimal in
the sense that it makes best use of what can be inferred about
the spatial structure in the surface to be interpolated from an
analysis of the control point data
Methods used in the South African mining industry by David Krige
Theory of regionalized variables (Georges Matheron, 1960)
Statistic for Spatial Data (Noel A. C. Cressie 1993)
Three steps
1) Produce a description of the spatial variation in the sample control
point data
2) Summarizing the spatial variation by a regular mathematical function
3) Using this model to determine the interpolation weights
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Describing the spatial variation: the semi-variogram
P
4
8
2
10
0 2 d
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Describing the spatial variation: the semi-variogram
Example of variogram cloud
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Describing the spatial variation: the semi-variogram
1
2 (d )
n(d ) d ij d
( z i z j ) 2
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Describing the spatial variation: the semi-variogram
1
2 (d ) i j
n(d ) d ij d
( z z ) 2
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Describing the spatial variation: the semi-variogram
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Describing the spatial variation: the semi-variogram
a b c d e
a 0 1 1 3 2.5
1 0 2 2 3
a (10) Distance b
matrix c 1 2 0 3 1
b (12) c (8)
d 3 2 3 0 3
4. Kriging
- Describing the spatial variation: the semi-variogram
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
Mathematical Functions
Nugget model
Linear model
Spherical model
Exponential model
Power model
Gaussian model
Others
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
Nugget = c0
(c0)
d
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
=d When d < a
a d
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
Spherical model starts from a nonzero variance (c0) and rise as
an elliptical arc to a maximum value (c0+c1) at distance a.
If d <= a then
3d d
3
(d ) c0 c1 0.5
2a a
If d > a then
(d ) c0 c1
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Summarize the spatial variation by a regular
mathematical function
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Use the model to determine interpolation weights by
Kriging
Assumptions
4. Kriging
- Use the model to determine interpolation weights by
Kriging
zs w1 z1 w2 z 2 ... wn z n
Minimize E{[
z s z s }
] 2
n n n
2 wi (d is ) wi w j (d ij )
i 1 i 1 j 1
4. Kriging
- Use the model to determine interpolation weights by
Kriging
4. Kriging
- Use the model to determine interpolation weights by
Kriging
(d ) 1
wa (d aa ) wb (d ab ) wc (d ac ) (d as )
a (10) wa (d ba ) wb (d bb ) wc (d bc ) (d bs )
3 b (8)
1 wa (d ca ) wb (d cb ) wc (d cc ) (d cs )
s 2 wa wb wc 1
2 4
c (8) What is the value of wa, wb, wc, and ?
What is the value of s?
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Use the model to determine interpolation weights by
Kriging
(d ) d if d <=2
(d ) 2 if d > 2
a (10)
3 b (8)
1
s 2 What is the value of wa, wb, wc, and ?
2 4 What is the value of s?
c (8) What is the value of s with IDW method?
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Use the model to determine interpolation weights by
Kriging
Software
ArcMap Geostatistics
R Package
IDRISI (G-Stat)
GSLIB
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Use the model to determine interpolation weights by
Kriging
Trend analysis
Semivariogram
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Use the model to determine interpolation weights by
Kriging
Kriging
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
- Use the model to determine interpolation weights by
Kriging
Conclusion
1) Kriging is computationally intensive
2) All the results depend on the model we fit to the
estimated semi-variogram from the sample data
3) If the corrected model is used, the methods used in
kriging have an advantage over other interpolation
procedures
University of Wisconsin-Milwaukee
Geographic Information Science
4. Kriging
Variations
1) Simple kriging (the summation of the weights does not
equal to one)
2) Ordinary kriging (taught in this class)
3) Universal kriging (combine trend analysis with ordinary
kriging)
4) Co-kriging (more than one variable)
University of Wisconsin-Milwaukee