United States
Environmental Protection
Agency
Environmental Monitoring
Systems Laboratory
Las Vegas NV 89193-3478
Research and Development
EPA/600/S4-88/033 Feb. 1989
SEPA Project Summary
Geo-EAS (Geostatistical
Environmental Assessment
Software) User's Guide
Evan J. Englund and Allen R. Sparks
This report describes how to install
and use the Geo-EAS (Geosta-
tistical Environmental Assessment
Software) software package on an
IBM-PC compatible computer sys-
tem, A detailed example is provided
showing how to use the software to
conduct a geostatistical analysis of a
data set
Thirteen Geo-EAS programs are
documented. The principal functions
of the package are the production of
2-dimensional grids and contour
maps of interpolated (kriged) esti-
mates from sample data. Other
functions include data preparation,
data maps, univariate statistics,
scatter plots/linear regression, and
vario-gram computation and model
fitting. Extensive use of screen
graphics such as maps, histograms,
scatter plots and variograms help the
user search for patterns, corre-
lations, and problems in a data set.
Data maps, contour maps, and
scatter plots can be plotted on an HP
compatible pen plotter. Individual
programs can be run independently;
the statistics and graphics routines
may prove useful even when a full
geostatistical study is not appro-
priate. For ease of use, the programs
are controlled inter-actively through
screen menus, and use simple ASCII
data files.
This Protect Summary was devel-
oped by EPA's Environmental Moni-
toring Systems Laboratory, Las Vegas,
NV, to announce key findings of the
research project that is fully docu-
mented in a separate report of the
same title (see Protect Report
ordering Information at back).
Introduction
Geostatistical methods are useful for
site assessment and monitoring situa-
tions where data are collected on a
spatial network of sampling locations, and
are particularly suited to cases where
contour maps of pollutant concentration
(or other variables) are desired.
Examples of environmental applications
include lead and cadmium concentrations
in soils surrounding smelter sites, out-
door atmospheric N02 concentrations in
metropolitan areas, and regional sulfate
deposition in rainfall. Kriging is a
weighted moving average method used
to interpolate values from a sample data
set onto a grid of points for contouring.
The kriging weights are computed from a
variogram, which measures the degree of
correlation among sample values in the
area as a function of the distance and
direction between samples.
Kriging has a number of advantages
over most other interpolation methods:
Smoothing - Kriging smooths, or
regresses, estimates based on the
proportion of total sample variance
accounted for by random "noise". The
noisier the data set, the less individual
samples represent their immediate
vicinity, and the more they are
smoothed.
Declustering - The kriging weight as-
signed to a sample is lowered to the
degree that its information is dupli-
cated by nearby, highly correlated
-------
samples. This helps mitigate the
impact of oversampling "hot spots".
Anisotropy - When samples are more
highly correlated in a particular
direction, kriging weights will be
greater for samples in that direction.
Precision - Given a variogram repre-
sentative of the area to be estimated,
kriging will compute the most precise
estimates possible from the available
data. In practice, this is only approx-
imated, as the variogram must itself be
estimated from the available data.
Estimation of the variogram from
sample data is a critical part of a
geostatistical study. The procedure
involves interpretation and judgment, and
often requires a large number of "trial
and error" computer runs. The lack of
inexpensive, easy-to-use software has
prevented many people from acquiring
the experience necessary to use
geostatistical methods effectively. This
software is designed to make it easy for
the novice to begin using geostatistical
methods and to learn by doing, as well
as to provide sufficient power and
flexibility for the experienced user to
solve real-world problems.
The basic tools of applied geo-
statistics, variogram analysis and kriging,
were developed in the early 1960's for
use in the mining industry, and applied to
the problems of ore reserve estimation
and grade control. In recent years, use
of geostatistical methods has become
widespread among researchers in
various fields such as meteorology,
hydrology, and soils science. The
ongoing USEPA research program in
environmental geostatistics at the
Environmental Monitoring Systems
Laboratory - Las Vegas (EMSL-LV)
was begun about six years ago. As an
incidental result of various research
projects conducted under Cooperative
Agreements with Stanford University, the
University of Wyoming, and the Univer-
sity of Arizona, EMSL-LV acquired a
miscellaneous collection of public
domain geostatistical and statistical
software. Development of the Geo-EAS
package began in the summer of 1986,
as a means of making the software
widely available, adequately docu-
mented, and easy to use. The system
was designed in cooperation with the
Applied Earth Sciences Department of
Stanford University, and programming
was done by the Computer Sciences
Corporation, Las Vegas, NV. Design
features such as the simple ASCII file
formats, standardized menu screens, and
integrated graphics, give Geo-EAS
flexibility for future expansion; it is
anticipated that Geo-EAS will become a
significant technology transfer mecha-
nism for more advanced methods
resulting from the EMSL-LV research
and development program.
The Geo-EAS System
Geo-EAS (Geostatistical Environ-
mental Assessment Software) is a
collection of interactive software tools for
performing two-dimensional geostatis-
tical analyses of spatially distributed
data. Programs are provided for data file
management, data transformations,
univariate statistics, variogram analysis,
cross validation, kriging, contour
mapping, post plots, and line or scatter
graphs. Features such as hierarchical
menus, informative messages, full-
screen data entry, parameter files, and
graphical displays are used to provide a
high degree of interactivity, allowing
users to easily alter parameters and re-
calculate results.
Data Files
The Geo-EAS programs use a simple
ASCII file structure for data input. The
files contain a header record, the number
of variables, a list of variable names and
units, and a numeric data table. The first
few lines of an example file are listed
below.
Example.dat - Geostatistical
Environmental Assessment Software
5
Easting feet
Northing feet
Arsenic ppm
Cadmium ppm
Lead ppm
288.0 311.0 .850 11.5 18.25
285.6 288.0 .630 8.50 30.25
273.6 269.0 1.02 7.00 20.00
280.8 249.0 1.02 10.7 19.25
Menu Screens
All Geo-EAS programs are controlled
interactively through menu screens
(Figure 1) which permit the user to select
options and enter control parameters.
While default choices for many
parameters and options make the
programs easier to use, the programs
are structured to avoid a "black box"
approach to data analysis. Several of the
more complex programs permit the user
to save and read "parameter files",
making it easy to quickly rerun a
program at a later date.
File Utilities
The programs DATAPREP and JRf
provide capability for manipulating G
EAS data files. Files can be appende<
merged, and variables can be crea
transformed, or deleted. Transforma
operations include natural log, squ
root, rank order, indicator, and arithm
operations.
Data Maps
POSTPLOT creates a map (Figure
of a data variable in a Geo-EAS c
file. Symbols representing the quartile;
the data values and/or the data val
themselves are plotted at the sam
locations.
Univariate Statistics
STAT1 computes univariate statist
such as mean, standard deviation.etc.,
variables in a Geo-EAS data file, <
plots histograms (Figure 3) and pr
ability plots.
X-Y Plots
SCATTER and XYGRAPH both ere
x-y plots with optional linear regress
for any two variables in a Geo-EAS d
file. SCATTER (Figure 4) is most usi
for quick exploratory data analysis, wl
XYGRAPH provides additional capa
ities such as multiple 'y' variables, ;
scaling and labelling options.
Variogram Analysis
PREVAR creates an intermedi
binary file of data pairs for use in VAF
which computes and displays plots
variograms for specified distance i
directional limits. Variogram models <
be interactively fitted to the experimei
points (Figure 5). The fitted model rr
be the sum of up to five independ
components, which can be a
combination of nugget, linear, spheric
exponential, or gaussian models. XVAI
is a cross-validation program which (
test a variogram model by estimat
values at sampled locations fn
surrounding data and comparing 1
estimates with the known sample value
Interpolation
KRIGE provides kriged estimates
for a two-dimensional grid of points
blocks. The user may specify the 5
parameters; an elliptical sear
neighborhood; and up to five "neste
independently anisotropic, variogn
model components. During execution
shaded map of estimated values
-------
A program to compute uniuariate descriptive statistic*
Pile Prefix: C:\GeoEAS\Data\
File
Data File Nane : Exanple.dat
Variable
Variable : CadMiu*
Weight : None
Log Option : Off
Lin its
Minimm : .880
MaxiftuH : 16.780
* Uariables 5
S Data records 68
t Hissing Data 8 (Z
Execute
Use this option to conpu'
display the statistics.
of additional graphs and
will be displayed.
Obs<=6)
te and
A Menu
options
Prefix Data Variable Linits
Conpute basic descriptive stats.
figure 1. Initial menu for program STAT t.
Batch Statistics Quit
Po«tplot or Cadmium from data file Exompl«.dot
3OO
1
200
100
a
K a
X
X
OD
1»t OuorUl.:
2n* OuarVto:
«uortHK
Coating
.GOO tf -f S.3OO
S.3OO < X 7.SOO
7. BOO < Q « 1O.SOO
1O.SOO < « « 16.TOO
BOO
Figun 2. Sample location map from program POSTPLA T.
displayed (Figure 6), and a Geo-EAS
file of kriged grid results is produced.
Contour Maps
CONREC generates contour maps
(Figure 7) from a gridded Geo-EAS
data file, usually the output from KRIGE.
Options are provided for contour intervals
and labels, degree of contour line
smoothing, high-low symbols, and for
dashed contour lines below a specified
level.
Pen Plotting
The programs POSTPLOT, XYGRAPH,
and CONREC are based on subroutines
originally developed by the National
Center for Atmospheric Research
(NCAR), and produce graphics "meta-
files" which can be saved and replotted
later. HPPLOT reads a metafile and
produces a file of HPGL commands
which can be plotted on Hewlett-
Packard compatible plotters. VIEW reads
a metafile and displays the plot on the
monitor for review.
User Profile
The Geo-EAS user should have some
familiarity with personal computers and
DOS (Disk Operating System) com-
mands such as DIR (Directory), CD
(Change Directory), COPY, etc., and how
to insert and use diskettes. EDLIN or
some other ASCII file text editor will often
be needed for the initial formatting of
Geo-EAS data files (adding header
records, missing value codes, etc.). It is
assumed that the Geo-EAS user has a
basic understanding of geostatistical
-------
Histovrax
Data til*: XxaMplv.dat
9.
S 6.
e
1
c,
IK
3.
0
i i
1
9. 4. 8. 12.
CadniuM (PPM)
__
Statistics
1 N Total 68
n
N ttiss B
N Used 68
Mean 7.885
Variance 15.531
Std. Dew 3.941
X C.V. 49.981
Skeuness - . 151
Kurtosis 2.464
Hlninun .888
25th * 5.388
Median 7.688
75th X 18.888
Haxinun 16.788
16. 20.
Figure 3. Histogram from program STAT 1.
Scatter Plot
488.
388.
B
* 288.
iaa.
a.
a
fpon data til* Exanpie.dat
+
+
* i
* * 4 ^ '
+ J-^--^
l^r^Tf^ * +
Regression Results:
Pairs : 68
Slope : 6.678
Intercept : -3.649
Correl. coeff.: .462
4. 8. 12. 16. 2B.
CadMiUH
Figure 4. XY plot with linear regression from program SCA TTER.
concepts, and preferably some prior
experience in variogram analysis and
kriging; however, the Geo-EAS User's
Guide includes a fully worked example
which can provide a starting point for the
novice user.
Hardware Requirements
This system was designed to run
under DOS (Disk Operating System) on
an IBM PC, XT, AT, PS2, or compatible
computer. Graphics capability is not
required, but is highly recommended, as
most programs will produce graphics
output. Graphics support is provided for
the Hercules monochrome graphics card,
the Color Graphics Adapter (CGA), and
he Enhanced Graphics Adapter (EGA).
640 kilobytes (Kbytes) of random access
memory (RAM) is required. An arithmetic
co-processor chip is strongly recom-
mended due to the computationally
intensive nature of the programs, but is
not required for use. Programs may be
run from floppy diskette, however, a fixed
disk is required to use the programs from
the system menu. The system storage
requirement is approximately thi
megabytes. For hardcopy of results
graphics printer (IBM graphics cc
patible) is required. Support is provk
for plotters which accept HPGL plotl
commands.
Geo-EAS Software Availability
The Geo-EAS software in its exe
table form is entirely in the put
domain, and can be obtained by send
the appropriate number of diske
(PRE-FORMATTED, PLEASE!) to
following address:
-------
18.
IS.
i -
6.
3.
U*rloff**M for- CadMiun
-- - » *
./
40. 80. 120. 1C
Distance
File :ExanpIe.pcf
Pair* : 1242
Oirect.: .888
Tol. : 98.888
(laxBand: n/a
Cadntun Llnlts
nininun: .888
tlaxlnun: 16.788
dean : 7.885
Var : 1S.S31
1.
Figure 5. Variogram with fitted model from program VA RIO.
Block krivinv: CaJnitut
:::-« » ' ' ' « :::*::
\{ ::::::: * :;::::: ::«::::::
::%:; »:::"":::>::::::
** > . ,*^. . . . . M. .
i S »
> : :«: S %._£ . » M
* 7« % o « 0* m mmmmmmmm m m
fum-mmmm»mm m mum mfm
H
* x y z*
143 5B8. 320. 8.87
Cadnlui*
< 9.3OO
: : < 7. coo
;: < 1O.8OO
X - Hissin*
ok N
2.28 3
Figure 6. Screen display of interpolated results from program KRIGE.
Evan J. England (Geo-EAS)
USEPA EMSL-LV, EAD
P.O. Box 93478
Las Vegas, NV 89193-3478
The executable files and example data
sets take approximately 3 megabytes of
storage, and require several diskettes,
depending on the diskette type.
Type
Number
51/4" 1.2MB
5 1/4" 360KB
31/2" 1.44MB
3 1/2" 722KB
3
9
3
6
The source code is written in
FORTRAN using the Microsoft 4.01
(Microsoft Corporation, Redmond, WA)
FORTRAN compiler. The graphics in
Geo-EAS are accomplished through the
use of a slightly modified version of the
proprietary GRAFLIB graphics utilities
(Sutra Software, Sugarland TX), and a PC
version of the NCAR graphics utilities
developed at the National Center for
Atmospheric Research in Boulder,
Colorado. The NCAR and Geo-EAS
-------
source code are in the public domain.
For further information on the Geo-EAS
source code and programmer docu-
mentation, contact:
Geo-EAS
Computer Sciences Corporation
P.O. Box 93478
Las Vegas, NV 89193-3478
Krfgi'ng estimates produced from data file Example.
Contours for »Cadmrum
i2O.
280.
240.
200.
180.
120.
290. 300. 340. SBO. 42O. 40O. 5OO.
Eqatina
Figun 7. Contour map of kriged estimates from program CONREC.
-------
The EPA author, Evan J. England (also the EPA Project Officer see below), it, ..
the Environmental Monitoring Systems Laboratory, Las Vegas, NV, and Allen R.
Sparks is with Computer Sciences Corporation, Las Vegas, NV 89119.
The complete report consists of paper copy and software, entitled "Geo-EAS
(Geostatistical Environmental Assessment Software) User's Guide,"
Paper Copy, (Order No. PB 89-151 252/AS/AS; Cost: $21.95)
Software, (Order No. PB 89-151 245/AS/AS; Cost: $60.00; cost of software
includes paper copy)
The above items will be available only from: (costs subject to change)
National Technical Information Service
5285 Port Royal Road
Springfield, VA 22161
Telephone: 703-487-4650
The EPA Project Officer can be contacted af:
Environmental Monitoring Systems Laboratory
U.S. Environmental Protection Agency
Las Vegas, NV 89193-3478
United States Center for Environmental Research
Environmental Protection Information
Agency Cincinnati OH 45268
Official Business
Penalty for Private Use $300
EPA/600/S4-88/033
0000329 PS
60604
------- |