Lab#8 (Report)

Chapter 15
Spatial Interpolation
Task #1 | Use Trend Surface Model for Interpolation
File Requirement:
stations.shp and idoutlgd
Steps:
1. Launch ArcMap software  Add folder connection to 106382605_Lab#8  Insert New Data Frame and
named as Chap15Task1
2. Go to Customize menu  make sure that Geostatistical Analysist and Spatial Analysist extensions are
checked.
3. Go to Geostatistical Analysist Tool-Bar menu ( )

 click drop down menu  Explore Data  Trend Analysist  click drop down menu and select stations
for layer  select ANN_PREC attribute.
4. Go to Geostatistical Analyst dropdown menu  select Geostatistical Wizard  in Method Frame select
Global Polynomial Interpolation  Next  select the order of Polynomial 1  click Finish.
5. Go to Catalog tree  point to Global Polynomial Interpolation Maps  Right click and select Properties
 click Symbology Tab  uncheck the box except Filled Contour  click classify. In the classification
dialog box select Manual method and choose 7 classes  enter the class break of 10, 15, 20, 25, 30, 35 
click OK.
Figure 1. Global Polynomial Interpolation Map
6. To clip Global Polynomial Interpolation Prediction Map fit with Idaho map:
Right click at Global Polynomial Interpolation Prediction Map  point to Data  select Export to Raster
 in the GA Layer to Grid dialog box  specify trend5_temp for output raster  enter 2000 (meters) for
Cell size  click OK. The layer trend5_temp will appear in to the map.
Now ready to clip:
Go to ArcToolBox  Spatial Analysist Tools  Extraction Toolset  select Extract by Mask Tool  in
the dialog box select trend5_temp for the input raster  select idoutlgd for the input future mask data 
specify the trend5 as a name of output raster  click OK. The trend5 will clipped of trend5_temp.
9. Generating the contour from trend5 for data visualization:

Go to ArcToolBox  select Spatial Analysist Tools  Surface Toolset  Contour Tool  in the dialog
box select trend5 for input raster  save the output polyline feature as trend5ctour.shp enter 5 for the
interval  enter 10 for base contour  OK.
10. To labels the contour:

Go to catalog tree  right click on trend5ctour  check the box to label feature in this layer  select
CONTOUR from Labels Field dropdown menu  click OK. Now map appear in the catalog tree.
Figure 2. Precipitation Map (Global Polynomial Interpolation)
Task Question #1:

What is the RMS statistic for power of 5?
Answer:
The result of RMS with power about 5 is 4.543
Task #2 | Compute Kernel Density Estimation
File Requirement:
deer.shp
Steps:
1. Go to Insert Menu  Insert New Data Frame and named as Chap15Task2.
2. Right click on the context menu of deer.shp  select Properties  on the Symbology Tab select Quantities
 Graduated symbols  in the Show Box select SIGHTING for Value dropdown list  click OK.
2. Go to ArcToolBox  Spatial Analysist  Density Toolset  Kernel Density Tool  select deer.shp as an
input point or polyline feature  select SIGHTINGS for population field  specify kernel_d for the output
raster  enter 100 for output cell  enter 100 for the search radius  select HECTARES for area unit 
click OK.
Figure 3. Kernel Density of Sighting Deer
Task Question #2:

What is the value range of SIGHTING?
Answer:
The range value of SIGHTING is 1-15
Task Question #3:

What is the value range of deer shighting densities?
Answer:
The range value of deer sighting densities are 0 to 22,349
Task #3 | Use IDW for Interpolation
File Requirement:
stations.shp and idoutlgd
Steps:
1. Go to Insert Menu  Insert New Data Frame and named as Chap15Task3.
2. Right click on Chap15Task3  add stations.shp and idoutlgd
3. Go to Geostatistical Analysist dropdown list  select Geostatistical Wizard  click Inverse Distance
Weighting (IDW) in the Method Frame  make sure that Source Dataset is station.shp and the Data Field
is ANN_PREC  click Next.
4. To get the optimize value: click Power button in the method frame  and the Power field shows a value of
3.191  click NEXT.
5. To clip the maps, the step same as the Task 1 using Extract by Mask Tool in Spatial Analysis Tools.
Figure 4. Interpolation use IDW

Task Question #4:
What is the RMS statistic when you use the default parameters including the optimal power value?
Answer:
The RMS result is 4,407 (in the Power value 2)
Task Question #3:

Change the Power to 2 and the maximum number of neighbors to 10 and the minimum number to 6. What RMS
statistic do you get?
Answer:
The RMS result is 3.983
Task #4 & #5 | Use Ordinary Kriging for Interpolation & Use Universal Kriging for Interpolation
Task #4 Use Ordinary Kriging

File Requirement:
station s.shp dan idoutlgd
Steps:
1. Go to Insert Menu  Insert New Data Frame and named as Chap15Task4&5.
2. Go to Geostatistical Analysist dropdown menu  point to Explore Data  select
Semivariogram/Covariance Cloud  select stations.shp for the Layer  select ANN_PREC for the
attribute  enter 82000 for the lag size  enter 12 for the number of lags.
3. Go to Geostatistical Analysist menu  select Geostatistical Wizard  make sure that the source dataset is
stations.shp  select ANN_PREC for data field  click Kriging/CoKriging in the Method frame  click
Next  select Ordinary for Kriging Type and Prediction for Output Surface Type  Next  select
Model#1 frame  click the dropdown arrow for Type and select Spherical  Change lag size to 40000 and
number of lag to 12  Change Anisotropy to be true  Next.
Back to the step 3  click optimize button to optimize entire model  check the RMS value  click
Finish.
4. Follow step as a task 1 to clip the map.
Figure 5. Prediction Standard Error Map Figure 6. Ordinary Kriging Prediction Map
Task Question #6:

What is the RMS value from step 5?
Answer:
Task Question #7:

Does the optimal model have a lower RMS statistic than your answer to Q6?
Answer:
The RMS result higher than step 5, it about 0,978
Task #5 Use Universal Kriging

File Requirement:
station s.shp dan idoutlgd
Steps:
1. Go to Insert Menu  Insert New Data Frame and named as Chap15Task4&5.
2. Go to Geostatistical Analysist dropdown  select Geostatistical Wizard  select stations for the source
dataset  select ANN_PREC for data field  click Kriging/CoKriging in the Method Frame  Next.
3. In the step 2  click Universal for Kriging Type and Prediction for the output type  select First from
Order of Trend removal list  Next
4. In the step 4  click optimize button to optimize model  click OK  Next.
5. In the step 6  click FINISH
6. To clip the map we can follow the step in the Task #1.
Figure 7. Prediction Standard Error Map (Universal) Figure 8. Universal Kriging Prediction Map
Task Question #8:

What is the RMS value from step 6?
Answer:

Lab#8 (Report)

Uploaded by

Copyright:

Available Formats

Lab#8 (Report)

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lab#8 (Report)

Uploaded by

Copyright:

Available Formats

Chapter 15

Task #1 | Use Trend Surface Model for Interpolation

3. Go to Geostatistical Analysist Tool-Bar menu ( )

Figure 1. Global Polynomial Interpolation Map

9. Generating the contour from trend5 for data visualization:

10. To labels the contour:

Task Question #1:

Task #2 | Compute Kernel Density Estimation

Figure 3. Kernel Density of Sighting Deer

Task Question #2:

Task Question #3:

Figure 4. Interpolation use IDW

Task Question #3:

Task #4 Use Ordinary Kriging

Task Question #6:

Task Question #7:

Task #5 Use Universal Kriging

Task Question #8:

You might also like