Scribd
Upload
152 views

Geostatistical Analysis

This document discusses geostatistical analysis and the ArcGIS Geostatistical Analyst extension. It provides an overview of geostatistics and its uses. The geostatistical workflow involves exploring data, creating predictions using methods like kriging, evaluating models, and simulating realizations. The document outlines a hands-on tutorial demonstrating how to interpolate temperature data using simple kriging and empirical Bayesian kriging in ArcGIS and compare the results.

Uploaded by

zendy.saputra
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
152 views

Geostatistical Analysis

This document discusses geostatistical analysis and the ArcGIS Geostatistical Analyst extension. It provides an overview of geostatistics and its uses. The geostatistical workflow involves exploring data, creating predictions using methods like kriging, evaluating models, and simulating realizations. The document outlines a hands-on tutorial demonstrating how to interpolate temperature data using simple kriging and empirical Bayesian kriging in ArcGIS and compare the results.

Uploaded by

zendy.saputra
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 25

Geostatistical Analysis

Ajeng Salma Yarista


[email protected]
Agenda

• Production Overview
• Hands-On Tutorial
What is geostatistics?

• Geostatistics is a class of statistics used to analyze and predict the values


associated with spatial or spatiotemporal phenomena.
• Many geostatistical tools were originally developed as a practical means to
describe spatial patterns and interpolate values for locations where samples were
not taken.
Use cases

• Meteorological applications
• Petroleum and mining exploration
• Environmental analysis
• Precision agriculture
• Fish and wildlife studies
• Public health
Geostatistical workflow

More on:
http://desktop.arcgis.com
/en/arcmap/latest/extensi
ons/geostatistical-
analyst/the-geostatistical-
workflow.htm
Product Overview
Architecture Platform

ArcMap ArcGIS Pro


Desktop Web Device

Portal

Server Online Content


and Services
ArcGIS Geostatistical Analyst
An extension for ArcGIS Pro, ArcMap, and ArcGIS Enterprise

• It is not always possible or practical to predict and model spatial phenomena


through real world observations.
• ArcGIS Geostatistical Analyst lets you generate optimal surfaces from sample
data and evaluate predictions for better decision making.
Explore Your Data

ArcGIS Geostatistical Analyst extension offers a suite of interactive tools to visually


investigate your data prior to analysis. These tools allow you to:
• Investigate the distribution of your data and look for outliers (Histogram, QQ Plots)
• Look for systematic trends in your data (Trend Analysis)
• Explore local variability and clusters (Voronoi Map)
• Visualize spatial correlation within and between datasets (Semivariogram/Cross-
Covariance Clouds)
Create Precise Predictions

When data are incomplete or subject to error, ArcGIS


Geostatistical Analyst provides a probabilistic framework for
quantifying uncertainties. Create surfaces from sample data
using these interpolation methods:
• Inverse distance weighted
• Radial-based functions
• Global and local polynomials
• Kriging for exact data and for error-contaminated data
• Cokriging (multivariate version of the above-mentioned
kriging models)
• Isotropical or anisotropical models
Evaluate and Assess

Evaluate how your models perform using the following diagnostics.


• Cross-validation for checking the model's quality
• Validation for checking prediction quality
• Compare cross-validation results of several models
• Show predicted value at cursor (MapTips)
Simulate Realizations

Create multiple versions of a surface to perform


risk analyses. Geostatistical simulation produces
multiple surfaces that mimic the real phenomenon and
provide possible values. This provides a basis for risk
analyses, economic decision making, and other
estimations involving uncertainty, allowing analysts to
make more informed decisions.
Hands-On Tutorial
Hands-On
1. Explore Your Data

1. Explore data
2. Create a histogram for temperature
3. Explore the statistics
Question: Where are the lowest temperature?
Hands-On
Examine the Values!

EBK Regression
Summary statistic Simple kriging EBK
Prediction
Average CRPS … … …
Inside 90 Percent
… … …
Interval
Inside 95 Percent
… … …
Interval
Mean … … …
Root-Mean-Square … … …
Mean Standardized … … …
Root-Mean-Square
… … …
Standardized
Average Standard
… … …
Error
Hands-On
2a. Interpolate temperature using simple kriging

1. On Analysis tab, open Geostatistical Wizard


2. Choose Kriging/CoKriging
3. Choose Simple Kriging → Prediction
4. Explore Semivariogram/Covariance Modeling
5. Optimize Model
6. Finish
7. Explore the map

Semivariogram defines exactly how similar the values of the points are given how
far apart they are.
Hands-On
2b. Anatomy of semivariogram page
Hands-On
2c. Anatomy of cross validation page
Hands-On
3. Interpolate temperature using empirical Bayesian kriging

1. Re-do the previous step, but use empirical Bayesian kriging


2. Notice the differences (in terms of statistics and appearance) between two
models
Hands-On
4a. Incorporate explanatory variables with EBK
Regression Prediction

1. Add Impervious Surface layer from the Living Atlas


2. Extract by Mask with Block_Groups layer
3. Create a scatter plot of temperature and impervious surfaces:
- For X-axis number, choose TemperatureF
- For Y-axis number, choose RASTERVALU
4. Interpolate temperature using the EBK Regression Prediction tool
5. Perform cross validation
6. Change the symbol
Hands-On
4b. Estimate the average temperature within each block
group

1. Predict the average temperature in each block group using Zonal Statistics
2. Join the predictions to the block groups using Add Join
3. Apply relevant symbology
Hands-On
4c. Identify block groups with high numbers of vulnerable
residents

1. Use a query to identify any block groups that have both high average
temperatures and a high density of residents over the age of 65
2. Create a scatter plot:
- For X-axis number, choose Mean
- For Y-axis number, choose DensityOver65
Hands-On
Result:

EBK Regression
Summary statistic Simple kriging EBK
Prediction
Average CRPS N/A 0.894 0.713
Inside 90 Percent
N/A 89.928 91.971
Interval
Inside 95 Percent
N/A 96.403 93.431
Interval
Mean 0.144 0.158 0.068
Root-Mean-Square 1.775 1.715 1.300
Mean Standardized 0.044 0.048 0.031
Root-Mean-Square
1.075 0.994 0.950
Standardized
Average Standard
1.568 1.684 1.353
Error
More Resources

• https://www.esri.com/training/
• https://pro.arcgis.com/
• http://learn.arcgis.com

You might also like