Transcript GIS and Spatial Analysis Michael F. Goodchild University of California Santa Barbara Outline GIS-oriented definitions of spatial analysis  The role of the GIS  Taxonomies of.

GIS and Spatial Analysis
Michael F. Goodchild
University of California
Santa Barbara
Outline
GIS-oriented definitions of spatial
analysis
 The role of the GIS
 Taxonomies of spatial analysis
 A six-way classification
 Issues and concerns

Definitions

Spatial data
– information about phenomena organized in
a spatial frame
– the geographic frame

Methods applied to spatial data that
– add value
– reveal patterns and anomalies
– support decisions
Spatial analysis

Methods whose results depend on the
locations of phenomena in the frame
– are not invariant under relocation

Some types of relocation may not affect
social processes
– rotation
– relocation
– inversion
The geographic frame
The atomic form <x,z>
 Location abstracted

– distance matrix
– adjacency matrix
– invariance under rotation, inversion,
relocation
Spatial analysis as a
collaboration
The computer as butler to the human
mind
 Are maps “mere”?
 Humans as sources of context

– cross-sectional data are already rich in
context
The role of the GIS

The infrastructure for handling data
types
– to spatial data as Excel is to tables, as SPlus is to statistical data, as Word is to text
– spatial data or geographic data?
– the housekeeper
– the editor

The visualization tool
The GIS data types

Discrete geographic features
– points, lines, areas
– the contents of maps
– with associated attributes
– countable
– conceived as tables with associated
feature geometry

ESRI shapefiles
Fields

Geography as a collection of continuous
variables
– measured on nominal, ordinal, interval,
ratio scales
– vector fields of direction and magnitude
– exactly one value per point
– z=f(x)
– population density, land ownership, zoning
Field representations
Raster of rectangular cells
 Raster of uniformly spaced points
 Irregularly spaced points
 Irregular areas (polygons)
 Digitized contours
 Triangular mesh (triangulated irregular
network or TIN)
 ESRI coverages

GIS as a data access
mechanism

The geolibrary
– place-based search
– integrating information about a place
– making access transparent
Taxonomies of spatial analysis

Thousands of methods
– every one a command, menu item, icon, …

Based on data type
– point pattern analysis
– area (polygon) analysis
– analysis of interactions
– Bailey and Gatrell, Haining, Unwin
A six-way conceptual
classification
Query and reasoning
 Measurement
 Transformation
 Descriptive summary
 Optimization
 Hypothesis testing

Queries and reasoning

Real-time answers to geographic
questions
– Where is…?
– What is this?
– How do I get from here to here?

Based on alternative views of a
database
Measurements
Area
 Distance
 Length
 Perimeter
 Slope, aspect
 Shape

Transformations
Buffering
 Points in polygons
 Polygon overlay
 Spatial interpolation
 Density estimation

City limits
Areas reachable in 5
minutes
Areas reachable in
10 minutes
Other areas
Courtesy of Dick Block
Descriptive summary
Centers
 Measures of spatial dispersion
 Spatial dependence
 Fragmentation
 Fractional dimension

Optimization
Design to achieve specific objectives
 Location of central point-like facilities to
serve dispersed demand
 Location of linear facilities
 Design of boundaries for elections

Hypothesis testing

Geographic objects as a sample from a
population
– what is the population?

The independence assumption
– the First Law of Geography
– failure to find spatial dependence is always
a Type II error
– hell is a place with no spatial dependence
Issues and concerns
Limits to representation
 Geographic or spatial?

– site or situation?

The critical perspective
1564
2886
995
1990
Information lost to the
representation
All sub-polygon spatial variation
 All within-decade temporal variation
 All identities

– instead of <xy, person> we have
<R, number>
<xy, xy, xy, xy, …, R>
Challenges of GIS

How to characterize what is missing?
– error, accuracy, uncertainty

How to choose the best representation?
– confounding influences

How to support many data models in a
single software package
Weaknesses of GIS

There are too many possible data
models
– special-purpose GIS
– lack of interoperability

Difficult to add data models retroactively
Brian Harley

Maps as reflections of the agendas of
their makers
– deconstructing the map
Maps as essential tools of imperial
power
 Whose agenda is in your glove
compartment?

– Dennis Wood, The Power of Maps
The Gulf War: the first GIS
war
Digital maps
 GPS in tanks, aircraft, hand-held by
infantry
 Precise routing and targeting of cruise
missiles and smart bombs
 Satellite surveillance

Another dimension to the
critique

GIS presents one view
– privileged
– rational, scientific, positivist
– vertical, God-like, masculinist
– precise boundaries, sharp edges

John Pickles, Ground Truth: The social
implications of GIS (1995)
It's very
pleasant
today in Santa
Barbara
Spoken word
Text
Picture
x, y, T
The GIS-2 agenda

A reinvented technology
– more humanistic in approach
– reflecting multiple views of the world
– human complexity and vagueness
Naïve Geography
What people believe about the world
 The continental US as a rectangle

– Seattle is due N of San Diego
– New York is due N of Miami

Options for GIS designers
– something a child of 10 can use
– something for an expert Spatially Aware
Professional