Spatial Data Analysis

Unit IV
 Spatial data analysis
 Analytical capabilities of a GIS use spatial and non-spatial
(attribute) data to answer questions about real-world
 It is the spatial analysis functions that distinguishes GIS from other
information systems.
 When use GIS to address real-world problems, you'll come up against
the question that which analysis function you want to use and to
solve the problems.
 This include:
› Spatial Data Functions (Format Transformations, Geometric Transformations
Projection Transformations etc. )
› Attribute Data Functions (Retrieval, Classification, Verification etc.)
› Integrated Analysis (Overlay, Neighborhood Function, Topographic Functions,
Interpolation etc.)
 Classification of analytical GIS
capabilities
 Classification, retrieval, and measurement functions
 Overlay functions
 Neighbourhood functions
 Connectivity functions
 Classification, retrieval, and
measurement functions
All functions in this category are performed on a single (vector or raster)
data layer, using the associated attribute data
 Classification allows the assignment of features to a class on the
basis of attribute values or attribute ranges
› Classification of different crops like potato and rice
 Retrieval functions allow the selective search of data
› Retrieval all agricultural fields where potato is grown
 Generalization is a function that joins different classes of objects with
common characteristics to a higher level (generalized) class
› Generalization potato and rice fields as food produce fields
 Measurement functions allow the calculation of distances, lengths, or
areas.
 Overlay functions

Allow the combination of two (or more) spatial data layers

comparing them position by position, and treating areas of
overlap—and of non-overlap—in distinct ways
 Intersection
› The potato fields on black soils
 Union
› The fields where potato or rice is the crop
 Difference
› The potato fields not on black soils
 Complement
› The fields that do not have potato as crop
 Neighbourhood functions
Evaluates the characteristics of an area surrounding a feature’s location;
scans the neighbourhood of the given feature and performs a computation
on it
 Search functions
› Allow the retrieval of features that fall within a given search window. This window
may be a rectangle, circle, or polygon
 Buffer zone generation
› Determines a spatial envelope (buffer) around given feature
 Interpolation functions
› Predict unknown values using the known values at nearby locations
 Topographic functions
› Determine characteristics of an area by looking at the immediate neighbourhood
› E.g. Slope calculation
 Connectivity functions
 Works on the basis of networks; represent spatial
linkages between features
 Contiguity functions
› contiguous area of forest of certain size and shape in a
satellite image
 Network analytic functions
› Road network, public transport routes, high voltage lines or
other forms of transportation infrastructure
 Visibility functions
› points visible from a given location (Viewshade mapping)
 (Classification, retrieval, and measurement)
Measurement

 Geometric measurement on spatial features includes counting,

distance and area size computations
 Measurements on vector data
 The primitives of vector data sets are point, (poly)line and
polygon.
 Related geometric measurements are location, length,
distance and area size.
 For measuring distance between two features
 If one or both of the features are not a point, minimal distance
between a location occupied by the first and a location
occupied by the second feature is computed
 (Classification, retrieval, and measurement)
Measurement
 Measurements on raster data
 Location is derived from the raster’s anchor point
and the position of the cell in the raster
 The area size is calculated as the number of cells
multiplied by the cell area
 The distance between two raster cells is the
standard distance function applied to the
locations of their respective mid-points
 (Classification, retrieval, and measurement)
Spatial selection queries

Interactive spatial selection

 Selection condition -> spatial object -> spatial data layer -> select
features
 Spatial data stored in a geo database is associated with its
attribute data through a key/foreign key link. Selections of features
lead to selections on the records
Selection condition is defined by
drawing spatial objects on the
screen display, after having
indicated the spatial data layer
from which to select features
Here selection object is circle.
 (Classification, retrieval, and measurement)
Spatial selection queries

Spatial selection by attribute conditions

 To select features by using selection conditions on feature
attributes. These conditions are formulated in SQL if the attribute
data reside in a geo-database.
 Spatial selection using the attribute condition Area < 400000
 (Classification, retrieval, and measurement)
Spatial selection queries
Combining attribute conditions
 Atomic conditions use a predicate symbols, < (less than), =
(equals), <= (less than or equal), > (greater than), >= (greater
than or equal) and <> (does not equal). 400000 and 80 are
expressions. Area and LandUSe are attribute names.
 E.g. Area < 400000, and LandUse = 80
 Composite conditions make use of AND, OR, NOT and the
bracket pair ( ).
 E.g. Area < 400000 AND LandUse = 80; Area < 400000 OR
LandUse = 80, NOT (LandUse = 80), (Area < 30000 AND
LandUse = 70) OR (Area < 400000 AND LandUse = 80)
 (Classification, retrieval, and measurement)
Spatial selection queries

Spatial selection using topological relationship

1. Selecting features that are inside selection objects: containment
relationship
In dark green, some District as the selection objects. In red, all
medical clinics located inside these areas, and thus inside the
district.
 (Classification, retrieval, and measurement)
Spatial selection queries
2. Selecting features that intersect
In dark green some District as the selection objects , and all roads in
the district are selected (in red).
 (Classification, retrieval, and measurement)
Spatial selection queries
3. Selecting features adjacent to selection objects: features that share
boundaries
 In dark green some town, in red industrial area near town
 (Classification, retrieval, and measurement)
Spatial selection queries
4. Selecting features based on their distance
In red, roads that are within 200 metres of a medical clinic shown in
dark green
 Classification
 Classification is a technique of purposefully
removing detail from an input data set to
reveal important patterns of spatial
distribution.
 User-controlled classification: a user selects the
attributes that will be used as the classification
parameters and defines the classification method
 Automatic classification: a user only specifies the
number of classes in the output data set and the
system automatically determines the class break
 Classification

Equal interval technique: The minimum and

maximum values Vmin and Vmax of the classification
parameter are determined and the interval size for
each category is calculated as
Vmax - Vmin / n
where n is the number of classes chosen by the
user
e.g. if you specify three classes for a field whose values
range from 0 to 300, the application will create three
classes with ranges of 0–100, 101–200, and 201–300.
 Classification
 Quantile or Equal frequency technique:
Each class contains an equal number of features.
Quantile assigns the same number of data
values to each class. There are no empty classes or
classes with too few or too many values.
Count the number of letters in
country names
Equal interval:
•Class 1: 4 – 8 (113
countries have four,
five, six, seven or eight
letters)
•Class 2: 8 – 12 (41)
•Class 3: 12 – 16 (12)
•Class 4: 16 – 20 (8)
•Class 5: 20 – 24 (2)
We generated 5 classes
but the number of
classes is entirely up to
you.
Max- min = 24 – 4 = 20
Then, it divides 20 by 5
and you get an interval
(20/5=4).
Quantile or Equal Frequency:
•Class 1: 4 – 6 (56 countries
have 4, 5 or 6-letter names)
•Class 2: 6 – 7 (38)
•Class 3: 7 – 8 (19)
•Class 4: 9 – 11 (36)
•Class 5: 12 – 24 (27)
It takes total of number of
features (176 countries in our
case).
Then, it divides the total by the
number of classes to get the
average (176/5=35.2).
Finally, quantile maps counts
the quantity in each group and
arranges them as close to the
average as possible.
 Overlay functions
 Technique of combining two spatial data layers and
producing a third from them
 Flow computation

 Flow computations are determined when a phenomenon does not spread

in all directions, but moves or ‘flows’ along a given, least-cost path,
determined again by local terrain characteristics.
 Raster (a) is original elevation raster. For each cell in that raster, the steepest
downward slope to a neighbour cell is computed, and its direction is stored in
a new raster.
 Raster (b) can be called the flow direction raster.
 From raster (b), the GIS can compute the accumulated flow count raster,
raster (c), a raster that for each cell indicates how many cells have their water
flow into the cell.
 Cells with a high accumulated flow count represent areas of
concentrated flow, and thus may belong to a stream.
 Cells with an accumulated flow count of zero are local topographic highs, and
can be used to identify ridges.
 Network analysis
 A network is a connected set of lines, representing
some geographic phenomenon
 Directed networks associate with each line a direction of
transportation; undirected networks do not
 Planar network can be embedded in a two-dimensional
plane
 Spatial analysis functions on networks are
› Optimal path finding: least cost-path on a network between a pair
of predefined locations
› Network partitioning: assigns network elements to different
locations using predefined criteria
Turning Cost Table
Ordered & Unordered path
finding
 Network partitioning
 Network partitioning is the process of creating zones
or territories from a street network, such that each
link is assigned to the closest or least cost service
location, based on a service value, such as driving
distance or time.
 For example, you could use network partitioning to
divide a city into zones based on the response time
from all of the fire stations within that city. Each zone
would be comprised of the streets for which its fire
station has the fastest response time.
The streets in this map
were partitioned into
zones based on the
driving time to the
nearest service point.
No matter where you
are in any of the zones,
the point that is the
shortest drive-time
away is the one located
within that zone.
 Network / Location Allocation
 Given facilities that provide goods and services and a set of
demand points that consume them, the goal of location-
allocation is to locate the facilities in a way that supplies the
demand points most efficiently. As the name suggests,
location-allocation is a twofold problem that simultaneously
locates facilities and allocates demand points to the facilities.
 Initially, it may appear that all location-allocation analyses
solve the same problem, but the best location is not the
same for all types of facilities. For instance, the best location
for an ERS center is different than the best location for a
manufacturing plant.
 Network / Location Allocation
 Example 1: Locating an ERS center
When someone calls for an ambulance, we trust it will come
to their aid almost instantly; the emergency response time
depends considerably on the distance between the
ambulance and the patient. Typically, the goal for
determining the best sites for ERS centers is to make it
possible for ambulances to reach the most people within a
defined time frame. The specific question may be: Where
should three ERS facilities be placed so that the greatest
number of people in the community can be reached within
four minutes?
 Network / Location Allocation
 Example 2: Locating a manufacturing plant
Many retail outlets receive their goods from
manufacturing plants. Whether producing
automobiles, appliances, or packaged food, a
manufacturing plant can spend a large percentage of
its budget on transportation. Location-allocation can
answer the following question: Where should the
manufacturing plant be located to minimize overall
transportation costs?
 Trace Analysis
 The term tracing is used here to describe building a
set of network elements according to some
procedure.
 GIS and It’s Application Models
 Mathematical construct for representing geographic
objects or surfaces as data
 Five characteristics of GIS-based application models:
› The purpose of the model,
› The methodology underlying the model,
› The scale at which the model works,
› Its dimensionality - i.e. whether the model includes spatial,
temporal
› Its implementation logic - i.e. the extent to which the model
uses existing knowledge about the implementation context.
 Characteristics of application models
 Purpose of the model
 refers to whether the model is descriptive,
prescriptive or predictive in nature.
 Descriptive models attempt to answer the “what is” -
question.
 Prescriptive models usually answer the “what should
be” question
 Predictive models focus upon the “what is likely to
be” questions
 Characteristics of application models
 Methodology
 refers to the operational components of the model.
 Stochastic models use statistical or probability functions to
represent random or semi-random of phenomena.
 Deterministic models are based upon a well-defined cause
and effect relationship
 Rule-based models attempt to model processes by using
local (spatial) rules
 Agent-based models (ABM) attempt to model movement
and development of multiple interacting agents
 Characteristics of application models
 Scale
 refers to whether the components of the model are
individual or aggregate in nature.
 refers to the ‘level’ at which the model operates.
 Individual-based models are based on individual
entities, such as the agent-based models such as
salary of individual
 Aggregate models deal with ‘grouped’ data such as
population census data.
 Characteristics of application models
 Dimensionality
 refer to whether a model is static or dynamic,and
spatial or aspatial.
 Spatial model operate in some geographically defined
space.
 Aspatial models have no direct spatial reference.
 Models can also be static, meaning they do not
incorporate a notion of time or change.
 In dynamic models, time is an essential parameter
 Characteristics of application models
 Implementation logic
 refers to how the model uses existing theory or
knowledge to create new knowledge.
 Deductive approaches use knowledge of the overall
situation in order to predict outcome conditions.
 This includes models that have some kind of formalized
set of criteria, often with known weightings for the
inputs, and existing algorithms are used to derive
outcomes.
 Inductive approaches try to generalize, trial and error
Error propagation in spatial data
processing
Thank You!