You are on page 1of 23

Density Analysis

takes known quantities of phenomena


and spreads it across the landscape
(area)
analysis based on the
quantity that is measured at each
location
spatial relationship of the locations of
the measured quantities

Why map density?


Density surfaces show where point or line
features are concentrated.
Create a surface showing the predicted
distribution throughout the area (spread of the
data)
Population per Km 2

Fish density per Km 2


Population Density surface example

Point pattern analysis

determine if points (events) are exhibiting


specific pattern or are randomly distributed.
estimate the intensity (density) of how the
point pattern is distributed over the study
area

determine if there is spatial dependence


among points (events)

A - collection of point objects

B - kernel function for one of the points

The kernels shape depends on the distance parameter (radius)

Increasing the radius : results in a broader and lower kernel


Reducing the radius : in a narrower and sharper kernel.
The result is a density surface whose smoothness depends on
the value of the distance parameter.

Kernal too small- (radius of 16 km)


each kernal isolated from neighbours

Kernel radius of 150 km

Spatial Interpolation

Deterministic vs. Stochastic


Interpolation
A deterministic interpolation method
provides no assessment of errors with
predicted values.
A stochastic interpolation method
offers assessment of prediction errors
with estimated variances.

What is interpolation?
Process of creating a surface based on
values at isolated sample points

Interpolation is used because field data


are sometimes expensive to collect, and
cant be collected everywhere

Interpolation

predict value at un-sampled locations within sampled region


based on spatial auto-correlation or spatial dependence
degree of relationship/dependence between near
and distant objects
Similarity of objects within an area
Level and strength of interdependence between the variables
everything is related to everything else, but close
things are closely related

Interpolation types

Deterministic:
Surface created from samples based on extent of similarity.
E.g., IDW, Spline
Stochastic/Geostatistical
Spatial variation modeled by random process with spatial
autocorrelation
Creates error surface indicate prediction validity
E.g., Kriging

Different interpolation methods will produce different results.

Inverse Distance Weighting (IDW)


assumes each sample point has influence that diminishes
with distance.
gives greater weight to points closer to the cell than to those
farther away.
POWER (p) option
Control significance of input points
upon the interpolated values based on
their distance from the output cell.
/influence

A larger power results in more distant


points having less influence on the
output.
Normally, lower power values will
tend to smooth the surface.

Spline
Spline is intended to fit a minimum-curvature
surface to the sample points. The surface passes
exactly through the sample points.
Spline method is best suited to sample data that
varies smoothly. It's not appropriate if there are
large changes in value within a short horizontal
distance.

Two types of Spline that can be used to


interpolate a surface:

regularised and tension


Regularised Spline
offers a looser fit, but
may have overshoots
and undershoots

Tension Spline
forces the curve. Makes a
coarser surface.

Kriging
Kriging is based on statistical models that
include autocorrelation.
Weights are based on:
The distance between the measured
points and the predicted location and
The overall spatial location among the
points.
Cell value can exceed sample value range

Kriging

18

Kriging

is implemented using a semi-variogram

Certainty of surface generated can be


determined :
"How good are the predictions?"

The goal is to calculate the parameters of the


curve to minimize the deviations from the
points according to some criterion
Sample locations separated by distances closer than the range are spatially
autocorrelated, whereas locations farther apart than the range are not.

GIS ANALYSIS MODEL

*BPI - Bathymetric position index

You might also like