Lecture 14

Interpolating environmental
datasets
•Outline
– creating surfaces from points
– interpolation basics
– interpolation methods
– common problems

Week GEOG2750 – Earth Observation and GIS of the Physical 1

 Introduction
• Definition:
“Spatial interpolation is the procedure of estimating the
values of properties at unsampled sites within an area
covered by existing observations.” (Waters, 1989)
• Complex problem
– wide range of applications
– important in addressing problem of data availability
– quick fix for partial data coverage
– interpolation of point data to surface/polygon data
– role of filling in the gaps between observations

Week GEOG2750 – Earth Observation and GIS of the Physical 2

 Creating surfaces from points

• Waters (1989) provides list of potential uses:

– to provide contours for displaying data graphically
– to calculate some property of a surface at a given point
– to change the unit of comparison when using different
data models in different layers
– to aid in the decision making process both in physical
and human geography and in related disciplines such as
mineral prospecting and resource evaluation

Week GEOG2750 – Earth Observation and GIS of the Physical 3

 Surfaces from points

Points Surface

Week GEOG2750 – Earth Observation and GIS of the Physical 4

 An essential skill

• Environmental data
– often collected as discrete observations at
points or along transects
– example: soil cores, soil mositure, vegetation
transects, meteorological station data, etc.
• Need to convert discrete data into
continuous surface for use in GIS modelling
– interpolation

Week GEOG2750 – Earth Observation and GIS of the Physical 5

 Interpolation basics
• Methods of spatial interpolation:
– many different methods available
– classification according to:
 exact or approximate
 deterministic or stochastic
 local or global
 gradual or abrupt
– examples:
 thiessen polygons
 spatial moving overage
 TINs
 Kriging

Week GEOG2750 – Earth Observation and GIS of the Physical 6

 Data sampling
• Method of sampling is critical for
subsequent interpolation...

Regular Random Transect

Stratified random Cluster Contour

Week GEOG2750 – Earth Observation and GIS of the Physical 7

 Question…

• How do you choose a method of

interpolation?

Week GEOG2750 – Earth Observation and GIS of the Physical 8

 Classification: local or global

• Global methods:
– single mathematical function applied to all
points
– tends to produces smooth surfaces
• Local methods:
– single mathematical function applied repeatedly
to subsets of the total observed points
– link regional surfaces into composite surface

Week GEOG2750 – Earth Observation and GIS of the Physical 9

 Classification: exact or
approximate
• Exact methods:
– honour all data points such that the resulting
surface passes exactly through all data points
– appropriate for use with accurate data
• Approximate methods:
– do not honour all data points
– more appropriate when there is high degree of
uncertainty about data points

Week GEOG2750 – Earth Observation and GIS of the Physical 10

 Classification: gradual or abrupt

• Gradual methods:
– produce smooth surface between data points
– appropriate for interpolating data of low local
variability
• Abrupt methods:
– produce surfaces with a stepped appearance
– appropriate for interpolating data of high local
variability or data with discontinuities

Week GEOG2750 – Earth Observation and GIS of the Physical 11

 Classification: deterministic or
stochastic
• Deterministic methods:
– used when there is sufficient knowledge about
the surface being modelled
– allows it to be modelled as a mathematical
surface
• Stochastic methods:
– used to incorporate random variation in the
interpolated surface

Week GEOG2750 – Earth Observation and GIS of the Physical 12

 Question…

• Think of data types that require:

– local or global interpolation?
– exact or approximate interpolation?
– gradual or abrupt interpolation?
– deterministic or stochastic interpolation?

Week GEOG2750 – Earth Observation and GIS of the Physical 13

 Interpolation methods

• Most GIS packages offer a number of

methods
• Typical methods are:
– Thiessen polygons
– Triangulated Irregular Networks (TINs)
– Spatial moving average
– Trend Surfaces

Week GEOG2750 – Earth Observation and GIS of the Physical 14

 Thiessen Polygons

• Thiessen (Voronoi) polygons:

– assume values of unsampled locations are equal
to the value of the nearest sampled point
• Vector-based method
– regularly spaced points produces a regular
mesh
– irregularly spaced points produces an network
of irregular polygons

Week GEOG2750 – Earth Observation and GIS of the Physical 15

 Thiessen polygon construction

Week GEOG2750 – Earth Observation and GIS of the Physical 16

 Example Thiessen polygon

Source surface with sample Thiessen polygons with sample

points points

Week GEOG2750 – Earth Observation and GIS of the Physical 17

 Question…

• What categories does the Thiessen polygon

method fall into:
– exact or approximate?
– deterministic or stochastic?
– gradual or abrupt?
– local or global?
• What could it be used for?

Week GEOG2750 – Earth Observation and GIS of the Physical 18

 TINs

• Another vector-based method often used to

create digital terrain models (DTMs)
– adjacent data points connected by lines
(vertices) to create a network of irregular
triangles
 calculate real 3D distance between data points along
vertices using trigonometry
 calculate interpolated value along facets between
three vertices

Week GEOG2750 – Earth Observation and GIS of the Physical 19

 TIN construction

value b

value c
Interpolate
d value x

value a

a c

Plan view Isometric view

Week GEOG2750 – Earth Observation and GIS of the Physical 20

 Example TIN

Source surface with sample Resulting TIN

points

Week GEOG2750 – Earth Observation and GIS of the Physical 21

 Question…

• What categories does the TIN method fall

into:
– exact or approximate?
– deterministic or stochastic?
– gradual or abrupt?
– local or global?
• What could it be used for?

Week GEOG2750 – Earth Observation and GIS of the Physical 22

 Spatial moving average

• Vector and raster method:

– most common GIS method
– calculates new value of each location based on
range of values associated with neighbouring
points
– Neighbourhood determined by a filter
 size, shape and character of filter?

Week GEOG2750 – Earth Observation and GIS of the Physical 23

 Spatial moving average (SMA)

Week GEOG2750 – Earth Observation and GIS of the Physical 24

 Example SMA (circular filter)

Source surface with sample

points

11x11 circular filter 21x21 circular filter SMA 41x41 circular filter SMA
SMA with sample points
Week GEOG2750 – Earth Observation and GIS of the Physical 25
 Question…

• What categories does the SMA method fall

into:
– exact or approximate?
– deterministic or stochastic?
– gradual or abrupt?
– local or global?
• What could it be used for?

Week GEOG2750 – Earth Observation and GIS of the Physical 26

 Trend surfaces
• Uses a polynomial regression to fit a least-squares
surface to the data points
– normally allows user control over the order of the
polynomial used to fit the surface
– as the order of the polynomial is increased, the surface
being fitted becomes progressively more complex
 higher order polynomial will not always generate the most
accurate surface, it dependent upon the data
 the lower the RMS error, the more closely the interpolated
surface represents the input points
 most common order of polynomials is 1 through 3.

Week GEOG2750 – Earth Observation and GIS of the Physical 27

Fitting a single polynomial trend surface

interpolated
point
data point

Week GEOG2750 – Earth Observation and GIS of the Physical 28

 Example trend surfaces
Source surface with sample
points

Linear Quadratic Cubic

Goodness of fit (R2) = Goodness

Goodness of fit (R2) = 82.11 % of fit (R2) = 92.72 %
45.42 %

Week GEOG2750 – Earth Observation and GIS of the Physical 29

 Question…

• What categories does the trend surface

method fall into:
– exact or approximate?
– deterministic or stochastic?
– gradual or abrupt?
– local or global?
• What could it be used for?

Week GEOG2750 – Earth Observation and GIS of the Physical 30

 Common problems
• Input data uncertainty
– Too few data points
– Limited or clustered spatial coverage
– Uncertainty about location and/or value
• Edge effects
– Need data points outside study area
– improve interpolation and avoid distortion at
boundaries

Week GEOG2750 – Earth Observation and GIS of the Physical 31

 Effects of data uncertainty
Interpolation based on 100 Error map
points Lo
w

Original surface High

Interpolation based on 10 Error map

points

Week GEOG2750 – Earth Observation and GIS of the Physical 32

 Edge effects

Original surface with sample Interpolated surface Error map and extract
points

Lo
w

High

Week GEOG2750 – Earth Observation and GIS of the Physical 33

 Question…

• Is it possible to use explanatory variables to

improve interpolation, and if so, how?

Week GEOG2750 – Earth Observation and GIS of the Physical 34

 Conclusions
• Interpolation of environmental point data is
important skill
• Many methods classified by
– local/global, approximate/exact, gradual/abrupt and
deterministic/stochastic
– choice of method is crucial to success
• Error and uncertainty
– poor input data
– poor choice/implementation of interpolation method

Week GEOG2750 – Earth Observation and GIS of the Physical 35

 Practical
• Interpolating surfaces from point data
• Task: Interpolate a selection of point data using
the most appropriate methods of your choosing
• Data: The following datasets are provided for the
Yorkshire area…
– 200m resolution DEM (derived from 1:50,000 OS
Panorama data)
– 25m interval contour data (derived from 1:50,000 OS
Panorama data)
– metstation data (mean annual rainfall)

Week GEOG2750 – Earth Observation and GIS of the Physical 36

 Practical
• Steps:
1. Look at the data carefully and choose appropriate
technique(s) for interpolating rainfall– which is
most appropriate and why?
2. Interpolate rainfall data using chosen method(s)
– have you chosen more than one method and if
so why?
3. Display the resulting surface – does it look right,
if not why?

Week GEOG2750 – Earth Observation and GIS of the Physical 37

 Learning outcomes

• Familiarisation with range of different

interpolation techniques
• Experience at applying interpolation
methods in Arc and ArcGRID to
environmental datasets

Week GEOG2750 – Earth Observation and GIS of the Physical 38

 Useful web links
• Another 2 lectures on interpolation
– http://www.geog.ubc.ca/courses/klink/gis.notes/ncgia/u
40.html
– http://www.geog.ubc.ca/courses/klink/gis.notes/ncgia/u
41.html

Week GEOG2750 – Earth Observation and GIS of the Physical 39

 Next week…

• Principles of grid-based modelling

– linking models to GIS
– basics of cartographic modelling
– modelling in ArcGRID
• Practical: Land Capability Mapping

Week GEOG2750 – Earth Observation and GIS of the Physical 40