Contents
Spatial data analysis Digital Elevation Model
Non-spatial data analysis Generation – Parameters
Spatial interpolation Modelling surface
Data retrieval Buffer analysis
Reclassification techniques DEM applications
Buffer analysis Digital Terrain Model and
Vector and Topographical visualization
overlay analysis TIN generation
Raster overlay analysis Cost Path analysis
Measurement DEM and DTM merits and
Spatial and non-spatial query demerits
Expert system
SPATIAL DATA ANALYSIS
Spatial analysis is the process by which turn raw data
into useful information.
.
The study of the locations, shapes of geographic features
and the relationships between them.
Spatial analysis generally requires both non-spatial
(attributes) and spatial information (location of objects).
The principal objective of spatial data analysis is to
transform and combine data from diverse
sources/disciplines into useful information, to
improve one’s understanding or to satisfy the
requirements of objectives of decision makers.
Spatial analysis is how we understand our world
mapping where things are, how they relate, what it
all means, and what actions to take.
WHAT WE DO WITH SPATIAL
ANALYSIS?
Identify high crime area
Selection of a best location for a new business
Spread of disease
Suitable site determination for garbage
dumping
Identifying the Bus routing (Shortest path)
Flood vulnerable zones identification and etc..
What is spatial interpolation?
Spatial interpolation is the process of using points
with known values to estimate values at other
points.
These points with known values are called known
points, control points, sampled points, or
observations.
Spatial interpolation is a process of intelligent guesswork
in which the investigator attempt to make a reasonable
estimate of the value of a continuous field at places
where the field has not actually been measured.
Spatial interpolation is therefore a means of creating surface
data from sample points so that the surface data can be
displayed as a 3-D surface or an isoline map and used for
analysis and modeling.
Applications
In estimating rainfall, temperature and other attributes at places
where no direct measurements of these variable are available
In estimating the elevation of the surface between the measured
locations of DEM
In contouring when it is necessary to guess where to place
contours between measured locations
In resampling raster, the operation that must take place
whenever raster data must be transformed to another grid
Type of spatial interpolation
1. Global interpolation and local interpolation
2. Exact interpolation and inexact interpolation
3. Deterministic interpolation and stochastic
interpolation
4. Abrupt vs Smooth
Global interpolation:
Use every point available to estimate an unknown value.
Global interpolators determine a single function which is mapped across the whole region
◦ e.g. Trend surface
Local interpolation:
Uses sample of known points to estimate an unknown values.
Local interpolators apply an algorithm repeatedly to a small portion of the total set of points
◦ e.g. Inverse distance weighted Global interpolation: Local interpolation:
More number of control Less number of control points
points are considered are considered
Designed to capture Designed to find short range
general trend of surface variation
Less accuracy More accuracy
Exact interpolation:
Predicts a value at the point location that is same as its known value.
Exact interpolators honor all data points
◦ e.g. Inverse distance weighted
Inexact interpolation:
Predicts a value at the point location that differs from its known value.
Approximate interpolators try to approach all data points
◦ e.g. Trend surface Exact interpolation Inexact interpolation
Generates a surface Generates a surface
that passes through the that slightly differs
control points from the control points
Deterministic interpolation:
A deterministic interpolation method provides no
assessment of errors with predicted values.
Stochastic interpolation:
A stochastic interpolation method, offers assessment
of prediction errors with estimated variances.
Gradual/Abrupt
Interpolators
Gradual/smooth interpolators assume
continuous and smooth behavior of data
everywhere.
Abrupt interpolators allow for sudden changes
in data due to boundaries or undefined derivatives.
CLASSIFICATION OF SPATIAL INTERPOLATION
METHODS
SPATIAL INTERPOLATION METHODS
GLOBAL LOCAL
DETERMINIST DETERMINIST STOCHASTI
STOCHASTIC
IC IC C
THIESSEN
TREND SURFACE REGRESSIO KRIGING
(INEXACT) N E (EXACT)
DENSITY ESTIMATION
(INEXACT) X
INVERSE DISTANCE A
WEIGHTED C
T
SPLINES
GLOBAL METHODS
I. TREND SURFACE:
Trend surface analysis approximates points with known values with a
polynomial equation.
A linear or first order trend surface uses the equation :
Zx,y = bo + b1x +b2y
Where, Z is a attribute value with function x and y coordinates
bo , b1 and b2 are the coefficients estimated from known points
Example: precipitation
The trend surface model is computed by least square method,
the ‘goodness of fit’ of model can be measured and tested.
If the distribution of most natural phenomenon is more complex
than an incline lane surface from first order model.
Hence higher order trend surface is required to approximate
more complex surfaces.
Example: hills and valleys [Third order model]
GIS package offers upto 12th order trend surface models
II. REGRESSION MODEL:
A regression model relates a dependent variable to a number of independent
variables in a linear equation (an interpolator) which can be then used for
prediction and estimation.
This model uses both spatial and nonspatial attributes for the interpolation.
Z = bo + b1x + b2y + b3e +b4p
Where, Z is a dependent variable
bo,b1,b2,b3and b4 are coefficients and
x, y, e and p are the independent variables
Example: snow water equivalent
Local methods
Find the closest point to
Points within the radius Points within each
the point to be estimated
quadrant
I. THIESSEN POLYGON:
Thiessen polygon interpolation also known as Nearest neighbor interpolation.
This is conceptually the simplest interpolation method, in the sense that the
mathematical function used is the simple equality function, and only one point,
the nearest point, is used to assign a value to an unknown location.
Thiessen polygon interpolation do not use an interpolator but require initial
triangulation for connecting known points can form different set of triangles
(Delauney triangulation).
After triangulation, Thiessen polygon can be easily constructed by connecting
lines drawn perpendicular to the sides of each triangle at their mid points.
Example: Average areal precipitation
Thiessen polygon (thick) are interpolated from known
points and Delaunay triangulation (thinner).
II. DENSITY ESTIMATION:
Density estimation measures cell densities in a
raster by using a sample of known points.
There are two types of Density Estimation Methods:
1. Simple density estimation method
2. Kernel density estimation method
III. INVERSE DISTANCE WEIGHTED INTERPOLATION:
The IDW is simple and intuitive deterministic interpolation method
based on principle that sample values closer to the prediction location
have more influence on prediction value than sample values farther
apart. Using higher power assigns more weight to closer points resulting
in less smoother surface.
On the other hand, lower power assigns low weight to closer points
resulting in smoother surface. Major disadvantage of IDW is “bull's
eye” effect (higher values near observed location) and edgy surface.
Inverse distance weighting results in smooth interpolated surfaces. The
values do not jump discontinuously at edges, as occurs with Thiessen
polygons, and sometimes with fixed radius interpolation.
IV. Splines
•The mathematical equivalent of using a flexible ruler (called a
spline)
•Can be used as an exact or approximate interpolator, depending
upon the degrees of freedom granted (e.g. polynomial order)
•Best for smooth datasets, can cause wild fluctuations otherwise
Kriging
Developed by Georges Matheron, as the "theory of regionalized
variables", and D.G. Krige as an optimal method of interpolation for
use in the mining industry.
Kriging is the geostatistical method for spatial interpolation.
Basis of technique is the rate at which the variance between points
changes over space
This is expressed in the variogram which shows how the average
difference between values at points changes with distance between
points
Theissen Polygon
GLY560: GIS AND RS 9/28/2021
Inverse Distance Weighting
GLY560: GIS AND RS 9/28/2021
Kriging
GLY560: GIS AND RS 9/28/2021
• Interpolation method depends upon
• Character of data
• Your assumptions of data behavior
• When possible, best way to compare methods is to
1. try several methods
2. make sure you understand theory
3. refine best method
Reclassification Technique
The process of taking input cell values and replacing them
with new output cell values
Reclassification is often used to simplify or change the
interpretation of raster data by changing a single value to a new
value, or grouping ranges of values into single values—for
example, assigning a value of 1 to cells that have values of 1 to
50, 2 to cells that range from 51 to 100, and so on.
Reclassification serves three main purpose
◦Creating a simplified raster: eg 1 for slopes 0-10%, 2 for
10-20%
◦Creating new raster that contains a unique category or values:
eg slopes of 10-20%, irrigated croplands
◦Creating a new raster that shows the ranking of cell values in
the input raster: eg 1 to 5, with 1 being the least suitable and 5
being the most suitable
DATA RETRIEVAL
Data retrieval is the process of identifying and extracting data from
database.
Data retrieval is feasible and easy if there is no ambiguity in the data
and it should be presented in standard structure.
Data retrieval: 1. Locating, 2. Selecting by attributes 3. Buffering 4, Map
overlay 5. Map algebra.
Data retrieval is done by applying the rules of Boolean logic to operate on
the attributes.
DATA RETRIEVAL – SOURCES
(Example)
Digital Library (Books, Journals)
Web Search engine (Flight ticket, Movie, Education)
USGS Data Library (Satellite image – Free of cost)
NRSC Data Center ( Purchasing Indian satellite)
Etc..
BUFFER
A buffer is a zone with a width created around a spatial feature and is
.
measured in units of distance from the feature.
Buffering is used for neighborhood analysis which aims to evaluate the
characteristics of the area surrounding the spatial feature.
Common examples of buffering include the identification of properties
within a certain distance of an object,
Delineation of areas around natural features where human activities are
restricted, determination of areas affected by location etc
Query
.
Query is a request to select features or records from a database is known as a
Query.
Query is often written as a statement or logical expression. Analysing the data by
querying it is Known as the Query Analysis. This is an immensely powerful
feature that allows you to view a subset of the layer without selecting & exporting
those features to a new layer each time. Three types of Queries are there (a)
Interactive (b) Selection (SQL) (c) Spatial (Location) and Graphical
Spatial Measurement Methods
Measurements allow to produce ratios of lengths to widths and of perimeters
to areas
The GIS user need to describe not only what objects are, how many objects
exist and where they are, but also how large they are, how far apart and what
the distance between them is like
Method of measurements depend upon the type of data, data model and
availability of software
In raster, measurements are done
using Pythagorean geometry
Fig 1: Length Calculation
Fig 2: Perimeter Calculation
Fig 3: Area Calculation
In vector, measurements are also
done using Pythagorean geometry
Fig 4: Vector Distance Calculation
What is expert system and its components?
Expert system, a computer program that uses artificial-intelligence methods to
solve problems within a specialized domain that ordinarily requires human
expertise.
An expert system generally consists of four components: a knowledge base,
the search or inference system, a knowledge acquisition system, and the user
interface or communication system. Knowledge systems solve difficult
problems of the real world by performing inference processes on explicitly stated
knowledge
The internal structure of an expert system can be considered
to consist of three parts: the knowledge base ; the database; the
rule interpreter. the set of productions; the set of facts held as
working memory and a rule interpreter. The knowledge base
holds the set of rules of inference that are used in reasoning.
Limitations of Expert System
•The response of the expert system may get wrong if the knowledge
base contains the wrong information.
•Like a human being, it cannot produce a creative output for different
scenarios.
•Its maintenance and development costs are very high.
•Knowledge acquisition for designing is much difficult.
What is the purpose of an expert system?
In artificial intelligence, an expert system is a
computer system emulating the decision-making ability of a
human expert. Expert systems are designed to solve complex
problems by reasoning through bodies of knowledge,
represented mainly as if–then rules rather than through
conventional procedural code.