GIS week 5

Question 1

What is spatial analysis and modelling in GIS?

Answer 1

Methods to examine, summarise, and interpret spatial data, identifying patterns and interactions.
Used to identify patterns, associations, connections, interactions, and evidence of change through time and location.
1. Spatial query.
2. Spatial operations: Reclassifying maps, Overlay analysis Measuring geometry and distance, Characterising neighborhoods.
3. Spatial interpolation: Inverse distance weights and Kriging

Question 2

What are the three core types of spatial analysis techniques?

Answer 2

proximity analysis, overlay analysis, statistical analysis and temporal analysis

Question 3

What is a spatial query in GIS?

Answer 3

Selecting and extracting features based on attributes or location.

Question 4

How does a query by attribute work in GIS?

Answer 4

By retrieving features that match specific attribute values using a query language like SQL.
To retrieve all features with particular attribute values from one data layer or feature class in a spatial database and display their locations in a map
e.g. ‘Retrieve all water mains installed before 2010 with a diameter less than 30cm’.

Question 5

How does a query by location work in GIS?

Answer 5

By retrieving features based on their spatial relationship to other features using spatial operators.
Uses 11 spatial operators. equals, disjoint, intersects, touches, crosses, within, contains, overlaps, relate, LocateAlong and LocateBetween.
Usually involves two or more data layers
To identify attribute values associated with features at particular locations

Question 6

What is an example of a query by attribute?

Answer 6

Retrieving all water mains installed before 2010 with a diameter less than 30cm.

Question 7

What is reclassification in spatial analysis?

Answer 7

Simplifying or merging areas by grouping features with the same attributes.

Question 8

What is overlay analysis in GIS?

Answer 8

A process of stacking multiple data layers with a common georeferencing system on top of each other so that the relationships between features at each location can be analysed.

The most common GIS operation for comparing and analysing multiple data layers simultaneously.

E.g. calculating the number of properties within a flood risk zone.

Overlay analysis can be conducted in both vector and raster

Question 9

What is a vector overlay in GIS?

Answer 9

Combining two or more vector layers to produce new geometries using operations like union, intersection, and difference (named after the result of the combination of two layers.)

Question 10

What is raster overlay (map algebra) in GIS?

Answer 10

superimposes at least two input raster layers to produce an output layer.
Each cell in the output layer is calculated from the corresponding pixels in the input layers

Question 11

What is map algebra in spatial analysis?

Answer 11

A mathematical framework for performing operations on raster layers.

Question 12

What is geometric and distance measurement in GIS?

Answer 12

Length, area, perimeter and shape. Useful for landscape metrics e.g. interaction between spatial pattern and ecological processes.

Geometric properties and distances are usually not encoded during spatial data input. GIS offers measurement functions to calculate them

Question 13

How are length, perimeter, and area measured in raster data?

Answer 13

By using cell counts and cell sizes to estimate geometric properties.

Question 14

What is buffering in GIS?

Answer 14

Buffering is a distance measurement tool for vector data commonly available in GIS. It creates a zone around a feature or a set of features with a specific width.

Question 15

What is a physical distance surface in GIS?

Answer 15

A raster showing the shortest distance from a source to every other location.

Calculates the shortest distances from a location to every other location and creates a distance surface in raster form.

The concentric rings of equal distance around the source location(s), as shown for roads.

Question 16

What is a cost distance surface in GIS?

Answer 16

A raster showing the least-cost path based on travel time, energy, or other factors.
Distance in raster can be measured as costs incurred over physical distance.
The cost-distance can be cost of travel time, energy consumption, etc. which may be affected by topography (slope, land cover, etc).
E.g., cost for constructing a highway include cost of construction and land purchase and include potential costs of environmental and social impacts

Question 17

What is spatial interpolation in GIS?

Answer 17

Estimating values of an environmental variable at locations whose values are unknown based on a sample of locations with known values.
Apply an interpolation method to a set of points with known values to create a continuous surface

Question 18

What are the main spatial interpolation methods in GIS?

Answer 18

Deterministic (IDW) and geostatistical (kriging) methods.
Through spatial interpolation, spatial distributions of the environmental phenomena can be approximated.

Question 19

What is Inverse Distance Weighting (IDW) interpolation?

Answer 19

A method where nearby points influence predictions more than distant points.
IDW estimates a value of each location by taking the distance-weighted average of the values of sample points in its neighbourhood.
Explicitly assumes that things closer to one another are more alike than those that further apart.
As p increases, the weights for distant points decrease rapidly. If the p value is very high, only the immediate surrounding points will influence the prediction.

Question 20

What is spatial autocorrelation?

Answer 20

Spatial autocorrelation means data values at locations close to each other generally exhibit less variability than data values at locations which are further away from each other (Tobler’s Law).
Positive spatial autocorrelation is when similar values cluster together.
Negative spatial autocorrelation is when dissimilar values cluster together (dispersed).
Spatial autocorrelation is an underlying assumption of IDW i.e. that closer values have more effect while further away ones have less effect

Question 21

How does the power term (p) in IDW affect the interpolation?

Answer 21

A higher p increases the influence of nearby points, while a lower p smooths the surface.

Question 22

What is kriging in GIS?

Answer 22

Kriging interpolates values and their probability at a specific location.
Uses input data to build a mathematical function with a semivariogram, to create a prediction surface, and then validate the model with cross validation.
A geostatistical method that provides an optimal prediction surface AND a measure of confidence in how likely that prediction will be true.

Question 23

What is a semivariogram in kriging?

Answer 23

A graph showing how spatial similarity decreases with distance.

Question 24

What does a kriging example illustrate?

Answer 24

How kriging builds a prediction surface based on known sample points.

Question 25

How do we validate a spatial interpolation model in GIS?

Answer 25

Using cross-validation metrics like mean error, RMSE, and R². Count = number of know values. Mean = average difference between known and predicted values (should be close to zero). RMSE = prediction accuracy (should be as small as possible). RMSS should be close to 1

Question 26

What are common sources of error in interpolation?

Answer 26

Method limitations (measured in terms of mean error, RMSE, r2) , sample data uncertainty (too few sample points, limited or clustered distributions and uncertainty about locations and/or values), and edge effects (distortions of the interpolated values near the boundary of the study area due to the lack of sample data outside the area)