\[ \newcommand\si[1]{\mathrm{#1}} \newcommand\SI[2]{#1\,\si{#2}} \newcommand\matr[1]{\mathbf{#1}} \DeclareMathOperator*{\argmax}{arg\,max} \DeclareMathOperator*{\argmin}{arg\,min} \]

GIS data analysis 1

Dr. Huidae Cho
Institute for Environmental and Spatial Analysis...University of North Georgia

1   Data analysis

Decision making process

Answer your research questions

1.1   Questions for GIS analysis

Think about locations, patterns, trends, conditions, implications, etc.


Queries: Method of data retrieval; We’ve tried these already!

  • Select by attributes: Aspatial query (e.g., how many haunted houses in your town?)
  • Select by location: Spatial query (e.g., how many houses within 10 miles of your house?)

More complex analyses

1.2   Vector vs. raster


  • Topology
  • Complexity
  • Computational time


  • Resolution
  • Scales of measurement (nominal vs. ratio)

1.3   Data analysis terminology

EntityAn individual point, line or area in a GIS database
AttributeData about an entity
FeatureAn object in the real world to be encoded in a GIS database
Data layerA data set for the area of interest in a GIS
ImageA data layer in a raster GIS
CellAn individual pixel in a raster image
Function/operationA data analysis procedure performed by a GIS
AlgorithmThe computer implementation of a sequence of actions designed to solve a problem

2   Measurements

Remember! Measurements are only approximations because GIS uses straight line segments (vector) or grid cells (raster).


2.1   House hunting case study


Distance from the office calculated using the proximity method

2.2   Calculating lengths and areas


2.3   Different distances


3   Buffer

Creates a zone of interest at a uniform distance around an entity (e.g., within 2 miles)

Many uses

  • Identifying entities within a buffer
  • Filtering neighbors used in raster
  • Can be complex when incorporating slope, accessibility, etc.

3.1   Buffering different geometry types


3.2   House hunting case study


Distance from the office adjusted for the road network

3.3   Radioactive waste case study


Local accessibility of potential disposal sites; 3 km buffer zones (blue) around the rail network (red)

3.4   Proximity map for hotels


4   Spatial interpolation

Procedure for estimating the values at unsampled sites within an area covered by existing observations

Fills in gaps (e.g., height contours)

Inevitable uncertainty with interpolation

Edge effect due to less sampling near edges

4.1   Original terrain surface with sample points


4.2   Interpolation methods


5   Thiessen polygons


Also called the Voronoi diagram.

all locations in the Voronoi polygon are closer to the generator point of that polygon than any other generator point in the Voronoi diagram in Euclidean plane

Tran et al. 2009

6   Boolean operators


7   Map overlays

One of the key functions

Merges two or more data layers into a new layer


  • Uses geometries (topology)
  • Time consuming, complex


  • Map algebra
  • Add, subtract, multiple, or divide overlain pixels to produce output pixels
  • Quick, efficient, straightforward

7.1   Vector overlays

vector-overlays-1.png vector-overlays-2.png

(a) Point in polygon; (b) Line in polygon; (c) Polygon on polygon

7.2   Raster overlays


(a) Point in polygon (using add); (b) Line in polygon (using add); (c) Polygon on polygon (using add); (d) Polygon on polygon (using boolean alternatives)



8   Exercises

Use nc_spm_08_grass7_exercise.gdb.zip for these exercises.

8.1   Exercise: Schools close to major roads

Keywords: buffer

Find schools within 100 meters from major roads.

8.2   Exercise: Monthly average precipitation of a school

Keywords: Thiessen polygons

What is the monthly average precipitation of Fox Road Elementary School in September?

8.3   Exercise: Fire stations within the urban area

Keywords: intersect

Find fire stations within the urban area.

8.4   Exercise: Fire stations outside the urban area

Keywords: erase

Find fire stations outside the urban area.

8.5   Exercise: Urban areas or counties

Keywords: union

Union the urban area and county boundary. How is it different from copying features from one layer to another?