Spatiotemporal Change Pattern Mining: A Multi-disciplinary Perspective - Space-Time Integration in Geography and GIScience - page 298

dataset, points may represent instances of disease. In a public safety dataset, points
may represent crime incidents. Figure 17.2 b shows an example of spatial point data
in crime analysis. This is a map of drunk driving locations in Nebraska where the
two coordinates represent the longitude and latitude of the incidents (Mohan et al.
2011 ).

17.2.2.2 Lines and Paths

Spatial paths are sequences of values that are taken at locations along a curve in a
spatial framework. For example, in Fig. 17.3 , the data curve on the right shows the
vegetation cover observed in Africa (Tucker et al. 2004 ) measured in Normalized
Difference Vegetation Index (NDVI) (shown on left) along 18.5 E degree longitude.
Value change pattern along the path may reflect environmental change in different
latitudes.

17.2.2.3 Polygons

Polygon data on two dimensional space usually represent two dimensional spatial
objects such as lakes, or spatial regions in space such as political jurisdictions. Some

a

4

3

2

1

0

−1

−2

−3

−4

1900 1920 1940 1960 1980 2000

Time

Fig. 17.2 Examples of temporal and spatial input data ( a ) A time series ( b ) Spatial point data ( c )
Spatial polygon data (Adapted from Lu and Carlin ( 2005 ) with permission)