Spatial Data Mining

1
Spatial Data Mining

• Satoru Hozumi
• CS 157B

2
Learning Objectives

• Understand the concept of Spatial Data Mining
• Learn techniques on how to find spatial patterns

3
Examples of Spatial Patterns

• 1855 Asiatic Cholera in London.
• A water pump identified as the source.
• Cancer cluster to investigate health hazards.
• Crime hotspots for planning police patrol routes.
• Affects of weather in the US caused by unusual
  warming of Pacific ocean (El Nino).

4
What is a Spatial Pattern?

• What is not a pattern?
• Random, haphazard, chance, stray, accidental,
  unexpected.
• Without definite direction, trend, rule, method,
  design, aim, purpose.
• What is a Pattern?
• A frequent arrangement, configuration,
  composition, regularity.
• A rule, law, method, design, description.
• A major direction, trend, prediction.

5
Defining Spatial Data Mining

• Search for spatial patterns.
• Non-trivial search as automated as possible.
• Large search space of plausible hypothesis
• Ex. Asiatic cholera causes water, food, air,
  insects.
• Interesting, useful, and unexpected spatial
  patterns.
• Useful in certain application domain
• Ex. Shutting off identified water pump gt saved
  human lives.
• May provide a new understanding of the world
• Ex. Water pump Cholera connection lead to the
  germ theory.

6
What is NOT Spatial Data Mining

• Simple querying of Spatial Data
• Finding neighbors of Canada given names and
  boundaries of all countries (Search space not
  large)
• Uninteresting or obvious patterns
• Heavy rainfall in Minneapolis is correlated with
  heavy rainfall in St. Paul (10 miles apart).
• Common knowledge, nearby places have similar
  rainfall
• Mining of non-spatial data
• Diaper sales and beer sales are correlated in
  evenings

7
Families of Spatial Data Mining Patterns

• Location Prediction
• Where will a phenomenon occur?
• Spatial Interactions
• Which subset of spatial phenomena interact?
• Hot spot
• Which locations are unusual or share
  commonalities?

8
Location Prediction

• Where will a phenomenon occur?
• Which spatial events are predictable?
• How can a spatial event be predicted from other
  spatial events?
• Examples
• Where will an endangered bird nest?
• Which areas are prone to fire given maps of
  vegitation and drought?
• What should be recommended to a traveler in a
  given location?

9
Spatial Interactions

• Which spatial events are related to each other?
• Which spatial phenomena depend on other
  phenomenon?
• Examples
• Earth science
• climate and disturbance gt wild fires, hot, dry,
  lightning
• Epidemiology
• Disease type and enviornmental events gt West
  Nile disease, stagnant water source, dead birds,
  mosquitoes

10
Hot spots

• Is a phenomenon spatially clutered?
• Which spatial entities are unusual or share
  common characteristics?
• Examples
• Crime hot spots to plan police patrols

11
Spatial Queries

• Spatial Range Queries
• Find all cities within 50 miles of Paris
• Query has associated region (location, boundary)
• Answer includes overlapping or contained data
  regions
• Nearest-Neighbor Queries
• Find the 10 cities nearest to Paris
• Results must be ordered by proximity
• Spatial Join Queries
• Find all cities near a lake
• Join condition involves regions and proximity.

12
Unique Properties of Spatial Patterns

• Items in a traditional data are independent of
  each other, where as properties of location in a
  map are often auto-correlated (patterns exist)
• Traditional data deals with simple domains, e.g.
  numbers and symbols where as spatial data types
  are complex
• Items in traditional data describe discrete
  objects where as spatial data is continuous

13
Association Rules

• Support the number of time a rule shows up in a
  database
• Confidence Conditional probability of Y given X
• Example
• (Bedrock type limestone), (soil depth lt 50 ft)
  gt (sink hole risk high)
• Support 20 , confidence 0.8
• Interpretation Locations with limestone bedrock
  and low soil depth have high risk of sink hole
  formation.

14
Apriori Algorithm to mine association rules

• Key challenge
• Very large search space
• Key assumption
• Few associations are support above given
  threshold
• Associations with low support are not interesting
• Key insight
• If an association item set has high support, then
  so do all its subsets

15
Association rules Example
16
Techniques for Association Mining

• Classical method
• Association rules given item types and
  transactions
• Assumes spatial data can be decomposed into
  transactions
• Such decomposition may alter spatial patterns
• New spatial method
• Spatial association rule
• Spatial co-location

17
Associations, Spatial associations, co-location
18
Associations, Spatial associatins, co-location
19
Co-location Rules

• For point data in space
• Does not need transaction, works directly with
  continuous space
• Use neighborhood definition and spatial joins

20
Co-location rules
21
Clustering

• Process of discovering groups in large databases
• Spatial view rows in a database points in a
  multi-dimentional space.
• Visualization may reveal interesting groups

22
Clustering

• Hierarchical
• All points in one cluster
• Split and merge till a stop criterion is reached
• Partitional
• Start with random central point
• Assign points to nearest central point
• Update the central points
• Approach with statistical rigor
• Density
• Find clusters based on density of regions

23
Outliers

• Observations inconsistent with rest of the
  dataset
• Observations inconsistent with their
  neighborhoods
• A local instability or discontinuity

24
Variogram Cloud

• Create a variogram by plotting attribute
  difference, distance for each pair of points
• Select points common to many outlying pairs

25
Moran Scatter Plot

• Plot normalized attribute values, weighted
  average in the neighborhood for each location
• Select points in upper left and lower right
  quadrant

26
Scatter plot

• Plot normalized attribute values, weighted
  average in the neighborhood for each location
• Fit a liner regression line
• Select points which are unusually far from the
  regression line.

27
Conclusion

• Patterns are opposite of random
• Common spatial patterns
• Location prediction
• Feature interaction
• Hot spot
• Spatial patterns may be discovered using
• Techniques like associations, clustering and
  outlier detection