Presentation Template

CS621B/C Spatial Databases
Research presentation
Spatial data mining for
Analysis and prediction of
natural disaster
JUSTIN DONAGHY 11125993
DEPARTMENT OF COMPUTER SCIENCE
NUI MAYNOOTH
JUSTIN.DONAGHY.2012@MUMAIL.IE

Introduction
 Spatial data mining for Analysis and prediction of natural disasters
 Spatial data mining is the application of data mining methods to spatial
data
 Goal of Spatial data mining is to find patterns in data with respect to
Geography.
 Can we use Spatial mining techniques to predict Natural disasters
around the world.
 Natural disasters represent significant safety, economic, and security
threats, and the formalized goal focused communities on developing
adequate prevention, mitigation, response and recovery plans.
2

Introduction
 Why Spatial Data Mining?

Spatial Data mining is to find interesting, potentially usef
ul, non‐trivial patterns in large spatial datasets. –
A huge volume of spatial data coming from an
increasing number of geographical sensors and
satellites.
 “data rich but knowledge poor” problem in spatial analy
sis

history
John Snow was the first to discover that the cause of the
cholera in London was coming from a single pump. He did
this by talking to survivors and finding what well they drank
from, in collecting this spatial data , he was able to find a
pattern and the pump
So he became the first spatial data miner
6

Spatial data mining Architecture

Problems with Spatial Data Mining
 the spatial data mining algorithms are not efficient. Faced
with massive database systems, spatial data mining
process appears uncertain, the possibility of errors
dimension model and problems to be solved are great,
not only increases the algorithm of the search space, but
also increased the blind searches possibility. And
therefore it must be removed with the use of domain
knowledge discovery tasks unrelated data, effectively
reducing the dimension of the problem, design a more
effective knowledge discovery algorithms.
8

Problems with spatial data mining
There is no accepted standardized spatial data mining query
language. One reason for the rapid development of database
technology is the continuous improvement and development
of a database query language, therefore, to continue to
improve and develop spatial data mining is necessary to
develop spatial data mining query language, digging the
foundation for efficient spatial data.
THIS IS NOT AN EXACT SCIENCE

11
DATA MINING TECHNIQUES:
 The various data mining techniques are:
 Statistics
 Clustering
 Visualization
 Association
 Classification & Prediction
 Outlier analysis
 Trend and evolution analysis

12
European heatwave caused 35,000
deaths

Could this have been predicted using
SPATIAL DATA MINING TECHNIQUES

Climate data modelling
 “it is very likely that hot extremes, heat waves, and heavy
precipitation events will continue to become more
frequent”. (IPPC, 2014)

Future directions
 DISTRIBUTED/COLLECTIVE DATA MINING
 UBIQUITOUS DATA MINING (UDM)
 HYPERTEXT AND HYPERMEDIA DATA MINING
 MULTIMEDIA DATA MINING
 SPATIAL AND GEOGRAPHIC DATA MINING
 TIME SERIES/SEQUENCE DATA MINING
 CONSTRAINT- BASED DATA MINING
 PHENOMENAL DATA MINING

Future trends
 Geographic and spatial data mining: Geographical
databases are becoming increasingly common and more
detailed. They can be used for the extraction of implicit
knowledge, spatial relationships and other patterns that
are not explicit in them. One of the main challenges of
this field will be the design and architecture of the data
warehouses to store the information (given the very
particular nature of the data), as well as the integration of
heterogeneous data

Conclusion
Natural disasters are always going to be hard to predict but Spatial data
mining may help to save lives in the future. With the development of more
sophisticated techniques this could become more of an exact science
It is foreseeable that spatial data mining will not only promote space
science, the development of computer science, but also will enhance
human understanding of the world, the discovery of knowledge, in order to
better transform the world.
19

References
 European Environment agency (2010) Mapping the impacts of natural hazards and technological accidents in
Europe An overview of the last decade Luxembourg: Publications Office of the European Union, 2010.
 Ganguly ,Auroop. R and Steinhaeuser ,Karsten (2008) Data Mining for Climate Change and Impacts [online]
Available at: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4733959 (accessed 8th December 2015).
 International Conference on Circuit, Power and Computing Technologies (2015) ANALYSIS AND PREDICTION OF
NATURAL DISASTER USING SPATIAL DATA MINING TECHNIQUE , Department Of Computer Science and
Engineeering, Sathyabama University, Chennai
 I.P.P.C (2013) Europe [online] Available at: http://www.ipcc.ch/pdf/assessment-report/ar5/wg2/WGIIAR5-
Chap23_FINAL.pdf (accessed 8th December 2015).
 Otero, Abraham (2009) future trends in data mining [online] Available at:
http://biolab.uspceu.com/datamining/pdf/FutureTrends.pdf (accessed 8th December 2015).
 UCLA (2014)broad street pump outbreak [online] Available at:
http://www.ph.ucla.edu/epi/snow/broadstreetpump.html (accessed 8th December 2015).
 University of Minnesota(2010) Flood Prediction and Risk Assessment Using Advanced Geo-Visualization and Data
Mining Techniques: A Case Study in the Red-Lake Valley [online] Available at: http://www.wseas.us/e-
library/conferences/2014/Malaysia/ACACOS/ACACOS-02.pdf (accessed 8th December 2015).
 2008 IEEE International Conference on Data Mining Workshops (2008) Data Mining for Climate Change and
Impacts [online] Available at: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4733959 (accessed 8th
December 2015).
20

Presentation Template

More Related Content

What's hot (20)

Similar to Presentation Template (20)

Presentation Template