Transcript Predicting Earthquakes

Predicting Earthquakes
By Lois Desplat
Why Predict Earthquakes?
 To
minimize the loss of life and property.
 Unfortunately, current techniques do not
have a high enough accuracy to be able to
accurately predict earthquakes.
Estimating earthquake probabilities
 Scientists
study the histories of large
earthquakes in a specific area
 The rate at which strain accumulates in
the rock
Methods to earthquake prediction
 Need



to construct models based on:
Partial differential equations
Finite automata
Supervised learning techniques:
• Decision Tree
• Bayesian Classification
• Feed-Forward Neural Networks
Decision Tree
 Tries
to generate rules with high accuracy
 ID3, …
Bayesian Classifiers
 They
are statistical classifiers
 Only needs a small sample to find the
means and variances of the variables
necessary for classification
 It can find the probability that a given
sample belongs to a certain class
(earthquake > 3.0)
 Uses Bayes Theorem
Feed-Forward Neural Network
 Network
given a set of input and
respective output to start learning
 It connects each Perceptron and the
algorithm tries to minimize the weigths
between Perceptrons to the minimum so
that the input give the right output
The Bagging Method
 Combine
the predictions of the past three
algorithms
 You get a much more accurate prediction
 Give different learning samples to each
algorithm
Some Problems
 The
Data can have a lot of extra
information that adds noise
i.e. We might not want small scale
earthquakes that are really just
aftershocks of big earthquakes
 We only look at the data in 1 dimension,
maybe if we plot the data in multiple
dimensions, we might some patterns
Not Good Enough!
 Authors
claim that their bagging method
has 92% accuracy.
 Highly doubt accuracy of that number but
even if true:

We still cannot predict earthquakes with
enough confidence
Solution
 Do
short-term predictions instead of longterm
 Analyze the data in multiple dimensions
over space, time and feature space.
Visualization of the Data Space

Data Space uses Magnitude, Epicentral
Coordinate, Depth and Time of occurrence
 7D space uses:







NS: Degree of spatial non-randomness at short
distances
LS: Degree of spatial non-randomness at long
distances
CD: Spatial correlation dimension
SR: Degree of spatial repetitiveness
AZ: Average Depth
TI: Time Interval for the occurance of 100 events in
the sample space.
MR: Ratio of two events falling into different
magnitude ranges
Conclusion
 This
method is able to find precursor
events just prior to an earthquake.
 Unfortunately, it only works for short-term
predictions and cannot predict years or
months in advance.
 Plenty of work can still be done!
References
“Predicting the Earthquake using Bagging Method in
Data Mining”, S.Sathiyabama, K.Thyagarajah, D.
Ayyamuthukumar
 “A Bagging Method using Decision Trees in the Role of
Base Classifiers”, Kristína Machová, František Barčák,
Peter Bednár
 “Cluster Analysis, Data-Mining, Multi-dimensional
Visualization of Earthquakes over Space, Time and
Feature Space”, Witold Dzwinel, David A. Yuen,
Krzysztor Boryczko, Yehuda Ben-Zion, Shoichi Yoshioka,
Takeo Ito
 http://cse.stanford.edu/class/sophomorecollege/projects-00/neuralnetworks/Architecture/feedforward.html
