Download presentation
Presentation is loading. Please wait.
Published byMagdalen Shelton Modified over 8 years ago
1
Predicting Earthquakes By Lois Desplat
2
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.
3
Estimating earthquake probabilities Scientists study the histories of large earthquakes in a specific area The rate at which strain accumulates in the rock
4
Methods to earthquake prediction Need to construct models based on: Partial differential equations Partial differential equations Finite automata Finite automata Supervised learning techniques: Supervised learning techniques: Decision TreeDecision Tree Bayesian ClassificationBayesian Classification Feed-Forward Neural NetworksFeed-Forward Neural Networks
5
Decision Tree Tries to generate rules with high accuracy ID3, …
6
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
7
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
8
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
9
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
10
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 We still cannot predict earthquakes with enough confidence
11
Solution Do short-term predictions instead of long- term Analyze the data in multiple dimensions over space, time and feature space.
13
Visualization of the Data Space
15
Data Space uses Magnitude, Epicentral Coordinate, Depth and Time of occurrence 7D space uses: NS: Degree of spatial non-randomness at short distances NS: Degree of spatial non-randomness at short distances LS: Degree of spatial non-randomness at long distances LS: Degree of spatial non-randomness at long distances CD: Spatial correlation dimension CD: Spatial correlation dimension SR: Degree of spatial repetitiveness SR: Degree of spatial repetitiveness AZ: Average Depth AZ: Average Depth TI: Time Interval for the occurance of 100 events in the sample space. TI: Time Interval for the occurance of 100 events in the sample space. MR: Ratio of two events falling into different magnitude ranges MR: Ratio of two events falling into different magnitude ranges
16
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!
17
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/sophomore- college/projects-00/neural- networks/Architecture/feedforward.html
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.