Earthquake prediction technique based on GPS dual frequency system in equatorial region
ABSTRACT The ionospheric Total Electron Content (TEC) measurements were investigated at Universiti Teknologi Malaysia, UTMJ on 20 February - 20 March 2007. The observation was made 14 days before earthquake and 14 days after earthquake. TEC is extracted using GPS dual frequency data which in RINEX format that supplied by JUPEM (Jabatan Ukur dan Pemetaaan Malaysia). In order to reveal possible earthquake precursor through the changes variation of TEC reading, Southern Sumatra Indonesia earthquake that happened on 6th March 2007 is chosen as a study case. The results show that satellite facilities may detect earthquake precursors in ionosphere 5-11 days or a few hours before main shock and various grounds based or satellite observation have shown strong perturbation of the ionosphere after earthquake. The results show a good agreement with other researchers who studied other earthquakes.
SourceAvailable from: rosendo romero andrade02/2014, Degree: Mc
[Show abstract] [Hide abstract]
ABSTRACT: Since early ages, people tried to predicate earthquakes using simple observations such as strange or atypical animal behavior. In this paper, we study data collected from past earthquakes to give better forecasting for coming earthquakes. We propose the application of artificial intelligent predication system based on artificial neural network which can be used to predicate the magnitude of future earthquakes in northern Red Sea area including the Sinai Peninsula, the Gulf of Aqaba, and the Gulf of Suez. We present performance evaluation for different configurations and neural network structures that show prediction accuracy compared to other methods. The proposed scheme is built based on feed forward neural network model with multi-hidden layers. The model consists of four phases: data acquisition, pre-processing, feature extraction and neural network training and testing. In this study the neural network model provides higher forecast accuracy than other proposed methods. Neural network model is at least 32% better than other methods. This is due to that neural network is capable to capture non-linear relationship than statistical methods and other proposed methods.Journal of King Saud University - Science 10/2012; 24(4):301–313. DOI:10.1016/j.jksus.2011.05.002
[Show abstract] [Hide abstract]
ABSTRACT: Earthquake is a natural disaster which causes extensive damage as well as the death of thousands of people. Earthquake professionals for many decades have recognized the benefits to society from reliable earthquake predictions. Techniques like: mathematical modelling, hydrology analysis, ionosphere analysis and even animal responses have been used to forecast a quake. Most of these techniques rely on certain precursors like, stress or seismic activity. Data mining techniques can also be used for prediction of this natural hazard. Data mining consists of evolving set of techniques such as association rule mining that can be used to extract valuable information and knowledge from massive volumes of data. The aim of this study is to predict a subsequent earthquake from the data of the previous earthquake. This is achieved by applying association rule mining on earthquake data from 1979 to 2012. These associations are polished using predicate-logic techniques to draw stimulating production-rules to be used with a rule-based expert system. Prediction process is done by an expert system, which takes only current earthquake attributes to predict a subsequent earthquake. The rules generated for predicting the earthquake are mathematically validated as well as tested on real life earthquake data. Results from our study show that the proposed rule-based expert system is able to detect 100 % of earthquakes which actually occurred within 15 hours at-most within a defined range, depth and location. This work solely relies on previous earthquake data for predicting the next.Journal of Intelligent Information Systems 04/2014; 43(2). DOI:10.1007/s10844-014-0316-5 · 0.63 Impact Factor