Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 2

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
w słowach kluczowych:  przewidywanie trzęsień ziemi
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
Is it possible to predict location, time and magnitude of earthquakes through identifying their precursors based on remotely sensed data? Earthquakes are usually preceded by unusual natural incidents that are considered as earthquake precursors. With the recent advances in remote sensing techniques which have made it possible monitoring the earth’s surface with diferent sensors, scientists are now able to better study earthquake precursors. Thus, the present study aims at developing the algorithm of classic PS-InSAR processing for obtaining crustal deformation values at the epicenter of earthquakes with magnitude larger than 5.0 on the Richter scale and with oblique thrust faulting and then after calculating temperature values using remotely sensed thermal imagery at the epicenter of same earthquakes; thermal and crustal deformation anomalies were calculated using data mining techniques before earthquake occurrence. In the next stage, taking the correlation between thermal anomalies and crustal deformation anomalies at the epicenter of the study earthquakes into account, an integrated technique was proposed to predict probable magnitude and time of oblique thrust earthquakes occurrence over the earthquake-prone areas. Eventually, the validity of the proposed algorithm was evaluated for an earthquake with a diferent focal mechanism. The analysis results of the thermal anomalies and crustal deformation anomalies at the epicenter of April 16, 2016, Japan-Kumamoto earthquake of magnitude 7.0 with strike-slip faulting, showed completely diferent trends than the suggested patterns by the proposed algorithm.
Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar’s statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.