Thermal anomaly detection using NARX neural network method to estimate the earthquake occurrence time

In this study, the remotely sensed thermal data from the earth’s surface of the center zone of the earthquake was used to predict the time of earthquake occurrence. The provided methods for approximating the time and severity of the earthquake are classified into two categories of non-smart and smart. In non-smart methods, the earthquake predicting parameters must be obtained continuously and point to point, to prevent the errors caused by interpolation uncertainty, which requires high levels of cost and furthermore we will be limited in terms of tools in these methods. The smart methods which include Artificial Neural Networks (ANN), Support Vector Machine (SVM), Genetic Algorithm (GA), etc., contain different uncertainties depending on their training algorithms in such a way that by defining an inappropriate threshold between the predicted value and the real ones, they are not able to isolate the variable but natural behavior of the under-study area from anomaly. Because a series of time-dependent data should be used in studying earthquakes, the prediction of theses time series can be done using Artificial Neural Networks. To make more accurate, two different methods of dynamic NARX (Nonlinear Auto Regressive with eXternal input) neural network algorithm namely Levenberg-Marquardt and Scaled conjugated gradient has been applied. The responses of these two methods have been compared with the response derived from mean and variance. The important advantage of the NARX neural network is that small thermal anomaly due to the natural climate changes did not detect and considered as earthquake pre-indicator. The results elucidate that the earthquake, 7 days before (first method response) and 12 days before (second method response) occur has been predicted. The thermal anomaly about 5 degrees of kelvin of earthquake center zone detected. Thus the thermal anomaly detected by this method can be a good pre-indicator for earthquake prediction.