Earthquake precursor data abnormity detection method

Abstract

The invention provides an earthquake precursor data abnormity detection method. The method comprises the following steps: obtaining a historical earthquake precursor data set, carrying out data pre-processing and dividing the processed data set into a training set, a verification set and a test set; constructing an LSTM-RNN prediction model; serving the data in the training set as input, and training the prediction model; checking error changes during training with the data in the verification set; setting an abnormal trigger threshold according to a loss function; testing the prediction modelwith the data in the test set, and adjusting the value of hyperparameters according to recognition rate of abnormal data in the test set; and carrying out earthquake precursor data abnormity detection by utilizing the prediction model. The method can identify all kinds of abnormities in the earthquake precursor data and make clear description and accurate distinguishing, and can identify the abnormal information that is not easily perceived by human.

Description

technical field [0001] The invention relates to the field of seismic data detection, in particular to a method for abnormal detection of earthquake precursor data. Background technique [0002] The observation of earthquake precursors and the identification of precursor anomalies are the basis of earthquake prediction. Earthquake prediction is a comprehensive judgment on the development trend of future earthquakes based on the abnormal changes of the observed data before the earthquake. Therefore, earthquake prediction is an interdisciplinary subject highly dependent on observation techniques and data processing methods. Since the M8.0 Wenchuan earthquake in 2008 and the M9.0 earthquake in Japan in 2011, a large number of scholars have revealed the relationship between abnormal changes in data and the occurrence of earthquakes through the analysis of precursor observation data. To sum up, all kinds of precursory data anomalies can be mainly divided into trend turning point...

AI Technical Summary

Problems solved by technology

The above methods are only suitable for a certain type of anomaly identification. However, in the actual observation process, various anomalies often appear superimposed, and the existing methods are difficult to complete the unified identification, clear description and accurate distinction of various anomalies.

Images