Earthquake and artificial blasting identification based on S-spectrum energy curve and convolutional neural networks

With the improvement of earthquake monitoring capabilities and the surge of monitoring data, researches on seismology has entered the era of big data. Especially with the increase of mining blasting, engineering demolition, military construction and other activities, seismic stations will collect a large number of natural and artificial blasting waveforms. Accurately and quickly identifying artificial blasting and natural earthquakes from waveforms has become one of the focuses of earthquake warning and prediction research. Numerous scholars have conducted in-depth researches on earthquake event classification and recognition. The use of convolutional neural network （CNN） technology for earthquake event detection and classification is currently one of the research hot-spots, but one of the key challenges is how to capture the different features of artificial blasting and natural earthquakes.

In order to further study the application of CNN in the field of earthquake event automatic detection and improve the efficiency of event automatic detection, a study was conducted on the classification and identification of natural earthquakes and blasting events based on CNN, with 12 936 artificial blasting micro-seismic records and 13 215 natural micro-seismic records with magnitude M_L1.3−3.0 as the research objects.

Firstly, the seismic waveforms are preprocessed. The original seismic waveforms are filtered using a band-pass filter with a range of 1−30 Hz to remove long-period interference components, resulting in distinct P- and S-wave records. Based on this, P-wave identification is performed using short-term/long-term average （STA/LTA） algorithm, with STA duration set as 0.2 seconds, LTA duration set as 1 second, and threshold size set as 2. The waveforms from 20 seconds before the first arrival time to 100 seconds after the last arrival time were taken as the screening result for this record, resulting in 12 132 effective natural earthquake screening records and 11 721 artificial blasting screening records.

Secondly, the S-transform is applied to obtain the S-transform spectrum of the preprocessed seismic signals. Based on the obtained S-transform spectrum, the S-spectrum energy curve that varies with frequency is then calculated by integrating the energy across different frequency bands. The S-spectrum energy curve can clearly depict the frequency and energy variation of seismic signals. Moreover, it can more effectively capture the characteristics of the original signals.

Then, based on the classic LeNet5 model, a CNN network model, was constructed, which includes one input layer, three convolutional groups consisting of three convolutional layers and three pooling layers, one fully connected layer, and one output layer. In order to reduce resource loss and time consumption, and improve operational efficiency, the three-channel RGB image of the S-spectrum energy curve is converted into a 32×32 pixel-grayscale feature map, which is used as input for CNN. The CNN model is trained using the training set to obtain the optimal CNN model parameters.

Finally, testing is conducted based on the trained CNN model to verify the identification accuracy of natural earthquakes and artificial blasting events. A certain proportion （50%−90%） of the preprocessed seismic record dataset is randomly extracted as training data, with the remaining data used for testing. The tests show that the more training samples there are, the better the classification and identification performance. When the training sample ratio is 90%, the average identification accuracy is up to 97.57%.

The algorithm performance was tested using the ten-fold cross validation method, with the process repeated 100 times. The average identification result was adopted, and the identification accuracy reached 97.80%. The values of the classification performance indicators, namely sensitivity （SE） and specificity （SP）, were close, which indicates good identification performance of the CNN algorithm.

To further test the effectiveness of the S-spectrum energy curve as a feature for seismic signal classification and identification, the S-spectrum, wavelet spectrum, short-time Fourier transform （STFT） spectrum, and fast Fourier transform （FFT） spectrum were used as inputs for CNN model training and testing. The results showed that in comparison to other signal spectra, the S-spectrum energy curve can intuitively reflect the energy magnitude and variations of each frequency component within the signal, with a higher recognition accuracy of over 97%.

The experimental results show that the S-spectrum energy curve can serve as an effective and reliable basis for classifying natural earthquakes and artificial blasting events, and the CNN model in this paper is reliable with good stability and accuracy.

It should be noted that, using simple binary classification problems such as natural earthquakes and artificial blasting alone is not enough to describe the complexity of earthquake event classification and recognition. In the next step, we will collect sample data from different regions and earthquake events, optimize the structural model of CNN training networks, and make the model for earthquake event detection and identification more accurate and the identification effect more intelligent.