A Method for Recognition of Earthquake Event Arrival Time Based on ssnet Model
A technology for identifying methods and events, applied in seismology, earthquake measurement, neural learning methods, etc., can solve the problems of model design, improvement and tuning due to lack of seismic data characteristics, and achieve the effect of improving accuracy
Active Publication Date: 2021-04-20
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these existing technologies are still stuck in applying basic neural network models to solve problems in the field of earthquakes, lacking model design, improvement, and tuning for the characteristics of seismic data
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0028] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0029] Such as figure 1 Shown, the present invention is based on the seismic event arrival identification method of SSNet model, and concrete steps are as follows:
[0030] (1) Collect continuous waveform records of ground vibration recorded by seismic monitoring stations for timely identification of earthquake events. The feature dimension of the sample is 3×3000, where 3 means that the waveform record has three direction components: east-west, north-south, and vertical. The dimension of 3000 means that the time length of the intercepted data is 30s, and the sampling frequency of the data is 100Hz.
[0031] (2) the present invention adopts such as figure 2The SSNet model shown is used to identify the arrival time of earthquake events. The convolutiona...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an SSNet model-based earthquake event arrival time identification method, which includes: (1) collecting a large number of ground vibration waveform records of earthquake monitoring stations and corresponding earthquake catalogs; (2) proposing the SSNet model to solve the earthquake event arrival time Identification problem; (3) use seismic event samples and randomly collected non-seismic event ground vibration samples to train the SSNet model to obtain a recognition model for seismic event detection; (4) use seismic event samples and seismic phase arrival records The SSNet model is trained to obtain a recognition model for earthquake phase arrival recognition. According to the characteristics of seismic waveform data, the present invention specifically designs a deep network model, comprehensively utilizes technologies such as convolutional neural networks to extract the characteristics of seismic waveform data, captures the characteristics of data, and improves the accuracy and seismicity of seismic event detection tasks. The accuracy of picking tasks when they arrive.
Description
technical field [0001] The invention belongs to the technical field of earthquake early warning, and in particular relates to an SSNet model-based earthquake event arrival identification method. Background technique [0002] Geologists have used the continuous waveform data recorded by seismic monitoring stations for many years to conduct a lot of work and research in the fields of earthquake early warning, earthquake rapid report, and earthquake mechanism; among them, seismic event detection, automatic seismic phase picking, and rapid estimation of earthquake magnitude Such tasks are the focus and hotspots of related research. Seismic event detection refers to the continuous waveform data recorded by seismic monitoring stations to detect whether a certain piece of data belongs to a seismic event, so as to give a judgment on whether an earthquake has occurred at a certain moment; After knowing that a certain segment of waveform data belongs to a seismic event, the exact tim...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01V1/00G06N3/04G06N3/08
CPCG06N3/084G06N3/045G01V1/01
Inventor 赵莎徐逸志李石坚方毅董霖潘纲
Owner ZHEJIANG UNIV