A seismic activity fault monitoring and early warning method and system

Abstract

The application discloses a seismic activity fault monitoring and early warning method and system, and the early warning method comprises the following steps: taking the average deformation rate as a first feature and taking the cumulative deformation variable as a second feature; obtaining the position change and speed change of a monitoring area based on GNSS data, extracting a third feature according to the position change and extracting a fourth feature according to the speed change; extracting a fifth feature based on leveling observation data and extracting a sixth feature based on fault gas measurement data; constructing and training a first deep learning model and a second deep learning model, inputting the first feature, the second feature, the third feature and the fourth feature into the first deep learning model to obtain a first result, inputting the fifth feature and the sixth feature into the second deep learning model to obtain a second result; constructing and training a third deep learning model; and inputting the first result and the second result into the third deep learning model to obtain stratum early warning information.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of stratum early warning, in particular to a seismic activity fault monitoring and early warning method and system. BACKGROUND

[0002] A large number of relevant researches at home and abroad show that active faults are the source of earthquakes and the culprit of earthquake disasters. The surface rupture and dislocation of active faults in earthquakes cause serious direct damage to ground buildings, and superimpose on the damage caused by earthquake vibration, which aggravates the ground damage and disaster degree along the active fault, and shows that active faults have obvious control effect on the distribution of serious earthquake disaster zones. The practical experience of earthquake disaster prevention at home and abroad shows that monitoring the spatial position of active faults, scientifically evaluating the seismic risk thereof, and reasonably avoiding or taking effective engineering measures on this basis are effective ways to reduce the risk of earthquake disasters and reduce disaster losses. However, there is a lack of long-term monitoring and early warning method and system for stratum activity in the prior art. SUMMARY

[0003] In view of the above prior art, the present application provides a seismic activity fault monitoring and early warning method and system, which mainly solves the technical problems in the background art.

[0004] To achieve the above purpose, the technical scheme of the embodiment of the present application is as follows:

[0005] The first aspect of the present application discloses a seismic activity fault monitoring and early warning method, which comprises the following steps:

[0006] Obtaining synthetic aperture radar data, GNSS data, leveling observation data and fault gas measurement data;

[0007] Obtaining the average deformation rate and the cumulative deformation amount of each pixel point based on the synthetic aperture radar data, taking the average deformation rate as the first feature and the cumulative deformation amount as the second feature;

[0008] Obtaining the position change and the speed change of the monitoring area based on the GNSS data, extracting the third feature according to the position change and the fourth feature according to the speed change;

[0009] Extracting the fifth feature based on the leveling observation data and the sixth feature based on the fault gas measurement data;

[0010] Constructing and training the first deep learning model and the second deep learning model, inputting the first feature, the second feature, the third feature and the fourth feature into the first deep learning model to obtain the first result, and inputting the fifth feature and the sixth feature into the second deep learning model to obtain the second result;

[0011] A third deep learning model is constructed and trained. The first result and the second result are input into the third deep learning model to obtain stratum early warning information.

[0012] Optionally, the average deformation rate of each pixel point is obtained based on the synthetic aperture radar data, and specifically includes:

[0013] Synthetic aperture radar images are acquired, and the synthetic aperture radar images are preprocessed;

[0014] Based on the preprocessed synthetic aperture radar images, a series of interferograms are generated;

[0015] The SBAS-InSAR method is used to analyze the time series of the interferograms, and the deformation time series data of each pixel point is extracted;

[0016] The deformation values of each pixel point at multiple time points are obtained in the deformation time series data of each pixel;

[0017] The deformation values are fitted using the least square method to form a deformation straight line, and the slope of the deformation straight line is the average deformation rate.

[0018] Optionally, the cumulative deformation amount of each pixel point is obtained based on the synthetic aperture radar data, and specifically includes:

[0019] Synthetic aperture radar images are acquired, and the synthetic aperture radar images are preprocessed;

[0020] Based on the preprocessed synthetic aperture radar images, a series of interferograms are generated;

[0021] The SBAS-InSAR method is used to analyze the time series of the interferograms, and the deformation time series data of each pixel point is extracted;

[0022] The deformation values of each pixel point from the start time to the end time are obtained in the deformation time series data of each pixel, and the cumulative deformation amount is obtained based on the deformation values from the start time to the end time.

[0023] Optionally, a plurality of GNSS receivers are arranged in the monitoring area, the monitoring area contains a fracture zone, and the GNSS receivers include at least one fixed receiver and three mobile receivers, the mobile receivers perform data acquisition for not less than three effective periods at each measuring point.

[0024] Optionally, the position change of the monitoring area is obtained based on the GNSS data, and specifically includes:

[0025] The GNSS receivers are used to obtain coordinate positions of each GNSS receiver at each time node of each measuring point, and the coordinate positions are plotted into a time sequence diagram with time variation;

[0026] The position variation of each receiver is extracted from the time sequence, and is expressed in coordinate variation in east direction, north direction and vertical direction;

[0027] The coordinate difference between adjacent time nodes is calculated, and the final position variation is obtained based on multiple coordinate differences.

[0028] Optionally, the velocity variation of the monitoring area is obtained based on GNSS data, specifically including: after the multiple coordinate differences are obtained, the coordinate differences are fitted by a least square method to obtain a coordinate difference straight line, and the slope of the coordinate difference straight line is calculated, which is the velocity variation.

[0029] Optionally, a leveling time sequence is obtained from leveling observation data, and the leveling time sequence is taken as a fifth feature.

[0030] Optionally, a gas time sequence is obtained from fault gas measurement data, and the gas time sequence is taken as a sixth feature.

[0031] The second aspect of the present application discloses a seismic activity fault monitoring and early warning system, which comprises a level, a radon detector, a first data acquisition terminal, a second data acquisition terminal and an Internet of Things platform, the level is used to collect leveling observation data, the radon detector is used to collect fault gas measurement data, the first data acquisition terminal is used to receive data from a synthetic aperture radar and GNSS data, the second data acquisition terminal is used to receive leveling observation data and fault gas measurement data, and the Internet of Things platform is configured to receive data from the first data acquisition terminal and the second data acquisition terminal, and to generate stratum early warning information according to a first deep learning model, a second deep learning model and a third deep learning model.

[0032] The beneficial effects of this invention are as follows: By acquiring synthetic aperture radar (SAR) data, GNSS data, leveling observation data, and fault gas measurement data, the average deformation rate is obtained as the first feature from the SAR data, and the cumulative deformation is obtained as the second feature. The position and velocity changes of the monitoring area are obtained from the GNSS data, and a third feature is extracted from the position change, a fourth feature is extracted from the velocity change, a leveling time series is obtained from the leveling observation data as the fifth feature, and a gas time series is obtained from the fault gas measurement data as the sixth feature. The first, second, third, and fourth features are input into a first deep learning model to obtain the stratigraphic deformation analysis results based on radar conditions. The fifth and sixth features are input into a second deep learning model to obtain the stratigraphic deformation analysis results based on environmental conditions. Finally, the stratigraphic deformation analysis results based on radar conditions and the stratigraphic deformation analysis results based on environmental conditions are input into a third deep learning model to obtain the stratigraphic deformation results. By using multiple data sources such as GNSS, SAR, leveling observation, and fault gas measurement, crustal movement and earthquake precursor information can be more comprehensively reflected. Attached Figure Description

[0033] Figure 1 This is a flowchart of a seismic active fault monitoring and early warning method according to an embodiment of this application;

[0034] Figure 2 This is a schematic diagram of the module composition of an active fault monitoring and early warning system according to an embodiment of this application.

[0035] Explanation of icon numbers:

[0036] Level instrument 1, radon meter 2, first data acquisition terminal 3, second data acquisition terminal 4, and Internet of Things platform 5. Detailed Implementation

[0037] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. In the following description, the expression "some embodiments" refers to a subset of all possible embodiments; however, it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0038] In the following description, numerous specific details are set forth to provide a more thorough understanding of the present application. However, it will be apparent to one of skill in the art upon

[0039] It should be understood that the present application can be practiced with the elements in different order, and that the embodiments proposed herein should be construed in a manner consistent with the change thereof. Rather, the present application is to cover all modifications, equivalents, and alternatives falling within the scope of the present application. The terms used in the specification are for the purpose of describing particular embodiments only and are not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0040] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0041] For a thorough understanding of the present application, reference will be made to the following detailed description, taken in conjunction with the accompanying drawings, in which:

[0042] Reference will now be made to the drawings, in which Figure 1 The first aspect of the present application discloses a method for monitoring and early warning of seismic activity fault, the early warning method comprising the following steps:

[0043] S1, obtaining synthetic aperture radar data, GNSS data, leveling observation data and fault gas measurement data;

[0044] S2, obtaining the average deformation rate and the cumulative deformation of each pixel point based on the synthetic aperture radar data, taking the average deformation rate as the first feature, and taking the cumulative deformation as the second feature;

[0045] S3, obtain the position change and the speed change of the monitoring area based on the GNSS data, and extract a third feature according to the position change and a fourth feature according to the speed change;

[0046] S4, extract a fifth feature based on the leveling observation data and a sixth feature based on the fault gas measurement data;

[0047] S5, construct and train a first deep learning model and a second deep learning model, input the first feature, the second feature, the third feature and the fourth feature into the first deep learning model to obtain a first result, and input the fifth feature and the sixth feature into the second deep learning model to obtain a second result;

[0048] S6, construct and train a third deep learning model, input the first result and the second result into the third deep learning model to obtain the stratum early warning information.

[0049] In this embodiment, the average deformation rate is obtained from the synthetic aperture radar data as the first feature, the cumulative deformation amount is obtained as the second feature, the position change and the speed change of the monitoring area are obtained from the GNSS data, the third feature is extracted from the position change, the fourth feature is extracted from the speed change, the leveling time sequence is obtained from the leveling observation data as the fifth feature, the gas time sequence is obtained from the fault gas measurement data as the sixth feature, the first feature, the second feature, the third feature and the fourth feature are input into the first deep learning model to obtain the stratum deformation analysis result based on the radar condition, the fifth feature and the sixth feature are input into the second deep learning model to obtain the stratum deformation analysis result based on the environmental condition, and finally the stratum deformation analysis result based on the radar condition and the stratum deformation analysis result based on the environmental condition are input into the third deep learning model to finally obtain the stratum deformation result.

[0050] In a possible implementation, the types of the first deep learning model, the second deep learning model and the third deep learning model are all different, for example, the first deep learning model adopts a convolutional recurrent neural network, the second deep learning model adopts a long short-term memory (LSTM) model which can process long-time dependence and is suitable for time sequence prediction of seismic waveform data and is suitable for the leveling time sequence and the gas time sequence, and the third deep learning model adopts an autoencoder structure which can realize anomaly detection.

[0051] In a possible implementation, the average deformation rate of each pixel point is obtained based on the synthetic aperture radar data, and specifically includes:

[0052] S201, obtaining synthetic aperture radar images, which are usually obtained by satellites such as Sentinel-1 satellites of the European Space Agency or other commercial SAR satellites, and pre-processing the synthetic aperture radar images, wherein the pre-processing process includes geometric correction and atmospheric correction, wherein the geometric correction is used to eliminate the influence of terrain, and the atmospheric correction is to correct the atmospheric delay effect using an atmospheric model or auxiliary data (such as meteorological data),

[0053] S202, generating a series of interferograms based on the pre-processed synthetic aperture radar images;

[0054] S203, analyzing the time series of the interferograms using the SBAS-InSAR method, and extracting the deformation time series data of each pixel point;

[0055] S204, obtaining the deformation values of each pixel point at multiple time points in the deformation time series data of each pixel, for example, for pixel D1, obtaining the deformation values u1, u2, u3, u4 at time points t1, t2, t3, t4;

[0056] S205, using the least square method to fit the foregoing deformation values to form a deformation straight line, and the slope of the deformation straight line is the average deformation rate.

[0057] In a possible implementation, the cumulative deformation of each pixel point is obtained based on the synthetic aperture radar data, specifically including:

[0058] Obtaining synthetic aperture radar images and pre-processing the synthetic aperture radar images;

[0059] Generating a series of interferograms based on the pre-processed synthetic aperture radar images;

[0060] Analyzing the time series of the interferograms using the SBAS-InSAR method, and extracting the deformation time series data of each pixel point;

[0061] Obtaining the deformation values of each pixel point from the start time to the end time in the deformation time series data of each pixel, and obtaining the cumulative deformation based on the deformation values from the start time to the end time, for example, for pixel D1, obtaining the deformation values u1, u2, u3, u4 at time points t1, t2, t3, t4, and setting the initial value as u0, and the cumulative deformation value is u0+(u2-u2)+(u3-u2)+(u4-u3).

[0062] In a possible implementation, the Beidou satellite positioning system (compatible with other GNSS systems) is adopted. A plurality of domestic Beidou satellite positioning ground-based enhancement stations are arranged in the monitoring area, each of which is provided with a GNSS receiver, and the monitoring area constructed by the plurality of GNSS receivers connected with each other contains a fracture zone, and the GNSS receiver includes at least one fixed receiver and three mobile receivers, the mobile receivers perform data acquisition at each measuring point for not less than three effective periods, and each period of effective data is not less than 23.5 hours.

[0063] Further, the position change of the monitoring area is obtained based on the GNSS data, specifically including:

[0064] The coordinate position of each GNSS receiver at each measuring point is obtained through the GNSS receiver, and the change of the coordinate position with time is plotted into a time sequence diagram;

[0065] The position change of each receiver is extracted from the time sequence, and is expressed in the coordinate change in the east direction, the north direction and the vertical direction;

[0066] The coordinate difference between adjacent time nodes is calculated through a difference algorithm, and the final position change is obtained based on a plurality of coordinate differences.

[0067] Further, the velocity change of the monitoring area is obtained based on the GNSS data, specifically including: after the plurality of coordinate differences are obtained, the coordinate differences are fitted through a least square method to obtain a coordinate difference straight line, and the slope of the coordinate difference straight line is calculated, which is the velocity change.

[0068] Further, the leveling time sequence is obtained from the leveling observation data, and the leveling time sequence is taken as the fifth feature, wherein the technical requirements of leveling observation are measured according to the second-order leveling measurement method. The accuracy of the monitoring instrument should meet the requirements of its reliability. The error requirement in settlement observation is <±0.5mm, and the closure error requirement in leveling measurement is <4mm (L is the length of the measurement section, the unit is km; when the length of the measurement section is less than 0.1km, it is calculated as 0.1km). The settlement observation is measured by using the American Trimble DINI03 high-precision precision digital level and indium steel bar code level, and the error of the instrument in each kilometer of leveling measurement is ±0.3mm.

[0069] Further, previous studies have shown that seismic fault gas radon is the most likely to migrate to the surface in large quantities among the numerous fluid components generated inside the earth, and it is released at a certain point on the surface. Its abnormal concentration and flux can well reflect the situation of seismic activity and fault zone activity. Therefore, the greater the rupture strength of the active fault, the more fissures generated by the rupture, the more radon gas generated, and the high-value measurement points of active fault radon gas are mainly near the fault point and consistent with the fault strike. Through the geochemical characteristics of the soil gas of the seismic active fault, the activity of the fault can be reflected. Therefore, periodic comparative measurement of fault escape gas using reliable equipment can capture the precursory information of abnormal deformation and activity of the active fault.

[0070] The instrument used in this fault escape gas measurement is a KJD-2000R radon measurement instrument produced by Sichuan Xinxindada Measurement and Control Technology Co., Ltd. The air flow rate during measurement is 1 L / min; the measurement unit is Bq / m3 (indicating the number of radon atoms decaying per 1 m3 of gas per 1 second); the sampling rate is 300 s, that is, 5 minutes to read a value; the distance between points on the measurement line is mostly 20 m, and a few adjacent measurement points will have a little increase or decrease due to site restrictions; 3 data are read at each measurement point during measurement, and the second result or the average of the second and third measurement results is taken as the radon concentration at the point (because the first measurement value may not be stable), the reading is accurate to 0.1 Bq / m3, and finally the gas time sequence is obtained from the fault gas measurement data, and the gas time sequence is the sixth feature.

[0071] The second aspect of the present application discloses a seismic active fault monitoring and early warning system, which comprises a level meter 1, a radon measurement instrument 2, a first data acquisition terminal 3, a second data acquisition terminal 4 and an Internet of Things platform 5, wherein the level meter 1 is used for collecting level observation data, the radon measurement instrument 2 is used for collecting fault gas measurement data, the first data acquisition terminal 3 is used for receiving data from a synthetic aperture radar and GNSS data, the second data acquisition terminal 4 is used for receiving level observation data and fault gas measurement data, and the Internet of Things platform 5 is configured to receive data from the first data acquisition terminal 3 and the second data acquisition terminal 4, and generate stratum early warning information according to a first deep learning model, a second deep learning model and a third deep learning model.

[0072] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. The protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for monitoring and early warning of active seismic faults, characterized in that, The early warning method includes the following steps: Acquire synthetic aperture radar data, GNSS data, leveling observation data, and fault gas measurement data; The average deformation rate and cumulative deformation of each pixel are obtained based on the synthetic aperture radar data, with the average deformation rate as the first feature and the cumulative deformation as the second feature. The location and velocity changes in the monitoring area are obtained based on GNSS data, and a third feature is extracted based on the location change and a fourth feature is extracted based on the velocity change. The fifth feature is the leveling time series obtained from leveling observation data, and the sixth feature is the gas time series obtained from fault gas measurement data. Construct and train a first deep learning model and a second deep learning model. Input the first feature, the second feature, the third feature and the fourth feature into the first deep learning model to obtain a first result. Input the fifth feature and the sixth feature into the second deep learning model to obtain a second result. A third deep learning model is constructed and trained. The first and second results are input into the third deep learning model to obtain formation early warning information. The first deep learning model uses a convolutional recurrent neural network, the second deep learning model uses a long short-term memory network, and the third learning model uses an autoencoder structure.

2. The method for monitoring and early warning of active seismic faults according to claim 1, characterized in that, The average deformation rate of each pixel is obtained based on the synthetic aperture radar data, specifically including: Acquire synthetic aperture radar images and preprocess the synthetic aperture radar images; A series of interferograms are generated based on the preprocessed synthetic aperture radar image; The time series of the interferogram was analyzed using the SBAS-InSAR method, and the deformation time series data of each pixel was extracted. Obtain the deformation value of each pixel at multiple time points from the deformation time series data of each pixel; The deformation values ​​are fitted using the least squares method to form a deformation line, and the slope of the deformation line is the average deformation rate.

3. The method for monitoring and early warning of active seismic faults according to claim 2, characterized in that, The cumulative deformation of each pixel is obtained based on the synthetic aperture radar data, specifically including: Acquire synthetic aperture radar images and preprocess the synthetic aperture radar images; A series of interferograms are generated based on the preprocessed synthetic aperture radar image; The time series of the interferogram was analyzed using the SBAS-InSAR method, and the deformation time series data of each pixel was extracted. Obtain the deformation value of each pixel from the start to the end of the time in the deformation time series data of each pixel, and obtain the cumulative deformation value based on the deformation value from the start to the end of the time.

4. The method for monitoring and early warning of active seismic faults according to claim 3, characterized in that, Multiple GNSS receivers are set up in the monitoring area, which includes a fault zone, and the GNSS receivers include at least one fixed receiver and three mobile receivers, with the mobile receivers collecting data at each measuring point for no less than three effective time periods.

5. The method for monitoring and early warning of active seismic faults according to claim 4, characterized in that, The location changes in the monitoring area are obtained based on GNSS data, specifically including: The coordinates of each GNSS receiver at each measurement point at each time node are obtained using the GNSS receiver, and the changes of the coordinates over time are plotted as a time series graph. The positional changes of each receiver are extracted from the time series and represented by coordinate changes in the east, north, and vertical directions; Calculate the coordinate differences between adjacent time points, and obtain the final position change based on multiple coordinate differences.

6. The method for monitoring and early warning of active seismic faults according to claim 5, characterized in that, The velocity change in the monitoring area is obtained based on GNSS data, specifically including: after obtaining the multiple coordinate differences, fitting the coordinate differences using the least squares method to obtain a coordinate difference line, and calculating the slope of the coordinate difference line, which is the velocity change.

7. A seismic active fault monitoring and early warning system, said system being used to implement the seismic active fault monitoring and early warning method as described in any one of claims 1-6, characterized in that, The system includes: a level, a radon detector, a first data acquisition terminal, a second data acquisition terminal, and an Internet of Things (IoT) platform. The level is used to collect leveling observation data, the radon detector is used to collect fault gas measurement data, the first data acquisition terminal is used to receive data from synthetic aperture radar and GNSS data, the second data acquisition terminal is used to receive leveling observation data and fault gas measurement data, and the IoT platform is configured to receive data from the first and second data acquisition terminals, and to generate stratigraphic early warning information based on a first deep learning model, a second deep learning model, and a third deep learning model.

Images