Intelligent earthquake monitoring system and device based on artificial intelligence

Abstract

The embodiment of the invention discloses an earthquake intelligent monitoring system based on artificial intelligence and a device thereof. The invention provides an intelligent earthquake monitoring system based on artificial intelligence, and the system comprises a server which is used for carrying out the seismic facies pickup association and earthquake positioning through employing a large model, and transmitting the seismic facies information and positioning information obtained through pickup to a client; the client is used for displaying the seismic phase information and the positioning information and acquiring a unified cataloguing result from a seismic network center so as to manually recheck the seismic phase information, the positioning information and the unified cataloguing result, so that an integrated system of'automatic processing and manual rechecking 'is constructed, the optimal balance between efficiency and quality is realized, and the quality of the seismic data is improved. And the task processing accuracy is further improved.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of geophysics, and in particular to a kind of artificial intelligence-based seismic monitoring system and device thereof. BACKGROUND

[0002] In recent years, artificial intelligence technology has been widely applied in the field of seismic monitoring and has achieved remarkable results. A large number of studies have shown that the deep learning model trained based on massive data can achieve an accuracy rate of more than 90% in seismic phase identification tasks, and the pick-up accuracy is comparable to manual pick-up, while showing relative advantages in low signal-to-noise ratio signals and computing efficiency.

[0003] At present, most seismic intelligent automatic monitoring systems generally adopt BS architecture, which performs data access and processing in the background and displays the results through a Web interface. This type of design architecture is convenient for unified deployment and maintenance, but is limited by browser performance and still has a lot of room for improvement in terms of interactive experience and result confirmation.

[0004] Research and practice have shown that the earthquakes identified by artificial intelligence-based seismic detection methods are often much more than the earthquakes identified by manual methods. For earthquakes that exist in manual processing, statistical analysis and comparison can be used to evaluate the results, but for earthquakes detected by artificial intelligence methods, there is currently no authoritative and applicable way to automatically verify them.

[0005] In practice, although in the application of focusing on the number and spatial distribution of aftershocks, the artificial intelligence-based automatic monitoring method can meet the demand, but in the task of earthquake cataloging, high-credibility catalog construction, and non-natural earthquake monitoring, which requires high precision and certainty, the artificial intelligence alone is still not competent.

[0006] In particular, due to the earthquake information identified or misidentified by artificial intelligence, a corresponding review mechanism is needed to further improve the intelligent monitoring system and achieve the important demand of performance balance. Therefore, a more accurate seismic monitoring scheme is needed. SUMMARY

[0007] The embodiments of the present specification provide an artificial intelligence-based seismic monitoring system and device thereof to solve the technical problem of the need for a more accurate seismic monitoring scheme.

[0008] To solve the above technical problems, one or more embodiments of the present specification are implemented as follows:

[0009] In a first aspect, the embodiments of the present specification provide an intelligent earthquake monitoring system based on artificial intelligence, comprising: a server end configured to perform phase picking correlation and earthquake positioning by using a large model, and send picked phase information and positioning information to a client end; the client end is configured to display the phase information and the positioning information, and obtain a unified catalog result from a seismic network center, so as to manually review the phase information and the positioning information and the unified catalog result.

[0010] In a second aspect, one or more embodiments of the present specification provide an intelligent earthquake monitoring device based on artificial intelligence, comprising: a display module configured to display the phase information and the positioning information; an acquisition module configured to obtain a unified catalog result from a seismic network center; a review module configured to manually review the phase information and the positioning information and the unified catalog result; and a construction module.

[0011] The above at least one technical solution adopted by one or more embodiments of the present specification can achieve the following beneficial effects: by providing an intelligent earthquake monitoring system based on artificial intelligence, the system comprises: a server end configured to perform phase picking correlation and earthquake positioning by using a large model, and send picked phase information and positioning information to a client end; the client end is configured to display the phase information and the positioning information, and obtain a unified catalog result from a seismic network center, so as to manually review the phase information and the positioning information and the unified catalog result, thereby realizing the construction of an integrated system of "automatic processing + manual review", achieving the optimal balance between efficiency and quality, and further improving the accuracy of task processing. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present specification, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0013] Figure 1 A schematic diagram of an automatic method for detecting earthquake events based on artificial intelligence provided by the embodiments of the present specification;

[0014] Figure 2 A schematic diagram of a framework of an intelligent earthquake monitoring system based on artificial intelligence provided by one or more embodiments of the present specification;

[0015] Figure 3 A schematic diagram of an automatic processing example of a Gaomi, Shandong, China, blasting event by a system provided by the embodiments of the present specification;

[0016] Figure 4 This is a schematic diagram of the functional architecture of a client provided in an embodiment of this specification;

[0017] Figure 5 This is a structural schematic diagram of an artificial intelligence-based intelligent earthquake monitoring device provided for one or more embodiments of this specification. Detailed Implementation

[0018] This specification provides an artificial intelligence-based intelligent earthquake monitoring system and device.

[0019] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0020] In current earthquake monitoring, AI-based earthquake detection methods often identify far more earthquakes than those identified manually. This is primarily due to several factors: firstly, AI models are more sensitive to weak signals, effectively detecting more small-magnitude events; secondly, some small-magnitude non-natural earthquakes are not processed manually in routine data collection; and thirdly, due to the technical limitations of automated methods and the influence of seismic network layout, false detections can occur in automated results.

[0021] Therefore, the interactive review mode can not only distinguish between multiple detections and false detections, but also provide necessary accuracy guarantees for needs with high precision and reliability requirements. Taking cataloging as an example, its basic requirements are that earthquakes are not repeated, omitted, or over-reported; seismic phases are complete and accurate; and clear seismic phases such as PmP and PKP, which cannot be automatically detected by current AI methods, need to be annotated. Figure 1 As shown, Figure 1 This diagram illustrates an automated method for seismic event detection based on artificial intelligence, as provided in the embodiments of this specification. Although the earthquake location and correlation results are consistent with manual analysis, the S-wave phase of the second data stream needs to be supplemented to meet relevant requirements. Figure 1 In the right half of the image, the red box marks the seismic phases missed by the automated AI method, requiring manual verification for their inclusion. Furthermore, in the determination of special events such as blasting and collapses, final manual verification is also an indispensable step.

[0022] Based on this, embodiments of this application provide an artificial intelligence-based intelligent earthquake monitoring system and apparatus, which achieves more accurate earthquake monitoring through the interaction of artificial intelligence and human review.

[0023] Figure 2 This is a schematic diagram illustrating the framework of an artificial intelligence-based intelligent earthquake monitoring system provided for one or more embodiments of this specification. Specifically, the system includes:

[0024] The server is used to perform phase picking and earthquake location using a large model, and send the picked phase information and location information to the client; and the client is used to display the phase information and location information, and to obtain unified cataloging results from the seismic network center so as to manually verify the phase information, location information and unified cataloging results.

[0025] This invention provides an artificial intelligence-based intelligent earthquake monitoring system, comprising: a server for using a large model to perform seismic phase picking and correlation and earthquake location, and sending the picked seismic phase information and location information to a client; and a client for displaying the seismic phase information and location information, and obtaining unified cataloging results from the seismic network center for manual verification of the seismic phase information, location information, and unified cataloging results. This achieves an integrated system of "automatic processing + manual verification," realizing an optimal balance between efficiency and quality, and further improving the accuracy of task processing.

[0026] Furthermore, to better optimize automatic monitoring and event reliability assessment across the country and even globally, and to achieve front-end and back-end functional synergy, the manual review of the seismic phase information, location information, and unified cataloging results requires the following steps: generating an event catalog containing error and multiple classifications, identifying the causes of the event catalog, and analyzing the output characteristics of the event catalog.

[0027] In other words, by comparing with the unified cataloging results of the seismic network center, the phase information and location information in the existing system operation process are compared and analyzed to obtain the event catalog of error judgment and multiple judgment; the relevant event catalog is analyzed to preliminarily determine the error causes or output characteristics corresponding to different types of events.

[0028] When determining the cause of the event catalog, the client mainly determines the theoretical travel time of the phases in the event catalog and judges the cause of the event catalog based on the difference between the theoretical travel time and the actual travel time.

[0029] Furthermore, when manually reviewing the seismic phase information, location information, and unified cataloging results, the location information can be compared with the unified cataloging results to determine whether the earthquake event type belongs to a high-confidence earthquake event (e.g., whether it is a high-intensity earthquake event or whether it belongs to a shale gas event). If so, the accuracy and completeness of the seismic phase information are calculated, and a reliability judgment is made based on the accuracy and completeness of the seismic phase information.

[0030] Furthermore, for this type of high-reliability earthquake event, the client, in order to manually verify the seismic phase information, location information, and unified cataloging results, can compare the location information with the unified cataloging results to determine whether the earthquake event type belongs to the high-reliability requirement. If so, the accuracy and completeness of the seismic phase information are calculated, and a reliability judgment is made based on the accuracy and completeness of the seismic phase information. When the verification fails, the client can add, delete, modify, and query the event catalog containing erroneous and multiple classifications, and record the causes and output characteristics of the event catalog.

[0031] like Figure 3 As shown, Figure 3 This diagram illustrates an example of the automatic processing of a blasting event in Gaomi, Weifang, Shandong Province, provided in an embodiment of this specification. In this diagram, the system automatically records the corresponding seismic phase type, residual, confidence level, signal-to-noise ratio, and magnitude of a blasting event using artificial intelligence. Furthermore, the client can compare this data with data obtained from the seismic network center, and based on the comparison results and confidence levels, add, delete, modify, and query events in the event catalog containing erroneous and multiple classifications, and then report the results.

[0032] Furthermore, the client displays the seismic phase information and location information by sorting them according to the seismic phase quality and residual size, and by displaying the seismic phase information and location information separately.

[0033] Furthermore, the client is also used to add, delete, query, and modify the event directory after manual review, and submit the added, deleted, query, and modified event directory to the server so that the server can perform associated storage.

[0034] Furthermore, the client displays the seismic phase information and location information, including: displaying continuous waveforms, and distinguishing between associated seismic phases and isolated seismic phases by displaying or hiding them.

[0035] Furthermore, the client is also used to determine whether it is a strong earthquake based on the seismic phase information and location information, and to perform strong earthquake processing.

[0036] Furthermore, the server is also used for user authentication, enabling controllable interaction permissions for users logging in from the client.

[0037] like Figure 4 As shown, Figure 4 This is a schematic diagram of the functional architecture of a client provided in the embodiments of this specification. The client includes a backend section and a verification interaction section. Based on a preliminary client interaction prototype, the overall client design is completed; user login authentication and data encryption functions are implemented to ensure data security; functions for adding, deleting, searching, and modifying seismic phases are designed and implemented, along with sorting and distinguishing display functions based on seismic phase quality and residual size to improve the experience of identifying abnormal seismic phases; functions for adding, deleting, searching, and modifying earthquake events are designed and implemented, providing methods and display methods for earthquake event reliability assessment; a secondary location function for earthquake events and a seismic phase retrieval mechanism are designed and implemented; a continuous waveform browsing mechanism and functions for distinguishing and hiding associated and isolated seismic phases are designed and implemented; a local association algorithm is built-in and its configuration is visualized; multiple neural networks are built-in to achieve semi-automatic processing of interactive analysis; instrument response, local configuration of instrument information, and remote synchronization functions are designed and implemented to automate simulation processing; amplitude and travel time phases are visualized, and amplitude and travel time phases are automatically measured and picked up based on theoretical travel time; local information caching and batch submission functions are implemented. Through the above work, the user experience of the interactive client is improved and enhanced, achieving semi-automatic interaction that meets the requirements.

[0038] Based on the same idea, one or more embodiments of this specification also provide an apparatus corresponding to the above method, such as... Figure 5 As shown.

[0039] Figure 5 A schematic diagram of an artificial intelligence-based intelligent earthquake monitoring device provided for one or more embodiments of this specification, the device comprising:

[0040] Display module 501 is used to display the seismic phase information and location information;

[0041] Module 503 retrieves unified cataloging results from the seismic network center;

[0042] The verification module 505 manually verifies the seismic phase information, location information, and unified cataloging results.

[0043] Based on the same idea, embodiments of this specification also provide a non-volatile computer storage medium corresponding to the above method, which stores computer-executable instructions. When a computer reads the computer-executable instructions from the storage medium, the instructions cause one or more processors to execute the method as described in the first aspect.

[0044] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0045] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0046] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0047] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. An artificial intelligence-based intelligent earthquake monitoring system, the system comprising: a server configured to perform phase picking correlation and earthquake location using a large model, and send picked phase information and location information to a client; the client configured to display the phase information and location information, and obtain a unified catalog result from a seismic network center, so as to manually review the phase information and location information and the unified catalog result.

2. The system of claim 1, wherein, the client manually reviews the phase information and location information and the unified catalog result, comprising: generating an event catalog containing error discrimination and multiple discrimination, discriminating the causes of the event catalog, and analyzing the output characteristics of the event catalog.

3. The method of claim 2, wherein, the client manually reviews the phase information and location information and the unified catalog result, comprising: comparing the location information with the unified catalog result to determine whether the type of the earthquake event belongs to a high-accuracy earthquake event, and if so, calculating the accuracy and completeness of the phase information, and judging the reliability according to the accuracy and completeness of the phase information; when the review fails, the client adds, deletes, modifies, or inquires the event catalog containing error discrimination and multiple discrimination, and records the causes and output characteristics of the event catalog.

4. The system of claim 1, wherein the client is further configured to, after manual review, add, delete, modify, or inquire the event catalog, and submit the modified event catalog to the server for correlation storage.

5. The system of claim 1, wherein, The server is further configured for user authentication to realize controllable interaction permissions of the client login user.

6. The system of claim 1, wherein, The client displays the phase information and location information, comprising: The client sorts according to phase quality and residual size, and displays the phase information and location information separately.

7. The system of claim 2, wherein, The client displays the phase information and location information, comprising: displaying continuous waveforms, and displaying or hiding the associated phases and isolated phases separately.

8. The system of claim 2, wherein, The client discriminates the causes of the event catalog, comprising: determining the theoretical travel time of the phases in the event catalog, and determining the causes of the event catalog according to the difference between the theoretical travel time and the actual travel time.

9. The system of claim 1, wherein, The client is further configured to determine whether it is a strong earthquake according to the phase information and location information, and perform strong earthquake processing.

10. An artificial intelligence-based intelligent earthquake monitoring device, comprising: a display module configured to display the phase information and location information; an acquisition module configured to obtain a unified catalog result from a seismic network center; a review module configured to manually review the phase information and location information and the unified catalog result.

Images