US-20260126558-A1 - NEURAL NETWORK FOR AUTOMATED MICROSEISMIC DETECTION AND LOCATION

Abstract

A computer implemented method for detecting and locating microseismic events is provided. The method comprises using a processor set to receive a dataset from a number of real stations. The dataset comprises information associated with seismic signals in a time period. The processor set trains a neural network comprising a number of neural operators using the dataset. The number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period. The neural network further comprises a classification model and a regression model. The classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period. The processor set detects and locates a number of seismic events using the trained neural network.

Inventors

• Hongyu Sun

Assignees

• BOARD OF REGENTS, THE UNIVERSITY OF TEXAS SYSTEM

Dates

Publication Date

20260507

Application Date

20251027

Claims (20)

1. 1 . A computer implemented method comprising: receiving, by a processor set, a dataset from a number of real stations, wherein the dataset comprises information associated with seismic signals in a time period; training, by the processor set using the dataset, a neural network comprising a number of neural operators, wherein the number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period, and wherein the neural network further comprises a classification model and a regression model, and wherein the classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period; and detecting, by the processor set, a number of seismic events using the trained neural network.
2. 2 . The computer implemented method of claim 1 , wherein the combination of neural operator layers comprises a first neural operator for processing temporal features of the seismic signals in the time period and a second neural operator for processing spatial features of the seismic signals in the time period.
3. 3 . The computer implemented method of claim 1 , wherein detecting, by the processor set, the number of seismic events using the trained neural network comprises: receiving, by the processor set, data associated with the number of seismic events from a set of real stations; determining, by the processor set, probabilities for the number of seismic events for each real station from the set of real stations using the classification model from the trained neural network; and simultaneously identifying, by the processor set, origin times and locations for the number of seismic events using the regression model from the trained neural network.
4. 4 . The computer implemented method of claim 3 , further comprising: determining, by the processor set, whether the probabilities for the number of seismic events for each real station from the set of real stations exceed a first threshold; in response to determining that the probabilities for the number of seismic events for each real station from the set of real stations exceed the first threshold, determining, by the processor set, whether number for a portion of real stations exceeds a second threshold, wherein the portion of real stations are real stations from the set of real stations that are associated with probabilities exceeding the first threshold; and in response to determining that the number for the portion of real stations exceeds the second threshold, recording, by the processor set, at least locations and time for the number of seismic events in a catalog.
5. 5 . The computer implemented method of claim 1 , further comprising: generating, by the processor set, a number of virtual stations with random locations within a predefined area based on locations of the number of real stations; generating, by the processor set, a set of noise data comprising noise waveforms for the number of virtual stations and the number of real stations; and inserting, by the processor set, the set of noise data into the dataset.
6. 6 . The computer implemented method of claim 1 , wherein the neural network is trained using a loss function for optimizing a total loss generated based on a first loss for the classification model and a second loss for the regression model, and wherein the first loss and the second loss are weighted based on contribution of a regression task and a classification task for detecting the number of seismic events.
7. 7 . The computer implemented method of claim 1 , wherein the training of the neural network is performed using segments of data from the dataset, and wherein each segment of data from the segments of data corresponds to data from a sliding time window for the dataset, wherein the sliding time window ranges from 10 seconds to 60 seconds.
8. 8 . A computer system comprising: a processor set; a set of one or more computer-readable storage media; and program instructions stored on the set of one or more storage media to cause the processor set to perform operations comprising: receiving a dataset from a number of real stations, wherein the dataset comprises information associated with seismic signals in a time period; training a neural network comprising a number of neural operators using the dataset, wherein the number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period, and wherein the neural network further comprises a classification model and a regression model, and wherein the classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period; and detecting a number of seismic events using the trained neural network.
9. 9 . The computer system of claim 8 , wherein the combination of neural operator layers comprises a first neural operator for processing temporal features of the seismic signals in the time period and a second neural operator for processing spatial features of the seismic signals in the time period.
10. 10 . The computer system of claim 8 , wherein detecting the number of seismic events using the trained neural network comprises: receiving data associated with the number of seismic events from a set of real stations; determining probabilities for the number of seismic events for each real station from the set of real stations using the classification model from the trained neural network; and simultaneously identifying locations for the number of seismic events using the regression model from the trained neural network.
11. 11 . The computer system of claim 10 , wherein the operations further comprise: determining whether the probabilities for the number of seismic events for each real station from the set of real stations exceed a first threshold; in response to determining that the probabilities for the number of seismic events for each real station from the set of real stations exceed the first threshold, determining whether number for a portion of real stations exceeds a second threshold, wherein the portion of real stations are real stations from the set of real stations that are associated with probabilities exceeding the first threshold; and in response to determining that the number for the portion of real stations exceeds the second threshold, recording at least locations and time for the number of seismic events in a catalog.
12. 12 . The computer system of claim 8 , wherein the operations further comprise: generating a number of virtual stations with random locations within a predefined area based on locations of the number of real stations; generating a set of noise data comprising noise waveforms for the number of virtual stations and the number of real stations; and inserting the set of noise data into the dataset.
13. 13 . The computer system of claim 8 , wherein the neural network is trained using a loss function for optimizing a total loss generated based on a first loss for the classification model and a second loss for the regression model, and wherein the first loss and the second loss are weighted based on contribution of a regression task and a classification task for detecting the number of seismic events.
14. 14 . The computer system of claim 8 , wherein the training of the neural network is performed using segments of data from the dataset, and wherein each segment of data from the segments of data corresponds to data from a sliding time window for the dataset, wherein the sliding time window ranges from 10 seconds to 60 seconds.
15. 15 . A computer program product comprising: a set of one or more computer-readable storage media; program instructions stored in the set of one or more computer-readable storage media to perform operations comprising: receiving, by a processor set, a dataset from a number of real stations, wherein the dataset comprises information associated with seismic signals in a time period; training, by the processor set using the dataset, a neural network comprising a number of neural operators, wherein the number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period, and wherein the neural network further comprises a classification model and a regression model, and wherein the classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period; and detecting, by the processor set, a number of seismic events using the trained neural network.
16. 16 . The computer program product of claim 15 , wherein the combination of neural operator layers comprises a first neural operator for processing temporal features of the seismic signals in the time period and a second neural operator for processing spatial features of the seismic signals in the time period.
17. 17 . The computer program product of claim 15 , wherein detecting, by the processor set, the number of seismic events using the trained neural network comprises: receiving, by the processor set, data associated with the number of seismic events from a set of real stations; determining, by the processor set, probabilities for the number of seismic events for each real station from the set of real stations using the classification model from the trained neural network; and simultaneously identifying, by the processor set, locations for the number of seismic events using the regression model from the trained neural network.
18. 18 . The computer program product of claim 17 , wherein the operations further comprise: determining, by the processor set, whether the probabilities for the number of seismic events for each real station from the set of real stations exceed a first threshold; in response to determining that the probabilities for the number of seismic events for each real station from the set of real stations exceed the first threshold, determining, by the processor set, whether number for a portion of real stations exceeds a second threshold, wherein the portion of real stations are real stations from the set of real stations that are associated with probabilities exceeding the first threshold; and in response to determining that the number for the portion of real stations exceeds the second threshold, recording, by the processor set, at least locations and time for the number of seismic events in a catalog.
19. 19 . The computer program product of claim 15 , wherein the operations further comprise: generating, by the processor set, a number of virtual stations with random locations within a predefined area based on locations of the number of real stations; generating, by the processor set, a set of noise data comprising noise waveforms for the number of virtual stations and the number of real stations; and inserting, by the processor set, the set of noise data into the dataset.
20. 20 . The computer program product of claim 15 , wherein the training of the neural network is performed using segments of data from the dataset, wherein each segment of data from the segments of data corresponds to data from a sliding time window for the dataset, wherein the sliding time window ranges from 10 seconds to 60 seconds.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application claims the benefit of U.S. Provisional Patent Application Ser. No. 63/715,422, filed Nov. 1, 2024, and entitled “Automated Microseismic Detection and Location with Quake Neural Operator,” which is incorporated herein by reference in its entirety. BACKGROUND INFORMATION 1. Field The present disclosure relates generally to a neural network for automated microseismic detection and location. 2. Background Seismic events are occurrences that generate vibrations or waves propagating through the Earth. Seismic events are typically caused by sudden energy releases within the crust or upper mantle. These events can include natural phenomena such as earthquakes, volcanic eruptions, or human-induced activities like explosions, reservoir-induced tremors, and mining operations. Microseismic events are similar in nature but involve much smaller energy releases that often go unnoticed at the surface. Microseismic events occur on a micro scale, usually producing very weak vibrations that can only be detected by sensitive instruments placed close to the source. In this case, microseismic events can arise naturally from minor rock stress adjustments or be triggered by human activities such as hydraulic fracturing or underground excavation. SUMMARY An illustrative embodiment provides a computer-implemented method. The method comprises using a processor set to receive a dataset from a number of real stations. The dataset comprises information associated with seismic signals in a time period. The processor set trains a neural network comprising a number of neural operators using the dataset. The number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period. The neural network further comprises a classification model and a regression model. The classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period. The processor set detects a number of seismic events using the trained neural network. Another illustrative embodiment provides a computer system. The system comprises a processor set, a set of one or more computer-readable storage media, and program instructions stored on the set of one or more storage media to cause the processor set to perform operations comprising receiving a dataset from a number of real stations, where the dataset comprises information associated with seismic signals in a time period; training a neural network comprising a number of neural operators using the dataset, where the number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period, where the neural network further comprises a classification model and a regression model, and the classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period; and detecting a number of seismic events using the trained neural network. Another illustrative embodiment provides a computer program product. The computer program product comprises a set of one or more computer-readable storage media, and program instructions stored in the set of one or more storage media to perform operations comprising using a processor set to receive a dataset from a number of real stations, where the dataset comprises information associated with seismic signals in a time period; training a neural network comprising a number of neural operators using the dataset, where the number of neural operators comprise a combination of neural operator layers for identifying temporal-spatial information associated with the seismic signals in the time period, where the neural network further comprises a classification model and a regression model, and the classification model and the regression model are trained using the dataset and the temporal-spatial information associated with the seismic signals in the time period; and detecting a number of seismic events using the trained neural network. The features and functions can be achieved independently in various embodiments of the present disclosure or may be combined in yet other embodiments in which further details can be seen with reference to the following description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS The novel features believed characteristic of the illustrative embodiments are set forth in the appended claims. The illustrative embodiments, however, as well as a preferred mode of use, further objectives and features thereof, will best be understood by reference to the following detailed description of an illustrative embodiment of the present disclosure when read in conjunction with the accompanying drawings, wherein: FIG. 1 is a pictorial represen