A positioning method, device and equipment for marine seismic and readable storage medium

Abstract

The application provides a positioning method, device and equipment for marine earthquakes and a readable storage medium, relates to the technical field of earthquake prediction, and comprises the following steps: obtaining a plurality of historical earthquake data sets; obtaining a real-time earthquake data set; performing difference preprocessing on the plurality of historical earthquake data sets and the real-time earthquake data set to obtain a plurality of target earthquake data sets and a predicted earthquake data set; training a preset decision tree model based on the target earthquake data sets, stopping the training when a preset model index meets a set condition, and obtaining a target positioning model; and inputting the predicted earthquake data set into the target positioning model to obtain a target longitude and a target latitude of a target epicenter. The application learns the relationship between the longitude and latitude difference between an earthquake measuring station and an epicenter and the time difference between the earthquake measuring station and the epicenter in historical data by constructing a decision tree model, thereby predicting the epicenter position at the current moment, and the application can more accurately and quickly position the epicenter of marine earthquakes compared with the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of earthquake prediction, in particular to a positioning method and device for marine earthquake, equipment and readable storage medium. BACKGROUND

[0002] Epicenter positioning is an important part of the earthquake early warning system. The traditional epicenter positioning method achieves positioning effect by constructing a Voronoi diagram. This method often needs the seismic wave to pass through multiple seismic measurement stations to obtain a relatively accurate position. If the epicenter position is far away from the seismic measurement station, a large error will be generated. The marine earthquake epicenter position is relatively far away from the land seismic measurement station, and it is difficult to obtain the accurate position of the epicenter by the traditional positioning algorithm. SUMMARY

[0003] The purpose of the present application is to provide a positioning method, device, equipment and readable storage medium for marine earthquake to improve the above problems. In order to achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0004] In a first aspect, the present application provides a positioning method for marine earthquake, comprising:

[0005] obtaining a plurality of historical earthquake data sets, the historical earthquake data set comprising a plurality of alarm-triggering seismic station information and epicenter information, the alarm-triggering seismic station information comprising station longitude, station latitude and station trigger time, and the epicenter information comprising epicenter longitude and epicenter latitude;

[0006] obtaining a real-time earthquake data set, the real-time earthquake data set comprising alarm-triggering seismic station information;

[0007] differentially preprocessing the plurality of historical earthquake data sets and the real-time earthquake data set to obtain a plurality of target earthquake data sets and a predicted earthquake data set, the differential preprocessing being used to represent the differential calculation of the information in the historical earthquake data set;

[0008] training a preset decision tree model based on the target earthquake data set, stopping training when the preset model index meets the set condition, and obtaining a target positioning model;

[0009] inputting the predicted earthquake data set into the target positioning model to obtain the target longitude and target latitude of the target epicenter.

[0010] In a second aspect, the present application further provides a positioning device for marine earthquake, comprising:

[0011] The first acquisition unit is configured to acquire a plurality of historical seismic data sets, wherein the historical seismic data sets comprise a plurality of alarm-triggered seismic station information and epicenter information, the alarm-triggered seismic station information comprises station longitude, station latitude and station trigger time, and the epicenter information comprises epicenter longitude and epicenter latitude.

[0012] The second acquisition unit is configured to acquire a real-time seismic data set, wherein the real-time seismic data set comprises alarm-triggered seismic station information.

[0013] The preprocessing unit is configured to perform difference preprocessing on the plurality of historical seismic data sets and the real-time seismic data set to obtain a plurality of target seismic data sets and a predicted seismic data set, wherein the difference preprocessing is configured to represent difference calculation on information in the historical seismic data sets.

[0014] The first training unit is configured to train a preset decision tree model based on the target seismic data sets, stop training when a preset model index meets a set condition, and obtain a target positioning model.

[0015] The input unit is configured to input the predicted seismic data set into the target positioning model to obtain target longitude and target latitude of a target epicenter.

[0016] In a third aspect, the present application further provides a positioning device for marine earthquakes, comprising:

[0017] The memory is configured to store a computer program.

[0018] The processor is configured to implement the steps of the positioning method for marine earthquakes when the computer program is executed.

[0019] In a fourth aspect, the present application further provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the positioning method for marine earthquakes.

[0020] The present application has the following beneficial effects:

[0021] The present application learns the relationship between the longitude and latitude difference between the seismic station and the epicenter and the trigger time difference between the seismic station and the epicenter in the historical data by constructing a decision tree model, thereby predicting the epicenter position at the current time, and the epicenter of the marine earthquake can be positioned more accurately and quickly compared with the prior art.

[0022] Other features and advantages of the present application will be illustrated in the following description, and some will become apparent from the description, or will be understood by those skilled in the art from the description, or will be understood by implementing the embodiments of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the written description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0024] Figure 1 A flow chart of the positioning method of the marine earthquake described in the embodiments of the present application;

[0025] Figure 2 A structural schematic diagram of the positioning device of the marine earthquake described in the embodiments of the present application;

[0026] Figure 3 A schematic diagram of the earthquake triggering described in the embodiments of the present application;

[0027] Figure 4 A structural schematic diagram of the positioning device of the marine earthquake described in the embodiments of the present application.

[0028] Markings in the drawings:

[0029] 10, first training unit; 20, second training unit; 30, preprocessing unit; 40, first training unit; 50, input unit;

[0030] 800, positioning device of marine earthquake; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0031] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0032] It should be noted that similar reference numerals and letters refer to like items throughout the accompanying drawings, and once an item is defined in one drawing, it is not necessary to further define and explain it in the subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0033] Embodiment 1:

[0034] The embodiment provides a positioning method of marine earthquake.

[0035] Referring to Figure 1 , the method includes steps S10, S20, S30, S40 and S50.

[0036] Step S10. Obtain a plurality of historical earthquake data sets, the historical earthquake data set including a plurality of alarm-triggered seismic station information and epicenter information, the alarm-triggered seismic station information including station longitude, station latitude and station trigger time, and the epicenter information including epicenter longitude and epicenter latitude;

[0037] Step S20. Obtain a real-time earthquake data set, the real-time earthquake data set including alarm-triggered seismic station information;

[0038] Specifically, all earthquake data in a historical time period can be obtained through official channels such as China Seismic Station, and in general, earthquakes in the sea area around the to-be-predicted region and earthquakes in surrounding countries that may affect the to-be-predicted region are selected, so as to ensure a certain correlation between the historical earthquake data and the real-time prediction earthquake data. Earthquake data sets with a magnitude less than or equal to zero are deleted from all historical earthquake data, and earthquake events with less than 5 seismic stations responding after the earthquake are deleted, so as to reduce the interference of false data on the historical earthquake data set. In addition, any earthquake data with a trigger time difference between any responding seismic station and the first responding seismic station greater than 30 seconds is deleted, and the remaining earthquake data is used as the historical earthquake data set for training and verification of the positioning model.

[0039] Step S30. Difference preprocessing is performed on the plurality of historical earthquake data sets and the real-time earthquake data set to obtain a plurality of target earthquake data sets and a prediction earthquake data set, and the difference preprocessing is used to represent difference calculation on the information in the historical earthquake data set.

[0040] Specifically, considering that the epicenter position of marine earthquake is far away from the seismic station set on land, the epicenter position information cannot be accurately obtained by the existing seismic station positioning, and the correlation between the difference of the seismic station and the epicenter longitude and latitude and the difference between the trigger time of the seismic station and the epicenter time needs to be considered, so as to accurately position the epicenter position in the sea.

[0041] Specifically, step S30 specifically comprises step S31, step S32, step S33, step S34, step S35, step S36 and step S37:

[0042] Step S30. Compare the trigger times of multiple measuring stations, and take the measuring station corresponding to the minimum trigger time as the target measuring station;

[0043] Step S30. Calculate the trigger time difference between the remaining measuring stations and the target measuring station to obtain multiple measuring station trigger time differences;

[0044] Step S30. Calculate the longitude difference between the remaining measuring stations and the target measuring station to obtain multiple measuring station longitude differences;

[0045] Step S30. Calculate the latitude difference between the remaining measuring stations and the target measuring station to obtain multiple measuring station latitude differences;

[0046] Step S30. Calculate the difference between the epicenter longitude and the longitude of the target measuring station to obtain the epicenter longitude difference;

[0047] Step S30. Calculate the difference between the epicenter latitude and the latitude of the target measuring station to obtain the epicenter latitude difference;

[0048] Step S30. Take the multiple measuring station trigger time differences, multiple measuring station longitude differences, multiple measuring station latitude differences, epicenter longitude differences and epicenter latitude differences as the target earthquake data set.

[0049] Specifically, after an earthquake occurs, the response time of the first seismic measuring station is recorded as T1, the response time of the second seismic measuring station is recorded as T2, the response time of the third seismic measuring station is recorded as T3, and so on. Take the first seismic measuring station that triggers an alarm as the standard, calculate the time used by the first seismic measuring station to the second seismic measuring station as t1=T2-T1, and the time difference used by the subsequent seismic measuring stations to the first seismic measuring station can be obtained, such as Figure 2 As shown in the figure, five seismic measuring stations are identified, wherein t1 is the difference between the trigger time of the second seismic measuring station and the trigger time of the first seismic measuring station, t2 is the difference between the trigger time of the third seismic measuring station and the trigger time of the first seismic measuring station, t3 is the difference between the trigger time of the fourth seismic measuring station and the trigger time of the first seismic measuring station, and t4 is the difference between the trigger time of the fifth seismic measuring station and the trigger time of the first seismic measuring station.

[0050] Step S40. Train the preset decision tree model based on the target earthquake data set, and stop training when the preset model index meets the set condition to obtain the target positioning model;

[0051] Specifically, the decision tree (LightGBM) model is adopted in the present application, and the model has the following specific advantages: the leaf splitting algorithm is used as the tree growth strategy, which finds the leaf with the maximum split gain from all the current leaves each time, and then splits and repeats the cycle; the leaf splitting algorithm produces smaller errors and has higher positioning accuracy than the horizontal splitting algorithm; the histogram algorithm is used to calculate the split gain and quickly select the best split point when constructing the tree, effectively reducing the amount of calculation; the one-sided sampling algorithm based on gradient is used, which excludes most small gradient samples and only uses the remaining samples to calculate the information gain, which can reduce the amount of data while ensuring the positioning accuracy of the model, effectively reducing the amount of calculation; the mutually exclusive feature bundling algorithm is used, which bundles multiple features to form new features, effectively improving the calculation speed of the model.

[0052] Specifically, step S40 specifically includes steps S41, S42, S43, S44, S45, S46, S47, S48, S49, S410, S411 and S412:

[0053] Step S41. Divide the plurality of target seismic data sets into training samples, test samples and validation samples, respectively;

[0054] Step S42. Obtain the initial range of each target parameter;

[0055] Step S43. Generate operation: randomly generate a plurality of initial parameters based on the initial range of each target parameter;

[0056] Step S44. Selection operation: randomly select one initial parameter from the plurality of initial parameters of each target parameter for combination to obtain a plurality of parameter combinations, wherein at most two initial parameters in any two parameter combinations have the same value;

[0057] Step S45. Adjustment operation: adjust the decision tree model based on each parameter combination to obtain a plurality of initial positioning models;

[0058] Step S46. Training operation: bring the training samples into the plurality of initial positioning models for training, and calculate the model indicators to obtain a plurality of initial model indicators;

[0059] Specifically, the three important parameter values in the LightGBM model can be adjusted by the grid search method. By setting the value range interval of the three parameters, the grid search will search for the optimal parameters of the model in the selected interval. The final grid search result will select the three parameter values corresponding to the maximum evaluation index value in the selected interval, so as to obtain the target positioning model based on the three parameter values.

[0060] The application focuses on optimizing the following three parameters: learning rate, which determines the magnitude of model parameter updates in each iteration, a larger learning rate will cause the model parameters to be updated significantly in each iteration, while a smaller learning rate will cause the parameter update magnitude to decrease; maximum depth, which can be used to limit the depth of each tree to avoid overfitting the details of the training data, thereby reducing the risk of overfitting, limiting the depth of the tree can reduce the complexity of the model and improve the generalization ability of the model, especially when dealing with high-dimensional data, a deeper tree usually pays more attention to capturing the details of the training data, which may lead to better fitting results on the training set, but also increases the sensitivity of the model to noise; the number of iterations, increasing the number of iterations usually improves the performance of the model, especially for complex target functions, however, increasing the number of iterations may increase the risk of overfitting on the test set while the model performs well on the training set, and a larger number of iterations will also make the model training time longer and the model training efficiency lower.

[0061] Specifically, step S46 specifically includes steps S461, S462, S463, S464, S465, S466, S467, S468, S469 and S4610:

[0062] Step S461. The plurality of training samples are divided into a plurality of sets to obtain a plurality of training sets;

[0063] Step S462. Determine the operation: randomly determine any set from the plurality of training sets as the target set;

[0064] Step S463. Bring in operation: bring all training sets except the target set into the decision tree model for training to obtain a training positioning model;

[0065] Step S464. First calculation operation: calculate the model index corresponding to each training set except the target set based on the training positioning model to obtain a plurality of first indexes, the model index is used to represent the fitting degree of the training positioning model for the training set;

[0066] Step S465. Prediction operation: bring the target set into the training positioning model for prediction, and calculate the model index based on the prediction result to obtain a second index;

[0067] Step S476. Second calculation operation: sum all the first indexes to obtain a first sum result;

[0068] Step S467. Third calculation operation: sum the first sum result and the second index to obtain a second sum result;

[0069] Step S468. Fourth calculation operation: calculating the ratio of the second summation result and the training set quantity, to obtain a target ratio;

[0070] Step S469. Repeating the determination operation, the input operation, the first calculation operation, the prediction operation, the second calculation operation, the third calculation operation and the fourth calculation operation until the target ratio of the training set quantity is obtained;

[0071] Step S4610. Summing the plurality of target ratios, and dividing the summation result by the training set quantity to obtain an initial model index;

[0072] Specifically, in the present application, the training samples are divided into three parts, and the training set is input into the model training and learning by using triple cross-validation, so as to ensure that the model obtained by training can better learn all the features in the training samples.

[0073] Step S47. Screening operation: screening to obtain an optimal parameter combination according to all initial model indexes, the optimal parameter combination being a parameter combination corresponding to a best initial positioning model, and the best initial positioning model being an initial positioning model corresponding to the maximum value in the plurality of initial model indexes;

[0074] Step S48. Comparison operation: comparing each target parameter in the optimal parameter combination with the corresponding initial range, and adjusting the initial range when there is a target parameter belonging to the boundary of the corresponding initial range, to obtain an updated initial range;

[0075] Specifically, each target parameter has a pre-set initial range, and the optimal parameter is searched in the initial range to serve as the model parameter. When the optimal parameter is located at the boundary of the initial range, it is considered that the current initial range may limit the parameter value, and therefore the initial range needs to be updated.

[0076] Specifically, step S48 specifically includes step S481, step S482, step S483, step S484, step S485, step S486, step S487 and step S488:

[0077] Step S481. Taking a target parameter belonging to the boundary of the corresponding initial range in the first parameter combination as an adjustment parameter;

[0078] Step S482. Determining a suboptimal model index from all initial model indexes, the suboptimal model index being only less than the maximum model index;

[0079] Step S483. Obtaining a target parameter corresponding to the adjustment parameter in the target parameter combination corresponding to the suboptimal model index as a comparison parameter;

[0080] Step S484. Calculating the difference between the adjustment parameter and the comparison parameter to obtain a target difference;

[0081] Step S485. Compare the size of the target difference value with the second set threshold value to obtain a parameter comparison result;

[0082] Step S486. Determine the expansion multiple based on the parameter comparison result;

[0083] Step S487. Calculate the product of the target difference value and the expansion multiple to obtain an expansion range;

[0084] Step S488. Generate an updated initial range based on the initial range and the expansion range;

[0085] Specifically, from all parameter combinations, determine a suboptimal parameter combination next to the optimal parameter combination, take the parameter located on the boundary of the initial range in the optimal parameter combination as an adjustment parameter, and determine a comparison parameter of the same category as the adjustment parameter from the suboptimal parameter combination, calculate the difference between the comparison parameter and the adjustment parameter, when the difference is large, a large range is needed to expand the initial range, and when the difference is small, a small range is needed to expand the initial range, the expansion multiples corresponding to the two cases are different, the product of the expansion multiple and the difference is calculated as the range needed to be expanded, and finally the range needed to be expanded is superimposed with the initial range to obtain the adjusted initial range.

[0086] Step S409. Repeat the generation operation, selection operation, adjustment operation, training operation, screening operation and comparison operation until the target parameters in the optimal parameter combination all belong to the corresponding initial range, and take the initial positioning model corresponding to the optimal parameter combination as the to-be-tested positioning model;

[0087] Specifically, according to the updated range, the optimal parameters are determined again, and the relationship between the parameters and the updated range is compared until the optimal parameters are all located in the initial range, and then the optimal parameters are taken as the final parameters of the model.

[0088] Step S410. Bring the test sample and the verification sample into the to-be-tested positioning model for prediction respectively, and calculate the model indicators based on the prediction results respectively to obtain test model indicators and verification model indicators, the test model indicators being generated by comprehensively generating the longitude indicators and the latitude indicators;

[0089] Specifically, step S410 specifically includes step S4101, step S4102, step S4103, step S4104, step S4105, step S4106, step S4107 and step S4108:

[0090] Step S4101. Bring the plurality of test samples into the to-be-tested positioning model for prediction respectively to obtain a plurality of test prediction values, the test prediction values including predicted longitude differences and predicted latitude differences;

[0091] Step S4102. Calculate the difference between the epicenter longitude difference in the plurality of test samples and the corresponding predicted longitude difference, and calculate the square of each difference value to obtain a plurality of first difference values;

[0092] Step S4103. Calculate the sum of the epicenter longitude differences in the plurality of test samples to obtain a first result;

[0093] Step S4104. Calculate the difference between the plurality of predicted longitude differences and the first result, and calculate the square of each difference value to obtain a plurality of second difference values;

[0094] Step S4105. Calculate the sum of the plurality of first difference values to obtain a second result;

[0095] Step S4106. Calculate the sum of the plurality of second difference values to obtain a third result;

[0096] Step S4107. Calculate the ratio of the second result to the third result to obtain a fourth result;

[0097] Step S4108. Calculate the difference between the third set threshold value and the fourth result as the longitude index;

[0098] Specifically, the model index calculation formula is:

[0099]

[0100] wherein, is the longitude and latitude prediction value of the prediction positioning model; y i is the longitude and latitude actual value in the test sample; y - is the average value of the longitude and latitude actual values in all test samples; n is the number of prediction samples;

[0101] Since the positioning model outputs the epicenter longitude value and the epicenter latitude value, the model index corresponding to the longitude value and the model index corresponding to the epicenter latitude value need to be calculated respectively. The two model indexes are combined to represent the training situation of the current model, and the model index value is used to determine whether the model needs to be trained again.

[0102] Step S411. Calculate the difference between the test model index and the verification model index to obtain a target difference value;

[0103] Step S412. When the target difference value is less than a first set threshold value, the to-be-tested positioning model is taken as a target positioning model;

[0104] Specifically, according to the model trained by the training sample, the verification sample and the test sample are used to verify whether the model parameters are reasonable, and the verification sample and the test sample can test the performance of the model on unknown data. If the model index of the verification set is significantly less than the model index of the test set, it means that the model has the disadvantage of overfitting, and the model parameters need to be adjusted.

[0105] Step S50. Input the predicted earthquake data set into the target positioning model to obtain the target longitude and target latitude of the target epicenter.

[0106] Specifically, the to-be-predicted earthquake data is input into the trained target positioning model for positioning, and relatively accurate epicenter longitude and latitude information can be obtained.

[0107] Embodiment 2

[0108] As shown in Figure 3 The embodiment provides a positioning device for marine earthquakes, which comprises:

[0109] The first acquisition unit 10 is configured to acquire a plurality of historical earthquake data sets, wherein each historical earthquake data set comprises a plurality of alarm-triggered seismic station information and epicenter information, the alarm-triggered seismic station information comprises a station longitude, a station latitude and a station trigger time, and the epicenter information comprises an epicenter longitude and an epicenter latitude.

[0110] The second acquisition unit 20 is configured to acquire a real-time earthquake data set, wherein the real-time earthquake data set comprises alarm-triggered seismic station information.

[0111] The preprocessing unit 30 is configured to perform difference preprocessing on the plurality of historical earthquake data sets and the real-time earthquake data set to obtain a plurality of target earthquake data sets and a predicted earthquake data set, wherein the difference preprocessing is configured to represent difference calculation on information in the historical earthquake data set.

[0112] The first training unit 40 is configured to train a preset decision tree model based on the target earthquake data set, and stop training when a preset model index meets a set condition to obtain a target positioning model.

[0113] The input unit 50 is configured to input the predicted earthquake data set into the target positioning model to obtain a target longitude and a target latitude of a target epicenter.

[0114] In one specific embodiment disclosed in the present application, the preprocessing unit 30 comprises:

[0115] The first comparison unit is configured to compare the plurality of station trigger times and take the station corresponding to the minimum station trigger time as a target station.

[0116] A first calculation unit is configured to calculate a trigger time difference between the remaining measuring stations and the target measuring station to obtain a plurality of measuring station trigger time differences.

[0117] A second calculation unit is configured to calculate a longitude difference between the remaining measuring stations and the target measuring station to obtain a plurality of measuring station longitude differences.

[0118] A third calculation unit is configured to calculate a latitude difference between the remaining measuring stations and the target measuring station to obtain a plurality of measuring station latitude differences.

[0119] A fourth calculation unit is configured to calculate an epicenter longitude difference between the epicenter longitude and the longitude of the target measuring station.

[0120] A fifth calculation unit is configured to calculate an epicenter latitude difference between the epicenter latitude and the latitude of the target measuring station.

[0121] A first as unit is configured to take the plurality of measuring station trigger time differences, the plurality of measuring station longitude differences, the plurality of measuring station latitude differences, the epicenter longitude difference, and the epicenter latitude difference as a target earthquake data set.

[0122] In one specific embodiment disclosed in the present application, the first training unit 40 comprises:

[0123] A first division unit is configured to divide the plurality of target earthquake data sets into training samples, test samples, and verification samples, respectively.

[0124] A third acquisition unit is configured to acquire an initial range of each target parameter.

[0125] A generation unit is configured to generate an operation of randomly generating a plurality of initial parameters based on the initial range of each target parameter.

[0126] A selection unit is configured to select an operation of randomly selecting one initial parameter from the plurality of initial parameters of each target parameter for combination to obtain a plurality of parameter combinations, wherein at most two initial parameters in any two parameter combinations have the same value.

[0127] An adjustment unit is configured to adjust an operation of adjusting the decision tree model based on each parameter combination to obtain a plurality of initial positioning models.

[0128] A second training unit is configured to perform a training operation of bringing the training samples into the plurality of initial positioning models for training and calculating model indicators to obtain a plurality of initial model indicators.

[0129] A screening unit is configured to perform a screening operation of screening to obtain an optimal parameter combination according to all initial model indicators, wherein the optimal parameter combination is a parameter combination corresponding to a best initial positioning model, and the best initial positioning model is an initial positioning model corresponding to a maximum value in the plurality of initial model indicators.

[0130] The second comparison unit is configured to perform a comparison operation of comparing each target parameter in the optimal parameter combination with the corresponding initial range, and adjusting the initial range to obtain an updated initial range when there is a target parameter belonging to a boundary of the corresponding initial range.

[0131] The first repeating unit is configured to repeat the generating operation, the selecting operation, the adjusting operation, the training operation, the screening operation and the comparison operation until all the target parameters in the optimal parameter combination belong to the corresponding initial range, and take the initial positioning model corresponding to the optimal parameter combination as the positioning model to be tested.

[0132] The first bringing-in unit is configured to bring the test sample and the verification sample into the positioning model to be tested respectively for prediction, and calculate the model indicators based on the prediction results respectively to obtain test model indicators and verification model indicators, wherein the test model indicators are generated by comprehensively combining the longitude indicators and the latitude indicators.

[0133] The sixth calculating unit is configured to calculate a difference between the test model indicators and the verification model indicators to obtain a target difference.

[0134] The second taking unit is configured to take the positioning model to be tested as a target positioning model when the target difference is less than a first set threshold.

[0135] In one specific embodiment disclosed in the present application, the first bringing-in unit comprises:

[0136] The second dividing unit is configured to divide the plurality of training samples into a plurality of sets respectively to obtain a plurality of training sets.

[0137] The first determining unit is configured to determine any set as a target set from the plurality of training sets randomly.

[0138] The second bringing-in unit is configured to bring all the training sets except the target set into the decision tree model for training to obtain a training positioning model.

[0139] The seventh calculating unit is configured to perform a first calculating operation of calculating the model indicators corresponding to each training set except the target set based on the training positioning model to obtain a plurality of first indicators, wherein the model indicators are used to represent the fitting degree of the training positioning model to the training set.

[0140] The predicting unit is configured to perform a prediction operation of bringing the target set into the training positioning model for prediction, and calculate the model indicators based on the prediction results to obtain second indicators.

[0141] The eighth calculating unit is configured to perform a second calculating operation of summing all the first indicators to obtain a first summation result.

[0142] The ninth computing unit is configured to perform a third computing operation of summing the first sum result and the second index to obtain a second sum result.

[0143] The tenth computing unit is configured to perform a fourth computing operation of calculating a ratio of the second sum result to the number of training sets to obtain a target ratio.

[0144] The second repeating unit is configured to repeatedly perform the determining operation, the bringing operation, the first computing operation, the predicting operation, the second computing operation, the third computing operation, and the fourth computing operation until the target ratio of the number of training sets is obtained.

[0145] The summing computing unit is configured to perform summing computation on the plurality of target ratios, and divide the sum result by the number of training sets to obtain the initial model index.

[0146] In an embodiment disclosed in the present application, the second comparing unit comprises:

[0147] The third selecting unit is configured to select, as the adjustment parameter, a target parameter in the first parameter combination that belongs to the corresponding initial range boundary.

[0148] The second determining unit is configured to determine, from all the initial model indexes, a suboptimal model index that is only smaller than the maximum model index.

[0149] The fourth obtaining unit is configured to obtain, as the comparison parameter, a target parameter corresponding to the adjustment parameter in the target parameter combination corresponding to the suboptimal model index.

[0150] The eleventh computing unit is configured to calculate a difference between the adjustment parameter and the comparison parameter to obtain a target difference.

[0151] The third comparing unit is configured to compare the target difference with the second set threshold to obtain a parameter comparison result.

[0152] The third determining unit is configured to determine the expansion multiple based on the parameter comparison result.

[0153] The twelfth computing unit is configured to calculate a product of the target difference and the expansion multiple to obtain an expanded range.

[0154] The updating unit is configured to generate an updated initial range based on the initial range and the expanded range.

[0155] In an embodiment disclosed in the present application, the first bringing unit comprises:

[0156] The third bringing unit is configured to bring the plurality of test samples into the to-be-tested positioning model respectively to obtain a plurality of test prediction values, and the test prediction pair comprises a predicted longitude difference and a predicted latitude difference.

[0157] The thirteenth calculation unit is used to calculate the difference between the epicenter longitude difference and the corresponding predicted longitude difference in multiple test samples, and to calculate the square of each difference to obtain multiple first differences;

[0158] The fourteenth calculation unit is used to calculate the sum of the epicentral longitude differences in multiple test samples to obtain the first result;

[0159] The fifteenth calculation unit is used to calculate the differences between multiple predicted longitude differences and the first result, and to calculate the square of each difference to obtain multiple second differences;

[0160] The sixteenth calculation unit is used to calculate the sum of multiple first differences to obtain the second result;

[0161] The seventeenth calculation unit is used to calculate the sum of multiple second differences to obtain the third result;

[0162] The eighteenth calculation unit is used to calculate the ratio of the second result to the third result, and obtain the fourth result;

[0163] The nineteenth calculation unit is used to calculate the difference between the third set threshold and the fourth result, which serves as a longitude indicator.

[0164] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0165] Example 3:

[0166] Corresponding to the above method embodiments, this embodiment also provides a marine earthquake positioning device. The marine earthquake positioning device described below and the marine earthquake positioning method described above can be referred to in correspondence.

[0167] Figure 4 This is a block diagram illustrating a marine earthquake positioning device 800 according to an exemplary embodiment. Figure 4 As shown, the marine earthquake location device 800 may include a processor 801 and a memory 802. The marine earthquake location device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0168] The processor 801 is configured to control overall operations of the marine seismic positioning device 800 to complete all or part of the steps in the marine seismic positioning method described above. The memory 802 is configured to store various types of data to support the operation of the marine seismic positioning device 800, which can include, for example, instructions for any application or method operating on the marine seismic positioning device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the marine seismic positioning device 800 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0169] In an example embodiment, the marine seismic positioning device 800 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic devices to execute the above-described marine seismic positioning method.

[0170] In another example embodiment, a computer readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-described marine seismic positioning method is also provided. For example, the computer readable storage medium can be the above-described memory 802 including program instructions that can be executed by the processor 801 of the marine seismic positioning device 800 to complete the above-described marine seismic positioning method.

[0171] Embodiment 4:

[0172] Corresponding to the above method embodiments, a readable storage medium is also provided in the present embodiment, and the readable storage medium described below can be referred to in correspondence with the above-described marine seismic positioning method.

[0173] A readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the steps of the above-described marine seismic positioning method of the method embodiments.

[0174] The readable storage medium can specifically be a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0175] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0176] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of locating a marine seismic event, characterized by, The method comprises the following steps: obtaining a plurality of historical earthquake data sets, the historical earthquake data sets comprising a plurality of alarm-triggered seismic station information and epicenter information, the alarm-triggered seismic station information comprising station longitude, station latitude and station trigger time, and the epicenter information comprising epicenter longitude and epicenter latitude; obtaining a real-time earthquake data set, the real-time earthquake data set comprising alarm-triggered seismic station information; differentially preprocessing the plurality of historical earthquake data sets and the real-time earthquake data set to obtain a plurality of target earthquake data sets and a prediction earthquake data set, wherein the differential preprocessing is used to represent differential calculation on information in the historical earthquake data sets; training a preset decision tree model based on the target earthquake data sets, stopping the training when a preset model index meets a set condition, and obtaining a target positioning model; inputting the prediction earthquake data set into the target positioning model to obtain target longitude and target latitude of a target epicenter.

2. The method of claim 1, wherein The method comprises the following steps: comparing a plurality of station trigger times, and taking a station corresponding to the minimum station trigger time as a target station; calculating trigger time differences between the remaining stations and the target station to obtain a plurality of station trigger time differences; calculating longitude differences between the remaining stations and the target station to obtain a plurality of station longitude differences; calculating latitude differences between the remaining stations and the target station to obtain a plurality of station latitude differences; calculating an epicenter longitude difference between the epicenter longitude and the target station longitude; calculating an epicenter latitude difference between the epicenter latitude and the target station latitude; taking the plurality of station trigger time differences, the plurality of station longitude differences, the plurality of station latitude differences, the epicenter longitude difference and the epicenter latitude difference as the target earthquake data sets.

3. The method of claim 1, wherein The method comprises the following steps: training a preset decision tree model based on the target earthquake data sets, stopping the training when a preset model index meets a set condition, and obtaining a target positioning model, wherein the decision tree model comprises three target parameters, and the three target parameters comprise: dividing a plurality of target earthquake data sets into training samples, test samples and verification samples; obtaining an initial range of each target parameter; generating operation: randomly generating a plurality of initial parameters based on the initial range of each target parameter; selection operation: randomly selecting one initial parameter from the plurality of initial parameters of each target parameter to obtain a plurality of parameter combinations, wherein at most two initial parameters in any two parameter combinations have the same value; adjustment operation: adjusting the decision tree model based on each parameter combination to obtain a plurality of initial positioning models; training operation: training the training samples in the plurality of initial positioning models, and calculating model indexes to obtain a plurality of initial model indexes; screening operation: screening an optimal parameter combination from all initial model indexes, wherein the optimal parameter combination is a parameter combination corresponding to a best initial positioning model, and the best initial positioning model is an initial positioning model corresponding to the maximum value in the plurality of initial model indexes. The comparison operation: comparing each target parameter in the optimal parameter combination with the corresponding initial range, and adjusting the initial range when there is a target parameter belonging to the boundary of the corresponding initial range to obtain an updated initial range; The repeating of the generating operation, the selecting operation, the adjusting operation, the training operation, the screening operation and the comparison operation until the target parameters in the optimal parameter combination all belong to the corresponding initial range, and taking the initial positioning model corresponding to the optimal parameter combination as the to-be-tested positioning model; The test sample and the verification sample are respectively brought into the to-be-tested positioning model for prediction, and the model indicators are calculated based on the prediction results respectively to obtain test model indicators and verification model indicators, and the test model indicators are generated by comprehensively generating the longitude indicators and the latitude indicators; The difference between the test model indicators and the verification model indicators is calculated to obtain a target difference value; When the target difference value is less than a first set threshold, the to-be-tested positioning model is taken as the target positioning model.

4. The method of claim 3, wherein, The training operation: the training sample is respectively brought into a plurality of initial positioning models for training, and the model indicators are calculated to obtain a plurality of initial model indicators, including: The plurality of training samples are respectively divided into a plurality of sets to obtain a plurality of training sets; The determining operation: any set is randomly determined from the plurality of training sets as a target set; The bringing-in operation: all training sets except the target set are brought into the decision tree model for training to obtain a training positioning model; The first calculation operation: based on the training positioning model, the model indicators corresponding to each training set except the target set are calculated to obtain a plurality of first indicators, and the model indicators are used to represent the fitting degree of the training positioning model to the training set; The prediction operation: the target set is brought into the training positioning model for prediction, and the model indicators are calculated based on the prediction results to obtain a second indicator; The second calculation operation: the sum of all first indicators is calculated to obtain a first sum result; The third calculation operation: the first sum result and the second indicator are summed to obtain a second sum result; The fourth calculation operation: the ratio of the second sum result to the number of training sets is calculated to obtain a target ratio; The repeating of the determining operation, the bringing-in operation, the first calculation operation, the prediction operation, the second calculation operation, the third calculation operation and the fourth calculation operation until the target ratio of the number of training sets is obtained; The sum of a plurality of target ratios is calculated, and the sum result is divided by the number of training sets to obtain the initial model indicators.

5. A marine seismic positioning device, characterized in that It includes: The first acquisition unit is used for acquiring a plurality of historical earthquake data sets, and the historical earthquake data set includes a plurality of trigger alarm seismic measurement station information and epicenter information, the trigger alarm seismic measurement station information includes measurement station longitude, measurement station latitude and measurement station trigger time, and the epicenter information includes epicenter longitude and epicenter latitude; The second acquisition unit is used for acquiring a real-time earthquake data set, and the real-time earthquake data set includes trigger alarm seismic measurement station information; The preprocessing unit is configured to perform difference preprocessing on the plurality of historical seismic data sets and the real-time seismic data set to obtain a plurality of target seismic data sets and a predicted seismic data set, and the difference preprocessing is configured to represent difference calculation on information in the historical seismic data sets; The first training unit is configured to train a preset decision tree model based on the target seismic data sets, stop training when a preset model index meets a set condition, and obtain a target positioning model; The input unit is configured to input the predicted seismic data set into the target positioning model to obtain a target longitude and a target latitude of an earthquake epicenter.

6. The marine seismic positioning apparatus of claim 5, wherein, The preprocessing unit includes: The first comparison unit is configured to compare a plurality of measurement station trigger times and take a measurement station corresponding to a minimum measurement station trigger time as a target measurement station; The first calculation unit is configured to calculate trigger time differences between the remaining measurement stations and the target measurement station to obtain a plurality of measurement station trigger time differences; The second calculation unit is configured to calculate longitude differences between the remaining measurement stations and the target measurement station to obtain a plurality of measurement station longitude differences; The third calculation unit is configured to calculate latitude differences between the remaining measurement stations and the target measurement station to obtain a plurality of measurement station latitude differences; The fourth calculation unit is configured to calculate an epicenter longitude difference between an epicenter longitude and a target measurement station longitude to obtain an epicenter longitude difference; The fifth calculation unit is configured to calculate an epicenter latitude difference between an epicenter latitude and a target measurement station latitude to obtain an epicenter latitude difference; The first as unit is configured to take the plurality of measurement station trigger time differences, the plurality of measurement station longitude differences, the plurality of measurement station latitude differences, the epicenter longitude difference, and the epicenter latitude difference as the target seismic data sets.

7. The marine seismic positioning apparatus of claim 5, wherein, The first training unit includes: The first division unit is configured to divide the plurality of target seismic data sets into training samples, test samples, and verification samples, respectively; The third acquisition unit is configured to acquire an initial range of each target parameter; The generation unit is configured to generate an operation of randomly generating a plurality of initial parameters based on the initial range of each target parameter; The selection unit is configured to select an operation of randomly selecting one initial parameter from the plurality of initial parameters of each target parameter for combination to obtain a plurality of parameter combinations, wherein at most two initial parameters in any two parameter combinations have the same value; The adjustment unit is configured to perform an adjustment operation of adjusting the decision tree model based on each parameter combination to obtain a plurality of initial positioning models; The second training unit is configured to perform a training operation of bringing the training samples into the plurality of initial positioning models for training and calculating model indexes to obtain a plurality of initial model indexes; The screening unit is configured to perform a screening operation of screening an optimal parameter combination from all the initial model indexes, the optimal parameter combination being a parameter combination corresponding to a best initial positioning model, and the best initial positioning model being an initial positioning model corresponding to a maximum value in the plurality of initial model indexes; The second comparison unit is configured to perform a comparison operation of comparing each target parameter in the optimal parameter combination with a corresponding initial range, and when there is a target parameter belonging to a boundary of the corresponding initial range, adjusting the initial range to obtain an updated initial range. The first repeating unit is configured to repeat the generating operation, the selecting operation, the adjusting operation, the training operation, the screening operation, and the comparing operation until the target parameters in the optimal parameter combination all belong to the corresponding initial ranges, and to take the initial positioning model corresponding to the optimal parameter combination as the positioning model to be tested. The first bringing-in unit is configured to bring the test sample and the verification sample into the positioning model to be tested respectively for prediction, and to calculate the model indicators based on the prediction results respectively to obtain test model indicators and verification model indicators, wherein the test model indicators are generated by comprehensively combining the longitude indicators and the latitude indicators. The sixth calculating unit is configured to calculate a difference between the test model indicators and the verification model indicators to obtain a target difference. The second taking unit is configured to take the positioning model to be tested as the target positioning model when the target difference is less than a first set threshold.

8. The marine seismic positioning apparatus of claim 7, wherein, The first bringing-in unit includes: The second dividing unit is configured to divide a plurality of training samples into a plurality of sets to obtain a plurality of training sets. The first determining unit is configured to determine any set from the plurality of training sets as a target set. The second bringing-in unit is configured to bring all the training sets except the target set into the decision tree model for training to obtain a training positioning model. The seventh calculating unit is configured to calculate the model indicators corresponding to each training set except the target set based on the training positioning model to obtain a plurality of first indicators, wherein the model indicators are used to represent the fitting degree of the training positioning model to the training set. The prediction unit is configured to bring the target set into the training positioning model for prediction, and to calculate the model indicators based on the prediction results to obtain a second indicator. The eighth calculating unit is configured to sum all the first indicators to obtain a first summation result. The ninth calculating unit is configured to sum the first summation result and the second indicator to obtain a second summation result. The tenth calculating unit is configured to calculate a ratio of the second summation result to the number of training sets to obtain a target ratio. The second repeating unit is configured to repeat the determining operation, the bringing-in operation, the first calculating operation, the prediction operation, the second calculating operation, the third calculating operation, and the fourth calculating operation until the target ratio of the number of training sets is obtained. The summation calculating unit is configured to sum a plurality of target ratios, and to divide the summation result by the number of training sets to obtain the initial model indicators.

9. A marine seismic positioning apparatus, characterized by The memory is configured to store a computer program. The processor is configured to implement the steps of the positioning method of the marine earthquake according to any one of claims 1 to 4 when the computer program is executed. The computer program is stored on the readable storage medium, and the computer program is configured to implement the steps of the positioning method of the marine earthquake according to any one of claims 1 to 4 when the computer program is executed by the processor.

10. A readable storage medium, characterized by, ​

Images