CN114721035A - Earthquake forecasting method, device, equipment and medium based on remote sensing data - Google Patents
Earthquake forecasting method, device, equipment and medium based on remote sensing data Download PDFInfo
- Publication number
- CN114721035A CN114721035A CN202210179583.3A CN202210179583A CN114721035A CN 114721035 A CN114721035 A CN 114721035A CN 202210179583 A CN202210179583 A CN 202210179583A CN 114721035 A CN114721035 A CN 114721035A
- Authority
- CN
- China
- Prior art keywords
- data
- anomaly
- preset
- earthquake
- seismic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013277 forecasting method Methods 0.000 title claims description 15
- 230000002159 abnormal effect Effects 0.000 claims abstract description 162
- 238000012545 processing Methods 0.000 claims abstract description 67
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000001914 filtration Methods 0.000 claims abstract description 41
- 230000000694 effects Effects 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000005856 abnormality Effects 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims description 21
- 230000002123 temporal effect Effects 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims 1
- 238000011156 evaluation Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 12
- 230000003287 optical effect Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000002243 precursor Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/01—Measuring or predicting earthquakes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/36—Effecting static or dynamic corrections on records, e.g. correcting spread; Correlating seismic signals; Eliminating effects of unwanted energy
- G01V1/364—Seismic filtering
- G01V1/366—Seismic filtering by correlation of seismic signals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/30—Noise handling
- G01V2210/32—Noise reduction
- G01V2210/324—Filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/61—Analysis by combining or comparing a seismic data set with other data
- G01V2210/614—Synthetically generated data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/61—Analysis by combining or comparing a seismic data set with other data
- G01V2210/616—Data from specific type of measurement
- G01V2210/6161—Seismic or acoustic, e.g. land or sea measurements
Landscapes
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to the technical field of satellite image processing, and discloses an earthquake prediction method, device, equipment and medium based on remote sensing data. The method comprises the following steps: acquiring original remote sensing data of a target area in a first time range, and performing earthquake anomaly detection on the original remote sensing data to generate initial anomaly data; performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data; the preset earthquake abnormity identification conditions comprise space abnormity identification conditions and time abnormity identification conditions, and the target abnormity data is used for representing abnormity caused by earthquake activities; and determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range. By the technical scheme, the accuracy of identifying the data abnormality of the geophysical parameters caused by the earthquake is improved, so that the accuracy of earthquake prediction is improved.
Description
Technical Field
The invention relates to the technical field of satellite image processing, in particular to an earthquake forecasting method, device, equipment and medium based on remote sensing data.
Background
The occurrence of intense earthquakes in densely populated areas can cause immeasurable loss of personnel and economy. Therefore, accurate monitoring and forecasting of earthquakes becomes very urgent. The basic assumption of current seismic forecasting studies is that precursor information exists in geophysical parameter anomalies and that this information can be used to forecast future earthquakes at medium to short time scales (months to weeks). The satellite remote sensing data can monitor various physical parameters of the earth all day long without contact. Therefore, it is necessary to provide a scheme for monitoring and forecasting an earthquake by using satellite remote sensing data, so as to reduce the cost of earthquake forecasting and improve the frequency and accuracy of earthquake forecasting.
Disclosure of Invention
In order to solve the technical problems, the invention provides an earthquake forecasting method, an earthquake forecasting device, earthquake forecasting equipment and an earthquake forecasting medium based on remote sensing data so as to improve the accuracy of earthquake forecasting.
In a first aspect, the invention provides a method for seismic forecasting based on remote sensing data, the method comprising:
acquiring original remote sensing data of a target area in a first time range, and performing earthquake anomaly detection on the original remote sensing data to generate initial anomaly data;
performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data; the preset seismic anomaly identification conditions comprise spatial anomaly identification conditions and time anomaly identification conditions, and the target anomaly data are used for representing anomalies caused by seismic activities;
and determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range.
In some embodiments, the spatial anomaly identification condition is that an average anomaly absolute value of each effective pixel covered in a preset spatial range is greater than or equal to a first anomaly threshold; the effective pixel is a pixel with an abnormal absolute value greater than or equal to a second abnormal threshold, and the first abnormal threshold is greater than the second abnormal threshold;
the time anomaly identification condition is that the anomaly observation proportion meeting the space anomaly identification condition in the first time range is greater than or equal to a preset proportion threshold value.
In some embodiments, the performing anomaly filtering on the initial anomaly data based on a preset seismic anomaly identification condition, and generating target anomaly data includes:
performing sliding window processing based on the space anomaly identification condition on the initial anomaly data according to a preset moving direction, a preset moving step length and the preset space range to perform primary anomaly filtering on the initial anomaly data and generate intermediate anomaly data;
and performing secondary anomaly filtering on the intermediate anomaly data based on the time anomaly identification condition to generate the target anomaly data.
Optionally, the performing, according to a preset moving direction, a preset moving step length, and the preset spatial range, sliding window processing based on the spatial anomaly identification condition on the initial anomaly data to perform primary anomaly filtering on the initial anomaly data, and generating intermediate anomaly data includes:
determining a current processing pixel from the initial abnormal data;
judging whether each pixel value in the preset space range with the current processing pixel as the center meets the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result;
determining a next pixel which is away from the current processing pixel by a preset step length according to a preset moving direction, and updating the current processing pixel by using the next pixel;
and returning to the step of judging whether the pixel values in the preset space range with the current processing pixel as the center meet the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result until the initial abnormal data is traversed.
Optionally, the performing, based on the time anomaly identification condition, secondary anomaly filtering on the intermediate anomaly data, and generating the target anomaly data includes:
for each pixel position, determining the proportion of the number of abnormal values contained in the intermediate abnormal data in the pixel number, and reserving the pixel position when determining that the proportion meets the preset proportion threshold;
and generating the target abnormal data based on the reserved pixel positions.
In some embodiments, the spatial anomaly identification condition and the temporal anomaly identification condition are determined based on a preset seismic profile data set; the preset seismic example data set is used for recording seismic time, seismic positions and seismic intensity of multiple historical seismic events.
In some embodiments, the target area is within an area range of a preset seismic monitoring area; the preset earthquake monitoring area is a geographical area of which the historical earthquake occurrence frequency reaches a preset frequency threshold value.
In some embodiments, the time interval between two adjacent seismic forecasts is a duration corresponding to the second time range.
In some embodiments, after said determining at least one local region in the target region based on the target anomaly data and forecasting earthquakes for the local region within a second time range, the method further comprises:
determining an evaluation index value of the earthquake forecast based on the target abnormal data; the evaluation index comprises at least one of a report rate, a false report rate, a missing report rate, a normal rate and a Mauss correlation coefficient.
In a second aspect, the present invention provides an apparatus for seismic forecasting based on remote sensing data, the apparatus comprising:
the system comprises an initial abnormal data generation module, a time calculation module and a time calculation module, wherein the initial abnormal data generation module is used for acquiring original remote sensing data of a target area in a first time range, and performing earthquake abnormal detection on the original remote sensing data to generate initial abnormal data;
the target abnormal data generation module is used for carrying out abnormal filtering on the initial abnormal data based on a preset earthquake abnormal recognition condition to generate target abnormal data; the preset seismic anomaly identification conditions comprise spatial anomaly identification conditions and time anomaly identification conditions, and the target anomaly data are used for representing anomalies caused by seismic activities;
and the earthquake forecasting module is used for determining at least one local area in the target area based on the target abnormal data and carrying out earthquake forecasting on the local area within a second time range.
In some embodiments, the spatial anomaly identification condition is that an average anomaly absolute value of each effective pixel covered in a preset spatial range is greater than or equal to a first anomaly threshold; the effective pixel is a pixel with an abnormal absolute value greater than or equal to a second abnormal threshold, and the first abnormal threshold is greater than the second abnormal threshold;
the time anomaly identification condition is that the anomaly observation proportion meeting the space anomaly identification condition in the first time range is greater than or equal to a preset proportion threshold value.
In some embodiments, the target anomaly data generation module comprises:
the spatial filtering submodule is used for performing sliding window processing based on the spatial anomaly identification condition on the initial anomaly data according to a preset moving direction, a preset moving step length and the preset spatial range so as to perform primary anomaly filtering on the initial anomaly data and generate intermediate anomaly data;
and the time filtering submodule is used for carrying out secondary abnormity filtering on the intermediate abnormal data based on the time abnormity identification condition to generate the target abnormal data.
Optionally, the spatial filtering submodule is specifically configured to:
determining a current processing pixel from the initial abnormal data;
judging whether each pixel value in the preset space range with the current processing pixel as the center meets the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result;
determining a next pixel which is away from the current processing pixel by a preset step length according to a preset moving direction, and updating the current processing pixel by using the next pixel;
and returning to the step of judging whether the pixel values in the preset space range with the current processing pixel as the center meet the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result until the initial abnormal data is traversed.
Optionally, the temporal filtering submodule is specifically configured to:
for each pixel position, determining the proportion of the number of abnormal values contained in the intermediate abnormal data in the pixel number, and reserving the pixel position when determining that the proportion meets the preset proportion threshold;
and generating the target abnormal data based on the reserved pixel positions.
In some embodiments, the spatial anomaly identification condition and the temporal anomaly identification condition are determined based on a preset seismic profile data set; the preset seismic example data set is used for recording seismic time, seismic positions and seismic intensity of multiple historical seismic events.
In some embodiments, the target area is within an area range of a preset seismic monitoring area; the preset earthquake monitoring area is a geographical area with historical earthquake occurrence times reaching a preset time threshold value.
In some embodiments, the time interval between two adjacent seismic forecasts is a duration corresponding to the second time range.
In some embodiments, the remote sensing data-based seismic forecasting apparatus further comprises an evaluation index value determination module configured to:
after the earthquake prediction in a second time range is carried out on the local area, determining an evaluation index value of the earthquake prediction based on the target abnormal data; the evaluation index comprises at least one of a report rate, a false report rate, a missing report rate, a normal rate and a Mauss correlation coefficient.
In a third aspect, the present invention provides an electronic device, including:
a processor and a memory;
the processor is configured to perform the steps of the method of any embodiment of the invention by calling a program or instructions stored in the memory.
In a fourth aspect, the invention provides a computer readable storage medium storing a program or instructions for causing a computer to perform the steps of the method as described in any of the embodiments of the invention.
According to the earthquake forecasting method, the earthquake forecasting device, the earthquake forecasting equipment and the earthquake forecasting medium based on the remote sensing data, the original remote sensing data of a target area in a first time range can be obtained, earthquake abnormity detection is carried out on the original remote sensing data, and initial abnormal data are generated; performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data; the preset seismic anomaly identification conditions comprise spatial anomaly identification conditions and time anomaly identification conditions, and the target anomaly data are used for representing anomalies caused by seismic activities; and determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range. The method and the device realize that the accuracy of identifying the data abnormity of the geophysical parameters caused by the earthquake is improved by providing the preset earthquake abnormity identification conditions on the space dimension and the time dimension, thereby improving the accuracy of earthquake prediction.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a flow chart of a method for seismic forecasting based on remote sensing data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the interval between successive seismic forecasts provided by an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an earthquake prediction device based on remote sensing data according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention may be more clearly understood, a detailed description of aspects of the present invention will be made below. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the invention may be practiced otherwise than as described herein; it is to be understood that the embodiments described in this specification are only some embodiments of the invention, and not all embodiments.
The earthquake forecasting method based on the remote sensing data provided by the embodiment of the invention is mainly suitable for a scene of monitoring and forecasting the possible earthquake activity and a scene of evaluating the earthquake forecasting capability. The earthquake forecasting method based on the remote sensing data provided by the embodiment of the invention can be executed by an earthquake forecasting device based on the remote sensing data, the device can be realized by software and/or hardware, and the device can be integrated in electronic equipment, such as a notebook computer, a desktop computer or a server.
Fig. 1 is a flowchart of an earthquake forecasting method based on remote sensing data according to an embodiment of the present invention. Referring to fig. 1, the seismic forecasting method based on remote sensing data specifically includes:
s110, obtaining original remote sensing data of the target area in a first time range, and carrying out earthquake abnormity detection on the original remote sensing data to generate initial abnormal data.
The target area refers to an area to be monitored for seismic activity. The first time range is a historical time period prior to the current date, and may be, for example, a historical date range immediately adjacent to the current date. Illustratively, the first time range is a historical date range immediately preceding the current date for a period of 3 months. The reason for this is that while a longer anomaly monitoring time window may capture more counts of anomaly values of shorter duration, uncorrelated anomalies far from the time of the earthquake occurrence result in higher uncertainty in the seismic related signal. Therefore, the duration of the first time range is set to be 3 months, so that the correlation degree of the detected abnormality and the earthquake activity can be improved to a certain extent, and the accuracy of follow-up earthquake prediction is improved. The raw remote sensing data refers to remote sensing product data without subsequent data processing, and is related to the selected geophysical parameters. The initial abnormal data is an abnormal value of the geophysical parameter obtained by performing abnormal detection on the remote sensing data, and is abnormal data which is not subjected to subsequent abnormal value filtering processing.
Specifically, based on the basic assumption that precursor information exists in the geophysical parameter anomaly phenomenon and can be used for forecasting earthquakes (several months to several weeks) with medium and short time scales in the future, before earthquake monitoring and forecasting, according to various factors such as the physical nature of the earthquake, the sensitivity to the earthquake occurrence process, the inversion accuracy of satellite observation, the accessibility of a data source, the space-time resolution of remote sensing data and the like, the suitable geophysical parameters to be monitored, such as the surface temperature, the latent heat flux, the air temperature, the humidity, the emergent long-wave radiation, the brightness temperature of thermal infrared measurement and the like, are selected. And acquiring original remote sensing data in a first time range corresponding to the selected geophysical parameters from a remote sensing product website or a database.
And then, carrying out certain preprocessing operation on the original remote sensing data, such as geographical positioning, projective transformation, physical quantity conversion, mosaic, synthesis, quality control and the like, so as to ensure the consistency and accuracy of the preprocessed original remote sensing data. Meanwhile, in consideration of different requirements of different anomaly analysis methods/anomaly detection methods on input data, preprocessing operation specific to the anomaly detection method, such as neighborhood pixel normalization, can be further performed on the preprocessed original remote sensing data. The preprocessed remote sensing data obtained in this way can be used as the basis for subsequent data processing.
And then, carrying out abnormal value detection on the preprocessed original remote sensing data by using an abnormal detection method, namely identifying abnormal signals of the selected geophysical parameters in the preprocessed original remote sensing data, wherein the obtained result is the initial abnormal data.
The abnormality detection method may be a method capable of identifying an abnormality in the remote sensing data, such as a shift index ZS method or a Robust Satellite Technology (RST) method. Both of these methods aim to identify significant changes relative to their "normal" condition in the spatial and/or temporal domains.
The ZS method calculates the abnormal disturbance by normalizing the Z fraction as follows:
where v (x, y, t) is the current pel value at location (x, y) and time t; μ (x, y) is the average calculated from the reference pel values (also called background fields) for a number of years at position (x, y) and time t (or a time close to time t); δ (x, y) is the standard deviation of each background field described above.
In this ZS method, the upper and lower boundaries of the envelope are set to μ ± n δ. If the ZS value calculated from the pixel values in the preprocessed original remote sensing data falls outside the relevant upper and lower boundaries of the envelope, an abnormal signal is detected.
The RST is a multi-temporal statistical method for analyzing long-term satellite records with similar observation conditions (e.g., the same month, time of day, and sensor data). RST combines the normalization processing of neighborhood difference in the vorticity method and background field in the ZS method, and clearly defines the mathematical expression of earthquake-front abnormality in statistics. The RST formula is:
wherein the content of the first and second substances,
is the spatial average of the homogeneous neighborhood; Δ v (x, y, t) represents the difference between the pel value in position (x, y) and the surrounding uniform pel; mu.sΔv(x, y) and δΔv(x, y) are the mean and standard deviation of the background field calculated from Δ v (x, y, t), respectively.
In some embodiments, the target area is within an area of a predetermined seismic surveillance area.
The preset earthquake monitoring area is a geographical area with historical earthquake occurrence times reaching a preset time threshold value. The predetermined number threshold may be set empirically to determine the seismic activity area. For example, the preset earthquake monitoring area is an earthquake active area with frequent earthquake occurrence in the global scope/national scope/regional scope.
Specifically, in order to further improve the accuracy of the earthquake prediction, a preset earthquake monitoring area may be determined in advance. Then, based on the assumption that future earthquakes only occur in the preset earthquake monitoring area, and the geophysical parameter abnormity in the areas outside the preset earthquake monitoring area is irrelevant to the occurrence of the earthquakes, a target area is determined from the preset earthquake monitoring area for earthquake monitoring and forecasting.
The predetermined seismic surveillance area may be derived from historical seismic data and may be used to indicate a likely area of an impending earthquake in a predictive analysis to ensure that seismic prediction capability above natural probability is obtained as far as possible. Since the earthquakes are not randomly distributed in space, the historical earthquake cases may reflect earthquake activity on a global/national/regional basis. For example, seismic directory data provided by USGS of the United states geological survey in the embodiment of the invention, with a seismic magnitude of 6 or more and a seismic source depth of 70km or less for 4719 times in 1980 to 2020, is used to deduce a preset seismic surveillance area in the global scope. And marking a 5-degree multiplied by 5-degree grid around the grid with the earthquake times reaching a preset time threshold value in the earthquake directory data so as to obtain a preset earthquake monitoring area in the global range.
And S120, performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data.
Wherein the preset seismic anomaly identification condition is a condition which is set in advance and is used for identifying whether the anomaly value of the geophysical parameter is caused by seismic activity. The preset earthquake abnormity identification conditions comprise space abnormity identification conditions and time abnormity identification conditions. Namely, abnormal values caused by seismic activity are subjected to abnormal identification from a space dimension and a time dimension, so that the accuracy of abnormal identification is improved. Target anomaly data is data that characterizes anomalies caused by seismic activity.
In some embodiments, the spatial anomaly identification condition is that the average anomaly absolute value of each effective pixel covered in a preset spatial range is greater than or equal to a first anomaly threshold. The preset spatial range is a preset region with a certain spatial size, such as a spatial range of 5 degrees by 5 degrees around the central pixel. The effective pixel is a pixel whose absolute value of the anomaly is greater than or equal to a second anomaly threshold. In the embodiment of the invention, two abnormal value critical values with different numerical values are set, namely a second abnormal threshold value used for identifying whether the pixel value in the initial abnormal data is valid and a first abnormal threshold value used for identifying whether the abnormal value is caused by earthquake activity, wherein the first abnormal threshold value is slightly larger than the second abnormal threshold value. For example, if the second anomaly threshold is determined to be 2 within a range of 1.5 to 3.5, the first anomaly threshold may be a value greater than 0.5, that is, 2.5. The spatial anomaly identification condition is that effective pixels with the absolute values of pixel values (namely anomaly absolute values) in the initial anomaly data being greater than or equal to the second anomaly threshold value exist in a preset spatial range, and the average value (namely average anomaly absolute value) of the absolute values of the effective pixels is greater than or equal to the first anomaly threshold value.
In some embodiments, the temporal anomaly identification condition is that the anomaly observation ratio satisfying the spatial anomaly identification condition in the first time range is greater than or equal to a preset ratio threshold. The abnormal observation ratio refers to the ratio of the number of abnormal observations satisfying the spatial abnormality recognition condition to all the number of observations. The preset proportion threshold is a preset critical value of the abnormal observation proportion. For example, if the time resolution of the raw telemetry data is one day and the first time range is 120 days for 3 months, there are 120 observations in the first time range. And if the number of days for a certain pixel to meet the spatial anomaly identification condition within 120 days is not less than 10 days, the anomaly observation ratio is greater than or equal to 1/12. If the preset proportion threshold is 1/12, the abnormal observation proportion in the example is greater than or equal to the preset proportion threshold, that is, the image element meets the time abnormal recognition condition and the space abnormal recognition condition.
The setting of the spatial anomaly identification condition and the temporal anomaly identification condition can ensure that the identified anomaly values are related to the seismic activity as much as possible, thereby ensuring the seismic forecasting capability of acquiring the seismic activity higher than the natural probability.
In some embodiments, the spatial anomaly identification condition and the temporal anomaly identification condition are determined based on a preset seismic data set. Wherein the preset seismic profile dataset is used for recording seismic time, seismic position and seismic intensity (such as seismic magnitude) of a plurality of historical seismic events. In order to improve the lateral comparability of various earthquake forecasting methods, a preset earthquake case data set of a global scope/national scope/regional scope for many years can be constructed in advance in the embodiment of the invention and used as reference data for carrying out statistical analysis on various geophysical parameters and anomaly detection methods. For example, a global seismic catalog from the United States Geological Survey (USGS) may be used to select 1825 seismic events having a magnitude of 6 or more and a source depth of 70km or less from 2006 to 2020 to construct a global representative seismic case dataset. Then, using part of the seismic example data in the preset seismic example data set to perform seismic retrospective analysis, namely analyzing the relation between each seismic example and the abnormal data in the first time range before the seismic example to determine parameters in the spatial abnormality identification condition and the temporal abnormality identification condition. And performing predictive analysis on parameters in the determined spatial anomaly identification condition and the determined temporal anomaly identification condition by using another part of seismic data in the preset seismic data set, namely performing seismic prediction by using the parameters and the abnormal data in the spatial anomaly identification condition and the temporal anomaly identification condition, and performing prediction correctness verification analysis on the seismic prediction result and the another part of seismic data.
Specifically, according to the above description, the initial anomaly data is an abnormal value of a geophysical parameter calculated from a mathematical formula and observation data, which does not characterize the correlation between the abnormal value and seismic activity. Therefore, in the embodiment of the invention, after the initial abnormal data is obtained, the abnormal value filtering is performed on the initial abnormal data by using the preset earthquake abnormal recognition condition so as to recognize the abnormal value which has correlation with the earthquake activity in the initial abnormal data, and the obtained result is the target abnormal data.
S130, determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range.
The second time range is a time category of the earthquake prediction, and is a date range corresponding to a certain time length immediately after the current date, and may be, for example, 10 days, 20 days, or 30 days after the current date.
Specifically, according to the above description, the pixel value included in the target abnormal data is an abnormal value related to the seismic activity, and the seismic prediction can be performed based on the abnormal value. For example, the regional dimension of the earthquake prediction, i.e. the local region (e.g. the region of 5 ° × 5 ° around the position of the pixel value) is determined according to the position of the pixel value in the target abnormal data. Then, earthquake prediction of a certain magnitude of a second time range is performed in each local area. Such as forecasting that an earthquake with a certain magnitude and a certain source depth will occur in the local area range and in the second time range in the future. The predicted magnitude and source depth may be determined from the magnitude and source depth of a typical seismic event collected in the predetermined set of seismic event data. For example, the predicted magnitude is greater than or equal to the magnitude in a typical seismic case, and the predicted source depth is less than or equal to the source depth in a typical seismic case. Therefore, the accuracy of earthquake prediction can be improved to a certain extent.
In some embodiments, the time interval between two adjacent seismic forecasts is a duration corresponding to the second time range. I.e. there is no repeat date between the second time ranges corresponding to two adjacent seismic forecasts. Therefore, repeated data calculation and repeated alarming of the same earthquake can be avoided, and the earthquake prediction can be more objective.
Referring to fig. 2, seismic monitoring is performed using raw remote sensing data of a first time range (horizontal line fill) before the current date (diagonal line fill) of the first seismic forecast, and seismic forecast is performed in a second time range (vertical line fill). After the end of the earthquake prediction, the current date is changed to the date immediately after the second time range, i.e., the current date' of the example in fig. 2 is filled with diagonal lines. Then, the second earthquake prediction is carried out by using the original remote sensing data of the first time range 'before the current date for earthquake monitoring, and the earthquake prediction is carried out in the second time range'.
According to the earthquake forecasting method based on the remote sensing data, provided by the embodiment of the invention, the original remote sensing data of the target area in the first time range can be obtained, and earthquake abnormity detection is carried out on the original remote sensing data to generate initial abnormal data; performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data; the preset earthquake abnormity identification conditions comprise space abnormity identification conditions and time abnormity identification conditions, and the target abnormity data is data used for representing abnormity caused by earthquake activities; and determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range. The method and the device realize that the accuracy of identifying the data abnormity of the geophysical parameters caused by the earthquake is improved by providing the preset earthquake abnormity identification conditions on the space dimension and the time dimension, thereby improving the accuracy of earthquake prediction.
In some embodiments, the filtering process of the abnormal values related to the seismic activity in S120 may be implemented as the following step a and step B.
And A, performing sliding window processing based on a space anomaly identification condition on the initial anomaly data according to a preset moving direction, a preset moving step length and a preset space range so as to perform primary anomaly filtering on the initial anomaly data and generate intermediate anomaly data.
Specifically, in the embodiment of the present invention, a sliding window process is performed on each image (pixel value is an abnormal value in the initial abnormal data) included in the initial abnormal data. And the processing process in each sliding window is to judge whether each abnormal value in the window meets the spatial abnormality recognition condition or not and determine whether the main pixel corresponding to the window is reserved or not according to the judgment result. And after each window sliding process, the window is moved according to the preset moving direction and the preset moving step length, and the next process in the sliding window is carried out. After all the images contained in the initial abnormal data are processed, the obtained result is intermediate abnormal data of which the initial abnormal data are subjected to spatial filtering.
Exemplarily, the step a may be embodied as:
and step A, determining the current processing pixel from the initial abnormal data.
Specifically, for any image in the initial abnormal data, a central pixel is determined according to a certain rule (for example, the first pixel from the top left corner of the image) as the current processing pixel in the image.
Step A2, judging whether each pixel value in a preset space range taking the current processing pixel as a center meets the space abnormity identification condition, and determining whether to filter the current processing pixel based on the judgment result.
Specifically, if it is determined that each pixel value in a preset spatial range centered on the current processing pixel meets a spatial anomaly identification condition, the current processing pixel is retained; and if the pixel values in the preset space range taking the current processing pixel as the center do not meet the space abnormity identification condition, filtering the current processing pixel.
Namely, according to the area size of the preset space range, the processing area of the filtering processing can be determined by taking the current processing pixel as the center. Then, comparing each pixel value contained in the processing area with a second abnormal threshold value, and determining the effective pixels contained in the processing area. Then, the average abnormal absolute value of the effective image elements is calculated and compared with a first abnormal threshold value. If the comparison result is that the average abnormal absolute value is greater than or equal to the first abnormal threshold, the current processing pixel is reserved; if the comparison result is that the average abnormal absolute value is smaller than the first abnormal threshold, the current processing pixel is rejected, for example, the abnormal value of the current processing pixel is replaced by a preset invalid value.
And A3, determining the next pixel which is away from the current processing pixel by a preset step length according to the preset moving direction, and updating the current processing pixel by using the next pixel.
Specifically, in the image, a preset step length is moved from the currently processed pixel according to a preset moving direction, and a new pixel is determined. The new pixel element is the next pixel element corresponding to the current processed pixel element in the sliding window processing. Then, the next pixel is used as a new current processing pixel, i.e. the current processing pixel is updated.
And step A4, returning to execute the step A2 until the initial abnormal data is traversed.
Specifically, the sliding window processing is performed in a loop according to the step a2 and the step A3 until the image processing is completed.
Then, according to the processes from step a1 to step a4, the abnormal value filtering process of the spatial dimension is performed on each image in the initial abnormal data, so as to obtain the intermediate abnormal data.
And B, performing secondary abnormal filtering on the intermediate abnormal data based on the time abnormal recognition condition to generate target abnormal data.
Specifically, for each pixel position, determining the proportion of the number of abnormal values contained in the intermediate abnormal data in the pixel number, and when the proportion is determined to meet a preset proportion threshold, retaining the pixel position; and generating target abnormal data based on the reserved pixel positions.
In specific implementation, the intermediate abnormal data is a time-series image set, and an abnormal value time series can be obtained at each pixel position. The abnormal value time series includes an abnormal value and an invalid value. Then, for any one pixel position, the ratio of the number of the abnormal values included in the abnormal value time sequence to the total number of the numerical values included in the entire abnormal value time sequence (i.e., the number of pixels) is calculated, and the abnormal observation ratio at the pixel position can be obtained. Then, the abnormal observation ratio is compared with a preset ratio threshold. If the abnormal observation proportion is larger than or equal to the preset proportion threshold value, the position of the pixel is reserved; and if the abnormal observation proportion is smaller than a preset proportion threshold value, rejecting the position of the pixel.
According to the process, abnormal value filtering of time dimension can be carried out on each pixel position, and finally an image which identifies the effective pixel position, namely target abnormal data, can be obtained. Each valid pel position contained in the target anomaly data may be considered a location at which seismic activity will occur. A local area to be subjected to seismic prediction can be subsequently determined according to the position of each effective pixel.
In some embodiments, after S130, the method for seismic forecasting based on remote sensing data further comprises: and determining an evaluation index value of the earthquake prediction based on the target abnormal data.
The evaluation index comprises at least one of a report rate, a false report rate, a missing report rate, a normal rate and a Mauss correlation coefficient.
Specifically, in order to improve the lateral comparability among various earthquake prediction methods, the embodiment of the invention provides an evaluation index of an earthquake prediction result, namely at least one of a report accuracy, a false alarm rate, a missing report rate, a normal rate and a mazis correlation coefficient. Thus, the seismic forecasting ability can be evaluated using the same evaluation index.
The meaning of the report accuracy, the false report rate, the missing report rate and the normal rate can be seen in table 1, which is four independent evaluation indexes.
Since many earthquake prediction methods only give a part of the four independent evaluation indexes, such as the prediction rate, and ignore other evaluation indexes, the earthquake prediction capability is not fully displayed. In the embodiment of the invention, a comprehensive evaluation index, namely an improved Mazis correlation coefficient is determined so as to comprehensively display the comprehensive results of the four independent evaluation indexes.
The improved Maxjews Correlation Coefficient (MCC) is obtained by applying the maxjews correlation coefficient in machine learning to the field of seismic prediction as the accuracy of seismic prediction, and its calculation formula is as follows:
wherein Acc is the number of reports, Nor is the number of normalities, Fal is the number of false reports, Mis is the number of missed reports.
The accuracy can be used as a confidence level of the earthquake prediction under the constraint of the improved McSess correlation coefficient MCC'. Therefore, evaluation indexes adaptive to the machine learning field can be provided, the understanding degree of researchers in various fields on the earthquake prediction accuracy is improved, the transverse comparability of various earthquake prediction methods is further improved, a sufficient confidence level of prediction reliability can be provided for the earthquake prediction, and the effectiveness of the earthquake prediction is further improved.
TABLE 1 evaluation index of earthquake prediction capability
Based on the method flow of the embodiment of the invention, the seismic forecasting capabilities of the ZS method and the RST method are transversely compared by using the seismic data in 2006-2020, so as to show the capability of realizing uniform and quantitative transverse comparison of forecasting efficiency of the embodiment of the invention. The ZS method and the RST method are similar in spatial distribution pattern of the reporting rate, and have the highest reporting rate in the earthquake active area. However, the false alarm rates of these two methods are also high in seismic active areas. Moreover, the normal rate is closely related to the false alarm rate. The MCC 'range for the ZS method and RST method is-0.48 to 0.21, but the ZS method generates relatively high MCC' values in most grids. According to the spatial distribution of the MCC 'values, the MCC' values of the regions with high reporting rate are not high, which indicates that the comprehensive index can reflect the comprehensive evaluation capability.
Fig. 3 is a schematic structural diagram of an earthquake forecasting device based on remote sensing data according to an embodiment of the present invention. Referring to fig. 3, the earthquake forecasting device 300 based on remote sensing data specifically includes:
the initial abnormal data generation module 310 is configured to obtain original remote sensing data of a target area in a first time range, perform seismic abnormal detection on the original remote sensing data, and generate initial abnormal data;
a target abnormal data generation module 320, configured to perform abnormal filtering on the initial abnormal data based on a preset seismic abnormal recognition condition, and generate target abnormal data; the preset earthquake abnormity identification conditions comprise space abnormity identification conditions and time abnormity identification conditions, and the target abnormity data is data used for representing abnormity caused by earthquake activities;
and the earthquake forecasting module 330 is configured to determine at least one local area in the target area based on the target abnormal data, and perform earthquake forecasting on the local area within a second time range.
The earthquake forecasting device based on the remote sensing data provided by the embodiment of the invention can acquire the original remote sensing data of the target area in a first time range, and carry out earthquake abnormity detection on the original remote sensing data to generate initial abnormal data; performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data; the preset earthquake abnormity identification conditions comprise space abnormity identification conditions and time abnormity identification conditions, and the target abnormity data is data used for representing abnormity caused by earthquake activities; and determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range. The method and the device realize that the accuracy of identifying the data abnormity of the geophysical parameters caused by the earthquake is improved by providing the preset earthquake abnormity identification conditions on the space dimension and the time dimension, thereby improving the accuracy of earthquake prediction.
In some embodiments, the spatial anomaly identification condition is that the average anomaly absolute value of each effective pixel covered in a preset spatial range is greater than or equal to a first anomaly threshold; the effective pixel is a pixel with an abnormal absolute value greater than or equal to a second abnormal threshold, and the first abnormal threshold is greater than the second abnormal threshold;
the time anomaly identification condition is that the anomaly observation proportion meeting the space anomaly identification condition in the first time range is greater than or equal to a preset proportion threshold value.
In some embodiments, the target anomaly data generation module 320 includes:
the spatial filtering submodule is used for performing sliding window processing based on a spatial anomaly identification condition on the initial anomaly data according to a preset moving direction, a preset moving step length and a preset spatial range so as to perform primary anomaly filtering on the initial anomaly data and generate intermediate anomaly data;
and the time filtering submodule is used for carrying out secondary exception filtering on the intermediate exception data based on the time exception identification condition to generate target exception data.
Optionally, the spatial filtering submodule is specifically configured to:
determining a current processing pixel from the initial abnormal data;
judging whether each pixel value in a preset space range with the current processing pixel as the center meets a space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on a judgment result;
determining a next pixel which is away from the current processing pixel by a preset step length according to a preset moving direction, and updating the current processing pixel by using the next pixel;
and returning to execute the step of judging whether each pixel value in a preset space range with the current processing pixel as the center meets the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result until the initial abnormal data is traversed.
Optionally, the temporal filtering submodule is specifically configured to:
for each pixel position, determining the proportion of the number of abnormal values contained in the intermediate abnormal data in the pixel number, and reserving the pixel position when determining that the proportion meets a preset proportion threshold;
target anomaly data is generated based on the retained pel positions.
In some embodiments, the spatial anomaly identification condition and the temporal anomaly identification condition are determined based on a preset seismic case data set; the preset seismic example data set is used for recording seismic time, seismic positions and seismic intensity of multiple historical seismic events.
In some embodiments, the target area is within an area range of a preset seismic surveillance area; the preset earthquake monitoring area is a geographical area with historical earthquake occurrence times reaching a preset time threshold value.
In some embodiments, the time interval between two adjacent seismic forecasts is a duration corresponding to the second time range.
In some embodiments, the telemetry-based seismic forecasting device 300 further comprises an evaluation index value determination module for:
determining at least one local area in the target area based on the target abnormal data, and determining an evaluation index value of the earthquake prediction based on the target abnormal data after the earthquake prediction in a second time range is carried out on the local area; the evaluation index comprises at least one of a report accuracy rate, a false report rate, a missing report rate, a normal rate and a Mazis correlation coefficient.
The earthquake forecasting device based on the remote sensing data provided by the embodiment of the invention can execute the earthquake forecasting method based on the remote sensing data provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
It should be noted that, in the embodiment of the earthquake prediction device based on remote sensing data, the modules and the sub-modules included in the embodiment are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional modules/sub-modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Referring to fig. 4, an electronic device 400 according to an embodiment of the present invention includes: a processor 420 and a memory 410; the processor 420 is used to perform the steps of the telemetry data based seismic prediction method provided by any of the embodiments of the invention by calling a program or instructions stored in the memory 410.
As shown in fig. 4, electronic device 400 is embodied in the form of a general purpose computing device. The components of electronic device 400 may include, but are not limited to: one or more processors 420, a memory 410, and a bus 450 that connects the various system components (including the memory 410 and the processors 420).
A program/utility 414 having a set (at least one) of program modules 415, which may include but are not limited to an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may include an implementation of a network environment, may be stored in, for example, memory 410. The program modules 415 generally perform the functions and/or methods of any of the embodiments described herein.
It should be noted that the electronic device 400 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments of the present invention.
Embodiments of the present invention also provide a computer-readable storage medium storing a program or instructions for causing a computer to perform the steps of the seismic forecasting method based on remote sensing data provided in any of the embodiments of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the present invention. As used in the specification and claims of this application, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. The term "and/or" includes any and all combinations of one or more of the associated listed items. Relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An earthquake forecasting method based on remote sensing data is characterized by comprising the following steps:
acquiring original remote sensing data of a target area in a first time range, and performing earthquake anomaly detection on the original remote sensing data to generate initial anomaly data;
performing exception filtering on the initial exception data based on a preset earthquake exception identification condition to generate target exception data; the preset seismic anomaly identification conditions comprise spatial anomaly identification conditions and time anomaly identification conditions, and the target anomaly data are used for representing anomalies caused by seismic activities;
and determining at least one local area in the target area based on the target abnormal data, and performing earthquake prediction on the local area within a second time range.
2. The method according to claim 1, wherein the spatial anomaly identification condition is that the average anomaly absolute value of each effective pixel covered in a preset spatial range is greater than or equal to a first anomaly threshold value; the effective pixel is a pixel with an abnormal absolute value greater than or equal to a second abnormal threshold, and the first abnormal threshold is greater than the second abnormal threshold;
the time anomaly identification condition is that the anomaly observation proportion meeting the space anomaly identification condition in the first time range is greater than or equal to a preset proportion threshold value.
3. The method of claim 2, wherein the performing anomaly filtering on the initial anomaly data based on preset seismic anomaly identification conditions to generate target anomaly data comprises:
performing sliding window processing based on the space anomaly identification condition on the initial anomaly data according to a preset moving direction, a preset moving step length and the preset space range to perform primary anomaly filtering on the initial anomaly data and generate intermediate anomaly data;
and performing secondary anomaly filtering on the intermediate anomaly data based on the time anomaly identification condition to generate the target anomaly data.
4. The method according to claim 3, wherein the performing sliding window processing based on the spatial anomaly identification condition on the initial anomaly data according to a preset moving direction, a preset moving step length and the preset spatial range to perform primary anomaly filtering on the initial anomaly data, and generating intermediate anomaly data comprises:
determining a current processing pixel from the initial abnormal data;
judging whether each pixel value in the preset space range with the current processing pixel as the center meets the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result;
determining a next pixel which is away from the current processing pixel by a preset step length according to a preset moving direction, and updating the current processing pixel by using the next pixel;
and returning to the step of judging whether the pixel values in the preset space range with the current processing pixel as the center meet the space abnormity identification condition or not, and determining whether to filter the current processing pixel or not based on the judgment result until the initial abnormal data is traversed.
5. The method according to claim 2, wherein the spatial anomaly identification condition and the temporal anomaly identification condition are determined based on a preset seismic profile data set; the preset seismic instance data set is used for recording seismic time, seismic positions and seismic intensity of multiple historical seismic events.
6. The method of claim 1, wherein the target area is within an area of a predetermined seismic surveillance area; the preset earthquake monitoring area is a geographical area with historical earthquake occurrence times reaching a preset time threshold value.
7. The method of claim 1, wherein the time interval between two adjacent seismic forecasts is a duration corresponding to the second time range.
8. An earthquake prediction device based on remote sensing data, comprising:
the system comprises an initial abnormal data generation module, a data acquisition module, a data analysis module and a data processing module, wherein the initial abnormal data generation module is used for acquiring original remote sensing data of a target area in a first time range, and performing earthquake abnormality detection on the original remote sensing data to generate initial abnormal data;
the target abnormal data generation module is used for carrying out abnormal filtering on the initial abnormal data based on a preset earthquake abnormal recognition condition to generate target abnormal data; the preset seismic anomaly identification conditions comprise spatial anomaly identification conditions and time anomaly identification conditions, and the target anomaly data are used for representing anomalies caused by seismic activities;
and the earthquake forecasting module is used for determining at least one local area in the target area based on the target abnormal data and carrying out earthquake forecasting on the local area within a second time range.
9. An electronic device, characterized in that the electronic device comprises:
a processor and a memory;
the processor is adapted to perform the steps of the telemetry data based seismic forecasting method of any of claims 1 to 7 by invoking a program or instructions stored in the memory.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a program or instructions for causing a computer to execute the steps of the method for seismic forecasting based on remote sensing data according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210179583.3A CN114721035A (en) | 2022-02-25 | 2022-02-25 | Earthquake forecasting method, device, equipment and medium based on remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210179583.3A CN114721035A (en) | 2022-02-25 | 2022-02-25 | Earthquake forecasting method, device, equipment and medium based on remote sensing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114721035A true CN114721035A (en) | 2022-07-08 |
Family
ID=82235762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210179583.3A Pending CN114721035A (en) | 2022-02-25 | 2022-02-25 | Earthquake forecasting method, device, equipment and medium based on remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114721035A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701847A (en) * | 2023-08-07 | 2023-09-05 | 中国石油大学(华东) | Pre-earthquake thermal anomaly extraction method based on space-time combination |
-
2022
- 2022-02-25 CN CN202210179583.3A patent/CN114721035A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701847A (en) * | 2023-08-07 | 2023-09-05 | 中国石油大学(华东) | Pre-earthquake thermal anomaly extraction method based on space-time combination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3316198A1 (en) | Method and system for managing performance indicators for addressing goals of enterprise facility operations management | |
| US9142106B2 (en) | Tailgating detection | |
| WO2010138864A2 (en) | Forecasting hotspots using predictive visual analytics approach | |
| CN116680658B (en) | Heat wave monitoring station site selection method and system based on risk evaluation | |
| Höhle et al. | Aberration detection in R illustrated by Danish mortality monitoring | |
| CN112215439B (en) | Geological disaster emergency command data processing method and system based on GIS | |
| CN116542604A (en) | Global e-commerce platform commodity purchase, sale and stock management method, device, equipment and medium | |
| CN114721035A (en) | Earthquake forecasting method, device, equipment and medium based on remote sensing data | |
| Hsu et al. | Two novel approaches to reduce false alarm due to non‐earthquake events for on‐site earthquake early warning system | |
| Zhou et al. | The risk management using limit theory of statistics on extremes on the big data era | |
| Elogne et al. | An application of Spartan spatial random fields in environmental mapping: focus on automatic mapping capabilities | |
| Canter | Using a geographic information system for tactical crime analysis | |
| CN114970621A (en) | Method and device for detecting abnormal aggregation event, electronic equipment and storage medium | |
| Kortas et al. | Exploring multi-scale variability in hotspot mapping: A case study on housing prices and crime occurrences in Heerlen | |
| Harrou et al. | Monitoring patient flow in a hospital emergency department: ARMA-based nonparametric GLRT scheme | |
| CN116994405B (en) | Intelligent disaster early warning method and system | |
| CN116703455B (en) | Medicine data sales prediction method and system based on time series hybrid model | |
| CN112665730B (en) | Pre-earthquake temperature anomaly detection method, pre-earthquake temperature anomaly detection device, pre-earthquake temperature anomaly detection equipment and storage medium | |
| Feng et al. | The effects of factor generalization scales on the reproduction of dynamic urban growth | |
| Kim et al. | A bootstrap based space–time surveillance model with an application to crime occurrences | |
| Liu et al. | The return periods and risk assessment of severe dust storms in Inner Mongolia with consideration of the main contributing factors | |
| CN113518205A (en) | Video patrol processing method based on AI analysis | |
| Navidi Nassaj et al. | Evaluation of three gauge-based global gridded precipitation datasets for drought monitoring over Iran | |
| Selvik et al. | How to classify failures when collecting data for safety-instrumented systems in the oil and gas industry | |
| CN114360735A (en) | Infectious disease time-space aggregation detection and analysis method and system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |