Intelligent monitoring and early warning method based on geological disaster cloud monitoring platform

Abstract

The present application belongs to the field of geological disaster monitoring, and relates to data analysis technology, and is used to solve the problem that the prior art cannot combine geological structure parameters and meteorological parameters to perform hidden risk prediction analysis of geological disasters, and specifically relates to an intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform, comprising a monitoring sub-method and a prediction sub-method; the monitoring sub-method comprises the following steps: step S1: data acquisition on geological disaster parameters; step S2: monitoring and early warning analysis on geological disasters; and step S3: alarm type analysis on geological disasters; the present application generates a concentration coefficient on the basis of the distribution characteristics of risk points, marks the disaster risk types of the geological disaster monitoring area through the concentration coefficient, thereby generating corresponding early warning signals, which is helpful for managers to perform risk control and management, and improves the risk processing efficiency of geological disasters.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of geological disaster monitoring, and relates to a data analysis technique, in particular to an intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform. BACKGROUND

[0002] The geological disaster intelligent monitoring and early warning system constructs a disaster prevention system covering the whole process of "monitoring-early warning-disposal" through three core modules of multi-source perception, intelligent analysis and real-time response, and significantly improves the efficiency of disaster risk identification and emergency response.

[0003] The invention patent with the publication number CN113192297B discloses an artificial intelligence-based geological disaster monitoring, prediction and early warning method. The early warning method improves the early warning algorithm through historical data warning and learning of historical data and disaster development process, realizes prediction of monitoring data, and provides early warning information based on real-time data and historical data and early warning information based on prediction data. However, the early warning method cannot combine geological structure parameters and meteorological parameters to perform geological disaster implicit risk prediction analysis, resulting in that the prior art cannot accurately predict geological disasters in advance, and the actual risk of geological disasters cannot be effectively curbed.

[0004] In view of the above technical problems, the present application provides a solution. SUMMARY

[0005] The present application aims to provide an intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform, which solves the problem that the prior art cannot combine geological structure parameters and meteorological parameters to perform geological disaster implicit risk prediction analysis.

[0006] The present application aims to provide an intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform, which solves the problem that the prior art cannot combine geological structure parameters and meteorological parameters to perform geological disaster implicit risk prediction analysis.

[0007] The object of the present application can be achieved by the following technical solutions:

[0008] The intelligent monitoring and early warning method based on the geological disaster cloud monitoring platform comprises a monitoring sub-method and a prediction sub-method.

[0009] The monitoring sub-method comprises the following steps:

[0010] Step S1: Collecting geological disaster parameters: setting a plurality of collection points in a geological disaster monitoring area, generating a monitoring period and dividing the monitoring period into a plurality of monitoring time periods, and obtaining a monitoring data set of the collection points at the end of the monitoring time period.

[0011] Step S2: monitoring and early warning analysis of geological disasters: generating a risk coefficient of the collection point from the collection data set of the collection point, comparing the risk coefficient with the preset risk threshold: if the risk coefficient is less than the risk threshold, marking the collection point as a safe point; if the risk coefficient is greater than or equal to the risk threshold, marking the collection point as a risk point; if all collection points are marked as safe points at the end of the monitoring period, executing the prediction sub-method; otherwise, executing step S3;

[0012] Step S3: alarm type analysis of geological disasters: connecting the risk points as the corner points of the polygon with the adjacent risk points, marking the closed polygon obtained as a risk area, marking the ratio of the area of the risk area to the area of the geological disaster monitoring area as a concentration coefficient, and marking the geological disaster risk type of the geological disaster monitoring area through the concentration coefficient.

[0013] Further, in step S1, the monitoring data set includes displacement data WY, inclination data QJ and crack data LF, the displacement data WY is the cumulative displacement of the collection point in the monitoring period, the inclination data QJ is the inclination angle change of the collection point in the monitoring period, and the crack data LF is the surface cracking width of the collection point.

[0014] Further, in step S2, the generation process of the risk coefficient of the collection point includes: constructing an analysis data row vector HK from the monitoring data set of the collection point, HK=[WY, QJ, LF], generating a weight column vector LK for the monitoring data set, LK=[a1, a2, a3] T , the risk coefficient of the collection point is calculated by point product of the analysis data row vector HK and the weight column vector LK of all collection points.

[0015] Further, in step S3, the specific process of marking the geological disaster risk type of the geological disaster monitoring area includes: comparing the concentration coefficient with the preset concentration threshold: if the concentration coefficient is less than the concentration threshold, it is determined that the geological disaster monitoring area exists concentrated disaster risk, a concentrated early warning signal is generated and the concentrated early warning signal and the risk area are sent to the mobile terminal of the management personnel; if the concentration coefficient is greater than or equal to the concentration threshold, it is determined that the geological disaster monitoring area exists dispersed disaster risk, a dispersed early warning signal is generated and the dispersed early warning signal and all risk points are sent to the mobile terminal of the management personnel.

[0016] Further, the prediction sub-method includes the following steps:

[0017] Step P1: multi-dimensional risk analysis of the geological disaster monitoring area: obtaining the rainfall data of the collection point at the end of the monitoring period, the rainfall data being the rainfall of the location of the collection point in the monitoring period, obtaining the slope value of the location of the collection point;

[0018] Step P2: risk prediction analysis on the geological disaster monitoring area: generate a rainfall evaluation set, a slope evaluation set, and a risk evaluation set; compare the rainfall evaluation set, the slope evaluation set, and the risk evaluation set to obtain a triple evaluation value, a rainfall evaluation value, and a slope evaluation value;

[0019] Step P3: generate a prediction analysis result: difference operation of the sum value of the rainfall evaluation value and the slope evaluation value in the monitoring period and the triple evaluation value to obtain a prediction evaluation value, mark the ratio of the prediction evaluation value and K1 as a prediction coefficient, and determine whether the geological disaster monitoring area has a geological disaster risk hidden danger in the monitoring period through the prediction coefficient.

[0020] Further, in step P2, the generation process of the rainfall evaluation set, the slope evaluation set, and the risk evaluation set includes: arranging the collection points in descending order of rainfall data to obtain a rainfall sequence, marking the K1 collection points at the front of the rainfall sequence as rainfall evaluation points, and constructing the rainfall evaluation set from all the rainfall evaluation points; arranging the collection points in descending order of slope value to obtain a slope sequence, marking the K1 collection points at the front of the slope sequence as slope evaluation points, and constructing the slope evaluation set from all the slope evaluation points; arranging the collection points in descending order of risk coefficient to obtain a risk sequence, marking the K1 collection points at the front of the risk sequence as risk evaluation points, and constructing the risk evaluation set from all the risk evaluation points.

[0021] Further, in step P2, the acquisition process of the triple evaluation value, the rainfall evaluation value, and the slope evaluation value includes: marking the elements in the intersection of the rainfall evaluation set, the slope evaluation set, and the risk evaluation set as triple points, marking the number of triple points as the triple evaluation value; marking the absolute value of the difference between the sequence number of the triple points in the rainfall sequence and the sequence number in the risk sequence as the rainfall coincidence value of the triple points, summing all the rainfall coincidence values of the triple points and taking the average to obtain the rainfall evaluation value; marking the absolute value of the difference between the sequence number of the triple points in the slope sequence and the sequence number in the risk sequence as the slope coincidence value of the triple points, summing all the slope coincidence values of the triple points and taking the average to obtain the slope evaluation value.

[0022] Further, in step P3, the specific process of determining whether the geological disaster monitoring area has a geological disaster risk hidden danger in the monitoring period includes: comparing the prediction coefficient with a preset prediction threshold value: if the prediction coefficient is less than the prediction threshold value, it is determined that the geological disaster monitoring area has a geological disaster risk hidden danger in the monitoring period, a hidden danger warning signal is generated, and the hidden danger warning signal is sent to the mobile terminal of the management personnel; if the prediction coefficient is greater than or equal to the prediction threshold value, it is determined that the geological disaster monitoring area does not have a geological disaster risk hidden danger in the monitoring period.

[0023] The present application has the following advantages:

[0024] 1. By collecting data on geological disaster parameters, the monitoring data group of all collection points is obtained in the form of point cloud data collection, and the risk coefficient of the collection point is calculated through the monitoring and early warning analysis process, and the risk degree of geological disasters in the geological disaster monitoring area is fed back through the risk coefficient of the collection point;

[0025] 2. By analyzing the alarm type of geological disasters, a concentration coefficient is generated based on the distribution characteristics of risk points, and the disaster risk type of the geological disaster monitoring area is marked through the concentration coefficient, thereby generating a corresponding early warning signal, which helps managers to control risks and improve the risk processing efficiency of geological disasters;

[0026] 3. By performing multi-dimensional risk analysis on the geological disaster monitoring area, the geological structure parameters and meteorological parameters of the collection points are collected to provide data support for the risk prediction analysis process, and the hidden risks of the geological disaster monitoring area are evaluated by comprehensively analyzing multi-source data, thereby reducing the actual occurrence probability of geological disasters;

[0027] 4. By performing risk prediction analysis on the geological disaster monitoring area, a prediction coefficient is generated based on the comparison results of the rainfall evaluation set, the slope evaluation set and the risk evaluation set, and a prediction analysis result is generated through the prediction coefficient, thereby improving the intuitiveness of the system output data. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Figure 1 The method flowchart of the first embodiment of the present application;

[0030] Figure 2 The method flowchart of the second embodiment of the present application;

[0031] Figure 3 The system block diagram of the third embodiment of the present application. DETAILED DESCRIPTION

[0032] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Intelligent monitoring and early warning methods based on geological disaster cloud monitoring platforms include monitoring sub-methods and prediction sub-methods.

[0034] Example 1: As Figure 1 As shown, the monitoring sub-method includes the following steps:

[0035] Step S1: Data collection of geological disaster parameters: Several collection points are set up in the geological disaster monitoring area, a monitoring cycle is generated and divided into several monitoring periods. At the end of the monitoring period, the monitoring data set of the collection point is obtained. The monitoring data set includes displacement data WY, tilt angle data QJ and crack data LF. The displacement data WY is the cumulative displacement of the collection point during the monitoring period, which is obtained by the LVDT displacement sensor. The tilt angle data QJ is the change in tilt angle of the collection point during the monitoring period, which is obtained by the MEMS tilt angle sensor. The crack data LF is the surface crack width of the collection point, which is obtained by the laser rangefinder.

[0036] Step S2: Conduct monitoring and early warning analysis of geological hazards: The analysis data row vector HK, HK=[WY, QJ, LF] is constructed from the monitoring data sets of the collection points, and a weighted column vector LK, LK=[a1, a2, a3] is generated for the monitoring data sets. T The risk coefficient of each collection point is calculated by performing a dot product between the row vector HK and the column vector LK of the analysis data from all collection points. The risk coefficient is then compared with a preset risk threshold: if the risk coefficient is less than the risk threshold, the collection point is marked as a safe point; if the risk coefficient is greater than or equal to the risk threshold, the collection point is marked as a risk point; if all collection points are marked as safe points at the end of the monitoring period, the prediction sub-method is executed; otherwise, step S3 is executed. Monitoring data sets of all collection points are acquired using point cloud data acquisition, and the risk coefficient of each collection point is calculated through the monitoring and early warning analysis process. The risk coefficient of each collection point is used to provide feedback on the degree of geological disaster risk in the geological disaster monitoring area.

[0037] Step S3: alarm type analysis of geological disasters: connecting the risk points as the corner points of the polygon with the adjacent risk points, marking the obtained closed polygon as a risk area, marking the ratio of the area of the risk area to the area of the geological disaster monitoring area as a concentration coefficient, comparing the concentration coefficient with a preset concentration threshold: if the concentration coefficient is less than the concentration threshold, it is determined that the geological disaster monitoring area has a concentrated disaster risk, a concentrated early warning signal is generated, and the concentrated early warning signal and the risk area are sent to the mobile terminal of the management personnel; if the concentration coefficient is greater than or equal to the concentration threshold, it is determined that the geological disaster monitoring area has a dispersed disaster risk, a dispersed early warning signal is generated, and the dispersed early warning signal and all risk points are sent to the mobile terminal of the management personnel; based on the distribution characteristics of the risk points, the concentration coefficient is generated, the disaster risk type of the geological disaster monitoring area is marked through the concentration coefficient, and the corresponding early warning signal is generated, which helps the management personnel to control the risk and improves the risk processing efficiency of the geological disasters.

[0038] Embodiment two: as shown in the following table, the prediction sub-method includes the following steps: Figure 2

[0039] Step P1: multi-dimensional risk analysis of the geological disaster monitoring area: acquiring the rainfall data of the collection point at the end of the monitoring period, the rainfall data being the rainfall of the location of the collection point in the monitoring period, and acquiring the slope value of the location of the collection point; collecting the geological structure parameters and the meteorological parameters of the collection point to provide data support for the risk prediction analysis process, and evaluating the hidden risk of the geological disaster monitoring area by comprehensively utilizing multi-source data to reduce the actual occurrence probability of the geological disasters;

[0040] ​Step P2: risk prediction analysis on the geological disaster monitoring area: arrange the collection points in descending order of rainfall data to obtain a rainfall sequence, mark the top K1 collection points in the rainfall sequence as rainfall evaluation points, and form a rainfall evaluation set from all the rainfall evaluation points; arrange the collection points in descending order of slope value to obtain a slope sequence, mark the top K1 collection points in the slope sequence as slope evaluation points, and form a slope evaluation set from all the slope evaluation points; arrange the collection points in descending order of risk coefficient to obtain a risk sequence, mark the top K1 collection points in the risk sequence as risk evaluation points, and form a risk evaluation set from all the risk evaluation points; mark the elements in the intersection of the rainfall evaluation set, the slope evaluation set and the risk evaluation set as triple points, and mark the number of triple points as a triple evaluation value; mark the absolute value of the difference between the sequence number of the triple points in the rainfall sequence and the sequence number in the risk sequence as the rainfall coincidence value of the triple points, and obtain the rainfall evaluation value by summing and averaging the rainfall coincidence values of all triple points; mark the absolute value of the difference between the sequence number of the triple points in the slope sequence and the sequence number in the risk sequence as the slope coincidence value of the triple points, and obtain the slope evaluation value by summing and averaging the slope coincidence values of all triple points;

[0041] Step P3: generate prediction analysis results: difference the sum of the rainfall evaluation value and the slope evaluation value in the monitoring period from the triple evaluation value to obtain a prediction evaluation value, mark the ratio of the prediction evaluation value to K1 as a prediction coefficient, and compare the prediction coefficient with a preset prediction threshold: if the prediction coefficient is less than the prediction threshold, it is determined that there is a geological disaster risk hidden danger in the monitoring period in the geological disaster monitoring area, a hidden danger warning signal is generated and sent to the mobile terminal of the management personnel; if the prediction coefficient is greater than or equal to the prediction threshold, it is determined that there is no geological disaster risk hidden danger in the monitoring period in the geological disaster monitoring area; generate the prediction coefficient based on the comparison results of the rainfall evaluation set, the slope evaluation set and the risk evaluation set, generate the prediction analysis result through the prediction coefficient, and improve the intuitiveness of the system output data.

[0042] Embodiment three: as shown in Figure 3 The intelligent monitoring and early warning system based on the geological disaster cloud monitoring platform includes a monitoring subsystem and a prediction subsystem. The monitoring subsystem includes a data acquisition module, a monitoring and early warning module, and an alarm processing module connected in sequence. The prediction subsystem includes a multidimensional analysis module, a prediction analysis module, and a result generation module connected in sequence.

[0043] The data acquisition module is used for data acquisition of geological disaster parameters to obtain a monitoring data set, and sends the monitoring data set to the monitoring and early warning module.

[0044] The monitoring and early warning module is used for monitoring and early warning analysis of geological disasters.

[0045] The alarm processing module is used for alarm type analysis on the geological disasters.

[0046] The multi-dimension analysis module is used for multi-dimension risk analysis on the geological disaster monitoring area.

[0047] The prediction analysis module is used for risk prediction analysis on the geological disaster monitoring area.

[0048] The result generation module is used for generating the prediction analysis result.

[0049] The intelligent monitoring and early warning method based on the geological disaster cloud monitoring platform, when working, sets a plurality of collection points in a geological disaster monitoring area, generates a monitoring period and divides the monitoring period into a plurality of monitoring time periods, obtains a monitoring data set of the collection point at the end of the monitoring time period, performs numerical calculation on the monitoring data set of the collection point to obtain a risk coefficient, evaluates the geological disaster risk of the geological disaster monitoring area through the risk coefficient, when there is no risk, performs multi-dimension risk analysis on the geological disaster monitoring area, generates a rainfall evaluation set, a slope evaluation set and a risk evaluation set, compares the rainfall evaluation set, the slope evaluation set and the risk evaluation set to obtain a prediction coefficient, and determines whether there is a geological disaster risk hidden danger in the geological disaster monitoring area in the monitoring time period through the prediction coefficient.

[0050] The above content is merely an example and description of the structure of the present application, and those skilled in the art can make various modifications or supplements or use similar ways to replace the described specific embodiments, as long as they do not deviate from the structure of the present application or exceed the scope defined by the present claims, which shall belong to the protection scope of the present application.

[0051] In the description of the present application, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0052] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The preferred embodiments do not describe all the details and limit the present application to the specific embodiments. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is limited by the claims and their entire scope and equivalents.

Claims

1. An intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform, characterized in that, Includes monitoring sub-methods and prediction sub-methods; The monitoring sub-method includes the following steps: Step S1: Collect geological disaster parameters: Set up several collection points in the geological disaster monitoring area, generate a monitoring cycle and divide the monitoring cycle into several monitoring periods, and obtain the monitoring data group of the collection points at the end of the monitoring period; Step S2: Monitor and analyze geological hazards: Generate risk coefficients for the collected data points using the collected data sets, and compare the risk coefficients with preset risk thresholds: If the risk coefficient is less than the risk threshold, mark the collected point as a safe point; if the risk coefficient is greater than or equal to the risk threshold, mark the collected point as a risk point; if all collected points are marked as safe points at the end of the monitoring period, execute the prediction sub-method; otherwise, execute step S3. Step S3: Analyze the alarm type of geological disasters: Connect the risk points as the corner points of the polygon to the adjacent risk points, mark the resulting closed polygon as the risk area, and mark the ratio of the area of ​​the risk area to the area of ​​the geological disaster monitoring area as the concentration coefficient. Mark the geological disaster risk type of the geological disaster monitoring area through the concentration coefficient. The prediction sub-method includes the following steps: Step P1: Conduct multi-dimensional risk analysis of the geological disaster monitoring area: At the end of the monitoring period, obtain the rainfall data of the collection point. The rainfall data is the amount of rainfall at the location of the collection point during the monitoring period. Obtain the slope value of the location of the collection point. Step P2: Conduct risk prediction analysis for the geological disaster monitoring area: Generate a rainfall assessment set, a slope assessment set, and a risk assessment set; compare the rainfall assessment set, slope assessment set, and risk assessment set to obtain triple assessment values, rainfall assessment values, and slope assessment values; arrange the collection points in descending order of risk coefficient, and the top K1 collection points constitute the risk assessment set; mark the elements in the intersection of the rainfall assessment set, slope assessment set, and risk assessment set as triple points, and mark the number of triple points as triple assessment values; Step P3: Generate predictive analysis results: The sum of the rainfall assessment value and the slope assessment value during the monitoring period is subtracted from the triple assessment value to obtain the predicted assessment value. The ratio of the predicted assessment value to K1 is marked as the prediction coefficient. The prediction coefficient is used to determine whether there are potential geological disaster risks in the geological disaster monitoring area during the monitoring period.

2. The intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform according to claim 1, characterized in that, In step S1, the monitoring data set includes displacement data WY, tilt angle data QJ, and crack data LF. Displacement data WY is the cumulative displacement of the acquisition point during the monitoring period, tilt angle data QJ is the change in tilt angle of the acquisition point during the monitoring period, and crack data LF is the surface crack width of the acquisition point.

3. The intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform according to claim 2, characterized in that, In step S2, the process of generating the risk coefficient for the collection points includes: constructing an analysis data row vector HK, where HK = [WY, QJ, LF], from the monitoring data sets of the collection points; and generating a weighted column vector LK, where LK = [a1, a2, a3], for the monitoring data sets. T The risk coefficient of each data point is obtained by performing a dot product between the row vector HK and the column vector LK of the analysis data from all data points.

4. The intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform according to claim 1, characterized in that, In step S3, the specific process of marking the geological disaster risk type in the geological disaster monitoring area includes: comparing the concentration coefficient with a preset concentration threshold; if the concentration coefficient is less than the concentration threshold, it is determined that there is a concentrated disaster risk in the geological disaster monitoring area, generating a concentrated early warning signal and sending the concentrated early warning signal and the risk area to the mobile terminal of the management personnel; if the concentration coefficient is greater than or equal to the concentration threshold, it is determined that there is a dispersed disaster risk in the geological disaster monitoring area, generating a dispersed early warning signal and sending the dispersed early warning signal and all risk points to the mobile terminal of the management personnel.

5. The intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform according to claim 1, characterized in that, In step P2, the generation process of the rainfall assessment set, slope assessment set, and risk assessment set includes: arranging the collection points in descending order of rainfall data to obtain a rainfall sequence; marking the top K1 collection points in the rainfall sequence as rainfall assessment points; and forming a rainfall assessment set from all the rainfall assessment points. Then, arranging the collection points in descending order of slope value to obtain a slope sequence; marking the top K1 collection points in the slope sequence as slope assessment points; and forming a slope assessment set from all the slope assessment points. Finally, arranging the collection points in descending order of risk coefficient to obtain a risk sequence; marking the top K1 collection points in the risk sequence as risk assessment points; and forming a risk assessment set from all the risk assessment points.

6. The intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform according to claim 5, characterized in that, In step P2, the process of obtaining the triple assessment value, rainfall assessment value, and slope assessment value includes: marking the elements within the intersection of the rainfall assessment set, slope assessment set, and risk assessment set as triple points, and marking the number of triple points as triple assessment values; marking the absolute value of the difference between the sequence number of the triple point in the rainfall sequence and the sequence number in the risk sequence as the rainfall overlap value of the triple point, and summing and averaging all the rainfall overlap values ​​of the triple points to obtain the rainfall assessment value; marking the absolute value of the difference between the sequence number of the triple point in the slope sequence and the sequence number in the risk sequence as the slope overlap value of the triple point, and summing and averaging all the slope overlap values ​​of the triple points to obtain the slope assessment value.

7. The intelligent monitoring and early warning method based on a geological disaster cloud monitoring platform according to claim 6, characterized in that, In step P3, the specific process of determining whether there are potential geological disaster risks in the geological disaster monitoring area during the monitoring period includes: comparing the prediction coefficient with the preset prediction threshold; if the prediction coefficient is less than the prediction threshold, it is determined that there are potential geological disaster risks in the geological disaster monitoring area during the monitoring period, generating a hazard warning signal and sending the hazard warning signal to the mobile terminal of the management personnel; if the prediction coefficient is greater than or equal to the prediction threshold, it is determined that there are no potential geological disaster risks in the geological disaster monitoring area during the monitoring period.

Images