Geological monitoring method based on data twinning, data twinning platform and equipment

Abstract

The invention discloses a geological monitoring method based on data twinning, a data twinning platform and equipment, and relates to the technical field of geological monitoring, and the method comprises the steps: constructing a geological monitoring sample database, and constructing a geological data twinning model according to the sample database; mapping geological monitoring data obtained in real time to the geological data twinborn model to obtain a first twinborn model; carrying out differential analysis on the first twinborn model and the geological data twinborn model, and determining a geological hidden danger type; obtaining a geological hidden danger position according to the geological hidden danger type; inputting geological monitoring data obtained in real time into a pre-trained prediction model to obtain geological monitoring dynamic prediction data; mapping the dynamic prediction data into a geological data twinborn model to obtain a geological monitoring trend model; and calling a corresponding early warning scheme according to the geological monitoring trend model and the geological hidden danger position, and sending a corresponding early warning instruction. The geological monitoring accuracy can be effectively improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of geological monitoring technology, and in particular to a geological monitoring method, data twin platform and equipment based on data twin. Background Art

[0002] In recent years, with the needs of my country's economic development, large-scale engineering construction, resource development and the intensification of human activities have led to frequent geological disasters such as landslides and mud-rock flows. Therefore, the test for geological monitoring technology is very severe, and a geological monitoring method and equipment are needed to improve the accuracy and timeliness of geological monitoring.

[0003] Existing technologies for geological monitoring mainly monitor several aspects of geology separately, such as landslides, surface deformation, etc. However, in the face of the diverse trends and complex environment of geological changes, this current separate monitoring method cannot timely and comprehensively grasp the situation of geological changes and future geological change trends. When geological data changes occur, it is impossible to predict in advance and take measures to protect the safety of people and property.

[0004] Therefore, there is an urgent need for a geological monitoring method, data twin platform and equipment based on data twins that can predict trends and provide early warnings of geological changes and improve the accuracy of geological monitoring. Summary of the invention

[0005] The embodiments of the present application provide a geological monitoring method, data twin platform and equipment based on data twin, which are used to improve the accuracy of geological monitoring.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, a geological monitoring method based on data twin is provided, the method comprising:

[0008] Constructing a geological monitoring sample database, and constructing a geological data twin model based on the sample database, wherein the geological data twin model includes a groundwater level twin model, a surface deformation twin model, and a geological environment twin model;

[0009] Mapping the geological monitoring data acquired in real time to the geological data twin model to obtain a first twin model;

[0010] Performing differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard;

[0011] According to the type of geological hazard, the location of the geological hazard is obtained;

[0012] Inputting the geological monitoring data acquired in real time into a pre-trained prediction model to obtain geological monitoring dynamic prediction data;

[0013] Mapping the dynamic prediction data into the geological data twin model to obtain a geological monitoring trend model;

[0014] According to the geological monitoring trend model and the location of the geological hazard, the corresponding early warning plan is called and the corresponding early warning instruction is issued.

[0015] In a possible implementation of the first aspect, constructing a geological monitoring sample database and constructing a geological data twin model according to the sample database includes:

[0016] Obtain historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data;

[0017] Constructing a geological monitoring sample database with the historical groundwater level monitoring data, the historical surface deformation monitoring data and the historical geological environment monitoring data;

[0018] Selecting geological monitoring data within a preset time period from the geological monitoring sample database;

[0019] The historical groundwater level monitoring data is mapped to the corresponding groundwater level three-dimensional model to obtain a groundwater level twin model, the historical surface deformation monitoring data is mapped to the corresponding surface three-dimensional model to obtain a surface deformation twin model, and the historical geological environment monitoring data is mapped to the corresponding geological three-dimensional model to obtain a geological environment twin model.

[0020] In a possible implementation of the first aspect, performing differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard includes:

[0021] Determine the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model through the geological data twin model;

[0022] Performing spatial analysis on the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model to obtain target vertex information and target edge information;

[0023] Performing spatial analysis on the first twin model to obtain vertex information and edge position information of the first twin model;

[0024] The type of geological hazard is determined through the target vertex information and the vertex information, as well as the target edge information and the edge position information.

[0025] In a possible implementation manner of the first aspect, determining the type of geological hazard by using the target vertex information and the target edge information and the vertex information and the edge position information includes:

[0026] Based on the target vertex information, determine a first threshold range of the first twin model vertex information to obtain a target vertex range;

[0027] Based on the target edge information, determine a second threshold range of the edge position information of the first twin model to obtain a target edge range;

[0028] Determine an approximate model of the first twin model by using the target vertex range and the target edge range;

[0029] The monitoring data of the approximate model and the first twin model are obtained for similarity comparison, the data in the monitoring data whose similarity is greater than a preset value is excluded, the remaining data is used as geological hazard data, and the type of geological hazard is determined through the geological hazard data.

[0030] In a possible implementation of the first aspect, obtaining the location of the geological hazard according to the geological hazard type includes:

[0031] Determining a geological hazard model according to the geological hazard type;

[0032] Searching for monitoring points of the geological hazard model to determine the monitoring points of the geological hazard model;

[0033] Grouping the plurality of monitoring points, each group including at least one difference data, calculating the difference degree of the difference data, and if the difference degree is greater than a preset value, determining the monitoring point where the difference data is located;

[0034] Determine the area of ​​geological hazard location through the local grid formed by the monitoring points where the difference data are located;

[0035] Perform regional analysis on the area of ​​the geological hazard location to obtain the geological hazard location.

[0036] In a possible implementation of the first aspect, performing regional analysis on the geological hazard location area to obtain the geological hazard location includes:

[0037] Divide the geological hazard location area into multiple layers, and obtain model curves of the multiple layers, wherein each model curve corresponds to each geological monitoring data information;

[0038] Acquire a first curve waveform of the model curve and a second curve waveform of the geological data twin model;

[0039] Calculating the similarity between the first curve waveform and the second curve waveform and the corresponding reference waveform, and judging whether the similarity is greater than a preset threshold value, and if the similarity is greater than the preset threshold value, determining that the curve waveform has a geological hazard;

[0040] Obtaining the curve waveform deviation points, interpolating the curve waveform deviation points, and obtaining a spatial distribution map of geological hazard locations;

[0041] Through the spatial distribution diagram, a plurality of layers having the curve waveform deviation points are obtained to obtain a plurality of target layers;

[0042] Determine the spatial positions of the deviation points in the multiple target layers through the multiple target layers, and obtain one or more overlapping areas of the spatial positions of the deviation points;

[0043] Obtaining the overlapping frequency of the overlapping area through the overlapping area of ​​the spatial position of the deviation point;

[0044] According to the overlapping frequency, the overlapping area is divided into a high-frequency overlapping area and a low-frequency overlapping area, and the position corresponding to the high-frequency overlapping area is used as the geological hazard position.

[0045] In a possible implementation of the first aspect, performing regional analysis on the geological hazard location area to obtain the geological hazard location further includes:

[0046] In the case where the geological data twin models overlap, dividing the geological data twin models to determine overlapping models;

[0047] Acquire monitoring data of the overlapping model, and perform data separation on the monitoring data to obtain first model data and second model data;

[0048] constructing a first overlapping model according to the first model data, and constructing a second overlapping model according to the second model data;

[0049] Layer division is performed in the first overlapping model and the second overlapping model to obtain a model curve of the layer, and the location of the geological hazard is obtained through the model curve of the layer.

[0050] In a possible implementation of the first aspect, inputting the geological monitoring data acquired in real time into a pre-trained prediction model to obtain geological monitoring dynamic prediction data includes:

[0051] The geological monitoring data is obtained, and the geological monitoring data is input into a pre-trained deep learning model to obtain the geological monitoring dynamic prediction data, wherein the geological monitoring dynamic prediction data is groundwater level data, surface deformation data, and geological environment data within a preset time period in the future.

[0052] In a second aspect, the present application provides a data twin platform, including:

[0053] A geological data twin model construction module is used to construct a geological monitoring sample database, and to construct a geological data twin model based on the sample database, wherein the geological data twin model includes a groundwater level twin model, a surface deformation twin model, and a geological environment twin model;

[0054] A mapping module, used to map the geological monitoring data acquired in real time to the geological data twin model to obtain a first twin model;

[0055] A differential analysis module, used to perform differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard;

[0056] A geological hazard location determination module, used to obtain the geological hazard location according to the geological hazard type;

[0057] A data prediction module, used to input the geological monitoring data acquired in real time into a pre-trained prediction model to obtain geological monitoring dynamic prediction data;

[0058] A trend model determination module, used for mapping the dynamic prediction data into the geological data twin model to obtain a geological monitoring trend model;

[0059] The calling module is used to call the corresponding early warning plan and issue the corresponding early warning instruction according to the geological monitoring trend model and the geological hidden danger location.

[0060] In a third aspect, the present application provides an electronic device, including:

[0061] a memory configured to store instructions; and

[0062] A processor is configured to call the instructions from the memory and to implement the above-mentioned geological monitoring method based on data twins when executing the instructions.

[0063] Through the above technical scheme, by establishing a sample database and constructing a geological data twin model, the geological monitoring data can be fully displayed, which is convenient for clear observation of the data; mapping the real-time monitoring data to the geological data twin model is helpful for differentiated analysis of the data, timely finding the location of geological hazards, and ensuring the accuracy of geological monitoring; by inputting the real-time geological monitoring data into the pre-trained prediction model, obtaining geological monitoring dynamic prediction data, and constructing a geological monitoring trend model based on the geological monitoring dynamic prediction data, and predicting the trend of future geological changes, it can effectively reduce the uncertainty of geological disasters, improve the decision-making efficiency of risk response, and enhance the response ability of the data twin platform in complex environments; according to the geological monitoring trend model, call the corresponding early warning plan and issue the corresponding early warning instructions to better protect personal and property safety.

[0064] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic flow chart of a geological monitoring method based on data twins provided in an embodiment of the present application;

[0066] Figure 2 A schematic diagram of the structure of a method for analyzing the location of geological hazards provided in an embodiment of the present application;

[0067] Figure 3 A structural diagram of a data twin platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0069] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0070] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0071] Figure 1 The following schematically shows a flow chart of a geological monitoring method based on data twin according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a geological monitoring method based on data twins, which may include the following steps.

[0072] S110, constructing a geological monitoring sample database, and constructing a geological data twin model based on the sample database, wherein the geological data twin model includes a groundwater level twin model, a surface deformation twin model, and a geological environment twin model;

[0073] S120, mapping the geological monitoring data acquired in real time to the geological data twin model to obtain a first twin model;

[0074] S130, performing differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard;

[0075] S140, obtaining the location of the geological hazard according to the type of geological hazard;

[0076] S150, inputting the geological monitoring data acquired in real time into the pre-trained prediction model to obtain geological monitoring dynamic prediction data;

[0077] S160, mapping the dynamic prediction data into the geological data twin model to obtain a geological monitoring trend model;

[0078] S170. According to the geological monitoring trend model and the location of geological hazards, the corresponding early warning plan is called and the corresponding early warning instruction is issued.

[0079] First, a geological monitoring sample database is constructed, and a geological data twin model is constructed based on the sample database. The geological monitoring sample database is mainly constructed by obtaining historical groundwater level monitoring data, historical surface deformation monitoring data, and historical geological environment monitoring data. The acquired historical data is preprocessed. In this embodiment, the purpose of preprocessing is to normalize the data, convert the data into a unified format and unit, and eliminate data inconsistency. The preprocessed raw data is constructed into a geological monitoring sample database.

[0080] Secondly, in the geological monitoring sample database, geological monitoring data within a preset time period is selected. The selected preset time period can be adjusted according to the actual situation of the plan. The selected geological monitoring data may include historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data; the selected historical groundwater level monitoring data, historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data are respectively mapped to the corresponding three-dimensional models through mapping. Mapping mainly refers to clearly displaying the acquired data through a three-dimensional model, and the changes in actual geological data can be displayed in real time through the three-dimensional model. After mapping, a groundwater level twin model, a surface deformation twin model and a geological environment twin model can be obtained. Among them, the three-dimensional model is obtained based on three-dimensional modeling and rendering technology. Specifically, three-dimensional modeling software, such as Maya and 3D MAX, is used to input the geological monitoring data into the three-dimensional modeling software to create a three-dimensional space model, thereby obtaining a groundwater level twin model, a surface deformation twin model and a geological environment twin model.

[0081] After obtaining the geological data twin model, geological monitoring data is acquired in real time through various types of sensors. In this embodiment, the various types of sensors include temperature sensors, air pressure sensors, distance sensors, humidity sensors, environmental monitoring sensors, and other sensors. The geological monitoring data acquired in real time is mapped to the geological data twin model by mapping to obtain a first twin model. The first twin model can be one or more of the groundwater level twin model, the surface deformation twin model, and the geological environment twin model, which is mainly determined by the geological monitoring data currently acquired in real time.

[0082] The obtained first twin model and the geological data twin model are subjected to differential analysis. First, the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model are determined through the geological data twin model, and the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model are spatially parsed. Spatial parsing refers to geographic data analysis technology based on the spatial layout of geographic objects, which can obtain target vertex information and target edge information; in this embodiment, the target vertex information refers to the data information that can represent the specific key points of the model in the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model. The target edge information refers to the specific key edge data information that can represent the edge curve of the model in the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model. The specific key point information and the specific key edge information can be determined according to the actual situation of the monitoring needs. Subsequently, the first twin model is spatially parsed to obtain the vertex information and edge position information of the first twin model. The vertex information and edge position information of the first twin model refer to the specific key point information and specific key edge information that can represent the first twin model. The vertex information obtained by the first twin model and the target vertex information obtained by the geological data twin model are range-screened and determined to determine the target vertex range. For example, when the vertex information and the target vertex information are in the same quadrant, the target vertex information can be used as the target vertex range of the first twin model. Similarly, the edge position information obtained by the first twin model and the target edge information obtained by the geological data twin model are range-screened and determined to determine the target edge range. For example, when the edge position information and the target edge information are in the same quadrant, the target edge information can be used as the target edge range of the first twin model. Through the target vertex range and the target edge range, the approximate model of the first twin model can be determined, wherein the approximate model refers to: obtaining the monitoring data of the approximate model and the first twin model for similarity comparison, filtering out the data in the monitoring data whose similarity is greater than a preset value, and using the remaining data as geological hazard data, the geological hazard type can be determined through the geological hazard data.

[0083] After determining the type of geological hazard, the location of the geological hazard is obtained according to the type of geological hazard. Specifically, the geological hazard model is determined by determining the type of geological hazard. The geological hazard model can be a groundwater level twin model, a surface deformation twin model, or a geological environment twin model. It is specifically determined by the geological monitoring data obtained in real time. If the geological monitoring data is groundwater level data, then after being mapped to the three-dimensional model, it is a groundwater level model. After the geological hazard model is obtained, the monitoring point position of the current geological hazard model is retrieved. The monitoring point is established for regularly collecting and monitoring geological data or information, and the monitoring points are grouped. The main purpose is to facilitate finding the monitoring point position where the geological hazard data is monitored. Each group includes at least one difference data. The difference data refers to the different numerical values ​​of the obtained geological monitoring data. The difference degree of the difference data is calculated. If the difference degree is greater than the preset value, the monitoring point where the difference data is located is determined. For example, after the current geological hazard model is retrieved by a computer, the monitoring point position of the geological hazard model is obtained, and these monitoring points are grouped. Each group contains at least one group of difference data with different numerical values ​​of geological monitoring data. The difference degree of the difference data is calculated. In this embodiment, the difference degree of the data is mainly calculated by the relative difference formula. The relative difference formula is:

[0084] Relative deviation = [(measured value - average value)] × 100%

[0085] When the obtained difference is greater than the preset value, the preset value here can be determined according to the actual situation, such as the preset value is 60%. When the difference is greater than 60%, it means that there is difference data at the current monitoring point. By calculating the difference of the data of each monitoring point, the monitoring point where the difference data is located is found. After obtaining the monitoring point where the difference data is located, the monitoring point where the difference data is located is formed into a local grid. The local grid refers to connecting the monitoring points where there is difference data to form a grid space. This grid space is a local grid. Through the local grid, the scope of the geological hazard location area is determined. Regional analysis is performed on the scope of the geological hazard location area. Regional analysis refers to analyzing the relationship between data and space in the scope of the geological hazard location area. After regional analysis of the scope of the geological hazard location area, the geological hazard location is obtained.

[0086] The real-time acquired geological monitoring data is input into a pre-trained prediction model, wherein the real-time acquired geological monitoring data is acquired through multiple types of sensors, and the pre-trained prediction model is a deep learning model. The geological monitoring data is processed by the pre-trained deep learning model to obtain geological monitoring dynamic prediction data, wherein the geological data prediction value is groundwater level data, surface deformation data, and geological environment data within a preset time period in the future. The preset time period here can be set according to monitoring needs, and the future geological change trend can be predicted through the obtained geological monitoring dynamic prediction data.

[0087] The dynamic prediction data of geological monitoring is mapped to the geological data twin model to obtain the geological monitoring trend model, which can clearly show the dynamic changes of geological monitoring. The model mapped by the prediction data is combined with the model mapped by the real-time monitoring data to obtain the combination of the current geological monitoring model and the future geological monitoring model, which is more convenient for the continuous observation of geological changes.

[0088] Through the previously obtained geological monitoring trend model and geological hazard location, different early warning plans are called for different geological hazard types and different geological hazard locations using the calling module, and different early warning instructions are issued. For example, when the real-time geological monitoring data is input into the pre-trained deep learning model, and the geological monitoring dynamic prediction data is mapped to form a geological monitoring trend model as a groundwater level model, the obtained geological hazard location is a monitoring point next to the mountain, which indicates that the current groundwater level monitoring data is abnormal data, and geological disasters and landslides may occur due to the rise or fall of the groundwater level. For example, a sharp drop in the groundwater level may cause ground subsidence, ground cracks and other geological environmental problems, and a rapid rise in the groundwater level may cause soil salinization, swamping and other phenomena. At this time, it is necessary to call the groundwater level emergency plan and the landslide emergency plan, such as notifying relevant personnel to evacuate in advance, setting a ground cordon, using lasers to set a warning area to prevent others from entering the area, and taking measures such as early evacuation of personnel in the landslide area, and issuing early warning instructions. The early warning instructions can send different instructions according to different geological disaster levels. For example, the size of ground cracks is limited. When the crack size exceeds a certain value, it is a level one risk. The value here can be set according to the actual situation. The level one risk level is broadcast via mobile phone text messages, telephone calls, and radio. The level two risk level is broadcast via mobile phone text messages and radio. The level three risk level is broadcast via radio, thereby ensuring the safety of people and property.

[0089] Through the above technical scheme, by establishing a sample database and constructing a geological data twin model, the geological monitoring data can be fully displayed, which is convenient for clear observation of the data; mapping the real-time monitoring data to the geological data twin model is helpful for differentiated analysis of the data, timely finding the location of geological hazards, and ensuring the accuracy of geological monitoring; by inputting the real-time geological monitoring data into the pre-trained prediction model, obtaining geological monitoring dynamic prediction data, and constructing a geological monitoring trend model based on the geological monitoring dynamic prediction data, and predicting the trend of future geological changes, it can effectively reduce the uncertainty of geological disasters, improve the decision-making efficiency of risk response, and enhance the response ability of the data twin platform in complex environments; according to the geological monitoring trend model, call the corresponding early warning plan and issue the corresponding early warning instructions to better protect personal and property safety.

[0090] In one implementation of this embodiment, a geological monitoring sample database is constructed, and a geological data twin model is constructed according to the sample database, including:

[0091] S210, obtaining historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data;

[0092] S220, constructing a geological monitoring sample database using historical groundwater level monitoring data, historical surface deformation monitoring data, and historical geological environment monitoring data;

[0093] S230, selecting geological monitoring data within a preset time period from a geological monitoring sample database;

[0094] S240. Map the historical groundwater level monitoring data to the corresponding groundwater level three-dimensional model to obtain a groundwater level twin model, map the historical surface deformation monitoring data to the corresponding surface three-dimensional model to obtain a surface deformation twin model, and map the historical geological environment monitoring data to the corresponding geological three-dimensional model to obtain a geological environment twin model.

[0095] In this embodiment, firstly, historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data are obtained. The historical monitoring data can be obtained by searching the data published on the official website.

[0096] The acquired historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data are preprocessed. The purpose of preprocessing is to normalize the data, convert the data into a unified format and unit, and eliminate data inconsistency. In this embodiment, the preprocessing method is data normalization processing, which normalizes the data to a unified scale and uses a linear normalization method to normalize the original data. After preprocessing the historical monitoring data, the historical monitoring data constitutes a geological monitoring sample database.

[0097] In the geological monitoring sample database constructed previously, geological monitoring data within a preset time period is selected. The preset time period selected in this embodiment can be adjusted according to the actual situation of the scheme. For example, for analyzing the geological monitoring data within ten years, the preset time period can be selected as the geological monitoring data within ten years, and the selected geological monitoring data are historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data.

[0098] The selected historical groundwater level monitoring data, historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data are mapped to the corresponding three-dimensional models respectively. Mapping mainly refers to clearly displaying the acquired data through a three-dimensional model, and then obtaining the corresponding groundwater level twin model, surface deformation twin model and geological environment twin model respectively.

[0099] In one implementation of this embodiment, differential analysis is performed on the first twin model and the geological data twin model to determine the type of geological hazard, including:

[0100] S310, determining the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model through the geological data twin model;

[0101] S320, performing spatial analysis on the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model to obtain target vertex information and target edge information;

[0102] S330, performing spatial analysis on the first twin model to obtain vertex information and edge position information of the first twin model;

[0103] S340, determining the type of geological hazard through target vertex information and vertex information, as well as target edge information and edge position information.

[0104] Through the geological data twin model, the groundwater level spatial model, the surface deformation spatial model and the geological environment spatial model are determined. Specifically, the geological data twin model includes the groundwater level twin model, the surface deformation twin model and the geological environment twin model. The groundwater level twin model is obtained by mapping the historical groundwater level monitoring data to the corresponding groundwater level three-dimensional model, the surface deformation twin model is obtained by mapping the historical surface deformation monitoring data to the corresponding surface three-dimensional model, and the surface deformation twin model is obtained by mapping the historical geological environment monitoring data to the corresponding geological three-dimensional model to obtain the geological environment twin model. The groundwater level twin model, the surface deformation twin model, and the geological environment twin model are determined in three-dimensional space through the geological data twin model, and then the spatial positions of the groundwater level twin model, the surface deformation twin model, and the geological environment twin model are further refined. For example, the groundwater level twin model is distinguished from other models by color marking, and the data of the groundwater level twin model in three-dimensional space is obtained more accurately. The model formed by the obtained data in three-dimensional space is color-marked, and the marked model is the groundwater level space model. The surface deformation space model and the geological environment space model are determined in the same way as above.

[0105] After determining the surface deformation spatial model and the geological environment spatial model, the groundwater level spatial model, the surface deformation spatial model and the geological environment spatial model are spatially parsed, wherein spatial parsing refers to a geographic data analysis technology based on the spatial layout of geographic objects. In this embodiment, spatial parsing refers to analyzing the groundwater level spatial model, the surface deformation spatial model and the geological environment spatial model, and obtaining target data of the groundwater level spatial model, the surface deformation spatial model and the geological environment spatial model. The target data is the vertex information and edge information of the model. Through spatial parsing, the target vertex information and target edge information are obtained. For example, the groundwater level spatial model is spatially parsed. First, the groundwater level spatial model is obtained, and the vertices of the groundwater level spatial model are searched to obtain the position information of the target vertex. The position information of the target vertex is the distance between multiple target vertices and the three-dimensional model plane, and the distance between multiple target vertices and adjacent target vertices; secondly, the edge surface information of the groundwater level spatial model is obtained to obtain the target edge information. The target edge information is the distance length of the edge of the model from the three-dimensional model plane in three-dimensional space.

[0106] The first twin model is spatially analyzed. In this embodiment, the first twin model is obtained by mapping the geological monitoring data acquired in real time to the geological data twin model. Specifically, the vertices of the first twin model in the three-dimensional space are searched to obtain multiple first twin model vertices, and the information of the first twin model vertices is obtained, wherein the first twin model vertex information is the distance between the multiple vertices of the first twin model and the three-dimensional model plane, and the distance between the multiple vertices and adjacent vertices; the edge surface information of the first twin model in the three-dimensional space is obtained to obtain the edge position information of the first twin model, wherein the edge position information of the first twin model is the distance length of the model edge of the first twin model from the three-dimensional model plane in the three-dimensional space.

[0107] The type of geological hazard is determined by the target vertex information and vertex information, as well as the target edge information and edge position information. Specifically, the target vertex information of the geological data twin model is compared with the vertex information of the first twin model to determine the location of the vertex information of the first twin model, and the target edge information of the geological data twin model is compared with the edge position information of the first twin model to determine the area where the edge position of the first twin model is located. The location of the vertex information of the first twin model and the area where the edge position of the first twin model is located can be determined by the location of the vertex information of the first twin model and the area where the edge position of the first twin model is located, so that the position of the first twin model in the groundwater level space model, the surface deformation space model, and the geological environment space model can be determined, thereby determining the type of geological hazard.

[0108] In one implementation of this embodiment, the type of geological hazard is determined by using target vertex information and target edge information and vertex information and edge position information, including:

[0109] S410, based on the target vertex information, determining a first threshold range of the vertex information of the first twin model to obtain a target vertex range;

[0110] S420, based on the target edge information, determining a second threshold range of the edge position information of the first twin model to obtain a target edge range;

[0111] S430, determining an approximate model of the first twin model through a target vertex range and a target edge range;

[0112] S440, obtaining the monitoring data of the approximate model and the first twin model for similarity comparison, excluding the data in the monitoring data whose similarity is greater than a preset value, and using the remaining data as geological hazard data to determine the type of geological hazard through the geological hazard data.

[0113] Based on the target vertex information, a first threshold range of the vertex information of the first twin model is determined to obtain the target vertex range. The first threshold range is determined by the area where the vertex information of the first twin model is located. Specifically, the vertex information of the first twin model is compared with the target vertex information, and the range where the vertex information of the first twin model is located is determined to obtain the target vertex range. For example, by spatially parsing the groundwater level spatial model, multiple target vertex information of the groundwater level spatial model is obtained, and the spatial coordinate positions of the multiple target vertex information of the groundwater level spatial model in the three-dimensional space are obtained. The spatial coordinate positions of the multiple target vertex information of the groundwater level spatial model constitute the coordinate range of the target vertex information of the groundwater level spatial model. Similarly, the surface deformation spatial model is spatially parsed to obtain multiple target vertex information of the surface deformation spatial model, and multiple target vertex information of the surface deformation spatial model is obtained. The spatial coordinate positions of the target vertex information of the surface deformation spatial model are obtained by the spatial coordinate positions of the multiple target vertex information of the surface deformation spatial model; the geological environment spatial model is spatially parsed to obtain the multiple target vertex information of the geological environment spatial model, and the spatial coordinate positions of the multiple target vertex information of the geological environment spatial model in the three-dimensional space are obtained, and the coordinate range of the target vertex information of the geological environment spatial model is constituted by the spatial coordinate positions of the multiple target vertex information of the geological environment spatial model. For example, the geological environment spatial model is spatially parsed to obtain the multiple target vertex information of the geological environment spatial model, and the spatial coordinate positions of the multiple target vertex information of the geological environment spatial model in the three-dimensional space are obtained, and the coordinate range of the target vertex information of the geological environment spatial model is constituted by the spatial coordinate positions of the multiple target vertex information of the geological environment spatial model.

[0114] The three-dimensional spatial coordinate position of the vertex information of the first twin model is compared with the coordinate range of the target vertex information of the groundwater level space model, the coordinate range of the target vertex information of the geological environment space model, and the coordinate range of the target vertex information of the surface deformation space model to determine the range of the vertex information of the first twin model, thereby determining the target vertex range of the first twin model.

[0115] Based on the target edge information, the second threshold range of the edge position information of the first twin model is determined to obtain the target edge range. The second threshold range is determined by the area where the edge position information of the first twin model is located. Specifically, the edge position information of the first twin model is compared with the target edge information, and the range where the edge position information of the first twin model is located is determined to obtain the target edge range. For example, the target edge information of the groundwater level space model is obtained by spatially analyzing the groundwater level space model, and the spatial coordinate position of the target edge information of the groundwater level space model in the three-dimensional space is obtained. The groundwater level space model is constructed by the spatial coordinate position of the target edge information of the groundwater level space model. The coordinate range of the target edge information; similarly, the surface deformation space model is spatially analyzed to obtain the target edge information of the surface deformation space model, and the spatial coordinate position of the target edge information of the surface deformation space model in the three-dimensional space is obtained, and the spatial coordinate position of the target edge information of the surface deformation space model constitutes the coordinate range of the target edge information of the surface deformation space model; the geological environment space model is spatially analyzed to obtain the target edge information of the geological environment space model, and the spatial coordinate position of the target edge information of the geological environment space model in the three-dimensional space is obtained, and the spatial coordinate position of the target edge information of the geological environment space model constitutes the coordinate range of the target edge information of the geological environment space model.

[0116] The three-dimensional spatial coordinate position of the edge position information of the first twin model is compared with the coordinate range of the target edge information of the groundwater level space model, the coordinate range of the target edge information of the geological environment space model, and the coordinate range of the target edge information of the surface deformation space model to determine the range of the edge position information of the first twin model, thereby determining the target edge range of the first twin model.

[0117] The approximate model of the first twin model is determined by the target vertex range and the target edge range. Specifically, the target vertex range and the target edge range of the first twin model are compared with the vertex information and the edge information of the groundwater level space model, the surface deformation space model, and the geological environment space model to determine the model in which the target vertex range and the target edge range of the first twin model are located, and the approximate model of the first twin model is determined. For example, if the three-dimensional spatial coordinate positions of the model in which the target vertex range and the target edge range of the first twin model are located are both within the fifth quadrant, and the three-dimensional spatial coordinate range of the vertex information and the edge information of the groundwater level space model are also within the fifth quadrant, then the approximate model of the first twin model is determined to be the groundwater level space model.

[0118] The monitoring data of the approximate model of the first twin model is obtained and a similarity comparison is performed. The similarity comparison can be compared through the correlation coefficient. The correlation coefficient is a method for measuring the strength and direction of the linear relationship between two variables. It can also be used to compare the similarity of data. The data with a similarity greater than a preset value in the monitoring data is excluded. The preset value can be determined according to the actual situation of the plan. The remaining data is used as geological hazard data. Determining the type of geological hazard through the geological hazard data means analyzing the geological hazard data to determine the regional range of the geological hazard data in the three-dimensional space model, and determining the type of geological hazard through the regional range.

[0119] In one implementation of this embodiment, obtaining the location of the geological hazard according to the type of geological hazard includes:

[0120] S510, determining a geological hazard model according to the geological hazard type;

[0121] S520, searching for monitoring points of the geological hazard model to determine the monitoring points of the geological hazard model;

[0122] S530, grouping the multiple monitoring points, each group including at least one difference data, calculating the difference degree of the difference data, and if the difference degree is greater than a preset value, determining the monitoring point where the difference data is located;

[0123] S540, determining the area of ​​the geological hazard location through the local grid formed by the monitoring points where the difference data are located;

[0124] S550: Perform regional analysis on the area of ​​the geological hazard location to obtain the geological hazard location.

[0125] The geological hazard model is determined by the geological hazard type. Specifically, the geological hazard model is determined by the geological hazard type obtained previously. The geological hazard model can be a groundwater level twin model, a surface deformation twin model, or a geological environment twin model, which is specifically determined by the geological monitoring data obtained in real time. For example, when the difference between the geological monitoring data obtained in real time and the historical geological monitoring data is greater than a preset value, the preset value preset here is determined according to the actual situation, such as 60%. When the difference is greater than 60%, it indicates that the geological monitoring data obtained in real time is abnormal data. The abnormal data is mapped to the target vertex range and the target edge range in the three-dimensional space to determine the quadrant of the abnormal data in the three-dimensional space. The groundwater level twin model, the surface deformation twin model, and the geological environment twin model are in the fifth quadrant, the first quadrant, the second quadrant, and the third quadrant, respectively. They are compared with the geological hazard model to determine whether they belong to the same quadrant. If they are in the same quadrant, the geological hazard model is determined.

[0126] The monitoring points of the geological hazard model are retrieved to determine the monitoring points of the geological hazard model. Specifically, after the geological hazard model is obtained, the monitoring point locations of the current geological hazard model are retrieved by computer. The monitoring points are generally established to regularly collect and monitor geological data or information, and all monitoring points of the geological hazard model are determined.

[0127] After all monitoring points of the geological hazard model are retrieved by computer, the monitoring points are grouped. The main purpose is to find the location of the monitoring point where the geological hazard data is monitored. Each group includes at least one difference data. The difference data refers to the different numerical values ​​of the geological monitoring data obtained. The difference between the data can be calculated by calculating the difference degree of the difference data. If the difference degree is greater than the preset value, the monitoring point where the difference data is located is determined. For example, after the current geological hazard model is retrieved, the location of the monitoring point of the geological hazard model is obtained, and these monitoring points are grouped. Each group contains at least one group of difference data with different numerical values ​​of geological monitoring data. The difference degree is calculated for the difference data. In this embodiment, the difference degree of the data is mainly calculated by the relative difference calculation formula. When the difference degree obtained is greater than the preset value, the preset value here can be determined according to the actual situation. For example, the preset value is 60%. When the difference degree is greater than 60%, it means that there is difference data at the current monitoring point. By calculating the difference degree of the data of each monitoring point, the monitoring point where the difference data is located is found.

[0128] After obtaining the monitoring points where the difference data is located, the monitoring points where the difference data is located are formed into a local grid. The local grid here refers to connecting the monitoring points with difference data to form a grid space. This grid space is the local grid. Through the local grid, the scope of the geological hazard location area can be determined.

[0129] The regional analysis of the geological hazard location area refers to the analysis of the association between data and space in the regional analysis of the geological hazard location area. After the regional analysis of the geological hazard location area, the geological hazard location is obtained. Specifically, first, the model of the geological hazard location area is divided to obtain multiple layers, and the model curves of the multiple layers are obtained to obtain the model curves of the multiple layers, wherein each model curve corresponds to each geological monitoring data information, indicating that each model curve is composed of geological monitoring data through mapping, so each model curve corresponds to each geological monitoring data information. Secondly, the first curve waveform of the model curve and the second curve waveform of the geological data twin model are obtained, and the similarity between the first curve waveform and the second curve waveform and the corresponding reference waveform is calculated to determine whether the similarity is greater than the preset threshold. If the similarity is greater than the preset threshold, it is determined that the curve waveform has a geological hazard. Obtain curve waveform deviation points, interpolate the curve waveform deviation points, obtain a spatial distribution map of the geological hazard location, and obtain multiple layers with curve waveform deviation points based on the spatial distribution map to obtain multiple target layers; determine the spatial positions of the deviation points in the multiple target layers through the multiple target layers, obtain one or more overlapping areas of the spatial positions of the deviation points, and obtain the overlapping frequency of the overlapping area through the overlapping area of ​​the spatial positions of the deviation points; divide the overlapping area into a high-frequency overlapping area and a low-frequency overlapping area based on the overlapping frequency, and use the position corresponding to the high-frequency overlapping area as the geological hazard location.

[0130] In one implementation of this embodiment, regional analysis is performed on the geological hazard location area to obtain the geological hazard location, including:

[0131] S610, dividing the geological hazard location area into multiple layers, and obtaining model curves of the multiple layers, wherein each model curve corresponds to each geological monitoring data information;

[0132] S620, obtaining a first curve waveform of the model curve and a second curve waveform of the geological data twin model;

[0133] S630, calculating the similarity between the first curve waveform and the second curve waveform and the corresponding reference waveform, and determining whether the similarity is greater than a preset threshold value. If the similarity is greater than the preset threshold value, determining that the curve waveform has a geological hazard;

[0134] S640, obtaining curve waveform deviation points, interpolating the curve waveform deviation points, and obtaining a spatial distribution map of geological hazard locations;

[0135] S650, obtaining multiple layers with curve waveform deviation points through the spatial distribution map to obtain multiple target layers;

[0136] S660, determining the spatial positions of the deviation points in the multiple target layers through the multiple target layers, and obtaining an overlapping area of ​​one or more spatial positions of the deviation points;

[0137] S670, obtaining an overlapping frequency of the overlapping area through the overlapping area of ​​the deviation point spatial position;

[0138] S680. Divide the overlapping area into a high-frequency overlapping area and a low-frequency overlapping area according to the overlapping frequency, and use the position corresponding to the high-frequency overlapping area as the geological hazard position.

[0139] like Figure 2 The figure shows a structural schematic diagram of the geological hazard location obtained by performing regional analysis on the regional scope of the geological hazard location;

[0140] The geological hazard location area is divided into multiple layers. Specifically, the model of the geological hazard location area can be divided into multiple layers, and the model curves of the multiple layers are obtained, wherein the geological hazard location area is a local grid formed by the monitoring points where the difference data is located. The local grid refers to connecting the monitoring points with difference data to form a grid space. The geological hazard location area is determined by the local grid. The model of the geological hazard location area is divided. For example, after the model of the geological hazard location area is obtained, it can be divided using advanced three-dimensional drawing software, such as Cinema 4D, and cut according to the structure required by the actual situation to obtain the model curves of multiple layers, wherein each model curve corresponds to each geological monitoring data information, indicating that each model curve is obtained by mapping the geological monitoring data, so each model curve corresponds to each geological monitoring data information.

[0141] The first curve waveform of the model curve is obtained. The first curve waveform refers to the model curve on the layer obtained by dividing the model of the geological hazard location area. The model of the geological hazard location area and the geological data twin model are analyzed by obtaining the first curve waveform of the model curve and the second curve waveform of the geological data twin model. The second curve waveform refers to dividing the geological data twin model using advanced three-dimensional drawing software to obtain multiple layers of geological data twin models. The model curve on the layers of multiple geological data twin models is the second curve waveform.

[0142] The similarity calculation of the first curve waveform and the second curve waveform obtained previously and the corresponding reference waveform is performed, and the reference waveform here refers to the waveform used as a reference in the process of analyzing the first curve waveform and the second curve waveform. In this embodiment, the reference waveform is a geological data twin model constructed by obtaining historical geological monitoring data to divide the layers, and the curve waveform is extracted from the obtained layers, and the model curve of the geological monitoring data is selected as the reference waveform when there is no geological hazard. The similarity calculation of the first curve waveform and the second curve waveform and the corresponding reference waveform is performed by a dynamic time warping algorithm. The dynamic time warping algorithm is an algorithm that efficiently processes the similarity measurement problem of time series, and determines whether the similarity is greater than a preset threshold. The preset threshold can be determined according to the monitoring accuracy requirements. For example, the preset threshold is 80%. If the similarity is greater than 80%, it means that the curve waveform is inconsistent with the reference waveform, and there are abnormal data, so it is determined that the curve waveform has geological hazards.

[0143] After determining that there are geological hazards in the curve waveform, the curve waveform is analyzed to obtain the curve waveform deviation point, where the curve waveform deviation point means that the point where the curve waveform data is different from the data on the reference waveform is the deviation point. The curve waveform deviation point can be obtained by searching the deviation point by computer and interpolating the curve waveform deviation point. Interpolation is to interpolate continuous functions on the basis of discrete data so that this continuous curve passes through all given discrete data points. Interpolation is often used in data analysis and visualization analysis to better show the trend of data changes. By interpolating the curve waveform deviation points, a spatial distribution map of the geological hazard position can be obtained. For example, after calculating the similarity of the first curve waveform, multiple points with different data whose similarity is greater than a preset threshold are obtained. Multiple deviation points are interpolated and marked in three-dimensional space, thereby obtaining a spatial distribution map of the deviation points, and the spatial distribution map of the deviation points is used as the spatial distribution map of the geological hazard position, thereby obtaining a spatial distribution map of the geological hazard position.

[0144] After obtaining the spatial distribution map of the geological hazard location, multiple layers with curve waveform deviation points are obtained to obtain multiple target layers. Specifically, the layers with curve waveform deviation points are extracted and the layers with curve waveform deviation points are used as target layers.

[0145] After obtaining multiple target layers, the spatial positions of the deviation points in the multiple target layers are determined through the spatial distribution map of the geological hazard positions. Specifically, multiple target layers are obtained, the positions of the multiple target layers in the spatial distribution map of the geological hazard positions are determined, and the spatial positions of the deviation points in the multiple target layers are determined, thereby obtaining overlapping areas of one or more spatial positions of the deviation points. The overlapping area refers to the parts where the deviation points in the multiple target layers overlap in space. For example, the deviation points of multiple target layers are obtained, and there is an overlapping phenomenon in the deviation points in the multiple target layers, thereby obtaining overlapping areas of one or more spatial positions of the deviation points.

[0146] The overlapping frequency of the overlapping area is obtained through the overlapping area of ​​the deviation point spatial position. That is to say, the overlapping area of ​​one or more deviation point spatial positions is obtained, and the overlapping area can be determined by the interval overlapping algorithm. The interval overlapping algorithm is a computer algorithm used to determine whether there is an overlapping part between multiple intervals, and to calculate the overlapping frequency of the area where the overlapping phenomenon exists. Specifically, the number of all deviation points in the deviation point spatial position is obtained, and the number of overlapping deviation points in the deviation point spatial position is determined. The number of overlapping deviation points is divided by the number of all deviation points in the deviation point spatial position to obtain the overlapping frequency of the overlapping area.

[0147] According to the overlapping frequency, the overlapping area is divided into a high-frequency overlapping area and a low-frequency overlapping area. That is to say, the overlapping area is divided into a high-frequency overlapping area and a low-frequency overlapping area by the overlapping frequency of the overlapping area of ​​the deviation point spatial position calculated before. For example, the overlapping frequency of the overlapping area of ​​the deviation point spatial position is calculated, and the overlapping frequencies obtained are 80%, 50%, 40%, etc. The overlapping frequencies are arranged from small to large, and the largest overlapping frequency is taken as the high-frequency overlapping area, and the smallest overlapping frequency is taken as the low-frequency overlapping area. The high-frequency overlapping area here refers to the area with the most overlapping deviation points in the deviation point spatial position, and the high-frequency overlapping area refers to the area with the least overlapping deviation points in the deviation point spatial position. When there is the most overlapping deviation points, it means that the area has the most abnormal data. Therefore, the area with the most overlapping deviation points is taken as the geological hazard position.

[0148] In one implementation of this embodiment, performing regional analysis on the geological hazard location area to obtain the geological hazard location also includes:

[0149] S710, when there is overlap in the geological data twin models, dividing the geological data twin models to determine overlapping models;

[0150] S720, acquiring monitoring data of the overlapping model, and performing data separation on the monitoring data to obtain first model data and second model data;

[0151] S730: construct a first overlapping model according to the first model data, and construct a second overlapping model according to the second model data;

[0152] S740, dividing the first overlapping model and the second overlapping model into layers to obtain model curves of the layers, and obtaining the location of geological hazards through the model curves of the layers.

[0153] When there is overlap in the twin models of geological data, that is, when there is overlap in the groundwater level twin model, the surface deformation twin model, and the geological environment twin model in the twin models of geological data, the overlapping parts are segmented to ensure the accuracy of regional analysis of the location and scope of geological hazards. To segment the overlapping parts, first, the overlapping parts are determined, mainly through mechanical design software, such as SolidWorks, using the interference detection function in the mechanical design software to find the overlapping model parts.

[0154] After finding the overlapping model part, the monitoring data of the overlapping model is obtained, and the monitoring data of the overlapping model is separated. The data separation of the monitoring data of the overlapping model can be performed by cross-validation. The cross-validation method is to divide the data set into k mutually exclusive subsets of similar size, and use the union of k-1 subsets as the training set each time, and the remaining subset as the test set. In this way, k training and testing are performed, and the mean of the k test results is finally returned to separate the data. After the monitoring data of the overlapping model is separated by the cross-validation method, the first model data and the second model data are obtained, wherein. The first model data is the data corresponding to one of the models of the overlapping part, and the second model data is the data corresponding to the other model of the overlapping part.

[0155] According to the first model data, a first overlapping model is constructed, and according to the second model data, a second overlapping model is constructed. Specifically, after determining the first model data and the second model data, the first model data and the second model data are mapped to the three-dimensional space by mapping to obtain the first overlapping model and the second overlapping model. The first overlapping model and the second overlapping model are obtained by separating the monitoring data and constructing the model.

[0156] Layer division is performed in the first overlapping model and the second overlapping model to obtain multiple layers, and model curves of the multiple layers are obtained to obtain the model curves of the multiple layers, and the deviation points of the model curve waveform are obtained, and the curve waveform deviation points are interpolated to obtain the spatial distribution map of the geological hazard position, wherein the interpolation can adopt the nearest neighbor interpolation method, and the nearest neighbor interpolation method is to select the gray value of the pixel point closest to the pixel point to be determined as the interpolation result; then, according to the spatial distribution map, multiple layers with curve waveform deviation points are obtained to obtain multiple target layers; through the multiple target layers, the spatial positions of the deviation points in the multiple target layers are determined to obtain one or more overlapping areas of the spatial positions of the deviation points, and the overlapping frequency of the overlapping area is obtained through the overlapping area of ​​the spatial positions of the deviation points; according to the overlapping frequency, the overlapping area is divided into a high-frequency overlapping area and a low-frequency overlapping area, and the position corresponding to the high-frequency overlapping area is used as the geological hazard position.

[0157] In one implementation of this embodiment, the geological monitoring data acquired in real time is input into a pre-trained prediction model to obtain geological monitoring dynamic prediction data, including:

[0158] S810. Obtain geological monitoring data, input the geological monitoring data into a pre-trained deep learning model, and obtain geological data prediction values, wherein the geological data prediction values ​​are groundwater level data, surface deformation data, and geological environment data within a preset time period in the future.

[0159] First, geological monitoring data is obtained. In this embodiment, geological monitoring data is obtained through multiple types of sensors including temperature sensors, pressure sensors, ranging sensors, humidity sensors, environmental monitoring sensors and other sensors. The geological monitoring data obtained in real time is input into a pre-trained prediction model, wherein the pre-trained prediction model is a deep learning model. The deep learning model uses the pre-trained prediction model to predict and analyze the geological monitoring data to predict the geological change trend. The geological monitoring data is input into the pre-trained deep learning model and the data is output after analysis, thereby obtaining geological monitoring dynamic prediction data, wherein the geological data prediction value is the groundwater level data, surface deformation data, and geological environment data within a preset time period in the future. The preset time period here can be set according to the monitoring needs. For example, when it is necessary to analyze and predict the geological monitoring data within twenty years, the preset time period can be twenty years.

[0160] Secondly, after obtaining the geological monitoring dynamic prediction data, the obtained geological monitoring dynamic prediction data is used to predict the future geological change trend. The geological monitoring dynamic prediction data is mapped to the geological data twin model through mapping. Mapping refers to representing the acquired data in the form of a three-dimensional model, and then obtaining a geological monitoring trend model. The geological monitoring trend model can clearly display the dynamic changes of geological monitoring. Through the model of predictive data mapping and the model of real-time monitoring data mapping, a more comprehensive monitoring of geological changes can be carried out.

[0161] Figure 3 A schematic diagram of the structure of a data twin platform provided in an embodiment of the present application is shown. Figure 3 As shown, the embodiment of the present application also provides a data twin platform, including:

[0162] A geological data twin model construction module 10 is used to construct a geological monitoring sample database, and to construct a geological data twin model based on the sample database, wherein the geological data twin model includes a groundwater level twin model, a surface deformation twin model, and a geological environment twin model;

[0163] A mapping module 20 is used to map the geological monitoring data acquired in real time to a geological data twin model to obtain a first twin model;

[0164] A differential analysis module 30 is used to perform differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard;

[0165] A geological hazard location determination module 40 is used to obtain the geological hazard location according to the geological hazard type;

[0166] The data prediction module 50 is used to input the geological monitoring data acquired in real time into the pre-trained prediction model to obtain geological monitoring dynamic prediction data;

[0167] A trend model determination module 60 is used to map the dynamic prediction data into the geological data twin model to obtain a geological monitoring trend model;

[0168] The calling module 70 is used to call the corresponding early warning plan and issue the corresponding early warning instruction according to the geological monitoring trend model and the location of geological hazards.

[0169] The present application also provides an electronic device, including:

[0170] a memory configured to store instructions; and

[0171] A processor is configured to call instructions from a memory and implement the above-mentioned geological monitoring method based on data twins when executing the instructions.

[0172] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0173] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0174] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0176] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0177] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0178] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0179] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0180] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A geological monitoring method based on data twins, characterized in that: include: Constructing a geological monitoring sample database, and constructing a geological data twin model based on the sample database, wherein the geological data twin model includes a groundwater level twin model, a surface deformation twin model, and a geological environment twin model; Mapping the geological monitoring data acquired in real time to the geological data twin model to obtain a first twin model; Performing differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard; According to the type of geological hazard, the location of the geological hazard is obtained; Inputting the geological monitoring data acquired in real time into a pre-trained prediction model to obtain geological monitoring dynamic prediction data; Mapping the dynamic prediction data into the geological data twin model to obtain a geological monitoring trend model; According to the geological monitoring trend model and the location of the geological hazard, the corresponding early warning plan is called and the corresponding early warning instruction is issued.

2. The method according to claim 1, characterized in that The step of constructing a geological monitoring sample database and constructing a geological data twin model according to the sample database includes: Obtain historical groundwater level monitoring data, historical surface deformation monitoring data and historical geological environment monitoring data; Constructing a geological monitoring sample database with the historical groundwater level monitoring data, the historical surface deformation monitoring data and the historical geological environment monitoring data; Selecting geological monitoring data within a preset time period from the geological monitoring sample database; The historical groundwater level monitoring data is mapped to the corresponding groundwater level three-dimensional model to obtain a groundwater level twin model, the historical surface deformation monitoring data is mapped to the corresponding surface three-dimensional model to obtain a surface deformation twin model, and the historical geological environment monitoring data is mapped to the corresponding geological three-dimensional model to obtain a geological environment twin model.

3. The method according to claim 1, characterized in that: The performing differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard includes: Determine the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model through the geological data twin model; Performing spatial analysis on the groundwater level spatial model, the surface deformation spatial model, and the geological environment spatial model to obtain target vertex information and target edge information; Performing spatial analysis on the first twin model to obtain vertex information and edge position information of the first twin model; The type of geological hazard is determined through the target vertex information and the vertex information, as well as the target edge information and the edge position information.

4. The method according to claim 3, characterized in that Determining the type of geological hazard by using the target vertex information and the target edge information, the vertex information and the edge position information includes: Based on the target vertex information, determine a first threshold range of the first twin model vertex information to obtain a target vertex range; Based on the target edge information, determine a second threshold range of the edge position information of the first twin model to obtain a target edge range; Determine an approximate model of the first twin model by using the target vertex range and the target edge range; The monitoring data of the approximate model and the first twin model are obtained for similarity comparison, the data in the monitoring data whose similarity is greater than a preset value is excluded, the remaining data is used as geological hazard data, and the type of geological hazard is determined through the geological hazard data.

5. The method according to claim 1, characterized in that The step of obtaining the location of the geological hazard according to the type of geological hazard includes: Determining a geological hazard model according to the geological hazard type; Searching for monitoring points of the geological hazard model to determine the monitoring points of the geological hazard model; Grouping the plurality of monitoring points, each group including at least one difference data, calculating the difference degree of the difference data, and if the difference degree is greater than a preset value, determining the monitoring point where the difference data is located; Determine the area of ​​geological hazard location through the local grid formed by the monitoring points where the difference data are located; Perform regional analysis on the area of ​​the geological hazard location to obtain the geological hazard location.

6. The method according to claim 5, characterized in that The performing of regional analysis on the geological hazard location area to obtain the geological hazard location includes: Divide the geological hazard location area into multiple layers, and obtain model curves of the multiple layers, wherein each model curve corresponds to each geological monitoring data information; Acquire a first curve waveform of the model curve and a second curve waveform of the geological data twin model; Calculating the similarity between the first curve waveform and the second curve waveform and the corresponding reference waveform, and judging whether the similarity is greater than a preset threshold value, and if the similarity is greater than the preset threshold value, determining that the curve waveform has a geological hazard; Obtaining the curve waveform deviation points, interpolating the curve waveform deviation points, and obtaining a spatial distribution map of geological hazard locations; Through the spatial distribution diagram, a plurality of layers having the curve waveform deviation points are obtained to obtain a plurality of target layers; Determine the spatial positions of the deviation points in the multiple target layers through the multiple target layers, and obtain one or more overlapping areas of the spatial positions of the deviation points; Obtaining the overlapping frequency of the overlapping area through the overlapping area of ​​the spatial position of the deviation point; According to the overlapping frequency, the overlapping area is divided into a high-frequency overlapping area and a low-frequency overlapping area, and the position corresponding to the high-frequency overlapping area is used as the geological hazard position.

7. The method according to claim 6, characterized in that The performing of regional analysis on the geological hazard location area to obtain the geological hazard location also includes: In the case where the geological data twin models overlap, dividing the geological data twin models to determine overlapping models; Acquire monitoring data of the overlapping model, and perform data separation on the monitoring data to obtain first model data and second model data; constructing a first overlapping model according to the first model data, and constructing a second overlapping model according to the second model data; Layer division is performed in the first overlapping model and the second overlapping model to obtain a model curve of the layer, and the location of the geological hazard is obtained through the model curve of the layer.

8. The method according to claim 1, characterized in that The step of inputting the real-time acquired geological monitoring data into a pre-trained prediction model to obtain geological monitoring dynamic prediction data includes: The geological monitoring data is obtained, and the geological monitoring data is input into a pre-trained deep learning model to obtain the geological monitoring dynamic prediction data, wherein the geological monitoring dynamic prediction data is groundwater level data, surface deformation data, and geological environment data within a preset time period in the future.

9. A data twin platform, characterized in that: include: A geological data twin model construction module is used to construct a geological monitoring sample database, and to construct a geological data twin model based on the sample database, wherein the geological data twin model includes a groundwater level twin model, a surface deformation twin model, and a geological environment twin model; A mapping module, used to map the geological monitoring data acquired in real time to the geological data twin model to obtain a first twin model; A differential analysis module, used to perform differential analysis on the first twin model and the geological data twin model to determine the type of geological hazard; A geological hazard location determination module, used to obtain the geological hazard location according to the geological hazard type; A data prediction module, used to input the geological monitoring data acquired in real time into a pre-trained prediction model to obtain geological monitoring dynamic prediction data; A trend model determination module, used for mapping the dynamic prediction data into the geological data twin model to obtain a geological monitoring trend model; The calling module is used to call the corresponding early warning plan and issue the corresponding early warning instruction according to the geological monitoring trend model and the geological hidden danger location.

10. An electronic device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and to implement the data twin-based geological monitoring method according to any one of claims 1 to 8 when executing the instructions.

Images