Landslide geological disaster early warning method and system

Abstract

The invention provides a landslide geological disaster early warning method and system, and the method comprises the steps: obtaining corresponding landslide geological disaster early warning demand levels for a plurality of terrain surfaces of each geological subarea; calculating a sensing center of each geological subarea through a preset first algorithm in combination with the landslide geological disaster early warning demand levels of the plurality of terrain surfaces of each geological subarea; an optical fiber sensor is arranged at the sensing center of each geological subarea; the optical fiber sensor collects stratum stress data of a corresponding geological zone in real time, and the rainfall sensor collects rainfall data of a landslide geological site and uploads the rainfall data to the background early warning center; and the background early warning center carries out prediction analysis according to the rainfall data of the landslide geological site and the stratum stress data of each geological subarea, and outputs a risk value of landslide occurrence of the landslide geological site. According to the invention, occurrence of landslide geological disasters can be accurately predicted, and the investment and operation cost is low.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster early warning, and in particular to a landslide geological disaster early warning method and system. Background Art

[0002] Landslide refers to the natural phenomenon in which soil or rock on a slope slides down the slope as a whole or in a dispersed manner along a certain weak surface or weak zone under the action of gravity, due to factors such as river erosion, groundwater activity, rainwater soaking, earthquakes and artificial slope cutting.

[0003] Landslide monitoring is an important means to understand the development of landslide disasters and gain insight into the causes of disasters. Through long-term tracking and monitoring of landslide bodies, we can not only discover dangerous situations in a timely manner, but also explore the laws of their occurrence, providing an important basis for landslide early warning.

[0004] Due to the limitations of landslide terrain, traditional manual survey methods suffer from low efficiency, high risk, and difficulty. New technologies such as satellite remote sensing imagery, 3D laser scanners, ground-based synthetic aperture radar (SAR), and GNSS technology have been applied to landslide hazard investigation and monitoring research. While these methods have their own advantages, they also have limitations. Satellite remote sensing imagery has low accuracy, making it suitable only for preliminary surveys of large-scale landslides and difficult to guarantee real-time performance. 3D laser scanners and ground-based SAR are expensive and require sophisticated processing technology. While GNSS technology can measure high-precision 3D displacement, the high cost of its receivers has constrained its development. Summary of the Invention

[0005] To address at least one of the aforementioned technical issues, the present invention proposes a landslide geological disaster early warning method and system. This method and system accurately collects stratum stress data by rationally placing fiber optic data collection points based on geological environmental conditions. It also constructs a landslide risk early warning model, combining stress data with rainfall and other environmental factors to accurately predict the occurrence of landslide geological disasters. Furthermore, the method and system have low operating costs.

[0006] A first aspect of the present invention provides a landslide geological disaster early warning method, the method comprising:

[0007] The pre-set landslide geological site includes multiple geological zones, each of which is composed of multiple terrain surfaces;

[0008] For each geological zone, the corresponding landslide geological disaster warning demand level is obtained for each of the multiple terrain surfaces;

[0009] Combine the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, and calculate the sensing center of each geological zone through a preset first algorithm;

[0010] Fiber optic sensors are deployed at the sensing center of each geological zone;

[0011] Fiber optic sensors collect stratum stress data of corresponding geological zones in real time and upload it to the backend early warning center;

[0012] Rainfall sensors collect rainfall data at the landslide geological site and upload it to the backend early warning center;

[0013] The background early warning center conducts prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site.

[0014] Furthermore, the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone are combined, and the sensing center of each geological zone is calculated by a preset first algorithm, specifically including:

[0015] respectively obtaining the shape of each topographic surface of each geological partition, and respectively calculating the topographic center of each topographic surface of each geological partition using a second algorithm;

[0016] Cluster analysis is performed on the topographic centers of multiple topographic surfaces of each geological partition according to the density clustering algorithm to obtain the geological center;

[0017] According to the geological center of each geological zone, combined with the landslide geological disaster early warning demand levels of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated through the first algorithm.

[0018] Furthermore, the shape of each terrain surface of each geological partition is obtained respectively, and the terrain center of each terrain surface of each geological partition is calculated respectively by a second algorithm, specifically including:

[0019] Assume that each terrain surface of each geological partition is a plane polygon, and construct a plane coordinate system based on each terrain surface of each geological partition;

[0020] respectively obtaining the polygon vertex coordinates of each terrain surface of each geological partition, wherein the polygon vertex coordinates include abscissa and ordinate;

[0021] Based on each geological partition, the abscissas of all polygon vertices of each terrain surface are added to obtain the sum of first abscissas, and the sum of the first abscissas is divided by the total number of polygon vertices to obtain the abscissa of the terrain center of each terrain surface; the ordinates of all polygon vertices of each terrain surface are added to obtain the sum of first ordinates, and the sum of the first ordinates is divided by the total number of polygon vertices to obtain the ordinate of the terrain center of each terrain surface;

[0022] Based on each geological partition, the topographic center position of each topographic surface is determined according to the abscissa and ordinate of the topographic center of each topographic surface.

[0023] Furthermore, according to the geological center of each geological subdivision, combined with the landslide geological disaster warning demand levels of multiple terrain surfaces of each geological subdivision, the sensing center of each geological subdivision is calculated by the first algorithm, specifically including:

[0024] Obtain the landslide geological disaster warning demand level for multiple terrain surfaces in each geological zone;

[0025] Pass through the geological center of each geological partition, and draw two mutually perpendicular horizontal and vertical coordinate lines along the slope of each geological partition;

[0026] Based on each geological partition, each geological partition is divided into four geological blocks by abscissa lines and ordinate lines;

[0027] Based on the four geological blocks in each geological division, the terrain surfaces covered by each geological block are counted respectively, and the landslide geological disaster early warning demand levels of all terrain surfaces covered by each geological block are summed up to obtain the early warning demand level of each geological block;

[0028] Based on the four geological blocks of each geological partition, the block center of each geological block is calculated by the second algorithm;

[0029] Based on the four geological blocks of each geological partition, a ray is drawn for each geological block with the geological center as the origin and passing through the block center of each geological block;

[0030] Based on each geological partition, the ray direction of each geological block is used as the vector direction, and the warning requirement level of each geological block is used as the vector value to obtain the component vector of each geological block;

[0031] Based on each geological partition, the vectors of the geological blocks are vector-sum calculated to obtain the compensation vector of each geological partition based on the landslide geological disaster early warning needs;

[0032] The geological center of each geological partition is compensated according to the corresponding compensation vector to obtain the sensing center of each geological partition.

[0033] Furthermore, fiber optic sensors collect stratum stress data corresponding to geological zones in real time and upload it to the backend early warning center, including:

[0034] The fiber optic sensor collects the formation stress data of the corresponding geological partition in real time and transmits it to the multi-channel collector on site;

[0035] The multi-channel collector aggregates and obtains the formation stress data of multiple optical fiber sensors at the current moment;

[0036] The multi-channel collector compares the current formation stress data of the multiple optical fiber sensors at the current moment with the historical formation stress data of the multiple optical fiber sensors at the previous moment stored locally.

[0037] If the current formation stress data of the first optical fiber sensor is consistent with the corresponding historical formation stress data, the data item uploaded by the first optical fiber sensor to the background warning center is empty;

[0038] If the current formation stress data of the second optical fiber sensor is inconsistent with the corresponding historical formation stress data, the difference data between the two is calculated, and the data item uploaded by the second optical fiber sensor to the background warning center is the difference data;

[0039] After the multi-channel collector has completed comparison of the current formation stress data of multiple optical fiber sensors at the current moment with the historical formation stress data of multiple optical fiber sensors at the previous moment stored locally, it summarizes and obtains the formation stress data network package that needs to be uploaded at the current moment;

[0040] The multi-channel collector transmits the formation stress data network package to the background early warning center through the wireless network;

[0041] When the background warning center receives the formation stress data network package, it extracts the data item content of each optical fiber sensor;

[0042] The background early warning center retrieves the locally stored historical formation stress data of each optical fiber sensor at the previous moment;

[0043] The background early warning center updates the historical formation stress data of each optical fiber sensor at the previous moment based on the locally pre-stored data, combined with the data item content of the corresponding optical fiber sensor received, and restores the current formation stress data of each optical fiber sensor at the current moment.

[0044] Furthermore, the backend early warning center conducts forecast analysis based on the rainfall data at the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site, including:

[0045] The landslide risk prediction model is constructed by the background early warning center;

[0046] Optimize and train the landslide risk prediction model through sample data;

[0047] The rainfall data of the landslide geological site and the stratum stress data of each geological zone are input into the landslide risk prediction model, and the risk value of landslide occurrence at the landslide geological site is output.

[0048] Furthermore, after outputting the landslide risk value at the landslide geological site, the method further includes:

[0049] Acquiring on-site geological attribute data of a landslide geological site, wherein the on-site geological attribute data at least includes on-site geological slope and on-site geological rock and soil slump;

[0050] Acquire multiple reference landslide data based on big data technology, each reference landslide data at least including reference geological attribute data, reference rainfall data, reference stratum stress data, and actual landslide conditions, wherein the reference geological attribute data at least includes reference geological slope and reference geological rock and soil slump;

[0051] Performing characteristic calculation on the reference geological attribute data in each reference landslide data to obtain the geological attribute characteristic value of the reference landslide data;

[0052] Perform characteristic calculation on the on-site geological attribute data of the landslide geological site to obtain the geological attribute characteristic value of the landslide geological site;

[0053] Based on each reference landslide data, the geological attribute characteristic value of the reference landslide data and the geological attribute characteristic value of the landslide geological site are approximated to obtain the approximation between the two;

[0054] determining whether the approximation is greater than a second preset threshold, and if so, entering the corresponding reference landslide data into an approximation database;

[0055] Based on each reference landslide data in the approximate database, the corresponding reference rainfall data and reference stratum stress data are predicted and analyzed through the landslide risk prediction model to obtain the predicted risk value of the reference landslide;

[0056] Based on each reference landslide data in the approximate library, the predicted risk value of the reference landslide and the actual landslide situation are used to calculate the modified contribution value of each reference landslide data through a third algorithm;

[0057] Adding the modified contribution values ​​calculated from each reference landslide data in the approximate database to obtain the sum of the modified contribution values, and dividing the sum of the modified contribution values ​​by the amount of reference landslide data in the approximate database to obtain the modified value;

[0058] The correction value is added to the outputted risk value of landslide occurrence at the landslide geological site to obtain the corrected risk value of landslide occurrence at the landslide geological site.

[0059] A second aspect of the present invention further provides a landslide geological disaster early warning system, comprising a memory and a processor, wherein the memory comprises a landslide geological disaster early warning method program, and when the landslide geological disaster early warning method program is executed by the processor, the following steps are implemented:

[0060] The pre-set landslide geological site includes multiple geological zones, each of which is composed of multiple terrain surfaces;

[0061] For each geological zone, the corresponding landslide geological disaster warning demand level is obtained for each of the multiple terrain surfaces;

[0062] Combine the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, and calculate the sensing center of each geological zone through a preset first algorithm;

[0063] Fiber optic sensors are deployed at the sensing center of each geological zone;

[0064] Fiber optic sensors collect stratum stress data of corresponding geological zones in real time and upload it to the backend early warning center;

[0065] Rainfall sensors collect rainfall data at the landslide geological site and upload it to the backend early warning center;

[0066] The background early warning center conducts prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site.

[0067] Furthermore, the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone are combined, and the sensing center of each geological zone is calculated by a preset first algorithm, specifically including:

[0068] respectively obtaining the shape of each topographic surface of each geological partition, and respectively calculating the topographic center of each topographic surface of each geological partition using a second algorithm;

[0069] Cluster analysis is performed on the topographic centers of multiple topographic surfaces of each geological partition according to the density clustering algorithm to obtain the geological center;

[0070] According to the geological center of each geological zone, combined with the landslide geological disaster early warning demand levels of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated through the first algorithm.

[0071] Furthermore, the shape of each terrain surface of each geological partition is obtained respectively, and the terrain center of each terrain surface of each geological partition is calculated respectively by a second algorithm, specifically including:

[0072] Assume that each terrain surface of each geological partition is a plane polygon, and construct a plane coordinate system based on each terrain surface of each geological partition;

[0073] respectively obtaining the polygon vertex coordinates of each terrain surface of each geological partition, wherein the polygon vertex coordinates include abscissa and ordinate;

[0074] Based on each geological partition, the abscissas of all polygon vertices of each terrain surface are added to obtain the sum of first abscissas, and the sum of the first abscissas is divided by the total number of polygon vertices to obtain the abscissa of the terrain center of each terrain surface; the ordinates of all polygon vertices of each terrain surface are added to obtain the sum of first ordinates, and the sum of the first ordinates is divided by the total number of polygon vertices to obtain the ordinate of the terrain center of each terrain surface;

[0075] Based on each geological partition, the topographic center position of each topographic surface is determined according to the abscissa and ordinate of the topographic center of each topographic surface.

[0076] The present invention proposes a landslide geological disaster early warning method and system. The method obtains the corresponding landslide geological disaster early warning level for multiple terrain surfaces in each geological zone. The landslide geological disaster early warning level for each geological zone is combined with the landslide geological disaster early warning level for each terrain surface and a preset first algorithm is used to calculate the sensing center for each geological zone. Fiber optic sensors are deployed at the sensing center of each geological zone. The fiber optic sensors collect stratum stress data for the corresponding geological zone in real time, while rainfall sensors collect rainfall data at the landslide geological site and upload it to a backend early warning center. Finally, the backend early warning center performs a predictive analysis based on the rainfall data at the landslide geological site and the stratum stress data for each geological zone, outputting a landslide risk value for the landslide geological site. This allows personnel to promptly assess the likelihood of a landslide at the site and achieve accurate early warning. The present invention rationally arranges fiber optic collection points based on geological environmental conditions to accurately collect stratum stress data. A landslide risk early warning model is constructed, and combined with stress data, rainfall, and other environmental factors, accurate prediction of the occurrence of landslide geological disasters is achieved. Furthermore, the early warning method and system of the present invention have low operational costs.

[0077] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 A flow chart of a landslide geological disaster early warning method according to the present invention is shown;

[0079] Figure 2 A diagram showing the communication connection relationship between the optical fiber sensor, the multi-channel collector and the background warning center of the present invention;

[0080] Figure 3 A schematic diagram of the warning interface of the background warning center of the present invention is shown;

[0081] Figure 4 A block diagram of a landslide geological disaster early warning system according to the present invention is shown. DETAILED DESCRIPTION

[0082] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0083] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0084] Figure 1 The flowchart of a landslide geological disaster early warning method of the present invention is shown.

[0085] like Figure 1 As shown, the first aspect of the present invention provides a landslide geological disaster early warning method, the method comprising:

[0086] S102, the landslide geological site is pre-set to include multiple geological sub-areas, each of which is composed of multiple terrain surfaces; for each of the multiple terrain surfaces in each geological sub-area, a corresponding landslide geological disaster warning requirement level is obtained;

[0087] S104, combining the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological sub-district and calculating the sensing center of each geological sub-district using a preset first algorithm;

[0088] S106, deploying optical fiber sensors at the sensing center of each geological subarea;

[0089] S108, optical fiber sensors collect stratum stress data corresponding to the geological partition in real time and upload it to the backend early warning center;

[0090] S110, a rain sensor collects rainfall data at the landslide geological site and uploads the data to a backend early warning center;

[0091] S112: The back-end early warning center performs a prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs a risk value of landslide occurrence at the landslide geological site.

[0092] It should be noted that the landslide geological site can be divided according to the actual number of optical fiber sensors or early warning needs. For example, multiple parallel and spaced horizontal lines and multiple parallel and spaced vertical lines can be used to intersect each other vertically. Ultimately, the landslide geological site can be divided into multiple equal rectangular or square geological partitions, but the invention is not limited thereto.

[0093] According to a specific embodiment of the present invention, for each of the multiple terrain surfaces in each geological zone, the corresponding landslide geological disaster warning demand levels are obtained, specifically including:

[0094] Construct a prediction model for the level of early warning demand;

[0095] Optimize and train the early warning demand level prediction model through sample data;

[0096] Obtain image information of each terrain surface respectively;

[0097] The image information of each terrain surface is input into the early warning demand level prediction model, and the landslide geological disaster early warning demand level corresponding to each terrain surface is output.

[0098] It should be noted that, after outputting the landslide risk value of the landslide geological site, the method further includes:

[0099] When the risk value is higher than the first preset threshold, a landslide warning message is issued to relevant personnel to facilitate the organization and implementation of landslide disaster emergency measures.

[0100] The present invention obtains the corresponding landslide geological hazard warning level for multiple terrain surfaces in each geological zone. The landslide geological hazard warning level for each of the multiple terrain surfaces in each geological zone is combined and a pre-set first algorithm is used to calculate the sensing center for each geological zone. Fiber optic sensors are deployed at the sensing center of each geological zone. The fiber optic sensors collect stratum stress data for the corresponding geological zone in real time, while rainfall sensors collect rainfall data at the landslide geological site and upload the data to a backend warning center. Finally, the backend warning center performs a predictive analysis based on the rainfall data at the landslide geological site and the stratum stress data for each geological zone, outputting a landslide risk value for the landslide geological site. This allows personnel to promptly assess the likelihood of a landslide at the site and achieve accurate early warning. The present invention rationally arranges fiber optic collection points based on geological environmental conditions to accurately collect stratum stress data. A landslide risk warning model is then constructed, and combined with stress data, rainfall, and other environmental factors, accurate prediction of the occurrence of landslide geological hazards is achieved. Furthermore, the early warning method and system of the present invention have low operational costs.

[0101] According to an embodiment of the present invention, the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone are combined, and the sensing center of each geological zone is calculated using a preset first algorithm, specifically including:

[0102] respectively obtaining the shape of each topographic surface of each geological partition, and respectively calculating the topographic center of each topographic surface of each geological partition using a second algorithm;

[0103] Cluster analysis is performed on the topographic centers of multiple topographic surfaces of each geological partition according to the density clustering algorithm to obtain the geological center;

[0104] According to the geological center of each geological zone, combined with the landslide geological disaster early warning demand levels of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated through the first algorithm.

[0105] As can be understood, the present invention first calculates the topographic center of each topographic surface in each geological subdivision using the second algorithm. This topographic center is the geometric center of the corresponding topographic surface. Then, based on the landslide geological hazard warning requirement levels for multiple topographic surfaces within the same geological subdivision, a compensation calculation is performed on these topographic centers, ultimately deriving the sensing center for each geological subdivision. Therefore, the present invention uses the sensing centers calculated by the second and first algorithms, successively, to determine the optimal locations for fiber optic sensors, facilitating comprehensive and accurate monitoring of stratum stress data within the corresponding geological subdivision.

[0106] According to an embodiment of the present invention, the shape of each topographic surface of each geological partition is obtained respectively, and the topographic center of each topographic surface of each geological partition is calculated respectively by a second algorithm, specifically including:

[0107] Assume that each terrain surface of each geological partition is a plane polygon, and construct a plane coordinate system based on each terrain surface of each geological partition;

[0108] respectively obtaining the polygon vertex coordinates of each terrain surface of each geological partition, wherein the polygon vertex coordinates include abscissa and ordinate;

[0109] Based on each geological partition, the abscissas of all polygon vertices of each terrain surface are added to obtain the sum of first abscissas, and the sum of the first abscissas is divided by the total number of polygon vertices to obtain the abscissa of the terrain center of each terrain surface; the ordinates of all polygon vertices of each terrain surface are added to obtain the sum of first ordinates, and the sum of the first ordinates is divided by the total number of polygon vertices to obtain the ordinate of the terrain center of each terrain surface;

[0110] Based on each geological partition, the topographic center position of each topographic surface is determined according to the abscissa and ordinate of the topographic center of each topographic surface.

[0111] According to an embodiment of the present invention, based on the geological center of each geological subdivision, combined with the landslide geological disaster warning demand level of multiple terrain surfaces of each geological subdivision, and using a first algorithm to calculate the sensing center of each geological subdivision, specifically includes:

[0112] Obtain the landslide geological disaster warning demand level for multiple terrain surfaces in each geological zone;

[0113] Pass through the geological center of each geological partition, and draw two mutually perpendicular horizontal and vertical coordinate lines along the slope of each geological partition;

[0114] Based on each geological partition, each geological partition is divided into four geological blocks by abscissa lines and ordinate lines;

[0115] Based on the four geological blocks in each geological division, the terrain surfaces covered by each geological block are counted respectively, and the landslide geological disaster early warning demand levels of all terrain surfaces covered by each geological block are summed up to obtain the early warning demand level of each geological block;

[0116] Based on the four geological blocks of each geological partition, the block center of each geological block is calculated by the second algorithm;

[0117] Based on the four geological blocks of each geological partition, a ray is drawn for each geological block with the geological center as the origin and passing through the block center of each geological block;

[0118] Based on each geological partition, the ray direction of each geological block is used as the vector direction, and the warning requirement level of each geological block is used as the vector value to obtain the component vector of each geological block;

[0119] Based on each geological partition, the vectors of the geological blocks are vector-sum calculated to obtain the compensation vector of each geological partition based on the landslide geological disaster early warning needs;

[0120] The geological center of each geological partition is compensated according to the corresponding compensation vector to obtain the sensing center of each geological partition.

[0121] It can be understood that each geological block is a polygon, and the method for calculating the block center of each geological block using the second algorithm is the same as the method for calculating the terrain center of the polygonal terrain surface using the second algorithm mentioned above, which will not be repeated here.

[0122] It can be understood that the geological center of each geological partition is respectively compensated according to the corresponding compensation vector. Specifically, the coordinate displacement of the geological center of each geological partition can be calculated according to the corresponding compensation vector.

[0123] It can be understood that in the same geological partition, since the landslide geological disaster warning demand level of each terrain surface is not the same, the present invention further calculates the compensation vector based on the difference in warning demand level of different terrain surfaces in the same geological partition, and compensates the obtained geological center through the compensation vector, so that the final sensing center of each geological partition is more accurate and reasonable, which is conducive to each optical fiber sensor to more comprehensively and centrally cover and monitor the key positions of the corresponding geological partition, further improving the accuracy of landslide geological disaster warning.

[0124] According to an embodiment of the present invention, optical fiber sensors collect stratum stress data corresponding to geological zones in real time and upload the data to a backend early warning center, specifically including:

[0125] The fiber optic sensor collects the formation stress data of the corresponding geological partition in real time and transmits it to the multi-channel collector on site;

[0126] The multi-channel collector aggregates and obtains the formation stress data of multiple optical fiber sensors at the current moment;

[0127] The multi-channel collector compares the current formation stress data of the multiple optical fiber sensors at the current moment with the historical formation stress data of the multiple optical fiber sensors at the previous moment stored locally.

[0128] If the current formation stress data of the first optical fiber sensor is consistent with the corresponding historical formation stress data, the data item uploaded by the first optical fiber sensor to the background warning center is empty;

[0129] If the current formation stress data of the second optical fiber sensor is inconsistent with the corresponding historical formation stress data, the difference data between the two is calculated, and the data item uploaded by the second optical fiber sensor to the background warning center is the difference data;

[0130] After the multi-channel collector has completed comparison of the current formation stress data of multiple optical fiber sensors at the current moment with the historical formation stress data of multiple optical fiber sensors at the previous moment stored locally, it summarizes and obtains the formation stress data network package that needs to be uploaded at the current moment;

[0131] The multi-channel collector transmits the formation stress data network package to the background early warning center through the wireless network;

[0132] When the background warning center receives the formation stress data network package, it extracts the data item content of each optical fiber sensor;

[0133] The background early warning center retrieves the locally stored historical formation stress data of each optical fiber sensor at the previous moment;

[0134] The background early warning center updates the historical formation stress data of each optical fiber sensor at the previous moment based on the locally pre-stored data, combined with the data item content of the corresponding optical fiber sensor received, and restores the current formation stress data of each optical fiber sensor at the current moment.

[0135] According to a specific embodiment of the present invention, after the multi-channel collector transmits the formation stress data network packet to the background early warning center via the wireless network, the method further includes:

[0136] The multi-channel collector replaces the historical formation stress data of each optical fiber sensor at the previous moment with the formation stress data of each optical fiber sensor at the current moment, so as to update the local pre-stored data.

[0137] According to a specific embodiment of the present invention, after restoring the current formation stress data of each optical fiber sensor at the current moment, the method further includes:

[0138] The background early warning center will restore the current formation stress data of each optical fiber sensor at the current moment to replace the historical formation stress data of each optical fiber sensor at the previous moment, so as to update the local pre-stored data.

[0139] like Figure 2 As shown, in a specific embodiment, a plurality of optical fiber sensors (such as Figure 2 The optical fiber sensor 21, the optical fiber sensor 22, and the optical fiber sensor 23 are respectively connected to the multi-channel collector 24 through proximal communication, and the multi-channel collector 24 is connected to the background early warning center 25 through remote communication.

[0140] It is understandable that due to the large number of fiber optic sensors and the large amount of stress data collected by each fiber optic sensor, if all data are updated and uploaded at every moment, the network bandwidth requirements are high, which can easily lead to network delays or packet loss. The present invention pre-stores the stratum stress data of the previous moment in the local multi-channel collector and the background early warning center respectively. When the multi-channel collector collects the current stratum stress data at the current moment, it compares the difference with the local pre-stored stratum stress data of the previous moment to obtain the updated data. Since the amount of updated data is small, the multi-channel collector can transmit it to the background early warning center at high speed without pressure. The background early warning center then combines the local pre-stored historical stratum stress data of the previous moment with the updated data to restore the current stratum stress data at the current moment. Therefore, the present invention can ensure the integrity and real-time nature of the uploaded stress data, further improving the early warning response capability of landslide geological disasters.

[0141] According to an embodiment of the present invention, the background early warning center performs a prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of the landslide geological site, specifically including:

[0142] The landslide risk prediction model is constructed by the background early warning center;

[0143] Optimize and train the landslide risk prediction model through sample data;

[0144] The rainfall data of the landslide geological site and the stratum stress data of each geological zone are input into the landslide risk prediction model, and the risk value of landslide occurrence at the landslide geological site is output.

[0145] Specifically, each geological partition has a corresponding risk value, and combined with the topography and geomorphology of the landslide geological site, a landslide risk profile of the landslide geological site is formed. The risk value of each geological partition in the landslide risk profile can be updated in real time over time, such as Figure 3 At the same time, when the risk value of a geological partition exceeds the threshold, a color-coded warning will be issued.

[0146] According to an embodiment of the present invention, after outputting the risk value of landslide occurrence at the landslide geological site, the method further includes:

[0147] Acquiring on-site geological attribute data of a landslide geological site, wherein the on-site geological attribute data at least includes on-site geological slope and on-site geological rock and soil slump;

[0148] Acquire multiple reference landslide data based on big data technology, each reference landslide data at least including reference geological attribute data, reference rainfall data, reference stratum stress data, and actual landslide conditions, wherein the reference geological attribute data at least includes reference geological slope and reference geological rock and soil slump;

[0149] Performing characteristic calculation on the reference geological attribute data in each reference landslide data to obtain the geological attribute characteristic value of the reference landslide data;

[0150] Perform characteristic calculation on the on-site geological attribute data of the landslide geological site to obtain the geological attribute characteristic value of the landslide geological site;

[0151] Based on each reference landslide data, the geological attribute characteristic value of the reference landslide data and the geological attribute characteristic value of the landslide geological site are approximated to obtain the approximation between the two;

[0152] determining whether the approximation is greater than a second preset threshold, and if so, entering the corresponding reference landslide data into an approximation database;

[0153] Based on each reference landslide data in the approximate database, the corresponding reference rainfall data and reference stratum stress data are predicted and analyzed through the landslide risk prediction model to obtain the predicted risk value of the reference landslide;

[0154] Based on each reference landslide data in the approximate library, the predicted risk value of the reference landslide and the actual landslide situation are used to calculate the modified contribution value of each reference landslide data through a third algorithm;

[0155] Adding the modified contribution values ​​calculated from each reference landslide data in the approximate database to obtain the sum of the modified contribution values, and dividing the sum of the modified contribution values ​​by the amount of reference landslide data in the approximate database to obtain the modified value;

[0156] The correction value is added to the outputted risk value of landslide occurrence at the landslide geological site to obtain the corrected risk value of landslide occurrence at the landslide geological site.

[0157] Understandably, given that the prediction model is constrained by its own parameters, the predicted risk value may be biased. The present invention analyzes and calculates multiple reference landslide data sets to derive a correction value for the prediction model. This correction value is then used to modify the landslide risk value at the landslide geological site, thereby predicting a more accurate landslide risk value and further facilitating precise monitoring of the landslide geological site.

[0158] According to a specific embodiment of the present invention, the modified contribution value of each reference landslide data is calculated by the third algorithm, specifically including:

[0159] Compare the predicted risk value of the reference landslide with the first preset threshold. If it is greater than or equal to the first preset threshold and the actual landslide situation is that a landslide has occurred, the correction contribution value of the reference landslide data is recorded as 0; if it is greater than or equal to the first preset threshold and the actual landslide situation is that no landslide has occurred, the correction contribution value of the reference landslide data is recorded as the difference between the first preset threshold and the predicted risk value of the reference landslide, and is a negative value; if it is less than the first preset threshold and the actual landslide situation is that a landslide has occurred, the correction contribution value of the reference landslide data is recorded as the difference between the first preset threshold and the predicted risk value of the reference landslide, and is a positive value; if it is less than the first preset threshold and the actual landslide situation is that no landslide has occurred, the correction contribution value of the reference landslide data is recorded as 0.

[0160] According to a specific embodiment of the present invention, feature calculation is performed on reference geological attribute data in each reference landslide data to obtain geological attribute characteristic values ​​of the reference landslide data; feature calculation is performed on on-site geological attribute data of the landslide geological site to obtain geological attribute characteristic values ​​of the landslide geological site; and based on each reference landslide data, an approximation calculation is performed between the geological attribute characteristic values ​​of the reference landslide data and the geological attribute characteristic values ​​of the landslide geological site to obtain the approximation between the two, specifically including:

[0161] Extract the reference geological slope from the reference geological attribute data in each reference landslide data, preset the slope range for landslide disasters as minimum slope to maximum slope, and calculate the slope characteristic value of the reference landslide data as (reference geological slope - minimum slope) / (maximum slope - minimum slope);

[0162] Extracting the reference geological rock and soil slump from the reference geological attribute data in each reference landslide data, presetting the rock and soil slump range to be between minimum slump and maximum slump, and calculating the geotechnical characteristic value of the reference landslide data as (reference geological rock and soil slump - minimum slump) / (maximum slump - reference geological rock and soil slump);

[0163] Extract the on-site geological slope from the on-site geological attribute data of the landslide geological site, and calculate the slope characteristic value of the landslide geological site as (on-site geological slope-minimum slope) / (maximum slope-minimum slope);

[0164] Extract the on-site geological rock and soil slump from the on-site geological attribute data of the landslide geological site, and calculate the geotechnical characteristic value of the landslide geological site as (on-site geological rock and soil slump - minimum slump) / (maximum slump - reference geological rock and soil slump);

[0165] Based on each reference landslide data, a similarity calculation is performed between the slope characteristic value of each reference landslide data and the slope characteristic value of the landslide geological site to obtain the slope characteristic similarity based on each reference landslide data;

[0166] Based on each reference landslide data, a similarity calculation is performed between the geotechnical characteristic value of each reference landslide data and the geotechnical characteristic value of the landslide geological site to obtain the geotechnical characteristic similarity based on each reference landslide data;

[0167] The preset slope and geotechnical properties have different influence weights on determining whether the reference geological attribute data of the reference landslide data are similar to the on-site geological attribute data of the landslide geological site;

[0168] Based on each reference landslide data, the corresponding slope characteristic similarity is multiplied by the influence weight of the slope to obtain the slope characteristic weight similarity, and the corresponding geotechnical characteristic similarity is multiplied by the influence weight of the geotechnical to obtain the geotechnical characteristic weight similarity;

[0169] Based on each reference landslide data, the corresponding slope characteristic weight similarity and the corresponding geotechnical characteristic weight similarity are added to obtain a first value;

[0170] Add the influence weight of the slope and the influence weight of the rock and soil to obtain a second value;

[0171] Based on each reference landslide data, the first value is divided by the second value to obtain the similarity between the geological attribute characteristic value of the reference landslide data and the geological attribute characteristic value of the landslide geological site.

[0172] Figure 4 A block diagram of a landslide geological disaster early warning system according to the present invention is shown.

[0173] like Figure 4 As shown, the second aspect of the present invention further proposes a landslide geological disaster early warning system 4, including a memory 41 and a processor 42, wherein the memory includes a landslide geological disaster early warning method program, and when the landslide geological disaster early warning method program is executed by the processor, the following steps are implemented:

[0174] The pre-set landslide geological site includes multiple geological zones, each of which is composed of multiple terrain surfaces;

[0175] For each geological zone, the corresponding landslide geological disaster warning demand level is obtained for each of the multiple terrain surfaces;

[0176] Combine the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, and calculate the sensing center of each geological zone through a preset first algorithm;

[0177] Fiber optic sensors are deployed at the sensing center of each geological zone;

[0178] Fiber optic sensors collect stratum stress data of corresponding geological zones in real time and upload it to the backend early warning center;

[0179] Rainfall sensors collect rainfall data at the landslide geological site and upload it to the backend early warning center;

[0180] The background early warning center conducts prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site.

[0181] According to an embodiment of the present invention, the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone are combined, and the sensing center of each geological zone is calculated using a preset first algorithm, specifically including:

[0182] respectively obtaining the shape of each topographic surface of each geological partition, and respectively calculating the topographic center of each topographic surface of each geological partition using a second algorithm;

[0183] Cluster analysis is performed on the topographic centers of multiple topographic surfaces of each geological partition according to the density clustering algorithm to obtain the geological center;

[0184] According to the geological center of each geological zone, combined with the landslide geological disaster early warning demand levels of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated through the first algorithm.

[0185] According to an embodiment of the present invention, the shape of each topographic surface of each geological partition is obtained respectively, and the topographic center of each topographic surface of each geological partition is calculated respectively by a second algorithm, specifically including:

[0186] Assume that each terrain surface of each geological partition is a plane polygon, and construct a plane coordinate system based on each terrain surface of each geological partition;

[0187] respectively obtaining the polygon vertex coordinates of each terrain surface of each geological partition, wherein the polygon vertex coordinates include abscissa and ordinate;

[0188] Based on each geological partition, the abscissas of all polygon vertices of each terrain surface are added to obtain the sum of first abscissas, and the sum of the first abscissas is divided by the total number of polygon vertices to obtain the abscissa of the terrain center of each terrain surface; the ordinates of all polygon vertices of each terrain surface are added to obtain the sum of first ordinates, and the sum of the first ordinates is divided by the total number of polygon vertices to obtain the ordinate of the terrain center of each terrain surface;

[0189] Based on each geological partition, the topographic center position of each topographic surface is determined according to the abscissa and ordinate of the topographic center of each topographic surface.

[0190] The present invention proposes a landslide geological disaster early warning method and system. The method obtains the corresponding landslide geological disaster early warning level for multiple terrain surfaces in each geological zone. The landslide geological disaster early warning level for each geological zone is combined with the landslide geological disaster early warning level for each terrain surface and a preset first algorithm is used to calculate the sensing center for each geological zone. Fiber optic sensors are deployed at the sensing center of each geological zone. The fiber optic sensors collect stratum stress data for the corresponding geological zone in real time, while rainfall sensors collect rainfall data at the landslide geological site and upload it to a backend early warning center. Finally, the backend early warning center performs a predictive analysis based on the rainfall data at the landslide geological site and the stratum stress data for each geological zone, outputting a landslide risk value for the landslide geological site. This allows personnel to promptly assess the likelihood of a landslide at the site and achieve accurate early warning. The present invention rationally arranges fiber optic collection points based on geological environmental conditions to accurately collect stratum stress data. A landslide risk early warning model is constructed, and combined with stress data, rainfall, and other environmental factors, accurate prediction of the occurrence of landslide geological disasters is achieved. Furthermore, the early warning method and system of the present invention have low operational costs.

[0191] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0192] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0193] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0194] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0195] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0196] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A landslide geological disaster early warning method, characterized in that: The method comprises: The pre-set landslide geological site includes multiple geological zones, each of which is composed of multiple terrain surfaces; For each geological zone, the corresponding landslide geological disaster warning demand level is obtained for each of the multiple terrain surfaces; Combine the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, and calculate the sensing center of each geological zone through a preset first algorithm; Fiber optic sensors are deployed at the sensing center of each geological zone; Fiber optic sensors collect stratum stress data of corresponding geological zones in real time and upload it to the backend early warning center; Rainfall sensors collect rainfall data at the landslide geological site and upload it to the backend early warning center; The background early warning center conducts prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site.

2. A landslide geological disaster early warning method according to claim 1, characterized in that: Combined with the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, the sensing center of each geological zone is calculated through a preset first algorithm, specifically including: respectively obtaining the shape of each topographic surface of each geological partition, and respectively calculating the topographic center of each topographic surface of each geological partition using a second algorithm; Cluster analysis is performed on the topographic centers of multiple topographic surfaces of each geological partition according to the density clustering algorithm to obtain the geological center; According to the geological center of each geological zone, combined with the landslide geological disaster early warning demand levels of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated through the first algorithm.

3. A landslide geological disaster early warning method according to claim 2, characterized in that: The shape of each terrain surface of each geological partition is obtained respectively, and the terrain center of each terrain surface of each geological partition is calculated respectively by a second algorithm, specifically including: Assume that each terrain surface of each geological partition is a plane polygon, and construct a plane coordinate system based on each terrain surface of each geological partition; respectively obtaining the polygon vertex coordinates of each terrain surface of each geological partition, wherein the polygon vertex coordinates include abscissa and ordinate; Based on each geological partition, the abscissas of all polygon vertices of each terrain surface are added to obtain the sum of first abscissas, and the sum of the first abscissas is divided by the total number of polygon vertices to obtain the abscissa of the terrain center of each terrain surface; the ordinates of all polygon vertices of each terrain surface are added to obtain the sum of first ordinates, and the sum of the first ordinates is divided by the total number of polygon vertices to obtain the ordinate of the terrain center of each terrain surface; Based on each geological partition, the topographic center position of each topographic surface is determined according to the abscissa and ordinate of the topographic center of each topographic surface.

4. A landslide geological disaster early warning method according to claim 2, characterized in that: According to the geological center of each geological zone, combined with the landslide geological disaster warning demand level of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated by the first algorithm, specifically including: Obtain the landslide geological disaster warning demand level for multiple terrain surfaces in each geological zone; Pass through the geological center of each geological partition, and draw two mutually perpendicular horizontal and vertical coordinate lines along the slope of each geological partition; Based on each geological partition, each geological partition is divided into four geological blocks by abscissa lines and ordinate lines; Based on the four geological blocks in each geological division, the terrain surface covered by each geological block is counted respectively, and the landslide geological disaster early warning demand level of all terrain surfaces covered by each geological block is summed up to obtain the early warning demand level of each geological block; Based on the four geological blocks of each geological partition, the block center of each geological block is calculated by the second algorithm; Based on the four geological blocks of each geological partition, a ray is drawn for each geological block with the geological center as the origin and passing through the block center of each geological block; Based on each geological partition, the ray direction of each geological block is used as the vector direction, and the warning requirement level of each geological block is used as the vector value to obtain the component vector of each geological block; Based on each geological partition, the vectors of the geological blocks are vector-sum calculated to obtain the compensation vector of each geological partition based on the landslide geological disaster early warning needs; The geological center of each geological partition is compensated according to the corresponding compensation vector to obtain the sensing center of each geological partition.

5. A landslide geological disaster early warning method according to claim 1, characterized in that: Fiber optic sensors collect stratum stress data corresponding to geological zones in real time and upload it to the backend early warning center, including: The fiber optic sensor collects the formation stress data of the corresponding geological partition in real time and transmits it to the multi-channel collector on site; The multi-channel collector aggregates and obtains the formation stress data of multiple optical fiber sensors at the current moment; The multi-channel collector compares the current formation stress data of the multiple optical fiber sensors at the current moment with the historical formation stress data of the multiple optical fiber sensors at the previous moment stored locally. If the current formation stress data of the first optical fiber sensor is consistent with the corresponding historical formation stress data, the data item uploaded by the first optical fiber sensor to the background warning center is empty; If the current formation stress data of the second optical fiber sensor is inconsistent with the corresponding historical formation stress data, the difference data between the two is calculated, and the data item uploaded by the second optical fiber sensor to the background warning center is the difference data; After the multi-channel collector has completed comparison of the current formation stress data of multiple optical fiber sensors at the current moment with the historical formation stress data of multiple optical fiber sensors at the previous moment stored locally, it summarizes and obtains the formation stress data network package that needs to be uploaded at the current moment; The multi-channel collector transmits the formation stress data network package to the background early warning center through the wireless network; When the background warning center receives the formation stress data network package, it extracts the data item content of each optical fiber sensor; The background early warning center retrieves the locally stored historical formation stress data of each optical fiber sensor at the previous moment; The background early warning center updates the historical formation stress data of each optical fiber sensor at the previous moment based on the locally pre-stored data, combined with the data item content of the corresponding optical fiber sensor received, and restores the current formation stress data of each optical fiber sensor at the current moment.

6. A landslide geological disaster early warning method according to claim 1, characterized in that: The backend early warning center conducts forecast analysis based on the rainfall data at the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site, including: The landslide risk prediction model is constructed by the background early warning center; Optimize and train the landslide risk prediction model through sample data; The rainfall data of the landslide geological site and the stratum stress data of each geological zone are input into the landslide risk prediction model, and the risk value of landslide occurrence at the landslide geological site is output.

7. A landslide geological disaster early warning method according to claim 6, characterized in that: After outputting the landslide risk value at the landslide geological site, the method further includes: Acquiring on-site geological attribute data of a landslide geological site, wherein the on-site geological attribute data at least includes on-site geological slope and on-site geological rock and soil slump; Acquire multiple reference landslide data based on big data technology, each reference landslide data at least including reference geological attribute data, reference rainfall data, reference stratum stress data, and actual landslide conditions, wherein the reference geological attribute data at least includes reference geological slope and reference geological rock and soil slump; Performing characteristic calculation on reference geological attribute data in each reference landslide data to obtain geological attribute characteristic values ​​of the reference landslide data; Perform characteristic calculation on the on-site geological attribute data of the landslide geological site to obtain the geological attribute characteristic values ​​of the landslide geological site; Based on each reference landslide data, the geological attribute characteristic value of the reference landslide data and the geological attribute characteristic value of the landslide geological site are approximated to obtain the approximation between the two; determining whether the approximation is greater than a second preset threshold, and if so, entering the corresponding reference landslide data into an approximation database; Based on each reference landslide data in the approximate database, the corresponding reference rainfall data and reference stratum stress data are predicted and analyzed through the landslide risk prediction model to obtain the predicted risk value of the reference landslide; Based on each reference landslide data in the approximate library, the predicted risk value of the reference landslide and the actual landslide situation are used to calculate the modified contribution value of each reference landslide data through a third algorithm; Adding the modified contribution values ​​calculated from each reference landslide data in the approximate database to obtain the sum of the modified contribution values, and dividing the sum of the modified contribution values ​​by the amount of reference landslide data in the approximate database to obtain the modified value; The correction value is added to the outputted risk value of landslide occurrence at the landslide geological site to obtain the corrected risk value of landslide occurrence at the landslide geological site.

8. A landslide geological disaster early warning system, characterized in that: The system comprises a memory and a processor, wherein the memory comprises a landslide geological disaster early warning method program, and when the landslide geological disaster early warning method program is executed by the processor, the following steps are implemented: The pre-set landslide geological site includes multiple geological zones, each of which is composed of multiple terrain surfaces; For each geological zone, the corresponding landslide geological disaster warning demand level is obtained for each of the multiple terrain surfaces; Combine the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, and calculate the sensing center of each geological zone through a preset first algorithm; Fiber optic sensors are deployed at the sensing center of each geological zone; Fiber optic sensors collect stratum stress data of corresponding geological zones in real time and upload it to the backend early warning center; Rainfall sensors collect rainfall data at the landslide geological site and upload it to the backend early warning center; The background early warning center conducts prediction analysis based on the rainfall data of the landslide geological site and the stratum stress data of each geological zone, and outputs the risk value of landslide occurrence at the landslide geological site.

9. A landslide geological disaster early warning system according to claim 8, characterized in that: Combined with the landslide geological disaster warning demand levels of multiple terrain surfaces in each geological zone, the sensing center of each geological zone is calculated through a preset first algorithm, specifically including: respectively obtaining the shape of each topographic surface of each geological partition, and respectively calculating the topographic center of each topographic surface of each geological partition using a second algorithm; Cluster analysis is performed on the topographic centers of multiple topographic surfaces of each geological partition according to the density clustering algorithm to obtain the geological center; According to the geological center of each geological zone, combined with the landslide geological disaster early warning demand levels of multiple terrain surfaces of each geological zone, the sensing center of each geological zone is calculated through the first algorithm.

10. A landslide geological disaster early warning system according to claim 9, characterized in that: The shape of each terrain surface of each geological partition is obtained respectively, and the terrain center of each terrain surface of each geological partition is calculated respectively by a second algorithm, specifically including: Assume that each terrain surface of each geological partition is a plane polygon, and construct a plane coordinate system based on each terrain surface of each geological partition; respectively obtaining the polygon vertex coordinates of each terrain surface of each geological partition, wherein the polygon vertex coordinates include abscissa and ordinate; Based on each geological partition, the abscissas of all polygon vertices of each terrain surface are added to obtain the sum of first abscissas, and the sum of the first abscissas is divided by the total number of polygon vertices to obtain the abscissa of the terrain center of each terrain surface; the ordinates of all polygon vertices of each terrain surface are added to obtain the sum of first ordinates, and the sum of the first ordinates is divided by the total number of polygon vertices to obtain the ordinate of the terrain center of each terrain surface; Based on each geological partition, the topographic center position of each topographic surface is determined according to the abscissa and ordinate of the topographic center of each topographic surface.

Images