Ground disaster monitoring and early warning method and system based on space-time weighted fuzzy clustering analysis

Abstract

The invention discloses a ground disaster monitoring and early warning method and system based on space-time weighted fuzzy clustering analysis. The method comprises the steps that A1, a monitoring device is installed; a2, collecting multi-source data through a monitoring device, and constructing a spatio-temporal data set; a3, key parameters in the multi-source data are extracted, and whether the key parameters exceed the limit or not is judged; if the limit is exceeded, an early warning is directly given out; if not, executing the step A4; step A4, preprocessing the multi-source data, including removing abnormal values, and performing normalization and space-time alignment processing; a5, analyzing and processing the data by adopting an improved fuzzy clustering algorithm, and recording a clustering category; and step A6, according to a clustering analysis result, judging whether an early warning notification is sent out or not. According to the scheme, the space-time weight matrix is introduced, the time correlation and the space dependence of the geological disaster monitoring data are effectively fused, the limitation that only data static characteristics are considered in a traditional clustering method is broken through, and the reliability of an analysis result is greatly improved.

Description

Technical Field

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

[0002] Geological disaster monitoring and early warning is achieved by deploying monitoring devices in the monitoring area to obtain parameters related to the occurrence of geological disasters in the monitoring area. When one or more parameters are detected to be out of limit, the system analyzes and determines whether there is a risk of geological disaster, and further determines the level of geological disaster, providing early warnings to relevant units and personnel.

[0003] Current geological disaster monitoring devices have obvious technical defects: first, most existing equipment uses a single sensor configuration, such as only monitoring a single parameter such as surface displacement or rainfall. This one-sided data collection method is difficult to fully reflect the complex causal mechanism of geological disasters; second, the system architecture design physically separates the data collection and processing links, resulting in a response delay from data acquisition to analysis results of more than 10 minutes, which seriously affects the timeliness of early warning; third, the power supply guarantee for field monitoring sites is difficult, and the continuous working time of existing equipment is generally less than 1 month, which is difficult to meet the needs of long-term continuous monitoring.

[0004] There are also significant deficiencies in data analysis: the traditional fixed-threshold warning method has a high false alarm rate, often misjudging normal activities such as construction vibration, electromagnetic interference, and biological activities as geological disaster signals; although fuzzy clustering algorithms have been applied, existing implementation schemes fail to fully consider the unique temporal and spatial correlation characteristics of geological hazard data, resulting in insufficient reliability of analysis results; in addition, the current warning model lacks deep coupling with geomechanical mechanisms, the model decision-making process is poorly interpretable, and it is difficult to provide a physically meaningful warning basis. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a geological disaster monitoring and early warning method and system based on spatiotemporal weighted fuzzy clustering analysis, so as to solve the problem of insufficient reliability of analysis results raised in the above-mentioned background technology.

[0006] To achieve the above objectives, a geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis is provided, which is characterized by comprising: Step A1: Install monitoring device; Step A2: Collect multi-source data through monitoring devices and construct a spatiotemporal dataset; Step A3: Extract key parameters from multi-source data and determine whether they exceed the limit; if so, issue a warning; if not, proceed to step A4; Step A4: Preprocess the multi-source data, including removing outliers, normalizing, and performing spatiotemporal alignment. Step A5: Use the improved fuzzy clustering algorithm to analyze and process the data and record the cluster categories; Step A6: Determine whether to issue an early warning notification based on the cluster analysis results.

[0007] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis, in step A2, the multi-source data collected include displacement data, hydrological data, resistivity data and meteorological data of the monitoring area.

[0008] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis, in step A4, during data normalization processing, the continuous monitoring data displacement and water level are normalized using maximum and minimum values, where the extreme values ​​are taken from the 99th percentile of the sensor's historical data; categorical data are encoded using one-hot encoding; resistivity geophysical data are first logarithmically transformed and then normalized; and displacement rate is additionally normalized using Z-score. In the spatiotemporal alignment processing, UTC timestamp and CGCS2000 coordinate system are used to align multi-source data in spatiotemporal space.

[0009] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis, in step A5, based on the spatiotemporal distribution characteristics of the monitoring data, an improved fuzzy clustering algorithm is used to analyze and process the data to calculate the objective function: Where J represents the objective function, Expressed as a membership matrix, Cluster centers m represents the number of clusters, n represents the number of samples, and c represents the number of cluster centers. Represented as the kth cluster center in the space, Denoted as the k-th cluster center at time, Expressed as spatial weight, Expressed as time weight, Represented as the i-th sample in the space, Denoted as the i-th sample at time, and is expressed as a constant, and , is the noise penalty coefficient, Expressed as noise membership.

[0010] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis, the membership matrix The calculation method is: Where, It is represented as a membership matrix, Denotes the i-th sample, It represents the cluster center, m represents the number of clusters, and c represents the number of cluster centers. It is expressed as the cluster center value that minimizes the objective function; The calculation method of the cluster center value that minimizes the objective function is as follows: Where, It is represented as the cluster center value that minimizes the objective function, n is the number of samples, and m is the control fuzziness. It is represented as a membership matrix, Denotes the jth sample, Indicated as ***.

[0011] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis, the membership matrix is ​​substituted into the objective function J for calculation. When J is less than the set threshold, the process returns to step A2. When J is greater than the set threshold, the clustering result is output. The threshold is set according to the following formula: Where k is the number of iterations.

[0012] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis, in step A6, the monitoring area is divided into three cluster categories: Class I, Class II and Class III; wherein, Class I indicates that all parameters fluctuate within the historical normal range, which is a safe state; Category II corresponds to 1-2 parameters exceeding the baseline threshold but without forming a multi-parameter coordinated abnormality, which is a cautionary state; Category III indicates that multiple parameters are persistently abnormal and have spatiotemporal clustering characteristics. At this time, it is a warning state, a warning signal is generated, and an early warning is issued; The generation of early warning signals adopts a multi-condition coupling trigger mechanism: when Class II data appears for three consecutive monitoring cycles, a yellow warning is automatically issued, indicating the accumulation of potential risk; when Class III data appears and lasts for more than two cycles, it is upgraded to an orange warning, indicating that the probability of disaster occurrence has increased significantly; when Class III data accounts for more than 50% of the monitoring area and the displacement rate exceeds the critical value of 4mm / h, a red warning is triggered. At this time, the deformation has entered the acceleration stage, and the emergency response platform will be linked to initiate the evacuation plan.

[0013] According to the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis, in step A3, the key parameters include soil moisture content.

[0014] The geological disaster monitoring and early warning system based on spatiotemporal weighted fuzzy clustering analysis uses the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis as described above, which includes a monitoring device, which includes a data acquisition unit, a data processing unit, a communication unit, and a power supply unit; wherein, The data acquisition unit has a displacement monitoring module, a hydrological monitoring module, and a meteorological monitoring module; The data processing unit has a main control module, a co-processing module, and a storage module; The communication unit has a 5G communication module, a Beidou short message module, and a LoRa self-organizing network module; The power supply unit includes a solar power supply system, a wind power supply system and an energy storage system.

[0015] Beneficial effects: This paper proposes a fuzzy clustering analysis algorithm based on spatiotemporal weighting, introduces a spatiotemporal weight matrix, effectively integrates the temporal correlation and spatial dependence of geological hazard monitoring data, breaks through the limitation of traditional clustering methods that only consider static characteristics of data, and greatly improves the reliability of analysis results. The present invention adopts a multi-parameter integrated design in hardware, and greatly improves the accuracy of geological disaster monitoring and early warning through collaborative analysis of multi-source data. It has built-in edge computing capabilities to realize local real-time processing of monitoring data, and combined with multi-mode redundant communication guarantees, it greatly shortens the response time of geological disaster early warning.

[0016] 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

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments; Figure 1 Schematic diagram of the method flow of the present invention; Figure 2 This is the flow chart of fuzzy cluster analysis based on time-space weighting; Figure 3 This is the structural module diagram of the monitoring device. DETAILED DESCRIPTION

[0018] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it should not be understood as a limitation on the scope of protection of the present invention.

[0019] Reference Figure 1-3 The present invention provides a geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis, which includes: Step A1: Install monitoring device; Step A2: Collect multi-source data through monitoring devices and construct a spatiotemporal dataset; Step A3: Extract key parameters from multi-source data and determine whether they exceed the limit; if so, issue a warning; if not, proceed to step A4; Step A4: Preprocess the multi-source data, including removing outliers, normalizing, and performing spatiotemporal alignment. Step A5: Use the improved fuzzy clustering algorithm to analyze and process the data and record the cluster categories; Step A6: Determine whether to issue an early warning notification based on the cluster analysis results.

[0020] Among them, in step A1, the monitoring device includes a data acquisition unit, which includes a displacement monitoring module (including a high-precision GNSS receiver, an inclination sensor, a displacement sensor, a stress sensor, etc.), a hydrological monitoring module (including a pore water pressure gauge, an ultrasonic water level meter and a flow meter, etc.), a meteorological monitoring module (a rain gauge, a soil moisture meter, a soil resistivity meter, etc.), etc., for collecting multi-source data in the monitoring area.

[0021] The monitoring data collection of various types of geological disasters can adopt a dynamic collection mode, such as using a rain gauge as a reference, automatically setting the collection frequency according to the rainfall, and encrypting the collection during heavy rain, so as to effectively collect key data at the moment of geological disaster initiation and improve the accuracy of early warning.

[0022] In step A2, the multi-source data collected includes displacement data, hydrological data, resistivity data, and meteorological data from the monitoring area. For each of these multi-source data, the corresponding sampling time and location are recorded, and the data sets are constructed into a spatiotemporal dataset. This allows for spatiotemporal alignment of these data types during subsequent data processing.

[0023] In step A3, the issuance of warning notifications not only considers the integration of parameter values ​​collected by various instruments but also considers key parameters. If these key parameters exceed the limit, a warning can also be issued if other values ​​do not meet the requirements. After the warning is issued, multi-source data collection can continue and be fed back to the indoor control center, without continuing to the subsequent steps.

[0024] Key parameters include soil moisture, a key indicator for geological hazards such as landslides. When soil moisture exceeds a limit, an early warning can be issued. The limit can be determined by testing the soil and hydrogeological conditions in the monitored area. This determination not only determines the limit for issuing an early warning, but also the soil moisture levels corresponding to different levels of early warning.

[0025] In step A4, preprocessing is the processing performed after data collection and before cluster analysis. It includes deleting duplicate data, filling missing data to remove outliers, normalizing, and performing time-space alignment processing. Among them, removing outliers means that some data in the data collection process are higher or lower than the normal range and should be deleted. Normalization is to facilitate the construction of tensor matrices during cluster analysis. During data normalization, different dimensional parameters are processed separately: continuous monitoring data displacement and water level are normalized by maximum and minimum values, where the extreme values ​​are taken from the 99% quantile of the sensor's historical data; categorical data are encoded using one-hot encoding; resistivity geophysical data are first logarithmically transformed and then normalized; and displacement rate is additionally normalized by Z-score.

[0026] During the spatiotemporal alignment process, multi-source data were aligned using UTC timestamps and the CGCS2000 coordinate system. Specifically, using the timing system as a benchmark, linear interpolation was performed to compensate for data with acquisition delays, ensuring that all data timestamps were aligned to the minute level. Spatially, each monitoring point was uniformly transformed to the CGCS2000 coordinate system using Gauss-Krüger projection, and Kriging interpolation was performed on the resistivity profile to generate 50m×50m grid data. To address inconsistent sampling frequencies, a data resampling algorithm based on a time weighting factor was used to uniformly generate a time series dataset with 10-minute intervals.

[0027] To verify the preprocessing effect, a three-dimensional evaluation indicator system was established: the time dimension was used to calculate the effective coverage rate of each sensor data, the spatial dimension was used to check the cross-validation error of the interpolation results, and the parameter dimension was used to analyze the distribution of normalized data. When the preprocessed data were stored in the spatiotemporal database, a hierarchical storage structure was adopted: the original layer retained the data before cleaning for future reference, the processed layer stored the normalized data and annotated it with quality control marks, and the application layer generated a spatiotemporal cube that could be directly used for analysis.

[0028] Cluster analysis analyzes collected displacement, hydrological, meteorological, and resistivity parameters, ultimately outputting cluster categories. These categories are then used to determine geological disaster risk and inform decision-making. The input is a matrix of multi-source monitoring data (including displacement change rate, pore water pressure, resistivity, rainfall intensity, and other parameters) along with prior geological knowledge, and the output is cluster categories.

[0029] In step A5, based on the spatiotemporal distribution characteristics of the monitoring data, an improved fuzzy clustering algorithm is used to analyze and process the data and calculate the objective function: Where J represents the objective function, Expressed as a membership matrix, Cluster centers m represents the number of clusters (number of categories), n represents the number of samples, and c represents the number of cluster centers. Represented as the kth cluster center in the space, Denoted as the k-th cluster center at time, Expressed as spatial weight, Expressed as time weight, Represented as the i-th sample in the space, Denoted as the i-th sample at time, and is expressed as a constant, and , is the noise penalty coefficient (the value can be 0.2), Expressed as noise membership.

[0030] Among them, the membership matrix The calculation method is: Where, It is represented as a membership matrix, Denotes the i-th sample, It represents the cluster center, m represents the number of clusters, and c represents the number of cluster centers. It is expressed as the cluster center value that minimizes the objective function; The calculation method of the cluster center value that minimizes the objective function is as follows: Where, It is represented as the cluster center value that minimizes the objective function, n is the number of samples, and m is the control fuzziness (the value can be 2). It is represented as a membership matrix, Denoted as the jth sample.

[0031] Substitute the membership matrix and cluster centers into the objective function J for calculation. When J is less than the set threshold, return to step A2. When J is greater than the set threshold, output the clustering result. The threshold value needs to be determined in combination with the characteristics of geology and actual monitoring data, and can be determined according to the following formula: Where k is the number of iterations.

[0032] In step A6, the geological hazard risk classification and warning triggering mechanism based on spatiotemporal weighted fuzzy cluster analysis performs dynamic risk assessment through multi-dimensional data fusion, dividing the monitoring area into three cluster categories: Class I, Class II, and Class III. Class I indicates that all parameters fluctuate within the historical normal range, indicating a safe state; Class II corresponds to one or two parameters exceeding the baseline threshold but without forming a multi-parameter coordinated anomaly, indicating a cautionary state; Class III indicates that multiple parameters have persistent anomalies with spatiotemporal clustering characteristics, indicating a warning state, generating a warning signal, and issuing an alert.

[0033] The generation of early warning signals adopts a multi-condition coupling trigger mechanism: when Class II data appears for three consecutive monitoring cycles, a yellow warning is automatically issued, indicating the accumulation of potential risk; when Class III data appears and lasts for more than two cycles, it is upgraded to an orange warning, indicating that the probability of disaster occurrence has increased significantly; when Class III data accounts for more than 50% of the monitoring area and the displacement rate exceeds the critical value of 4mm / h, a red warning is triggered. At this time, the deformation has entered the acceleration stage, and the emergency response platform will be linked to initiate the evacuation plan.

[0034] The present invention also discloses a geological disaster monitoring and early warning system based on spatiotemporal weighted fuzzy clustering analysis. Using the above-described method, the system includes a monitoring device comprising a data acquisition unit, a data processing unit, a communication unit, and a power supply unit. The data acquisition unit includes a displacement monitoring module (including a high-precision GNSS receiver, an inclination sensor, a displacement sensor, a stress sensor, etc.), a hydrological monitoring module (including a pore water pressure gauge, an ultrasonic water level meter, a flowmeter, etc.), and a meteorological monitoring module (including a rain gauge, a soil moisture meter, a soil resistivity meter, etc.). The data processing unit includes a main control module, a co-processing module, and a storage module; the communication unit includes a 5G communication module, a Beidou short message module, and a LoRa self-organizing network module; and the power supply unit includes a solar power supply system, a wind power supply system, and an energy storage system.

[0035] After the device is deployed and powered on, the communication unit ensures data synchronization and normal connectivity between components. The data acquisition unit collects parameters such as soil displacement, moisture content, and resistivity, and transmits them to the data processing unit in real time through the communication unit. The main control module and the co-processing module of the data processing unit work together to achieve efficient and rapid data processing and analysis, and store and back up the original data and analysis results. At the same time, the analysis results are transmitted to the indoor control center through the communication unit. If the analysis results show a high risk level, the on-site personnel will be notified directly by text message.

[0036] This approach enables collaborative analysis of multi-source data, significantly improving the accuracy of geological disaster monitoring and early warning. Collaborative analysis involves modeling the spatiotemporal correlations and dynamically coupling assessments of multi-source monitoring data, including soil displacement, hydrological parameters, meteorological parameters, and resistivity, collected in real time by monitoring equipment. First, standardized processing of multi-source data is achieved through temporal synchronization and spatial registration. An improved fuzzy clustering algorithm is then used to jointly analyze these parameters. By calculating the membership degree and cluster center of each monitoring point, a risk level label is ultimately output for each monitoring point, enabling a comprehensive assessment of the geological disaster's development trajectory.

[0037] Although the above methods are illustrated and described as a series of actions for simplicity of explanation, it should be understood and appreciated that these methods are not limited by the order of the actions, because according to one or more embodiments, some actions may occur in different orders and / or concurrently with other actions from the diagrams and descriptions herein or not illustrated and described herein but understood by those skilled in the art. Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Technicians can implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention. The various illustrative logic blocks, modules, and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read and write information from / to the storage medium. In an alternative embodiment, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative embodiment, the processor and storage medium may reside in the user terminal as discrete components. In one or more exemplary embodiments, the described functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or code.Computer-readable media include both computer storage media and communication media, including any media that facilitates the transfer of a computer program from one place to another. Storage media can be any available media that can be accessed by a computer. As an example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0038] The embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by ordinary technicians in the technical field without departing from the spirit of the present invention.

Claims

1. A geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy clustering analysis is characterized by: include: Step A1: Install monitoring device; Step A2: Collect multi-source data through monitoring devices and construct a spatiotemporal dataset; Step A3: Extract key parameters from multi-source data and determine whether they exceed the limit; if so, issue an alert directly; If the limit is not exceeded, proceed to step A4; Step A4: Preprocess the multi-source data, including removing outliers, normalizing, and performing spatiotemporal alignment. Step A5: Use the improved fuzzy clustering algorithm to analyze and process the data and record the cluster categories; Step A6: Determine whether to issue an early warning notification based on the cluster analysis results.

2. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 1 is characterized by: In step A2, the multi-source data collected include displacement data, hydrological data, resistivity data and meteorological data of the monitoring area.

3. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 1 is characterized in that: In step A4, during data normalization, the continuous monitoring data displacement and water level are normalized using the maximum and minimum values, where the extreme values ​​are taken from the 99th percentile of the sensor's historical data; categorical data are encoded using one-hot encoding; resistivity geophysical data are first logarithmically transformed and then normalized; and displacement rate is additionally normalized using the Z-score. In the spatiotemporal alignment processing, UTC timestamp and CGCS2000 coordinate system are used to align multi-source data in spatiotemporal space.

4. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 1, characterized in that: In step A5, based on the spatiotemporal distribution characteristics of the monitoring data, an improved fuzzy clustering algorithm is used to analyze and process the data and calculate the objective function: Where J represents the objective function, Expressed as a membership matrix, Cluster centers m represents the number of clusters, n represents the number of samples, and c represents the number of cluster centers. Represented as the kth cluster center in the space, Denoted as the k-th cluster center at time, Expressed as spatial weight, Expressed as time weight, Represented as the i-th sample in the space, Denoted as the i-th sample at time, and is expressed as a constant, and , is the noise penalty coefficient, Expressed as noise membership.

5. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 4 is characterized in that: Membership matrix The calculation method is: Where, It is represented as a membership matrix, Denotes the i-th sample, It represents the cluster center, m represents the number of clusters, and c represents the number of cluster centers. It is expressed as the cluster center value that minimizes the objective function; The calculation method of the cluster center value that minimizes the objective function is as follows: Where, It is represented as the cluster center value that minimizes the objective function, n is the number of samples, and m is the control fuzziness. It is represented as a membership matrix, Denoted as the jth sample.

6. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 5 is characterized by: Substitute the membership matrix into the objective function J for calculation. When J is less than the set threshold, return to step A2. When J is greater than the set threshold, output the clustering result. The threshold is set according to the following formula: Where k is the number of iterations.

7. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 1, characterized in that: In step A6, the monitoring area is divided into three cluster categories: Class I, Class II and Class III; Class I indicates that all parameters fluctuate within the historical normal range, which is a safe state; Category II corresponds to 1-2 parameters exceeding the baseline threshold but without forming a multi-parameter coordinated abnormality, which is a cautionary state; Category III indicates that multiple parameters are persistently abnormal and have spatiotemporal clustering characteristics. At this time, it is a warning state, a warning signal is generated, and an early warning is issued; The generation of early warning signals adopts a multi-condition coupling trigger mechanism: when Class II data appears for three consecutive monitoring cycles, a yellow warning is issued to indicate the accumulation of potential risk; when Class III data appears and lasts for more than two cycles, it is upgraded to an orange warning; when Class III data accounts for more than 50% of the monitoring area and the displacement rate exceeds the critical value of 4mm / h, a red warning is triggered. At this time, the deformation has entered the acceleration stage, and the emergency response platform will be linked to initiate the evacuation plan.

8. The geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to claim 1 is characterized by: In step A3, key parameters include soil moisture content.

9. A geological disaster monitoring and early warning system based on spatiotemporal weighted fuzzy cluster analysis, using the geological disaster monitoring and early warning method based on spatiotemporal weighted fuzzy cluster analysis according to any one of claims 1 to 8, characterized in that: The monitoring device includes a data acquisition unit, a data processing unit, a communication unit, and a power supply unit; wherein, The data acquisition unit has a displacement monitoring module, a hydrological monitoring module, and a meteorological monitoring module; The data processing unit has a main control module, a co-processing module, and a storage module; The communication unit has a 5G communication module, a Beidou short message module, and a LoRa self-organizing network module; The power supply unit includes a solar power supply system, a wind power supply system and an energy storage system.

Images