Geological disaster early warning method and system based on multi-source data fusion technology
Through multi-source data fusion technology, geological disaster warning models are collected, pre-processed and constructed, which solves the accuracy and real-time problems of traditional geological disaster warning methods, and achieves efficient geological disaster warning and emergency response.
Patent Information
- Application Number
- CN202510594243.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2025-07-08
AI Technical Summary
Traditional geological disaster warning methods rely on a single data source, and data quality and accuracy are easily affected, and lack real-time monitoring and early warning capabilities, resulting in insufficient accuracy and reliability of early warnings.
Multi-source data fusion technology is adopted to collect geological environmental data through disaster sensors, pre-process, data fusion and prediction model construction, generate geological disaster risk levels and send early warning information.
It improves the accuracy and timeliness of geological disaster warnings, realizes intelligent integration and processing of multi-source data, and supports real-time monitoring and timely early warning.
Smart Images
Figure CN120279668A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of geological disaster early warning, and particularly to a geological disaster early warning method and system based on multi-source data fusion technology. Background Art
[0002] Geological disasters, such as landslides, debris flows, etc., pose a huge threat to people's lives and property due to their suddenness and severity.
[0003] Traditional geological disaster early warning methods mainly rely on a single data source, such as rainfall monitoring data. The data quality and accuracy are easily affected by various factors, and this method often lacks the ability of real-time monitoring and early warning, and cannot guarantee the accuracy and reliability of geological disaster early warning.
[0004] Therefore, it is necessary to provide a geological disaster early warning method and system based on multi-source data fusion technology to solve the above technical problems. Summary of the Invention
[0005] To solve the above technical problems, the present invention provides a geological disaster early warning method and system based on multi-source data fusion technology to solve the problem that traditional geological disaster early warning methods rely on a single data source, the data quality and accuracy are easily affected by various factors, and this method lacks the ability of real-time monitoring and early warning, and cannot guarantee the accuracy and reliability of geological disaster early warning.
[0006] A geological disaster early warning method based on multi-source data fusion technology provided by the present invention, the early warning method includes: Collecting original geological environment data of a target geological disaster-prone area through disaster sensors; Performing a preprocessing operation on the original geological environment data to generate corresponding target geological environment data; Constructing a geological data fusion model, and performing fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data; Constructing a fused geological disaster prediction model, and performing disaster prediction on the fused geological environment data based on the fused geological disaster prediction model to generate corresponding geological disaster risk levels; Determining corresponding geological disaster early warning information according to the geological disaster risk level and sending it to the management terminal.
[0007] Preferably, the disaster sensors are deployed in the geological disaster-prone area, and the disaster sensors include a rain gauge sensor, a displacement gauge sensor, a piezometer sensor, and an inclinometer sensor.
[0008] Preferably, the preprocessing operation on the original geological environment data to generate corresponding target geological environment data specifically includes: Performing data cleaning on the original geological environment data to remove noise and outliers, and generating corresponding first geological environment data; Performing data format conversion on the first geological environment data to generate corresponding second geological environment data; Performing standardization processing on the second geological environment data to generate the corresponding target geological environment data.
[0009] Preferably, the construction of the geological data fusion model, and the fusion processing of the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data specifically includes: Setting the fusion category dataset as , where represents the th fusion category in the fusion category dataset , represents the total number of fusion categories in the fusion category dataset ; Based on the geological data fusion model, calculating the posterior probability of the fusion category under all target geological environment data conditions, and the corresponding calculation formula is as follows: In the formula, represents the th fusion category in the fusion category dataset ; represents the target geological environment data; represents the total number of target geological environment data; represents the posterior probability of the fusion category under all target geological environment data conditions, that is, the probability of the occurrence of the fusion category under all target geological environment data ; represents the likelihood probability, that is, the probability of the occurrence of all target geological environment data under the condition that the fusion category occurs; represents the prior probability of the fusion category ; represents the probability of the joint occurrence of all target geological environment data .
[0010] Preferably, the likelihood probability The calculation formula is as follows: In the formula, represents the fused category dataset the th fused category; represents the target geological environment data; represents the total quantity of the target geological environment data; represents the likelihood probability, that is, the probability that all the target geological environment data appear under the condition that the fused category occurs; represents the probability that the th target geological environment data appears under the condition that the fused category occurs; The expression of the posterior probability is: In the formula, represents the th fused category in the fused category dataset ; represents the target geological environment data; represents the total quantity of the target geological environment data; represents the posterior probability of the fused category under all the target geological environment data , that is, the probability that the fused category occurs under all the target geological environment data ; represents the probability that the th target geological environment data appears under the condition that the fused category occurs; represents the prior probability of the fused category ; represents the probability of the joint occurrence of all the target geological environment data ; Determine the fused category corresponding to the maximum value of the posterior probability as the target fused category, and perform fusion processing on the target geological environment data based on the target fused category to generate the corresponding fused geological environment data.
[0011] Preferably, the construction of the fused geological disaster prediction model, and the disaster prediction of the fused geological environment data based on the fused geological disaster prediction model to generate the corresponding geological disaster risk level specifically includes: Extract the fused geological environment features corresponding to the fused geological environment data, and perform predictive classification on the fused geological environment features based on the fused geological disaster prediction model. The corresponding optimization problem is as follows: In the formula, represents the weight vector of the -th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the -th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the -th fused geological environment feature is linearly inseparable in the -th support vector machine; represents the regularization parameter, which is used to control the trade-off between the classification margin and classification error; represents the total number of fused geological environment features; represents the operation of taking the minimum value; ∑ represents the summation symbol.
[0012] Preferably, the constraint conditions corresponding to the optimization problem are as follows: In the formula, represents the predicted class label corresponding to the -th fused geological environment feature; represents the -th fused geological environment feature; represents the weight vector of the -th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the -th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the -th fused geological environment feature is linearly inseparable in the -th support vector machine; represents the total number of fused geological environment features; Based on the predictive classification results of the fused geological environment features, determine the geological disaster risk level corresponding to the fused geological environment data.
[0013] Preferably, the geological disaster warning information includes geological disaster type, geological disaster warning level, geological disaster influence range, and geological disaster response measures.
[0014] A geological disaster early warning system based on multi-source data fusion technology, the early warning system comprising: A data acquisition module, configured to collect original geological environment data of a target geological disaster-prone area through disaster sensors; A data preprocessing module, configured to perform preprocessing operations on the original geological environment data to generate corresponding target geological environment data; A fusion processing module, configured to construct a geological data fusion model, and perform fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data; A disaster prediction module, configured to construct a fused geological disaster prediction model, and perform disaster prediction on the fused geological environment data based on the fused geological disaster prediction model to generate corresponding geological disaster risk levels; An early warning sending module, configured to determine corresponding geological disaster early warning information according to the geological disaster risk level and send it to the management terminal.
[0015] Compared with related technologies, a geological disaster early warning method and system provided by the present invention have the following beneficial effects: The present invention collects original geological environment data of a target geological disaster-prone area through disaster sensors; performs preprocessing operations on the original geological environment data to generate corresponding target geological environment data; constructs a geological data fusion model, and performs fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data; constructs a fused geological disaster prediction model, and performs disaster prediction on the fused geological environment data based on the fused geological disaster prediction model to generate corresponding geological disaster risk levels; determines corresponding geological disaster early warning information according to the geological disaster risk level and sends it to the management terminal, thereby integrating geological disaster data from different sources, formats, and types, solving the problem of insufficient accuracy of existing geological disaster early warning methods, and improving the accuracy and timeliness of geological disaster early warning.
[0016] The present invention can effectively integrate the collected geological environment data through a geological data fusion model based on multi-source data fusion technology, improving the accuracy and reliability of geological disaster early warning; at the same time, it can realize real-time monitoring and early warning of geological disasters through a fused geological disaster prediction model, generate corresponding geological disaster risk levels and early warning information, and then can transmit the early warning information to geological disaster management personnel to achieve timely transmission of early warning information and provide sufficient time for subsequent emergency responses; the present invention can realize intelligent fusion and processing of complex multi-source data, improving the intelligent level of the geological disaster early warning system. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1Flowchart of a geological disaster warning method based on multi-source data fusion technology of the present invention; Figure 2 Schematic diagram of deploying disaster sensors within the geological disaster-prone area of the present invention; Figure 3 System block diagram of a geological disaster warning system based on multi-source data fusion technology of the present invention. Detailed implementation manners
[0018] The present invention will be further described below with reference to the accompanying drawings and implementation manners.
[0019] Embodiment 1 As Figure 1 shown, a geological disaster warning method based on multi-source data fusion technology, the warning method includes: S1. Collect the original geological environment data of the target geological disaster-prone area through disaster sensors; S2. Perform preprocessing operations on the original geological environment data to generate corresponding target geological environment data; S3. Construct a geological data fusion model, and perform fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data; S4. Construct a fused geological disaster prediction model, and perform disaster prediction on the fused geological environment data based on the fused geological disaster prediction model to generate corresponding geological disaster risk levels; S5. Determine the corresponding geological disaster warning information according to the geological disaster risk level and send it to the management terminal.
[0020] Among them, by deploying a high-precision disaster sensor network, the original geological environment data can be systematically collected within the target geological disaster-prone area, and these data include key parameters such as surface displacement, underground water level change, soil moisture content, ground stress distribution, and seismic wave activity.
[0021] Furthermore, data preprocessing technologies can be adopted to perform preprocessing operations such as cleaning, denoising, standardization, and missing value filling on the collected original geological environment data, so as to eliminate data errors and outliers, ensure the accuracy and consistency of the data, and generate accurate target geological environment data that meets the analysis requirements.
[0022] It can be understood that by constructing a geological data fusion model, the interaction and correlation of various geological parameters can be comprehensively considered, and in-depth fusion processing can be performed on the preprocessed target geological environment data, effectively integrating geological information, and generating fused geological environment data with higher information density and prediction value.
[0023] Then, a combined geological disaster prediction model can be constructed to fully utilize the implicit laws and characteristics in the combined geological environment data, accurately predict the occurrence probability, scale, and potential impact of geological disasters, and generate scientific assessment results of geological disaster risk levels.
[0024] Finally, according to the assessment results of geological disaster risk levels, corresponding geological disaster warning information can be automatically generated. And through an efficient information transmission mechanism, the warning information can be sent to the management end in a timely and accurate manner, providing decision-making support for geological disaster emergency response and disaster prevention and mitigation work.
[0025] In the specific implementation process, as Figure 2 shown, the disaster sensors are deployed in the geological disaster-prone areas, and the disaster sensors include rain gauges, displacement gauges, piezometers, and inclinometers.
[0026] In practical applications, disaster sensors can be deployed in geological disaster-prone areas with complex geological structures and frequent historical disasters, so as to comprehensively and accurately monitor potential geological disasters.
[0027] Specifically, these disaster sensors cover a variety of professional measurement devices, including rain gauges for real-time monitoring of rainfall changes, displacement gauges for accurately measuring the displacement of the ground surface or buildings, piezometers for evaluating the change of water pressure inside the soil or rock, and inclinometers for detecting the change of the tilt angle of the ground or structures.
[0028] These high-precision sensors work together to collect and analyze key geological parameters in real time, which helps with subsequent geological disaster warning and emergency response.
[0029] The preprocessing operation on the original geological environment data to generate corresponding target geological environment data specifically includes: Performing data cleaning on the original geological environment data to remove noise and outliers, and generating corresponding first geological environment data; Performing data format conversion on the first geological environment data to generate corresponding second geological environment data; Performing standardization processing on the second geological environment data to generate the corresponding target geological environment data.
[0030] It can be understood that first, data cleaning can be performed on the original geological environment data to identify and eliminate noise and outliers in the dataset, generating a purer first geological environment data.
[0031] Subsequently, the first geological environment data can be converted from the original format to a unified and standardized data format to generate the second geological environment data, which is convenient for subsequent data processing and analysis.
[0032] Finally, the second geological environment data can be standardized. By scaling or normalizing the second geological environment data, it can be ensured that all data are at the same magnitude, generating the target geological environment data that meets the analysis requirements, thereby improving the data quality and ensuring the accuracy and reliability of subsequent analysis.
[0033] Constructing the geological data fusion model, and performing fusion processing on the target geological environment data based on the geological data fusion model to generate the corresponding fused geological environment data, specifically including: Setting the fusion category dataset as , where represents the -th fusion category in the fusion category dataset , represents the total number of fusion categories in the fusion category dataset ; Based on the geological data fusion model, calculate the posterior probability of the fusion category under all target geological environment data . The corresponding calculation formula is as follows: In the formula, represents the -th fusion category in the fusion category dataset ; represents the target geological environment data; represents the total number of target geological environment data; represents the posterior probability of the fusion category under all target geological environment data , that is, the probability of the occurrence of the fusion category under all target geological environment data ; represents the likelihood probability, that is, the probability of the occurrence of all target geological environment data under the condition that the fusion category occurs; represents the prior probability of the fusion category ; represents the probability of the joint occurrence of all target geological environment data .
[0034] The calculation formula of the likelihood probability is as follows: In the formula, represents the fused category dataset the th fused category; represents the target geological environment data; represents the total number of the target geological environment data; represents the likelihood probability, that is, the probability that all the target geological environment data appear under the condition that the fused category occurs; represents the probability that the th target geological environment data appears under the condition that the fused category occurs; The expression of the posterior probability is as follows: In the formula, represents the fused category dataset the th fused category; represents the target geological environment data; represents the total number of the target geological environment data; represents the posterior probability of the fused category under all the target geological environment data conditions, that is, the probability that the fused category occurs under all the target geological environment data conditions; represents the probability that the th target geological environment data appears under the condition that the fused category occurs; represents the prior probability of the fused category ; represents the probability of the joint appearance of all the target geological environment data ; Determine the fused category corresponding to the maximum value of the posterior probability as the target fused category, and perform fusion processing on the target geological environment data based on the target fused category to generate the corresponding fused geological environment data.
[0035] Among them, first, a fused category dataset can be set, which contains multiple fused categories. Then, a geological data fusion model can be used to calculate the posterior probability of each fused category under all the target geological environment data conditions.
[0036] Specifically, the calculation of the posterior probability is based on Bayes' theorem. By combining the likelihood probability and the prior probability, the occurrence probability of each fused category under the given data conditions can be obtained. By comparing the posterior probability values of different fused categories, the fused category corresponding to the maximum posterior probability can be used as the target fused category.
[0037] Based on this target fused category, the target geological environment data can be fused to generate the corresponding fused geological environment data.
[0038] The construction of the fused geological disaster prediction model and the disaster prediction of the fused geological environment data based on the fused geological disaster prediction model to generate the corresponding geological disaster risk level specifically include: Extract the fused geological environment features corresponding to the fused geological environment data, and perform prediction classification on the fused geological environment features based on the fused geological disaster prediction model. The corresponding optimization problem is as follows: In the formula, represents the weight vector of the -th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the -th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the -th fused geological environment feature is linearly inseparable in the -th support vector machine; represents the regularization parameter, which is used to control the trade-off between the classification margin and the classification error; represents the total number of fused geological environment features; represents the operation of taking the minimum value; ∑ represents the summation symbol.
[0039] The constraint conditions corresponding to the optimization problem are as follows: In the formula, represents the predicted class label corresponding to the -th fused geological environment feature; represents the -th fused geological environment feature; represents the weight vector of the -th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the -th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the th slack variable when the integrated geological environment feature is linearly inseparable in the th support vector machine; represents the total number of integrated geological environment features; Based on the predicted classification result of the integrated geological environment feature, determine the geological disaster risk level corresponding to the integrated geological environment data.
[0040] It should be noted that first, the key features in the integrated geological environment data can be extracted, and these features comprehensively reflect the influence of various factors such as geological structure, topography, climate conditions, and human activities on the possibility of geological disasters.
[0041] Subsequently, based on the constructed integrated geological disaster prediction model, these integrated geological environment features can be classified and predicted to determine the geological disaster risk level corresponding to the integrated geological environment data.
[0042] In the process of prediction classification, the support vector machine (SVM) algorithm can be used to construct the corresponding optimization problem. And this optimization problem needs to meet the corresponding constraint conditions to ensure that the integrated geological disaster prediction model can still maintain a certain generalization ability when dealing with linearly inseparable data.
[0043] Finally, based on the above optimization problem and constraint conditions, the predicted classification result of the integrated geological environment feature can be obtained, and then the geological disaster risk level corresponding to the integrated geological environment data can be accurately determined, which is helpful for the early warning and prevention of geological disasters.
[0044] The geological disaster early warning information includes the type of geological disaster, the early warning level of geological disaster, the influence scope of geological disaster, and the countermeasures for geological disaster.
[0045] In practical applications, the geological disaster early warning information can comprehensively cover the key elements of geological disasters. Specifically, this early warning information clarifies the type of geological disaster, such as landslide, debris flow, collapse, and ground subsidence. Since different types of disasters have different formation mechanisms and influence characteristics, this early warning information can detail different geological disaster early warning levels, such as extremely serious, serious, relatively large, and general, according to the possibility of disaster occurrence and the degree of potential harm, so as to take corresponding countermeasures.
[0046] In addition, this early warning information also accurately defines the influence scope of geological disasters. Through the application of geographic information system, the specific areas that may be affected by the disaster are drawn, providing accurate guidance for personnel evacuation and material transfer.
[0047] Finally, the early warning information details the geological disaster response measures, which specifically include multiple aspects such as pre-disaster prevention preparations, emergency responses during disasters, and post-disaster recovery and reconstruction, so as to minimize the losses and impacts brought by geological disasters.
[0048] Embodiment 2 As Figure 3 shown, a geological disaster early warning system based on multi-source data fusion technology, the early warning system includes: A data acquisition module for collecting original geological environment data of a target geological disaster-prone area through disaster sensors; A data preprocessing module for preprocessing the original geological environment data to generate corresponding target geological environment data; A fusion processing module for constructing a geological data fusion model and performing fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fusion geological environment data; A disaster prediction module for constructing a fusion geological disaster prediction model and performing disaster prediction on the fusion geological environment data based on the fusion geological disaster prediction model to generate corresponding geological disaster risk levels; An early warning sending module for determining corresponding geological disaster early warning information according to the geological disaster risk level and sending it to the management terminal.
[0049] Through the introduction of the above embodiments, the present invention uses a geological disaster early warning method and system based on multi-source data fusion technology. Through disaster sensors, it collects original geological environment data of a target geological disaster-prone area; preprocesses the original geological environment data to generate corresponding target geological environment data; constructs a geological data fusion model and performs fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fusion geological environment data; constructs a fusion geological disaster prediction model and performs disaster prediction on the fusion geological environment data based on the fusion geological disaster prediction model to generate corresponding geological disaster risk levels; determines corresponding geological disaster early warning information according to the geological disaster risk level and sends it to the management terminal, so as to integrate geological disaster data from different sources, formats, and types, solve the problem of insufficient accuracy of existing geological disaster early warning methods, and improve the accuracy and timeliness of geological disaster early warning.
[0050] The present invention can effectively integrate the collected geological environment data through a geological data fusion model based on multi-source data fusion technology, improving the accuracy and reliability of geological disaster early warning. At the same time, it can achieve real-time monitoring and early warning of geological disasters by integrating a geological disaster prediction model, generating corresponding geological disaster risk levels and early warning information, and then transmitting the early warning information to geological disaster management personnel to achieve the timely transmission of early warning information and provide sufficient time for subsequent emergency responses. The present invention can realize the intelligent fusion and processing of complex multi-source data, improving the intelligent level of the geological disaster early warning system.
[0051] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.
[0052] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium capable of carrying or storing data.
[0053] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.
Claims
1. A geological disaster early warning method based on multi-source data fusion technology, characterized in that, The early warning method includes: Collecting original geological environment data of a target geological disaster-prone area through disaster sensors; Performing preprocessing operations on the original geological environment data to generate corresponding target geological environment data; Constructing a geological data fusion model, and performing fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data; Constructing a fused geological disaster prediction model, and performing disaster prediction on the fused geological environment data based on the fused geological disaster prediction model to generate corresponding geological disaster risk levels; Determining corresponding geological disaster early warning information according to the geological disaster risk level and sending it to the management terminal; The constructing a geological data fusion model, and performing fusion processing on the target geological environment data based on the geological data fusion model to generate corresponding fused geological environment data specifically includes: Set the fused category dataset as , where represents the fused category dataset the th fused category, represents the total number of fused categories in the fused category dataset ; Calculate the fusion category based on the geological data fusion model Among all the target geological environment data The posterior probability under the conditions, and the corresponding calculation formula is as follows: In the formula, represents the fused category dataset the th fused category; represents the target geological environment data; represents the total quantity of the target geological environment data; represents the fused category under the condition of all target geological environment data i.e., the posterior probability of the fused category under the condition of all target geological environment data occurring; represents the likelihood probability, i.e., the probability of all target geological environment data appearing under the condition that the fused category occurs; represents the prior probability of the fused category ; represents the probability of all target geological environment data appearing jointly; The likelihood probability is calculated as follows: In the formula, represents the fused category dataset in the th fused category; represents the target geological environment data; represents the total number of the target geological environment data; represents the likelihood probability, that is, the probability that all target geological environment data appear under the condition that the fused category occurs; represents the probability that the th target geological environment data appears under the condition that the fused category occurs; The posterior probability is expressed as: In the formula, represents the fused category dataset The th fused category; represents the target geological environment data; represents the total number of the target geological environment data; represents the fused category The posterior probability under all target geological environment data conditions, that is, under all target geological environment data conditions, the probability of the occurrence of the fused category ; represents the probability of the occurrence of the th target geological environment data under the condition that the fused category occurs; represents the prior probability of the fused category ; represents the probability of the joint occurrence of all target geological environment data ; Determining the fusion category corresponding to the maximum value of the posterior probability as the target fusion category, and performing fusion processing on the target geological environment data based on the target fusion category to generate corresponding fused geological environment data.
2. The geological disaster early warning method based on multi-source data fusion technology according to claim 1, wherein, The disaster sensors are deployed in the geological disaster-prone area, and the disaster sensors include a rain gauge sensor, a displacement gauge sensor, a piezometer sensor, and an inclinometer sensor.
3. A geological disaster warning method based on multi-source data fusion technology according to claim 1, characterized in that, The performing preprocessing operations on the original geological environment data to generate corresponding target geological environment data specifically includes: Performing data cleaning on the original geological environment data to remove noise and outliers, and generating corresponding first geological environment data; Performing data format conversion on the first geological environment data to generate corresponding second geological environment data; Performing standardization processing on the second geological environment data to generate corresponding target geological environment data.
4. A geological disaster warning method based on multi-source data fusion technology according to claim 1, characterized in that, The constructing a fused geological disaster prediction model, and performing disaster prediction on the fused geological environment data based on the fused geological disaster prediction model to generate corresponding geological disaster risk levels specifically includes: Extracting the fused geological environment features corresponding to the fused geological environment data, and performing predictive classification on the fused geological environment features based on the fused geological disaster prediction model. The corresponding optimization problem is as follows: Wherein, represents the weight vector of the -th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the -th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the -th slack variable when the fused geological environment features are linearly inseparable in the -th support vector machine; represents the regularization parameter, which is used to control the trade-off between the classification margin and the classification error; represents the total number of the fused geological environment features; represents the minimum value operation; ∑ represents the summation symbol.
5. A geological disaster warning method based on multi-source data fusion technology according to claim 4, characterized in that, The constraint conditions corresponding to the optimization problem are as follows: In the formula, represents the prediction class label corresponding to the th fused geological environment feature; represents the th fused geological environment feature; represents the th weight vector of the support vector machine, which is used to determine the direction of the classification hyperplane; represents the th bias term of the support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the th slack variable when the th fused geological environment feature is linearly inseparable in the th support vector machine; represents the total number of fused geological environment features; Based on the predictive classification result of the fused geological environment features, determining the geological disaster risk level corresponding to the fused geological environment data.
6. The geological disaster warning method based on multi-source data fusion technology according to claim 1, characterized in that The geological disaster early warning information includes the type of geological disaster, the early warning level of geological disaster, the affected range of geological disaster, and the countermeasures for geological disaster.
7. A geological disaster early warning system based on multi-source data fusion technology, which is applied to a geological disaster early warning method based on multi-source data fusion technology according to any one of claims 1-6. The early warning system includes: A data acquisition module, which is used to collect original geological environment data of a target geological disaster-prone area through disaster sensors; A data preprocessing module, which is used to perform preprocessing operations on the original geological environment data to generate corresponding target geological environment data; The fusion processing module is used to construct a geological data fusion model, and based on the geological data fusion model, perform fusion processing on the target geological environment data to generate corresponding fused geological environment data; The disaster prediction module is used to construct a fused geological disaster prediction model, and based on the fused geological disaster prediction model, perform disaster prediction on the fused geological environment data to generate corresponding geological disaster risk levels; The early warning sending module is used to determine corresponding geological disaster early warning information according to the geological disaster risk level and send it to the management terminal.