Geological disaster risk early warning method and system based on environmental meteorological factors

By constructing a comprehensive geological disaster risk assessment model and virtual disaster scenarios, the problems of single data and simple evaluation model of geological disaster warning system in the existing technology are solved, and comprehensive evaluation and high resolution of factors such as meteorology, geological structure, and vegetation coverage are achieved. Virtual simulation improves the accuracy and timeliness of geological disaster warnings.

CN118941102APending Publication Date: 2024-11-12GUIZHOU POWER GRID CO LTD
View PDF 0 Cites 8 Cited by

Patent Information

Application Number
CN202410846428.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing geological disaster warning system has the problems of single data dimensions, simple evaluation models, and inconspicuous early warnings, making it difficult to provide comprehensive, accurate and intuitive geological disaster warnings.

Method used

Using geological disaster risk warning methods based on environmental meteorological factors, a comprehensive geological disaster risk assessment model is constructed by collecting multiple data (meteorological data, geological structure data, vegetation coverage data, surface deformation data, surface gas emission data, etc.), and using confrontation Generate network to build virtual disaster scenarios and conduct geological disaster warnings.

Benefits of technology

A comprehensive assessment of multi-dimensional data has been achieved, geological disaster prediction capabilities have been enhanced, high-resolution virtual simulation tools have been provided, and the accuracy of early warnings and public emergency preparedness have been improved, which has significantly improved the timeliness and accuracy of geological disaster warnings have been improved. and effectiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941102A_ABST
    Figure CN118941102A_ABST
Patent Text Reader

Abstract

The invention discloses a geological disaster risk early warning method and system based on environmental meteorological factors, and relates to the technical field of disaster early warning. Comprising the steps of collecting data related to geological disasters, and constructing a geological disaster risk assessment model; collecting geological disaster historical records, and constructing a virtual disaster scene based on the generative adversarial network according to the data related to the geological disaster and the geological disaster historical records; and according to the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scene based on the generative adversarial network, performing geological disaster early warning. Through multi-source data fusion, comprehensive assessment and high-resolution virtual simulation, a complete system from risk assessment to early warning release is provided, and the timeliness, accuracy and effectiveness of geological disaster early warning are remarkably improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of disaster early warning technology, and in particular to a method and system for early warning of geological disaster risks based on environmental meteorological factors. Background Art

[0002] With the continuous development of power transmission line monitoring technology and the increasing amount of information related to the operation of power transmission lines, the construction of a natural disaster monitoring and early warning system for power grids is particularly important. The temporal and spatial distribution characteristics of regional natural disasters, the vulnerability of the disaster-bearing body of the power grid system, the law of disaster coupling damage, risk assessment models and risk zoning, early warning models, etc., are used to establish a complete monitoring and early warning system for the power grid, improve the power grid system's ability to resist natural disasters, provide timely early warnings, accurately and comprehensively monitor the impact of various meteorological disasters on power grid equipment, and take effective preventive measures against various geological disasters in a timely and effective manner to minimize disaster losses. Summary of the invention

[0003] In view of the problems that the existing geological disaster warning has single data dimension, simple evaluation model and the warning is not intuitive enough, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is to provide a more comprehensive geological disaster risk assessment model, construct a virtual disaster scene, intuitively display possible disaster impacts and evacuation information, and provide a more comprehensive, accurate and intuitive geological disaster early warning solution.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In the first aspect, an embodiment of the present invention provides a geological disaster risk warning method based on environmental meteorological factors, which includes collecting data related to geological disasters and constructing a geological disaster risk assessment model; collecting historical records of geological disasters, and constructing a virtual disaster scenario based on an adversarial generative network based on the data related to geological disasters and the historical records of geological disasters; and conducting geological disaster warnings based on the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generative network.

[0007] As a preferred solution of the geological disaster risk warning method based on environmental meteorological factors of the present invention, the data related to geological disasters include meteorological data, geological structure data, vegetation coverage data, surface deformation data, surface gas emission data and hydrological data.

[0008] As a preferred solution of the geological disaster risk early warning method based on environmental meteorological factors of the present invention, the construction of a geological disaster risk assessment model includes: rainfall directly affects soil moisture, thereby increasing the risk of geological disasters, temperature has an important influence on the physical properties of soil and rock, and soil moisture is an important factor in geological disasters. Combined with rainfall, temperature and soil moisture, a comprehensive meteorological factor is obtained. The calculation formula of the comprehensive meteorological factor is as follows:

[0009]

[0010] Among them, M(t) represents the comprehensive meteorological factor, R(τ) represents rainfall, T(τ) represents temperature, S(τ) represents soil moisture, α1 represents the adjustment parameter, t0 represents the starting time, t represents the time variable, and τ represents the integral variable. Double integration is used to capture the spatial distribution of geological structures, and the influence of geological structure factors on specific points is expressed in the form of inverse distance. The calculation formula of geological structure factors is as follows:

[0011]

[0012] Among them, G(x,y) represents the geological structure factor, G(ξ,η) represents the geological structure intensity of point (ξ,η), (ξ,η) represents the coordinates of any point in the integral area, and A represents the integral area. The vegetation coverage rate is normalized and the complement value is taken to represent the positive impact of vegetation coverage on disaster risk. The calculation formula of vegetation coverage rate is as follows:

[0013]

[0014] Among them, V(x,y) represents the vegetation coverage rate, represents the normalized vegetation coverage, It represents the complementary value of vegetation coverage, reflecting that the risk in areas with sparse vegetation is higher. (x, y) represents the spatial position. The second-order partial derivative is used to capture the intensity and trend of surface deformation. The calculation formula of surface deformation is as follows:

[0015]

[0016] Among them, L(x,y) represents the surface deformation, and (x,y) represents the spatial position. A composite function is used to capture the complex relationship between the two. The calculation formula of the spatial risk factor is as follows:

[0017]

[0018] Among them, S(x,y) represents the spatial risk factor, represents the normalized vegetation coverage, (x, y) represents the spatial position, L(x, y) represents the surface deformation, and β represents the adjustment parameter. A complex summation function is used to represent the impact of emissions at different points on a specific point, where the inverse relationship of the square of the distance is used to represent the spatial attenuation of the emission gas. The gas emission factor calculation formula is as follows:

[0019]

[0020] Among them, P(x,y,t) represents the gas emission factor, which represents the comprehensive gas emission intensity of point (x,y) at time t, taking into account the impact of gas emissions from all monitoring points on the point, and n represents the total number of monitoring points. Indicates the i-th monitoring point (x i ,y i ) is the normalized gas emission at time t; the cumulative impact of meteorological factors and groundwater level changes over time is integrated to capture the long-term impact of meteorological conditions and groundwater level changes on geological hazards; the geological structural factors and comprehensive spatial risk factors are superimposed to capture the impact of geological and geographic spatial characteristics on geological hazard risks; the additional effect of surface gas emissions on geological hazard risks is introduced to construct a geological hazard risk assessment model that comprehensively considers the above factors. The formula of the geological hazard risk assessment model is as follows:

[0021]

[0022] Among them, R(x,y,t) represents the geological hazard risk assessment value, M(t) represents the comprehensive meteorological factor, D(t) represents the groundwater level change, γ represents the adjustment factor, G(x,y) represents the geological structure factor, S(x,y) represents the spatial risk factor, P(x,y,t) represents the gas emission factor, and t represents the current time.

[0023] As a preferred solution of the geological disaster risk warning method based on environmental meteorological factors of the present invention, wherein: constructing a virtual disaster scene based on a generative adversarial network includes: constructing a generative adversarial network, defining the goals of the generator and the discriminator; designing the generator and the discriminator; initializing the network, including weight initialization and hyperparameter setting, and defining the loss function; dividing the training set and the test set, and performing alternating training; evaluating the quality of the generated image, and performing parameter tuning; creating a virtual environment, and simulating a dynamic disaster process.

[0024] As a preferred solution of the geological disaster risk warning method based on environmental meteorological factors of the present invention, wherein: the input layer of the generator receives random noise, the hidden layer of the generator includes a fully connected layer, a convolutional transpose layer and an adaptive instance normalization, and the output layer of the generator uses a Tanh activation function to generate a final disaster scene image, and the output dimension is H×W×C; the input layer of the discriminator receives a real or generated disaster scene image, the hidden layer of the discriminator includes a convolution layer and a spatial attention mechanism, the convolution layer extracts image features through multiple convolution layers, and the LeakyReLU activation function is applied after each convolution layer. The spatial attention mechanism adds a spatial attention module to highlight the features of key areas in the disaster scene, and the output layer of the discriminator uses a Sigmoid activation function to output the authenticity probability of the image, ranging from 0 to 1.

[0025] As a preferred solution of the geological disaster risk warning method based on environmental meteorological factors of the present invention, alternating training means that in each training cycle, the discriminator is first fixed and the generator is trained; then the generator is fixed and the discriminator is trained; in one training iteration, a batch of real images is sampled from the real data set, a batch of random noise is sampled from the noise distribution, the corresponding virtual disaster scene is generated, the real image and the generated image are used to train the discriminator, the weight of the discriminator is updated, the generated image is used to train the generator, and the weight of the generator is updated.

[0026] As a preferred solution of the geological disaster risk early warning method based on environmental meteorological factors of the present invention, the geological disaster early warning is carried out according to the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scene based on the adversarial generation network, including: when R norm When R is less than 0.3, the risk level of geological disasters is judged to be low risk, and early warning information is sent to relevant departments and the public that may be affected, and low-intensity virtual disaster scenarios are generated and displayed for risk awareness training; when 0.3≤R norm When R is less than or equal to 0.7, the risk level of geological disasters is judged to be medium risk, and early warning information is sent to relevant departments. A virtual disaster scene of medium intensity is generated and displayed for risk communication and emergency drills. At the same time, the emergency response plan is activated to prepare evacuation and rescue resources. norm When the risk level of geological disasters is greater than 0.7, it is judged that the risk level of geological disasters is high, and an emergency warning is issued to all relevant departments and the public. A high-intensity virtual disaster scenario is generated and displayed for evacuation route planning and rescue strategy formulation. At the same time, the evacuation procedures and emergency response measures are immediately initiated.

[0027] In the second aspect, an embodiment of the present invention provides a geological disaster risk warning system based on environmental meteorological factors, which includes a model construction module for collecting data related to geological disasters and constructing a geological disaster risk assessment model; a scenario generation module for collecting geological disaster historical records and constructing a virtual disaster scenario based on an adversarial generation network based on the data related to geological disasters and the geological disaster historical records; and an early warning module for providing geological disaster early warning based on the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generation network.

[0028] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the geological disaster risk warning method based on environmental meteorological factors as in the first aspect of the present invention are implemented.

[0029] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program instructions are executed by a processor, the steps of the geological disaster risk warning method based on environmental meteorological factors as in the first aspect of the present invention are implemented.

[0030] The beneficial effects of the present invention are as follows: comprehensive collection of multi-dimensional data and construction of a geological disaster risk assessment model realizes a comprehensive assessment of factors such as meteorology, geological structure, vegetation cover, surface deformation and gas emissions, and enhances the model's ability to accurately predict geological disasters; using geological disaster historical records and multi-dimensional data, constructing a virtual disaster scene based on an adversarial generation network, realizing an integrated process from data collection and processing to high-resolution virtual simulation, and providing an effective tool for disaster warning and emergency drills; by continuously calculating risk assessment values, generating corresponding warning measures and virtual disaster scenes according to risk levels, dynamically adjusting warning levels and emergency response plans, and improving the accuracy of warnings and the public's emergency preparedness capabilities. Overall, the present invention provides a complete system from risk assessment to warning release through multi-source data fusion, comprehensive assessment and high-resolution virtual simulation, which significantly improves the timeliness, accuracy and effectiveness of geological disaster warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 This is a flow chart of the geological disaster risk early warning method based on environmental meteorological factors.

[0033] Figure 2 The schematic diagram of the structure of the computer equipment for the geological disaster risk early warning method based on environmental meteorological factors. DETAILED DESCRIPTION

[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0035] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0036] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0037] Example 1

[0038] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a geological disaster risk early warning method based on environmental meteorological factors, comprising:

[0039] S1: Collect data related to geological disasters and build a geological disaster risk assessment model.

[0040] Specifically, data related to geological disasters include meteorological data, geological structure data, vegetation cover data, surface deformation data, surface gas emission data and hydrological data.

[0041] Furthermore, the effects of rainfall, temperature and soil moisture on geological disasters are comprehensively considered. Rainfall will directly affect soil moisture, thereby increasing the risk of geological disasters. Temperature has an important influence on the physical properties of soil and rock, such as thermal expansion and contraction. Soil moisture is an important factor in causing geological disasters such as landslides and mudslides. These three factors are combined with nonlinear functions in the form of integration, and the cumulative effects of these three factors on geological disasters are comprehensively considered to construct a comprehensive meteorological factor. The calculation formula of the comprehensive meteorological factor is as follows:

[0042]

[0043] Among them, M(t) represents the comprehensive meteorological factor, R(τ) represents rainfall, which will directly increase soil moisture content and may cause landslides or mudslides, T(τ) represents temperature, which affects the physical properties of soil and rock, S(τ) represents soil moisture, which directly reflects the degree of soil saturation, α1 represents the adjustment parameter, t0 represents the starting time, t represents the time variable, and τ represents the integral variable.

[0044] Furthermore, the geological structure factor represents the impact of the spatial distribution of geological features on the risk of geological hazards. In a region, the complexity of geological structures is different, and the potential impact on geological hazards is also different. Double integration is used to capture the spatial distribution of geological structures. Because geological features closer to the point have a greater impact on the point, the impact of geological structure factors on specific points is expressed in the form of inverse distance. The calculation formula of geological structure factors is as follows:

[0045]

[0046] Among them, G(x,y) represents the geological structure factor, which represents the geological structure strength of a point (x,y), G(ξ,η) represents the geological structure strength of the point (ξ,η), (ξ,η) represents the coordinates of any point in the integration area, and A represents the integration area.

[0047] Furthermore, the spatial risk factor comprehensively considers the impact of vegetation coverage and surface deformation on geological hazards. The level of vegetation coverage is directly related to soil retention and the stability of rock and soil, while surface deformation is a direct indication of the occurrence of geological hazards. A composite function is used to capture the complex relationship between the two, and a parameter is used to adjust the impact of surface deformation on the comprehensive risk.

[0048] Vegetation coverage has a significant impact on geological disasters. The more vegetation there is, the lower the risk. The vegetation coverage is normalized and the complementary value is taken to represent the positive impact of vegetation coverage on disaster risk. The calculation formula of vegetation coverage is as follows:

[0049]

[0050] Among them, V(x,y) represents the vegetation coverage rate, represents the normalized vegetation coverage, represents the complementary value of vegetation coverage, reflecting that areas with sparse vegetation have higher risks, and (x, y) represents the spatial location;

[0051] Surface deformation is a direct indicator of geological hazards. The second-order partial derivative is used to capture the intensity and trend of surface deformation. The calculation formula of surface deformation is as follows:

[0052]

[0053] Among them, L(x,y) represents the surface deformation, (x,y) represents the spatial position;

[0054] Furthermore, the spatial risk factor combines vegetation cover and surface deformation to reflect the impact of environmental conditions on geological hazards. A composite function is used to capture the complex relationship between the two. The calculation formula of the spatial risk factor is as follows:

[0055]

[0056] Among them, S(x,y) represents the spatial risk factor, represents the normalized vegetation coverage, (x, y) represents the spatial position, L(x, y) represents the surface deformation, and β represents the adjustment parameter used to adjust the influence of the deformation.

[0057] Furthermore, the surface gas emission factor is constructed to include surface gas emissions, especially radon gas, as an early warning signal of geological activities in the geological disaster assessment. A complex summation function is used to represent the impact of emissions at different points on a specific point, where the inverse relationship of the square of the distance is used to represent the spatial attenuation of the emission gas. The gas emission factor calculation formula is as follows:

[0058]

[0059] Among them, P(x,y,t) represents the gas emission factor, which represents the comprehensive gas emission intensity of point (x,y) at time t, taking into account the impact of gas emissions from all monitoring points on the point, and n represents the total number of monitoring points. Indicates the i-th monitoring point (x i ,y i ) is the normalized gas emission at time t.

[0060] Furthermore, the cumulative impact of meteorological factors and groundwater level changes over time is integrated to capture the long-term impact of meteorological conditions and groundwater level changes on geological hazards. The geological structural factors and the comprehensive spatial risk factors are superimposed to represent the inherent geological characteristics of the point and the influence of vegetation coverage and surface deformation, capturing the impact of geological and geographic spatial characteristics on geological hazard risks. The additional effect of surface gas emissions on geological hazard risks is introduced. This additional effect reflects the importance of surface gas emissions as an early warning signal for geological activities. Combining the above factors, a geological hazard risk assessment model that comprehensively considers the above factors is constructed. The formula of the geological hazard risk assessment model is as follows:

[0061]

[0062] Among them, R(x,y,t) represents the geological hazard risk assessment value, M(t) represents the comprehensive meteorological factor, D(t) represents the groundwater level change, γ represents the adjustment factor, which controls the attenuation or growth rate of the exponential function, G(x,y) represents the geological structure factor, S(x,y) represents the spatial risk factor, P(x,y,t) represents the gas emission factor, and t represents the current time.

[0063] Furthermore, each part of the formula is normalized to ensure that the value of R(x, y, t) is between 0 and 1, and R norm (R(x,y,t) after normalization).

[0064] S2: Collect historical records of geological disasters, and construct virtual disaster scenarios based on adversarial generative networks based on data related to geological disasters and historical records of geological disasters.

[0065] Specifically, meteorological data are collected, including daily or hourly data such as rainfall, temperature, humidity, wind speed, and wind direction; geological data are collected, including topography, soil type, geological structure, slope information, etc.; historical records of geological disasters are collected, and the time, location, type (such as landslide, mud-rock flow), scale, and impact range of geological disasters are collected through the historical geological disaster database. The above collected data are preprocessed.

[0066] Furthermore, a generative adversarial network is constructed to define the generator and discriminator. The goal of the generator is to generate realistic disaster scene images from random noise. The goal of the discriminator is to distinguish between real disaster scene images and generated virtual images.

[0067] Furthermore, the input layer of the generator receives random noise, and the hidden layer of the generator includes a fully connected layer, a convolutional transpose layer, and an adaptive instance normalization. The fully connected layer maps the noise vector to a high-dimensional space and applies the ReLU activation function. The convolutional transpose layer gradually upsamples through a series of convolutional transpose layers and batch normalization layers to improve the image resolution. The adaptive instance normalization adjusts the mean and standard deviation of the feature map according to the statistical information of the input noise vector, thereby generating a more diverse image. The output layer of the generator uses the Tanh activation function to generate the final disaster scene image, and the output dimension is H×W×C (height, width, and number of channels).

[0068] Furthermore, the input layer of the discriminator receives real or generated disaster scene images. The hidden layer of the discriminator includes a convolutional layer and a spatial attention mechanism. The convolutional layer extracts image features through multiple convolutional layers. The LeakyReLU activation function is applied after each convolution layer to avoid the gradient vanishing problem. The spatial attention mechanism adds a spatial attention module to highlight the features of key areas in the disaster scene and improve the discriminative ability of the discriminator. The output layer of the discriminator uses a Sigmoid activation function to output the authenticity probability of the image, ranging from 0 to 1.

[0069] Furthermore, the network is initialized, including weight initialization and hyperparameter setting. The hyperparameter setting includes setting the initial learning rate, batch size, number of training iterations, etc.

[0070] Preferably, the learning rate is set to 0.0002, the batch size is set to 64, and the number of training iterations is 1000.

[0071] Furthermore, the loss function is defined. The loss of the generator adopts adversarial loss so that the images generated by the generator can deceive the discriminator. The loss of the discriminator contains the losses of the real image and the generated image to ensure that the discriminator can correctly distinguish between the two.

[0072] Furthermore, the Adam optimizer was used, with the learning rate set to 0.0002 and momentum parameters β1 = 0.5, β2 = 0.999.

[0073] Furthermore, the preprocessed data is divided into a training set and a test set. The generator receives a random noise vector and generates a virtual disaster scene. The discriminator evaluates the authenticity of the generated image, and the generator optimizes the loss function by adjusting the weights. The discriminator receives the real disaster scene and the generated virtual scene, and adjusts the discriminator weights by calculating the loss of the real image and the fake image so that it can accurately distinguish between the two.

[0074] Furthermore, alternating training is performed. In each training cycle, the discriminator is first fixed and the generator is trained; then the generator is fixed and the discriminator is trained. In one training iteration, a batch of real images is sampled from the real dataset, a batch of random noise is sampled from the noise distribution, the corresponding virtual disaster scene is generated, the real images and the generated images are used to train the discriminator and update its weights, and the generated images are used to train the generator and update its weights.

[0075] Preferably, a layer-by-layer training method is adopted to first train low-resolution image generation, then gradually increase the image resolution, and optimize the generator and discriminator layer by layer, which helps to stabilize the training process and reduce the instability in high-resolution training. The gradient penalty term is introduced to ensure the stability of the discriminator's gradient and prevent gradient vanishing and gradient explosion.

[0076] Furthermore, the quality of the generated images is evaluated by the FID (Frechet Inception Distance) and IS (Inception Score) indicators, and the parameters are tuned.

[0077] Specifically, different meteorological conditions are input into the generator to output high-resolution disaster scene images. A virtual environment is created using Unity, the generated disaster scene is imported, simulation parameters (such as rainfall intensity, wind speed, etc.) are set, and dynamic disaster process simulation is performed. The actual geographical environment and meteorological factors are combined to simulate the occurrence and evolution of disasters.

[0078] S3: Conduct geological disaster warning based on the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generative network.

[0079] Specifically, the geological disaster risk assessment model is used to continuously calculate the risk assessment value R of each monitoring point. norm , when R norm When the first threshold (0.3) is less than the first threshold (0.3), the risk level of geological disasters is judged to be low risk. norm ≤ the second threshold (0.7), the risk level of geological disasters is judged to be medium risk. norm When the risk level of geological disasters is higher than the second threshold (0.7), the risk level of geological disasters is judged to be high risk. norm Trigger an early warning of the corresponding level.

[0080] Furthermore, based on the current and predicted meteorological conditions, the trained generative adversarial network is used to generate high-resolution virtual disaster scene images, and the generated images are imported into the Unity virtual environment to simulate the dynamic disaster process.

[0081] When the risk is low (yellow warning), warning information will be sent to relevant departments and the public that may be affected, and low-intensity virtual disaster scenarios will be generated and displayed for risk awareness training.

[0082] When the risk is medium (orange warning), warning information will be sent to relevant departments, and medium-intensity virtual disaster scenarios will be generated and displayed for risk communication and emergency drills. At the same time, emergency response plans will be activated to prepare evacuation and rescue resources.

[0083] When at high risk (red alert), emergency warnings are issued to all relevant departments and the public, and high-intensity virtual disaster scenarios are generated and displayed for evacuation route planning and rescue strategy formulation, and evacuation procedures and emergency response measures are immediately initiated.

[0084] Preferably, the risk assessment value R is continuously updated based on real-time monitoring data.norm ,When the risk level changes, the warning level and corresponding measures are adjusted in time, the latest meteorological forecast data is used, the virtual disaster scenario is updated, and the possible trend of disaster evolution is provided.

[0085] Preferably, warning information is released through multiple channels, including mobile phone text messages, radio, television, social media, etc., and images or videos of virtual disaster scenes are released to intuitively display possible disaster impacts and provide evacuation routes and safe area information based on virtual scenes.

[0086] Preferably, record the circumstances of each warning triggering, including risk assessment values, virtual scene characteristics, actual disaster occurrence, etc., regularly analyze the accuracy and timeliness of warnings, optimize risk assessment models and warning thresholds, collect user feedback on virtual disaster scenes, and continuously improve the adversarial generative network and Unity simulation effects.

[0087] Furthermore, this embodiment also provides a geological disaster risk early warning system based on environmental meteorological factors, including:

[0088] Model building module, used to collect data related to geological hazards and build a geological hazard risk assessment model;

[0089] The scenario generation module is used to collect historical records of geological disasters and construct a virtual disaster scenario based on a generative adversarial network based on data related to geological disasters and historical records of geological disasters;

[0090] The early warning module is used to carry out geological disaster early warning according to the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generative network.

[0091] This embodiment also provides a computer device, which is suitable for the case of a geological disaster risk warning method based on environmental meteorological factors, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the geological disaster risk warning method based on environmental meteorological factors proposed in the above embodiment.

[0092] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0093] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for early warning of geological disaster risks based on environmental meteorological factors as proposed in the above embodiment is implemented.

[0094] In summary, the comprehensive collection of multi-dimensional data and the construction of a geological disaster risk assessment model have achieved a comprehensive assessment of factors such as meteorology, geological structure, vegetation cover, surface deformation and gas emissions, and enhanced the model's ability to accurately predict geological disasters; using geological disaster historical records and multi-dimensional data, a virtual disaster scene based on an adversarial generation network is constructed, realizing an integrated process from data collection and processing to high-resolution virtual simulation, providing an effective tool for disaster warning and emergency drills; by continuously calculating risk assessment values, generating corresponding warning measures and virtual disaster scenes according to risk levels, and dynamically adjusting warning levels and emergency response plans, the accuracy of warnings and the public's emergency preparedness capabilities are improved. Overall, the present invention provides a complete system from risk assessment to warning release through multi-source data fusion, comprehensive assessment and high-resolution virtual simulation, which significantly improves the timeliness, accuracy and effectiveness of geological disaster warnings.

[0095] Example 2

[0096] Reference Figure 1-2 , which is the second embodiment of the present invention, and this embodiment provides a geological disaster risk early warning method based on environmental meteorological factors. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0097] Table 1 Geological hazard risk assessment experimental data table

[0098]

[0099] Specifically, from the data in the table above, it can be seen that when rainfall, soil moisture and surface deformation increase, the risk assessment value also increases. For example, from June 1 to June 7, 2023, rainfall increased from 0mm to 30mm, soil moisture increased from 45% to 60%, surface deformation increased from 0.01mm to 0.04mm, and the risk assessment value increased from 0.35 to 0.55. This shows that as these influencing factors increase, the risk of geological disasters also increases.

[0100] Furthermore, geological structure factors and gas emission factors also have a significant impact on the risk assessment value. The geological structure factor reflects the complexity and intensity of the geological structure. The larger its value, the more complex the geological structure and the greater the risk of geological disasters. For example, on June 6 and June 7, 2023, the geological structure factors were 0.59 and 0.6, respectively, and the gas emission factors were 0.33 and 0.36, respectively. The corresponding risk assessment values ​​were 0.48 and 0.55, respectively, indicating that the increase in geological structure complexity and gas emission intensity will lead to an increase in the risk of geological disasters.

[0101] In summary, the comprehensive calculation of meteorological factors, geological structural factors, spatial risk factors and gas emission factors can reflect the risks of geological disasters more comprehensively and accurately.

[0102] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A geological disaster risk early warning method based on environmental meteorological factors, characterized by: include, Collect data related to geological hazards and build a geological hazard risk assessment model; Collect historical records of geological disasters, and construct virtual disaster scenarios based on adversarial generative networks based on data related to geological disasters and historical records of geological disasters; Geological disaster warning is carried out according to the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generative network.

2. The geological disaster risk early warning method based on environmental meteorological factors according to claim 1 is characterized in that: The data related to geological disasters include meteorological data, geological structure data, vegetation coverage data, surface deformation data, surface gas emission data and hydrological data.

3. The geological disaster risk early warning method based on environmental meteorological factors as claimed in claim 2 is characterized by: The construction of the geological disaster risk assessment model includes: Precipitation will directly affect soil moisture, thereby increasing the risk of geological disasters. Temperature has an important impact on the physical properties of soil and rock. Soil moisture is an important factor in geological disasters. Combining rainfall, temperature and soil moisture, we can get a comprehensive meteorological factor. The calculation formula of the comprehensive meteorological factor is as follows: Among them, M(t) represents the comprehensive meteorological factor, R(τ) represents rainfall, T(τ) represents temperature, S(τ) represents soil moisture, α1 represents the adjustment parameter, t0 represents the starting time, t represents the time variable, and τ represents the integral variable; Double integration is used to capture the spatial distribution of geological structures. The influence of geological structure factors on specific points is expressed in the form of inverse distance. The calculation formula of geological structure factors is as follows: Among them, G(x,y) represents the geological structural factor, G(ξ,η) represents the geological structural strength of the point (ξ,η), (ξ,η) represents the coordinates of any point in the integration area, and A represents the integration area; The vegetation coverage rate is normalized and the complementary value is taken to represent the positive impact of vegetation coverage on disaster risk. The calculation formula of vegetation coverage rate is as follows: Among them, V(x,y) represents the vegetation coverage rate, represents the normalized vegetation coverage, represents the complementary value of vegetation coverage, reflecting that areas with sparse vegetation have higher risks, and (x, y) represents the spatial location; The second-order partial derivatives are used to capture the intensity and trend of the surface deformation. The surface deformation is calculated as follows: Among them, L(x,y) represents the surface deformation, (x,y) represents the spatial position; Using a composite function to capture the complex relationship between the two, the calculation formula of the spatial risk factor is as follows: Among them, S(x,y) represents the spatial risk factor, represents the normalized vegetation coverage, (x, y) represents the spatial position, L(x, y) represents the surface deformation, and β represents the adjustment parameter; A complex summation function is used to represent the impact of emissions at different points on a specific point, where the inverse relationship of the square of the distance is used to represent the spatial attenuation of the emission gas. The gas emission factor is calculated as follows: Among them, P(x,y,t) represents the gas emission factor, which represents the comprehensive gas emission intensity of point (x,y) at time t, taking into account the impact of gas emissions from all monitoring points on the point, and n represents the total number of monitoring points. Indicates the i-th monitoring point (x i ,y i ) normalized gas emissions at time t; The cumulative impact of meteorological factors and groundwater level changes over time is integrated to capture the long-term impact of meteorological conditions and groundwater level changes on geological hazards. The geological structural factors and comprehensive spatial risk factors are superimposed to capture the impact of geological and geographic spatial characteristics on geological hazard risks. The additional effect of surface gas emissions on geological hazard risks is introduced to construct a geological hazard risk assessment model that comprehensively considers the above factors. The formula of the geological hazard risk assessment model is as follows: Among them, R(x,y,t) represents the geological hazard risk assessment value, M(t) represents the comprehensive meteorological factor, D(t) represents the groundwater level change, γ represents the adjustment factor, G(x,y) represents the geological structure factor, S(x,y) represents the spatial risk factor, P(x,y,t) represents the gas emission factor, and t represents the current time.

4. The geological disaster risk early warning method based on environmental meteorological factors according to claim 3 is characterized in that: The construction of a virtual disaster scenario based on a generative adversarial network includes: Build a generative adversarial network and define the goals of the generator and discriminator; Design the generator and discriminator; Initialize the network, including weight initialization and hyperparameter setting, and define the loss function; Divide the training set and test set, and perform alternating training; Evaluate the quality of generated images and perform parameter tuning; Create a virtual environment to simulate dynamic disaster processes.

5. The geological disaster risk early warning method based on environmental meteorological factors according to claim 4 is characterized in that: The input layer of the generator receives random noise, the hidden layer of the generator includes a fully connected layer, a convolutional transpose layer, and an adaptive instance normalization, and the output layer of the generator uses a Tanh activation function to generate the final disaster scene image, and the output dimension is H×W×C; The input layer of the discriminator receives real or generated disaster scene images. The hidden layer of the discriminator includes a convolution layer and a spatial attention mechanism. The convolution layer extracts image features through multiple convolution layers. The LeakyReLU activation function is applied after each convolution layer. The spatial attention mechanism adds a spatial attention module to highlight the features of key areas in the disaster scene. The output layer of the discriminator uses a Sigmoid activation function to output the authenticity probability of the image, ranging from 0 to 1.

6. The geological disaster risk early warning method based on environmental meteorological factors according to claim 5 is characterized in that: The alternating training means that in each training cycle, the discriminator is first fixed and the generator is trained; Then fix the generator and train the discriminator. In one training iteration, sample a batch of real images from the real dataset and a batch of random noise from the noise distribution to generate the corresponding virtual disaster scenes. Use the real images and generated images to train the discriminator and update the weight of the discriminator. Use the generated images to train the generator and update the weight of the generator.

7. The geological disaster risk early warning method based on environmental meteorological factors according to claim 6 is characterized in that: The geological disaster early warning according to the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generation network includes: When R norm When the risk level of geological disasters is less than the first threshold, the risk level of geological disasters is judged to be low, and early warning information is sent to relevant departments and the public that may be affected, and low-intensity virtual disaster scenarios are generated and displayed for risk awareness training; When the first threshold ≤ R norm When the risk level of geological disasters is less than or equal to the second threshold, it is judged that the risk level of geological disasters is medium risk and a report is sent to the relevant departments. Early warning information, generating and displaying medium-intensity virtual disaster scenarios for risk communication and emergency drills, while activating emergency response plans and preparing evacuation and rescue resources; When R norm >When the second threshold is reached, the risk level of geological disasters is judged to be high, and an emergency warning is issued to all relevant departments and the public. A high-intensity virtual disaster scenario is generated and displayed for evacuation route planning and rescue strategy formulation, and the evacuation procedures and emergency response measures are immediately initiated.

8. A geological disaster risk early warning system based on environmental meteorological factors, based on the geological disaster risk early warning method based on environmental meteorological factors according to any one of claims 1 to 7, characterized in that: Also includes, Model building module, used to collect data related to geological hazards and build a geological hazard risk assessment model; The scenario generation module is used to collect historical records of geological disasters and construct virtual disaster scenarios based on adversarial generative networks based on data related to geological disasters and historical records of geological disasters; The early warning module is used to carry out geological disaster early warning according to the geological disaster risk assessment value of the geological disaster risk assessment model and the virtual disaster scenario based on the adversarial generative network.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the geological disaster risk early warning method based on environmental meteorological factors described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the geological disaster risk early warning method based on environmental meteorological factors described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Vehicle-mounted geological disaster early warning system and method based on environmental perception

    CN119360555A

  • Intelligent geological disaster risk assessment method and system

    CN119624141A

  • Intelligent energy management method and device for emergency energy vehicle and storage medium

    CN119821136A

  • Intelligent Energy Management Method, Device and Storage Medium for Emergency Energy Vehicles

    CN119821136B

  • Multi-scene switching and evaluation method based on power transmission and transformation project construction analogue simulation

    CN120105558A