Geological disaster risk prediction method, server, medium and program product

Abstract

The invention provides a geological disaster risk prediction method, a server, a medium and a program product, and relates to the technical field of electric data digital processing. The method comprises the steps of firstly determining a geological bearing pollutant threshold value of a target area, then determining a distribution state and type characteristics of industrial enterprises in the area, collecting production data of the enterprises in different seasons, and predicting industrial environment pollutant information according to the production data of the enterprises through a pollutant output prediction model. And inputting the information into an industrial pollutant erosion geologic model subjected to machine learning training to obtain a pollution damage prediction result. After the current geological information is attenuated, the final geological information is compared with a bearing threshold value, if the bearing threshold value is smaller than a preset standard, it is determined that the geological disaster risk exists, and early warning information is sent to related enterprises. According to the method, the purpose of actively predicting the geological disaster risk from enterprise production data is achieved, the limitation of a traditional passive monitoring mode is broken through, and geological disaster early warning is more timely and accurate.

Description

Technical Field

[0001] The present application relates to the technical field of digital processing of electrical data, and in particular to a method, server, medium and program product for predicting geological disaster risk. Background Art

[0002] In today's social development, geological disasters pose a serious threat to human life and property safety, as well as the stable development of the social economy. Especially with the rapid advancement of industrialization, the impact of industrial activities on the geological environment is becoming increasingly significant, making the mechanisms of geological disasters more complex. Accurately predicting the risk of geological disasters is crucial for taking effective preventive measures and protecting people's lives and property.

[0003] Currently, relevant departments primarily conduct geological safety management through environmental monitoring stations. Specifically, fixed sampling points are set up in industrially concentrated areas to regularly collect soil and groundwater samples for physical and chemical testing. Monitoring personnel then send these samples to laboratories for analysis, obtaining data on heavy metal content and organic matter concentrations. Furthermore, surface deformation is recorded through field surveys and, combined with regional geological conditions and historical disaster data, empirical formulas are used to assess geological stability.

[0004] However, this passive monitoring approach has inherent flaws. Existing monitoring data only reflects pollution that has already occurred, and cannot predict the pollution loads that will be generated during industrial production processes. Due to the lack of real-time monitoring of industrial production activities, problems are often not discovered until the geological environment has been severely damaged, missing the optimal early warning opportunity for geological disasters. Summary of the Invention

[0005] This application provides a geological disaster risk prediction method, server, medium and program product for accurately warning of geological disaster risks caused by corporate industrial activities.

[0006] In the first aspect, the present application provides a method for predicting geological disaster risks, which is applied to a server. The method includes: after determining the current geological structure of the target area, determining the geological carrying pollutant threshold for the occurrence of geological disasters through simulation tests; after obtaining the geographic information data of the target area, determining the distribution status of industrial enterprises and enterprise activity characteristics in the target area based on the geographic information data, wherein the industrial enterprise distribution status includes the enterprise's geographic coordinates and plant area, and the enterprise type information includes the enterprise's production category and scale level; based on the industrial enterprise distribution status and enterprise type information, collecting industrial production data of industrial enterprises in different seasons within a set time, wherein the industrial production data includes raw material usage and environmental load data caused by industrial production; based on the industrial production data and the enterprise type information, determining the industrial environmental pollutant information generated by industrial activities through a preset pollutant generation prediction model, wherein the industrial environmental pollutant information includes pollutants Type, emission amount and emission cycle. The pollutant generation prediction model is obtained by machine learning training based on the environmental pollution data generated by different types of enterprises under historical industrial activities; the industrial environmental pollutant information and the distribution status of industrial enterprises are input into the preset industrial pollutant erosion geological model to obtain the pollution damage prediction results of industrial environmental pollutants on the geology. The industrial pollutant erosion geological model is obtained by machine learning training based on the annotation of historical pollution event data, geological damage samples and expert experience knowledge; the current geological information of the target area is attenuated according to the pollution damage prediction result to obtain the final geological information after attenuation; the final geological information is compared with the geological carrying pollutant threshold. If the comparison result is less than the preset standard, it is determined that there is a suspected geological disaster; it is determined that the suspected disaster involves an industrial enterprise in the corresponding area of ​​the geological disaster; and a geological disaster warning prompt information is sent to the communication terminal corresponding to the suspected disaster-involved industrial enterprise.

[0007] By employing this technical solution, we obtain information on the distribution and types of industrial enterprises, providing a clear target range for subsequent data collection. The industrial production data collected based on this information directly reflects the actual production conditions of the enterprises. Analyzing this data using a pollutant generation prediction model accurately predicts the specific details of industrial environmental pollutants. This information is then input into a geological model of industrial pollutant erosion and, combined with an assessment of the geological carrying capacity of pollutants, enables the timely identification of potential geological disaster risks. This prediction method, based on enterprise production data, transcends the limitations of traditional passive monitoring and enables proactive early warning of geological disaster risks.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after determining the current geological structure of the target area, the step of determining the geological carrying capacity of pollutants for the occurrence of geological disasters through simulation tests specifically includes: based on the geological type data of the target area, combining the physical and chemical characteristics of various types of geology and the chemical properties of pollutants to determine the chemical reaction between pollutants and geology; comparing the chemical reaction situation with the set reaction intensity, and determining the geological sensitivity level according to the chemical reaction intensity; simulating the geological changes of different pollutants under different geological sensitivity levels through simulation conditions; and determining the concentration when the geological change situation meets the preset geological disaster change standard as the geological carrying capacity of pollutants threshold.

[0009] By employing this technical solution, the specific chemical reactions are determined based on the geological type data of the target area and the chemical properties of the pollutants, providing a scientific basis for determining geological sensitivity levels. By observing the changes in different pollutants under various geological environments through simulation experiments, the critical concentration of pollutants that trigger geological hazards can be accurately determined. This method establishes a quantitative relationship between pollutant concentration and the occurrence of geological hazards, making the determination of geological carrying capacity thresholds more accurate and reliable.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of attenuating the current geological information of the target area according to the pollution damage prediction result to obtain the final geological information after attenuation, it also includes: obtaining the expected value of future pollutant emissions in the target area; inputting the geology, topography and future meteorological conditions of the target area where future pollutant emissions are expected to be emitted into the pollutant diffusion model to determine the predicted impact of future pollutant emissions on the geology. The pollutant diffusion model is established in advance through training through a machine learning algorithm based on historical pollutant emission data, long-term geological and topographic monitoring data of the target area, meteorological data of the corresponding period, and actual diffusion monitoring samples of pollutants under different geological, topographic and meteorological conditions; and adjusting the final geological information according to the predicted impact.

[0011] By employing this technical solution, we simulate pollutant diffusion trends using a pollutant diffusion model, based on projected future pollutant emissions and taking into account the geology, topography, and future meteorological conditions of the target area. This model, through machine learning algorithms, integrates historical pollutant emission data with actual diffusion monitoring samples to accurately predict pollutant diffusion patterns. This forecasting approach not only considers current pollution conditions but also anticipates future pollution trends, significantly improving the foresight and accuracy of geological disaster predictions.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after inputting the geology, topography, and future meteorological conditions of the target area for future pollutant emissions into the pollutant diffusion model and determining the predicted impact of future pollutant emissions on the geology, the method further includes: training the pollutant diffusion model using a diffusion concentration distribution function, where the diffusion concentration distribution function is: ,in is the initial pollutant emission, is the emission source location, D is the pollutant diffusion coefficient, It is a function that comprehensively considers the influence of geology G, topography T and meteorology M. x, y, and z are coordinates in the spatial rectangular coordinate system, which are used to determine the specific location of pollutants in space; t represents time and reflects the change of pollutant concentration over time.

[0013] By employing this technical solution, the pollutant diffusion model is trained using a diffusion concentration distribution function. This function comprehensively considers key factors such as initial pollutant emissions, emission source location, and diffusion coefficient, and mathematically models geological, topographic, and meteorological influences. This training method, based on a precise mathematical model, enables pollutant diffusion predictions to take into account both spatial distribution characteristics and temporal evolution, significantly improving their accuracy.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the industrial environmental pollutant information generated by industrial activities through a preset pollutant generation prediction model based on the industrial production data and enterprise type information, it also includes: collecting historical meteorological data within the set range of the target area through a meteorological data interface; constructing a climate-pollutant interaction relationship model by combining historical meteorological data and industrial environmental pollutant information; after obtaining climate forecast data within a set time in the future, inputting the climate forecast data into the climate-pollutant interaction relationship model to determine the final industrial environmental pollutant information under the corresponding climate.

[0015] By employing this technical solution, historical meteorological data collected through a meteorological data interface and combined with information on industrial environmental pollutants, a climate-pollutant interaction model was constructed. This model dynamically adjusts industrial environmental pollutant information based on future climate forecasts, more accurately reflecting the actual impact of pollutants on the geological environment under different climate conditions. This climate-inclusive forecasting approach makes geological disaster predictions more realistic.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining that there is a suspected disaster-involved industrial enterprise in the area corresponding to the geological disaster, it also includes: obtaining the enterprise pollution history files of the suspected disaster-involved industrial enterprise in the target area; dividing the suspected disaster-involved industrial enterprise into different risk levels based on the enterprise pollution history files and the suspected geological disaster; and determining differentiated supervision strategies for industrial enterprises of different risk levels in combination with a preset supervision strategy library.

[0017] By adopting the above-mentioned technical solutions, this hierarchical management method can not only highlight key regulatory targets, but also take corresponding regulatory measures according to different risk levels, thereby improving regulatory efficiency and realizing precise management of geological disaster prevention and control work.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the final geological information is compared with the geological pollutant carrying threshold. If the comparison result is less than the preset standard, after determining the suspected existence of a geological disaster, it also includes: matching with the emergency plan library according to the type and scale of the suspected geological disaster to determine the corresponding emergency plan; and sending the emergency plan to the backup receiving end.

[0019] By adopting the above-mentioned technical solution, this preset emergency response mechanism can immediately initiate corresponding emergency measures after discovering geological disaster risks, improve the emergency response capabilities of geological disaster prevention and control, and effectively reduce the losses that may be caused by geological disasters.

[0020] In a second aspect, the present application provides a server comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code comprising computer instructions, the one or more processors calling the computer instructions to cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a server, cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By adopting the above technical solution, since a technical means is adopted to establish a pollutant generation prediction model and an industrial pollutant erosion geological model based on enterprise production data, and these two models are trained through machine learning, the technical problem of the existing technology that it is difficult to predict the pollution load that will be generated in the production process of industrial enterprises by relying solely on fixed monitoring points is effectively solved. The technical effect of actively predicting geological disaster risks based on enterprise production data is achieved, and geological disaster warning is transformed from traditional passive monitoring to active prediction based on enterprise production data.

[0024] 2. By adopting the above technical solution, the technical problem of the difficulty in accurately determining the critical conditions for the occurrence of geological disasters in the existing technology is effectively solved because a reaction model is established based on geological type data and the chemical properties of pollutants, and the critical concentration of pollutants under different geological sensitivity levels is determined through simulation experiments. This effectively solves the technical problem of the difficulty in accurately determining the critical conditions for the occurrence of geological disasters in the existing technology, and thus achieves accurate quantification of the geological carrying capacity threshold of pollutants, providing a reliable judgment basis for geological disaster risk assessment, and significantly improving the accuracy of geological disaster warning.

[0025] 3. By adopting the above technical solution, the climate-pollutant interaction model is constructed by combining historical meteorological data with industrial environmental pollutant information, and the pollutant information is dynamically adjusted according to climate forecast data. Therefore, the technical problem of the existing technology that cannot accurately assess the impact of climate change on pollutants is effectively solved, thereby achieving accurate prediction of geological disaster risks under different climatic conditions, making the early warning results more in line with the actual situation, and significantly improving the adaptability and reliability of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of a method for predicting geological disaster risk in an embodiment of the present application; Figure 2 This is another flow chart of the geological disaster risk prediction method in the embodiment of the present application; Figure 3 This is a schematic diagram of the physical device structure of the server in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following examples of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and encompasses any or all possible combinations of one or more of the listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1 , which is a flow chart of the geological disaster risk prediction method in the embodiment of this application.

[0030] S101. After determining the current geological structure of the target area, determine the geological carrying capacity of pollutants for the occurrence of geological disasters through simulation tests; First, based on the target area's geological type data, combined with the geophysical and chemical characteristics of the geothermal system and the chemical properties of the pollutants, the chemical reaction between the pollutants and the geology is determined. Next, the chemical reaction is compared with the set reaction intensity to determine the geological sensitivity level. Then, under simulation conditions, the changes in different pollutants under different geological sensitivity levels are simulated. Finally, the simulated geological changes are compared with the preset geological hazard change standards, and the pollutant concentration that meets the standards is determined as the geological carrying capacity threshold. This step will be described in detail in steps S201-S204 and will not be repeated here.

[0031] S102. After obtaining geographic information data of the target area, determine the distribution status and enterprise activity characteristics of industrial enterprises in the target area based on the geographic information data, wherein the industrial enterprise distribution status includes the enterprise's geographic coordinates and factory area, and the enterprise type information includes the enterprise's production category and scale level; The server establishes a data connection with the Geographic Information System (GIS) platform to obtain geographic information data of the target area. These data include high-resolution satellite images, topographic data, basic geographic feature layers (such as roads, water systems, settlements, etc.) and related vector data.

[0032] The server processes satellite images using image recognition and pattern matching algorithms. By learning typical features of industrial buildings, such as the geometric shape of large factory buildings and the reflectance spectral characteristics of specific building materials, the location of industrial enterprises can be identified. For example, for steel companies, their large blast furnaces, factory buildings, and supporting transportation tracks have unique shapes and textures in satellite images. The server can accurately identify these features and determine the geographic coordinates of the enterprise. At the same time, combined with topographic data and basic geographic feature layers, the server can accurately delineate the scope of the factory area. If there are natural geographical boundaries such as rivers and mountains around the enterprise, or if there is a clear separation relationship with roads, other buildings, etc., the server will accurately define the boundaries of the factory area based on this information.

[0033] To determine company type information, the server obtains data from multiple channels. First, it connects with government business registration and tax databases to obtain company registration information, including key data such as production categories and scale levels. Second, it utilizes web crawler technology to extract information from official company websites, industry information platforms, and government reports. Natural language processing technology analyzes this text data to uncover information about the company's production category and scale level, which is then verified and supplemented with data in the database.

[0034] S103. Based on the distribution status and enterprise type information of the industrial enterprises, collect industrial production data of the industrial enterprises in different seasons within a set time period, wherein the industrial production data includes raw material usage and environmental load data caused by industrial production; The server develops a detailed data collection plan based on the distribution and type of industrial enterprises. For each type and size of enterprise, the server determines the appropriate data collection focus and frequency from a pre-set data collection database. For example, for large chemical companies, due to their complex production processes and high pollutant emissions, the server will increase the data collection frequency, focusing on raw material usage, waste gas and wastewater emissions, etc.; for small mechanical processing companies, the data collection frequency can be relatively low, focusing primarily on raw material usage and simple environmental impact data.

[0035] Leveraging IoT technology, the server communicates with the company's internal production management system and monitoring equipment. In the raw material storage area, pre-installed high-precision electronic scales and flow sensors monitor the incoming and outgoing raw materials in real time. For liquid raw materials, the flow sensors precisely measure flow and calculate usage based on time data. For solid raw materials, electronic scales record weight changes in real time, thereby determining raw material usage. For example, at a food processing company, a server monitors flour usage in real time using sensors installed on flour storage tanks, providing accurate data for subsequent analysis.

[0036] In the production workshop, servers connect to the control systems of production equipment to obtain operating parameters such as production time and power consumption. These parameters reflect the company's production intensity and, when combined with raw material usage, analyze the company's production efficiency and resource utilization. At the same time, various pollutant monitoring devices, such as gas analyzers and water quality monitors, are installed at the company's exhaust and wastewater outlets to collect real-time data on the types and concentrations of pollutants in the exhaust gas (such as sulfur dioxide, nitrogen oxides, and particulate matter), as well as environmental load data such as chemical oxygen demand (COD), ammonia nitrogen, and heavy metal content in the wastewater.

[0037] Taking into account the impact of different seasons on corporate production, the server will adjust its data collection strategy according to seasonal changes. In winter, some companies may increase energy consumption due to heating needs, which may affect the use of raw materials and pollutant emissions. In summer, high temperatures may cause some production equipment to operate less efficiently, or companies may adjust their production plans to meet market demand. The server will set different data collection priorities and frequencies in different seasons based on these seasonal characteristics. For example, in the summer, for chemical companies, the focus is on monitoring their cooling system water usage and the increase in volatile organic compound (VOC) emissions that may be caused by high temperatures. In the winter, for heating companies, the focus is on collecting data on the use of fuels such as coal and pollutant emissions.

[0038] S104. Determine, based on the industrial production data and the enterprise type information, industrial environmental pollutant information generated by the industrial activity using a preset pollutant generation prediction model, wherein the industrial environmental pollutant information includes pollutant type, emission amount, and emission period. The pollutant generation prediction model is pre-trained using machine learning based on environmental pollution data generated by historical industrial activities of different enterprise types. The server first loads a pre-trained pollutant generation prediction model. This model is based on a machine learning algorithm and is trained using a large amount of historical environmental pollution data generated by various enterprise types through industrial activities. The server extracts historical data related to the current enterprise type and production data from the database as input to the model. This historical data includes not only industrial production data (such as raw material usage, production time, equipment operating parameters, etc.), but also corresponding pollutant emission data (pollutant type, emission amount, emission period, etc.).

[0039] Before inputting data, the server encodes and performs feature engineering on industrial production data and company type information. For company type information, methods such as one-hot encoding are used to convert it into numerical features for model processing. For industrial production data, the server uses data normalization and standardization to unify data of varying magnitudes and units into a common scale, improving model training effectiveness and prediction accuracy.

[0040] The server inputs the processed data into a pollutant generation prediction model. If the model is a deep learning-based neural network, it automatically learns the complex nonlinear relationships within the input data. For example, at a steel company, the model will learn the relationship between the use of raw materials such as iron ore and coal and the emissions of sulfur dioxide and particulate matter in exhaust gas, as well as the impact of production process parameters (such as blast furnace temperature and smelting time) on pollutant emissions. By learning from historical data, the model can capture the patterns in how different factors influence pollutant generation.

[0041] During model execution, the server uses its prediction function to output predicted industrial environmental pollutant information based on the currently input industrial production data and enterprise type information. This information includes pollutant type, emission volume, and emission cycle. For example, the model predicts that a chemical company, given its current production scale and raw material usage, will emit a certain amount of organic waste gas over a period of time, with daily emissions occurring continuously. The primary pollutants emitted are volatile organic compounds (VOCs) such as benzene and toluene. Many industrial companies emit large amounts of waste gas pollutants containing sulfur oxides (such as sulfur dioxide) and nitrogen oxides during their production processes. These pollutants undergo a series of chemical reactions with water vapor in the atmosphere. For example, sulfur dioxide is oxidized in the air to sulfur trioxide, which then reacts with water to form sulfuric acid. Nitrogen oxides undergo a complex oxidation process to form nitric acid. When these acidic substances fall to the ground as rain, they lower the pH value of the rainwater, forming acid rain. Once on the ground, acid rain can cause multiple damages to geological structures. It dissolves mineral components, such as calcium carbonate, in soil and rock. For limestone areas, the erosive effect of acid rain is particularly obvious. It will accelerate the dissolution of limestone, increase and enlarge the pores and cracks in the rock, destroy the integrity and stability of the rock, and increase the risk of geological disasters such as landslides and mudslides.

[0042] In some embodiments, the server can also utilize a dedicated meteorological data interface to establish connections with meteorological department databases, professional meteorological data platforms, and other platforms. By defining the scope of a target area (which can be a rectangular area defined by longitude and latitude, or based on administrative divisions) and a time span (e.g., the past 10 or 20 years), historical meteorological data for that area can be obtained from a data source. This data covers a variety of meteorological factors, such as temperature, humidity, wind speed, wind direction, precipitation, and sunshine duration. Data analysis and machine learning techniques are then used to construct a climate-pollutant interaction model. First, data preprocessing is performed to standardize and normalize meteorological and pollutant data for comparability and within an appropriate numerical range. Next, an appropriate model algorithm is selected, using meteorological factors as independent variables and industrial environmental pollutant concentrations and diffusion ranges as dependent variables. By analyzing the correlation between meteorological factors and pollutant changes in historical data, the model coefficients are determined, thereby establishing a mathematical relationship between the two. For example, research has found that wind speed and direction significantly affect the direction and velocity of pollutant diffusion, and precipitation can affect pollutant deposition. Incorporating these relationships into the model allows it to reflect the changing patterns of pollutants under different meteorological conditions. After obtaining climate forecast data for a set future timeframe (e.g., a week, month, or quarter), the server inputs this data into the constructed climate-pollutant interaction model. Climate forecast data can be obtained from forecasts released by meteorological authorities or the output of specialized climate forecast models. Based on this input climate forecast data and the learned relationship between weather and pollutants, the model predicts changes in industrial environmental pollutants under specific future climate conditions, such as changes in pollutant concentrations and expansion or contraction of their diffusion range. This information then determines the final industrial environmental pollutant profile for the corresponding climate.

[0043] S105: Inputting the industrial environmental pollutant information and the distribution status of industrial enterprises into a preset industrial pollutant erosion geological model to obtain a prediction result of the pollution damage caused by industrial environmental pollutants to the geology. The industrial pollutant erosion geological model is previously obtained through machine learning training based on historical pollution event data, geological damage samples, and expert experience and knowledge. After receiving information on industrial environmental pollutants (including pollutant types, emissions, and emission cycles) and the distribution status of industrial enterprises (enterprise geographic coordinates and plant area), the server will call a pre-trained industrial pollutant erosion geological model from the storage. This model is trained using a machine learning algorithm by annotating a large amount of historical pollution event data, geological damage samples, and expert experience knowledge. It can accurately simulate the erosion process of industrial pollutants on the geology.

[0044] The server preprocesses input data to ensure it meets the model's input requirements. For industrial environmental pollutant information, pollutant types are digitally encoded, assigning specific numerical identifiers to different types of pollutants (such as heavy metals and organic pollutants). Emissions and emission cycles are normalized to bring the data to a uniform scale for easier model processing. For the distribution of industrial enterprises, the enterprise's geographic coordinates and plant area boundaries are converted into spatial vector data to reflect the enterprise's location and scale within the target area.

[0045] Once the data is prepared, the server feeds it into an industrial pollutant erosion geological model. This model can be based on a deep learning-based convolutional neural network (CNN) or recurrent neural network (RNN). CNNs, through their convolutional layers, automatically extract pollutant information and spatial features of enterprise distribution. For example, they analyze regional differences in pollutant concentration distribution and the clustering or dispersion of enterprise distribution. RNNs, using their time series processing capabilities, can capture the dynamic impacts of pollutant emission cycles on geology. For example, in a chemical industrial park, the server inputs information on chemical substances emitted by each enterprise within the park (such as wastewater containing high levels of heavy metals), as well as the specific location and size of the enterprises. Based on the patterns learned during training, the model simulates the migration and diffusion paths of these pollutants in soil and groundwater, as well as their physical and chemical reactions with geological media. For example, it predicts the adsorption and desorption of heavy metal ions on soil particle surfaces, as well as their diffusion range and concentration changes in groundwater over time. This allows the model to assess the impact on the stability of the surrounding geological structure, such as whether it will cause changes in soil pore structure or stratum stress distribution.

[0046] After the model runs, the server retrieves the pollution damage prediction output. These results are presented digitally and may include information such as the extent of geological structural changes (such as stratum displacement and changes in rock porosity), changes in geomechanical properties (such as the reduction in soil shear strength and changes in rock compressive strength), and the extent of the affected geological area. The server then organizes and visualizes these results, generating intuitive charts or reports to facilitate subsequent analysis and decision-making.

[0047] S106, attenuating the current geological information of the target area according to the pollution damage prediction result to obtain final geological information after attenuation; After the server obtains the predicted results of industrial pollutants' pollution and damage to the geology, it will retrieve the current geological information of the target area from the geological database. This information covers many aspects such as stratigraphic structure, rock properties, soil composition and mechanical parameters.

[0048] The server performs targeted attenuation processing on the current geological information based on data such as the degree of geological structure change and mechanical property changes in the pollution damage prediction results. For stratigraphic structures, if the prediction results show that the stratigraphic structure in a certain area has undergone a certain degree of displacement or deformation due to pollutant erosion, the server will adjust the spatial position information and structural integrity parameters of the stratigraphic structure in that area accordingly. For example, if the stratigraphic structure that was originally continuous and complete has cracks in some areas due to pollutants, the server will update the stratigraphic crack distribution, width, and extension direction in the geological information, while lowering the overall stability score of the stratigraphic structure in that area.

[0049] Regarding rock properties, if pollutants are predicted to chemically react with rocks, altering their mineral composition and physical properties, the server will adjust parameters such as rock hardness, density, and permeability based on the extent of the reaction. For example, if acidic pollutants erode limestone, the rock's calcium carbonate content will decrease, resulting in decreased hardness and increased permeability. The server will modify these parameter values ​​within the geological information. Regarding soil composition and mechanical parameters, if pollution damage predictions indicate an increase in heavy metal content in the soil, affecting the cohesion and friction between soil particles, the server will recalculate and update mechanical parameters such as soil shear strength and compression modulus.

[0050] The server comprehensively considers the attenuation of all geological information and generates the final attenuated geological information. During this process, the server uses data fusion and weighted calculation methods to assign corresponding weights to various geological parameters based on the degree of influence of different geological factors on geological stability. For example, the stability of the stratum structure has a greater impact on overall geological stability, and its weight will be relatively high; while changes in certain minor components of the soil have a smaller impact on geological stability, their weights will be lower. Through weighted calculation, the server can obtain a final geological information dataset that comprehensively reflects the geological status of the target area. This dataset more accurately reflects the actual geological conditions under the influence of industrial pollutants.

[0051] In some embodiments, after determining the final geological information, it is also possible to investigate the production plans of enterprises in the target area and other information, combined with the industry emission coefficient, to estimate the amount of various pollutants emitted in the future. The historical pollutant emission data, long-term geological and topographic monitoring data, corresponding meteorological data and actual diffusion monitoring samples are used to train the model with the help of machine learning algorithms. These data cover the types, quantities, and emission locations of pollutants emitted in the region over the years, the undulations of the geological and topographical conditions, soil types, rock characteristics, meteorological wind speed, wind direction, precipitation and other information, as well as the actual diffusion range of pollutants under different conditions, concentration changes, etc. The machine learning algorithm mines the rules and establishes a pollutant diffusion model. The obtained expected values ​​of future pollutant emissions, as well as the geology of the target area (such as soil texture, rock structure), topography (mountains, plains and other terrain features) and future meteorological conditions (wind speed and precipitation probability in weather forecasts, etc.) are input into the model. The model uses the diffusion concentration distribution function Calculate. is the initial pollutant emission, is the emission source location, D is the pollutant diffusion coefficient, This function comprehensively considers the influence of geology (G), topography (T), and meteorology (M). x, y, and z are coordinates in a rectangular spatial system, used to determine the specific location of pollutants in space; t represents time, reflecting the change in pollutant concentration over time. Through functional calculations, it simulates the future diffusion of pollutants in space and time, as well as their impact on geology. If the model predicts that future pollutant emissions will cause changes in soil pH or accelerated rock weathering in a certain area, the geological information for that area will be adjusted accordingly, such as by revising soil composition data and updating rock stability assessments, to make the geological information more relevant to future reality.

[0052] S107: Compare the final geological information with the geological pollutant carrying threshold. If the comparison result is less than the preset standard, it is determined that a geological disaster is suspected to exist. The server retrieves the final geological information after attenuation and the predetermined geological carrying capacity threshold for pollutants. This threshold is determined through simulation tests based on the geological type and physical and chemical properties of the target area, and represents the maximum amount of pollutants that the geology can withstand without causing disasters.

[0053] The server extracts key indicators from the final geological information, such as the actual concentration of specific pollutants, geological structure change data (such as stratum displacement and rock porosity change), and geomechanical property change parameters (such as soil shear strength and rock compressive strength change rate). For example, if the target area is at risk of heavy metal contamination, the server will focus on extracting actual heavy metal concentration data in the soil and groundwater.

[0054] Compare the extracted key indicators to the geological pollutant carrying capacity threshold. For pollutant concentrations, directly compare the actual concentration to the threshold concentration. For geological structure and mechanical property indicators, use pre-defined calculation methods to convert the changes into values ​​comparable to the threshold. For example, a specific formula can be used to convert formation displacement into a stability score, which is then compared to the stability score threshold.

[0055] Reasonable comparison criteria should be set. These can range from simple numerical comparisons to comprehensive assessments based on complex algorithms. For example, a weighted average approach can be used to assign weights to different indicators based on their importance to geological stability, calculate a comprehensive score, and then compare it with a preset comprehensive score threshold. If the final combined score of the key indicators of geological information is lower than the preset standard, the server will determine that a geological hazard is suspected to exist in the target area. Once a suspected geological hazard is confirmed, the server will record detailed information, including the scope of the affected area, the possible type of geological hazard (such as ground subsidence, landslides, mudslides, etc.), and the potential severity of the hazard (estimated based on the degree to which key indicators deviate from the threshold).

[0056] In some embodiments, the server can also clarify the type (such as landslide, debris flow, ground subsidence, etc.) and scale (quantitative indicators such as the scope of impact and the degree of damage that may be caused) of the suspected geological disaster based on its detailed information. The server then accesses a preset emergency plan library, which stores a variety of emergency plans developed for various types of geological disasters and their different scales. The server compares the type and scale of the suspected disaster with the plans in the plan library, selects the most matching emergency plan, and sends it to a backup receiving end, which is usually a disaster emergency command center or surrounding communities and businesses that may be affected.

[0057] S108. Determine if there are industrial enterprises involved in suspected disasters in the area corresponding to the geological disaster; Based on the identified suspected geological disaster area and previously acquired information on the distribution of industrial enterprises (enterprise geographic coordinates and factory boundaries), the server uses geographic information system (GIS) spatial analysis technology to screen out potentially affected industrial enterprises located in or around the disaster area. For example, by calculating the spatial intersection of an enterprise's factory boundary and the disaster area, the server can determine which enterprises are within the potential disaster area.

[0058] For the initially selected companies, the server further analyzes their production activity characteristics and pollutant emissions. Combining previously collected industrial production data with predicted industrial environmental pollutant information, it determines whether the company's production activities and pollutant emissions are associated with suspected geological hazards. For example, certain chemical companies, which discharge large amounts of acidic wastewater, could cause soil acidification and alter geological structures, making these companies a key focus.

[0059] If there are multiple suspected disaster-affected enterprises, the server prioritizes them based on factors such as their proximity to the disaster area, their production scale, and the amount of pollutant emissions. Enterprises that are closer to the disaster area, have larger production scales, and emit the most pollutants will be given higher priority in subsequent processing, allowing resources to be concentrated on high-risk enterprises.

[0060] The server integrates information on suspected disaster-affected industrial enterprises, including basic information such as enterprise name, geographic coordinates, production category, and scale, as well as assessment information such as the degree of relevance and priority of the enterprise to the disaster. This information provides an accurate basis for the subsequent formulation of differentiated regulatory strategies and the issuance of early warning information.

[0061] In some embodiments, after this step, historical pollution records of industrial enterprises suspected of being affected by the disaster in the target area may also be obtained. These records cover the types of pollutants emitted by the enterprises in the past, including heavy metals, chemicals, and radioactive substances; the amount of emissions, which accurately records the total amount of various pollutants emitted over different time periods; the frequency of emissions, which indicates whether the enterprise emits pollutants on a long-term, regular, or intermittent basis; and the pollution control measures implemented by the enterprises in the past and their effectiveness evaluations. These records can be obtained through various channels, such as the enterprise's own environmental reports, regulatory records from local environmental protection departments, and data from third-party environmental monitoring agencies. By referring to the types, amounts, and frequency of pollutant emissions in the enterprise's pollution records, if the enterprise has been emitting large quantities of highly toxic and difficult-to-degrade pollutants for a long time, it is more likely to cause damage to the geological environment, and the risk level will increase accordingly. The geographical location and production activities of the enterprise are analyzed to determine their relevance to the suspected geological disaster area. If the enterprise is located in close proximity to the suspected disaster area and its production activities may directly affect the geological stability of the area, the risk level of the enterprise will also be higher. The pollution control measures implemented by the enterprise in the past and their effectiveness are also considered. If the enterprise has comprehensive pollution control facilities and can effectively control pollutant emissions and reduce the impact on the geological environment, its risk level may be relatively low. Taking all the above factors into consideration, enterprises can usually be divided into three risk levels: high, medium, and low. High-risk enterprises refer to those that are seriously polluting, closely associated with suspected disasters, and have poor pollution control capabilities; medium-risk enterprises have a medium level of pollution, correlation, and control capabilities; low-risk enterprises are those that are less polluting, less closely associated with suspected disasters, and have better pollution control measures. In order to achieve precise supervision of industrial enterprises at different risk levels, it is necessary to establish a preset supervision strategy library. This strategy library contains a series of supervision measures formulated for different risk situations. After determining the risk level of the enterprise, the appropriate supervision strategy is selected from the strategy library and applied to the corresponding enterprise. In this way, the industrial enterprises involved in suspected disasters in the target area can be scientifically classified and precisely supervised, effectively reducing the risk of geological disasters.

[0062] S109: Send geological disaster warning information to the communication terminal corresponding to the industrial enterprise involved in the suspected disaster.

[0063] The server obtains communication information from industrial enterprises suspected of being affected by a disaster. This information can be pre-stored in an enterprise information database. Based on the communication preferences and actual conditions of each enterprise, the server selects an appropriate communication method to send the warning message. The warning information may include the type of suspected geological disaster (such as ground subsidence or debris flow risk), the possible impact range (clearly indicating the extent of the impact in the enterprise's area), the expected time of occurrence (an approximate time range estimated based on existing data and models), and recommended emergency measures (such as ceasing production activities in the dangerous area, evacuating personnel, and strengthening geological monitoring).

[0064] In the above embodiment, by determining the geological carrying capacity of pollutants in the target area, analyzing the distribution and production data of industrial enterprises, using multiple machine learning models to predict pollutant information and geological impacts, and performing comparisons and early warnings, a series of operations are performed to achieve the purpose of actively predicting geological disaster risks based on enterprise production data. This not only breaks through the limitations of traditional passive monitoring methods, making geological disaster warnings more timely and accurate, but also can comprehensively assess geological disaster risks based on multiple factors, provide strong support for the formulation of scientific and effective prevention and control measures, and improve the precision management level of geological disaster prevention and control work.

[0065] After combining the above content, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the geological disaster risk prediction method in the embodiment of this application.

[0066] S201. Based on the geological type data of the target area, the chemical reaction between the pollutants and the geology is determined in combination with the physical and chemical characteristics of the various geological types and the chemical properties of the pollutants; The server first retrieves geological data for the target area from a geological database. This data details the rock types and soil types, as well as their distribution, across different strata within the region. Simultaneously, the server acquires data on the chemical properties of various known pollutants, which can come from specialized chemical databases, scientific research literature, or long-term monitoring data.

[0067] To determine the chemical reactions between pollutants and geology, the server uses chemical simulation software and algorithms for analysis. Taking acidic pollutants (such as sulfuric acid) and limestone as an example, the server utilizes a chemical reaction kinetics model, incorporating the chemical reaction equation between calcium carbonate (the primary component of limestone) and sulfuric acid, to simulate the reaction process under various conditions (such as temperature, humidity, and pollutant concentration). By adjusting parameters, key indicators such as the reaction rate constant and equilibrium constant are calculated to determine the reaction's initiation, progress, and termination states, as well as the intermediate and final products produced during the reaction.

[0068] For complex geological environments, the server uses a multi-component reaction model. For example, in areas with soil rich in various minerals, where heavy metal pollutants and organic pollutants coexist, the server comprehensively considers the chemical reactions between various minerals in the soil and different pollutants, as well as the mutual influence of these reactions. Through iterative calculations and simulations, the server analyzes the adsorption and desorption processes of different pollutants on the surface of soil particles, as well as the possibility and extent of ion exchange and complexation reactions between these pollutants and minerals in the soil.

[0069] S202, comparing the chemical reaction situation with the set reaction intensity, and determining the geological sensitivity level according to the chemical reaction intensity; The server quantifies the chemical reactions between the pollutants and the geology determined in S201 into specific reaction intensity indicators. These indicators can include reaction rate, reactant consumption rate, product production, etc. For example, when assessing the impact of acidic pollutants on soil, the rate at which alkaline substances in the soil are consumed is an important reaction intensity indicator; for heavy metal pollutants, the migration rate of heavy metals in soil or rock is used as one of the reaction intensity measurement criteria.

[0070] The server pre-sets different levels of reaction intensity standards. These standards are based on a large amount of experimental data, historical geological disaster cases, and industry research results. For example, the reaction rate is divided into five levels: very low, low, medium, high, and very high, and each level corresponds to a specific numerical range. The set reaction intensity standards will vary for different types of pollutants and geology. For example, for clay-type geology that is more sensitive to environmental changes, the division of its reaction intensity level with heavy metal pollutants will be more detailed, while for relatively stable granite geology, the division standards will be relatively loose.

[0071] The actual calculated reaction intensity index is compared with the set reaction intensity standard. For example, in a region with heavy metal contamination, the server calculates the migration rate of the heavy metal in the soil and matches it with the preset reaction intensity standard. If the migration rate falls within the numerical range corresponding to low reaction intensity, the region's geological sensitivity to this heavy metal pollution is preliminarily determined to be low. If the migration rate reaches the high reaction intensity range, the geological sensitivity is high.

[0072] During the comparison process, the server considers the impact of multiple factors on reaction intensity. Geological factors such as pore structure, water content, and pH all influence the intensity of the pollutant-geological reaction. The server integrates these factors to adjust the reaction intensity, ensuring a more accurate determination of the geological sensitivity level. Specifically, based on extensive experimental data, historical research results, and professional knowledge, the server first determines the weighting of each influencing factor on the reaction intensity. Based on the quantified influencing factors and the determined weightings, the server establishes a reaction intensity correction model. A common approach is to use a weighted comprehensive approach: Corrected reaction intensity = Original reaction intensity × (Pore structure influence coefficient × Pore structure weight + Water content influence coefficient × Water content weight + pH influence coefficient × pH weight). The influence coefficient is determined based on the difference between the actual value of each factor and the standard reference value. For example, when the soil porosity exceeds the standard reference value, the pore structure influence coefficient is greater than 1, indicating that the pore structure promotes the reaction intensity; otherwise, it is less than 1. Assuming the original reaction intensity is 5 (measured by a set intensity index), the soil porosity in a certain area is greater than the standard value, with an influence coefficient of 1.2, the moisture content influence coefficient of 0.9 (because the moisture content is slightly lower than the standard value), and the pH influence coefficient of 1.0 (close to the standard value). Using the above weights, the corrected reaction intensity is 5 × (1.2 × 0.4 + 0.9 × 0.3 + 1.0 × 0.3) = 5 × (0.48 + 0.27 + 0.3) = 5 × 1.05 = 5.25. The server continuously monitors changes in the geological environment and obtains the latest data on influencing factors in real time. If changes are detected in factors such as pore structure, moisture content, and pH, the influence coefficients and weights are recalculated and the reaction intensity is dynamically adjusted.

[0073] S203, simulating geological changes of different pollutants under different geological sensitivity levels through simulation conditions; The server utilizes numerical simulation technology to create a simulation environment. Finite element analysis software, discrete element method, and other tools are used to construct a simulation system that includes geological models with varying geological sensitivity levels and pollutant dispersion models. For example, within the finite element analysis software, a three-dimensional geological model is created based on the geological data of the target area. Geological regions of varying sensitivity levels are clearly delineated and assigned corresponding physical and chemical parameters.

[0074] For different pollutants, the server sets simulation parameters based on their physical and chemical properties. For example, for volatile organic pollutants, parameters such as volatility coefficient and diffusion coefficient are set; for heavy metal pollutants, migration rate in different media and adsorption and desorption parameters are set. These parameters can be obtained from laboratory research data, relevant literature, or actual monitoring data to ensure the authenticity of the simulation.

[0075] During the simulation process, the server considers the influence of various environmental factors. Environmental factors such as temperature, humidity, and groundwater flow rate can significantly influence the migration and reaction of pollutants in the geology. For example, higher temperatures accelerate the diffusion of pollutants, while groundwater flow rate affects the migration path and distribution range of pollutants. By setting different combinations of environmental parameters, the server simulates the changes in pollutants in the geology under different environmental conditions.

[0076] Taking the geological environment surrounding a chemical park as an example, the server simulated various pollutants emitted by the park, such as heavy metals and organic pollutants, within geological models with varying geological sensitivity levels. The server simulated the migration of heavy metal pollutants in a highly sensitive clay formation, observing their diffusion and adsorption between clay particles and their impact on the clay's physical and mechanical properties, such as pore structure and compressive strength. It also simulated the degradation and migration of organic pollutants in a moderately sensitive sand formation, analyzing their changes in the sand's chemical composition and permeability. The server employed multiscale simulation methods, analyzing both microscopic and macroscopic levels. At the microscopic level, it simulated the interaction between pollutant molecules and the surfaces of geological particles. For example, atomic force microscopy simulations can demonstrate the adsorption of pollutants on geological surfaces at the atomic scale. At the macroscopic level, it observed the diffusion range and concentration distribution of pollutants throughout the entire geological region, as well as their impact on geological structural stability. For example, it assessed geological stability through simulated stratum displacement and stress changes. After the simulation, the server analyzed and compiled the results. The simulated geological change data (such as pollutant concentration distribution, geological structure deformation, chemical composition changes, etc.) are visualized to generate intuitive charts and images to facilitate subsequent analysis and judgment.

[0077] S204. Determine the concentration when the geological change situation meets the preset geological disaster change standard as the geological carrying pollutant threshold.

[0078] The server rigorously compares the simulated geological changes with pre-set geological hazard change standards. These pre-set standards are based on extensive historical geological hazard data, geological stability research results, and industry standards, and cover a wide range of geological hazard types and corresponding geological change indicators. For example, for land subsidence, the pre-set standards may stipulate that when the vertical displacement of the ground layer exceeds a certain value (such as 5 cm), and this displacement continues to increase and poses a potential threat to ground buildings and infrastructure, it is considered to meet the change standard for land subsidence.

[0079] During the comparison process, the server conducts detailed analysis of different geological change indicators and disaster types. For example, when analyzing geological changes caused by heavy metal pollution in a certain area, first check the distribution of heavy metal concentrations in the soil to determine whether there are local high-concentration areas. Next, pay attention to changes in soil physical properties caused by heavy metal accumulation, such as changes in soil porosity and permeability, and compare whether these changes meet the preset standards for related disasters such as ground subsidence or soil erosion. If the simulation results show that the increase in heavy metal concentration in the soil in a certain area causes the soil porosity to decrease, which in turn leads to stratum compression, and the vertical displacement gradually approaches or exceeds the preset displacement standard for ground subsidence disasters, the server will record the heavy metal concentration in the soil in that area at this time.

[0080] When the simulated geological changes meet the preset geological hazard change standards, the server will determine the corresponding pollutant concentration at this time as the geological carrying pollutant threshold. Since geology with different geological sensitivity levels has different tolerance to pollutants, each geological sensitivity level has its own corresponding threshold for different pollutants. For example, in soft soil geology with high sensitivity, the geological carrying pollutant threshold of heavy metal lead may be relatively low, assuming it is 50 mg / kg; while in hard rock geology with low sensitivity, the lead threshold may be much higher, such as 200 mg / kg. The server associates these thresholds with the corresponding geological sensitivity levels and pollutant types to form a geological carrying pollutant threshold database.

[0081] In the embodiments of the present application, by determining the chemical reaction between pollutants and geology based on the geological type data of the target area, determining the geological sensitivity level by comparing the reaction intensity, simulating the changes of different pollutants under geology of different geological sensitivity levels, and determining the geological carrying capacity threshold of pollutants, accurate quantification of the geological carrying capacity threshold of pollutants is achieved. This not only effectively solves the technical problem in the existing technology that it is difficult to accurately determine the critical conditions for the occurrence of geological disasters, but also provides a reliable judgment basis for geological disaster risk assessment, thereby significantly improving the accuracy of geological disaster warning.

[0082] The following describes the server in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a server in an embodiment of the present application.

[0083] It should be noted that Figure 3 The structure of the server shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0084] like Figure 3As shown, the server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0085] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, push button switches, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the removable media can be installed in the storage section 308 as needed.

[0086] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0087] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0089] Specifically, the server of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the geological disaster risk prediction method provided in the above embodiment is implemented.

[0090] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the server described in the above embodiments, or may exist independently and not incorporated into the server. The storage medium carries one or more computer programs, which, when executed by a processor of the server, enable the server to implement the geological hazard prediction method provided in the above embodiments.

[0091] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0092] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0093] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A geological disaster risk prediction method, applied to a server, characterized in that: The method comprises: After determining the current geological structure of the target area, the geological carrying capacity of pollutants for the occurrence of geological hazards is determined through simulation tests; After obtaining geographic information data of the target area, determining the distribution status and enterprise activity characteristics of industrial enterprises in the target area based on the geographic information data, wherein the industrial enterprise distribution status includes the enterprise's geographic coordinates and factory area, and the enterprise type information includes the enterprise's production category and scale level; Based on the distribution status and enterprise type information of the industrial enterprises, industrial production data of the industrial enterprises in different seasons within a set time period are collected, wherein the industrial production data includes raw material usage and environmental load data caused by industrial production; Determining, based on the industrial production data and the enterprise type information, industrial environmental pollutant information generated by the industrial activities using a preset pollutant generation prediction model, wherein the industrial environmental pollutant information includes pollutant type, emission amount, and emission period, and the pollutant generation prediction model is previously trained using machine learning based on environmental pollution data generated by historical industrial activities of different enterprise types; Inputting the industrial environmental pollutant information and the distribution status of industrial enterprises into a preset industrial pollutant erosion geological model to obtain a prediction result of the pollution damage caused by industrial environmental pollutants to the geology, wherein the industrial pollutant erosion geological model is previously obtained through machine learning training based on historical pollution event data, geological damage samples and expert experience knowledge; Attenuating the current geological information of the target area according to the pollution damage prediction result to obtain final geological information after attenuation; Comparing the final geological information with the geological pollutant carrying threshold, if the comparison result is less than the preset standard, it is determined that a geological disaster is suspected to exist; Determine the suspected disaster-related industrial enterprises in the corresponding area where geological hazards exist; Send geological disaster warning information to the communication terminal corresponding to the industrial enterprise involved in the suspected disaster.

2. The method according to claim 1, characterized in that After determining the current geological structure of the target area, the steps to determine the geological carrying capacity of pollutants for the occurrence of geological hazards through simulation tests include: Based on the geological type data of the target area, the chemical reaction between pollutants and geology is determined by combining the physical and chemical characteristics of various types of geology and the chemical properties of pollutants; Comparing the chemical reaction situation with the set reaction intensity, and determining the geological sensitivity level according to the chemical reaction intensity; Through simulation conditions, the geological changes of different pollutants under different geological sensitivity levels are simulated; The concentration when the geological changes meet the preset geological disaster change standards is determined as the geological carrying pollutant threshold.

3. The method according to claim 1, characterized in that After the step of attenuating the current geological information of the target area according to the pollution damage prediction result to obtain the final geological information after attenuation, the method further includes: Obtain the estimated values ​​of future pollutant emissions in the target area; Inputting the geology, topography, and future meteorological conditions of the target area for future pollutant emissions into a pollutant diffusion model to determine the predicted impact of future pollutant emissions on the geology. The pollutant diffusion model is previously trained using a machine learning algorithm based on historical pollutant emission data, long-term geological and topographic monitoring data of the target area, meteorological data of the corresponding period, and actual monitoring samples of pollutant diffusion under different geological, topographic, and meteorological conditions; The final geological information is adjusted according to the predicted impacts.

4. The method according to claim 3, characterized in that After inputting the geology, topography, and future meteorological conditions of the target area for future pollutant emissions into the pollutant dispersion model to determine the predicted impact of future pollutant emissions on the geology, the following steps are included: The pollutant diffusion model is trained by the diffusion concentration distribution function, which is: ,in is the initial pollutant emission, is the emission source location, D is the pollutant diffusion coefficient, It is a function that comprehensively considers the influence of geology G, topography T and meteorology M. x, y, and z are coordinates in the spatial rectangular coordinate system, which are used to determine the specific location of pollutants in space; t represents time and reflects the change of pollutant concentration over time.

5. The method according to claim 1, wherein After determining the information on industrial environmental pollutants generated by industrial activities using a preset pollutant generation prediction model based on the industrial production data and enterprise type information, the method further includes: Collect historical meteorological data within the target area through the meteorological data interface; Combining historical meteorological data with industrial environmental pollutant information to build a climate-pollutant interaction model; After obtaining climate prediction data within a set future time period, the climate prediction data is input into the climate-pollutant interaction model to determine final industrial environmental pollutant information under the corresponding climate.

6. The method according to claim 1, wherein After determining the suspected disaster-related industrial enterprises in the corresponding area where the geological disaster exists, the following steps are also included: Obtain historical pollution records of industrial enterprises involved in the suspected disaster within the target area; Classify the industrial enterprises involved in the suspected disaster into different risk levels based on the pollution history files of the enterprises and the suspected geological disasters; Differentiated regulatory strategies are determined for industrial enterprises with different risk levels based on the preset regulatory strategy library.

7. The method according to claim 1, characterized in that Comparing the final geological information with the geological pollutant carrying threshold, and if the comparison result is less than the preset standard, determining that a geological disaster is suspected to exist, further includes: According to the type and scale of suspected geological disasters, match them with the emergency plan database and determine the corresponding emergency plan; The emergency plan is sent to a standby receiving terminal.

8. A server, characterized in that: The server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the server to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a server, the server is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a server, the server is caused to perform the method according to any one of claims 1 to 7.

Images