Ecological environment big data processing method based on mining area pollutant migration behavior modeling

Abstract

The invention discloses an ecological environment big data processing method based on mining area pollutant migration behavior modeling, and relates to the technical field of big data processing. Comprising the steps that protection points in a target range and geodetic coordinate values of a mining area are obtained, the protection points comprise a mass residential area, an ecological protection area and a water source protection area, and the geodetic coordinate values are used for representing latitude and longitude coordinates and the altitude; and according to the first group of geodetic coordinate values and the geodetic coordinate values of the mining area, the maximum diffusion range interval of the mining area pollutants is determined, and the first group of geodetic coordinate values specifically refer to the geodetic coordinate values taken by any protection point type. According to the method, the three-dimensional geodetic coordinates of the protection point and the mining area are obtained, the pollutant diffusion range is scientifically defined, it is ensured that the space coverage of pollution monitoring is comprehensive and effective, potential threats of mining area pollution to surrounding people residential areas, ecological protection areas and water source protection areas can be accurately recognized, and the risk of mining area pollution to the surrounding people residential areas, ecological protection areas and water source protection areas is reduced. And the accuracy and pertinence of environmental risk assessment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and specifically to an ecological environment big data processing method based on modeling the migration behavior of pollutants in mining areas. Background Art

[0002] During the resource exploitation process in mining areas, a large amount of pollutants will be generated, including heavy metals, acidic water bodies, dust, and harmful gases. These pollutants often migrate and diffuse in soil, groundwater, and the atmosphere, seriously affecting the surrounding ecological systems and the health of residents. To predict the spatio-temporal distribution law of pollutants in complex geological environments and formulate precise treatment plans, a model for the migration behavior of pollutants in mining areas that processes ecological environment big data is needed.

[0003] After retrieval, the Chinese invention patent application with the publication number "CN110245029 A" discloses "A data processing method, device, storage medium, and server". By receiving an interface call task carrying configuration parameters sent by a client, parsing the interface call task to obtain the data to be processed in the interface call task and the data processing logic corresponding to the configuration parameters, then decomposing the interface call task into multiple data processing steps according to the data processing logic, determining the order of each data processing step, then determining the data processing logic implementation classes corresponding to each data processing step, and generating a processing chain according to the data processing logic implementation classes and the order of the data processing steps, and performing data processing on the data to be processed in the interface call task based on the processing chain. This solution can achieve the unification of subsystem interface docking calls, reduce the development difficulty, enable the system to respond to calls in a timely manner, and improve the efficiency of interface calls.

[0004] In addition, the Chinese invention patent application "CN119961707A" is disclosed, which discloses "A method for processing abnormal data during environmental air monitoring". By diagnosing equipment failures based on abnormal data of environmental air monitoring fluctuation trends, the reasons for abnormal data caused by equipment failures can be quickly located and identified, ensuring the normal operation of monitoring equipment and the reliability of monitoring data. And by uploading equipment failure data to the environmental air monitoring management cloud platform, the intellectualization and systematization of equipment maintenance are further realized, and the overall efficiency of the monitoring system is improved.

[0005] However, in the actual use process, the above-mentioned disclosed methods and the solutions disclosed in the prior art do not fully consider the weakening effect of natural neutralizing factors in the ecological system on the migration of pollutants, resulting in inaccurate prediction of the pollution diffusion range and migration path. In addition, environmental fluctuations and seasonal changes have a great interference on the identification of pollution trends, easily causing misjudgment or missed judgment of pollution trends, and affecting the reliability of environmental risk assessment and early warning. Summary of the Invention

[0006] The object of the present invention is to provide a method for processing ecological environment big data based on the modeling of pollutant migration behavior in mining areas, so as to solve the problems put forward in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: A method for processing ecological environment big data based on the modeling of pollutant migration behavior in mining areas, including:

[0008] Obtain the geodetic coordinate values of the protection points and the mining area within the target range. The protection points include: residential areas of the masses, ecological protection areas, and water source protection areas. The geodetic coordinate values are used to represent longitude and latitude coordinates and altitude;

[0009] According to the geodetic coordinate values of the first group and the geodetic coordinate values of the mining area, determine the maximum diffusion range interval of the pollutants in the mining area. The geodetic coordinate values of the first group specifically refer to the geodetic coordinate values taken for any one type of protection point;

[0010] Obtain the pollutant concentration gradient within the maximum diffusion range area;

[0011] Generate a migration behavior model of the pollutants in the mining area based on the concentration distribution results of the spatial detection area.

[0012] As a further preference of this technical solution, retrieve the corresponding neutralizing item within the ecological and geographical environment parameters of the target mining area type, and establish a neutralization efficiency index, which is used to update the migration behavior model.

[0013] As a further preference of this technical solution, the setting method of the neutralization efficiency index includes:

[0014] Extract the corresponding neutralizing factors in the pollutants from the ecological and geographical environment parameters, and establish a reaction control chart;

[0015] Identify the reaction relationship between the pollutant - neutralizing item in the reaction control chart;

[0016] Set the neutralization efficiency index according to the reaction relationship between the pollutant - neutralizing item. The neutralization efficiency index is used to evaluate the natural weakening effect of the neutralizing item on the pollutant migration behavior. The neutralization efficiency index is determined by establishing a spatial distribution map of the neutralizing item and evaluating the percentage of the intersection area with the pollutant migration path in the total area.

[0017] As a further preference of this technical solution, the reaction control chart extracts environmental factors with pollution neutralization ability from the ecological and geographical parameters obtained around the mining area. The environmental factors correspond to the pollutants in the mining area and can generate harmless substances through chemical reactions to reduce migration and bioavailability in the environment.

[0018] As a further preferred embodiment of the present technical solution, the migration frequency of the same pollution factors as the eco-geographical environmental parameters and the target mining area type is obtained, and a correction index is set based on the migration frequency. The correction index is used to update the migration behavior model, so that the migration behavior model can reduce the interference of environmental fluctuations on pollution trend identification during actual operation.

[0019] As a further preferred embodiment of the present invention, the method for setting the correction index includes:

[0020] Through a distributed environmental sensor network deployed around the mining area, the concentration time series data of target pollution factors over a historical period are collected;

[0021] The concentration series is decomposed into trend term, seasonal term and residual term, and a discrimination threshold is set. The cumulative trend of pollution is determined based on the comparison results between the trend term, seasonal term and residual term and the discrimination threshold;

[0022] A dynamic correction coefficient is constructed according to the degree of deviation between the residual term and the discrimination threshold.

[0023] As a further preferred embodiment of the present technical solution, the conditions for judging the pollution accumulation trend are:

[0024] When the linear regression slope of the trend term in the concentration curve exceeds the discrimination threshold α, the amplitude standard deviation of the seasonal term is greater than the discrimination threshold β, and there is a same-direction deviation in the residual term for six consecutive monitoring periods, it is determined that there is an upward trend in non-anthropogenic pollution;

[0025] The discrimination threshold α is obtained by using the monthly pollutant concentration data in the historical time series of the concentration curve and performing linear regression on the monthly average concentration series of the pollutants to obtain the slope of the trend term. The mean of the slope distribution at the 95% confidence level + 2 times the standard deviation is set as the discrimination threshold α. This is used to establish a dynamic benchmark value with statistical significance and effectively distinguish between natural fluctuations and abnormal accumulation phenomena.

[0026] The discrimination threshold β is determined by extracting twice the absolute value of the standard deviation between the historical seasonal item amplitude data and the real-time seasonal item amplitude data in the concentration curve graph.

[0027] As a further preferred embodiment of the present technical solution, the migration behavior model is updated based on the neutralization efficiency index and the correction index, and a visual report is output;

[0028] The updating method of the migration behavior model includes:

[0029] Integrate the neutralization efficiency index and the correction index into the input parameters of the migration behavior model;

[0030] Recalculate the concentration distribution of pollutants in spatial and temporal dimensions based on the updated input parameters;

[0031] Generate a visualization report based on the updated migration behavior model.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0033] The ecological environment big data processing method based on the modeling of pollutant migration behavior in mining areas completes the scientific definition of the pollutant diffusion range by obtaining the three-dimensional geodetic coordinates of the protection points and the mining areas, ensuring the comprehensive and effective spatial coverage of pollution monitoring, which helps to accurately identify the potential threats of mining area pollution to the surrounding residential areas, ecological protection areas and water source protection areas of the masses, improves the accuracy and pertinence of environmental risk assessment. By obtaining the pollutant concentration gradient within the maximum diffusion range, a migration behavior model based on spatial concentration distribution is constructed, providing a scientific quantitative basis for the dynamic evolution and migration path of pollutants in mining areas, realizing the fine simulation and prediction of the pollution diffusion process, and enhancing the early warning ability and decision-making support effect of environmental management;

[0034] In addition, by introducing a neutralization efficiency index based on the ecological and geographical environment parameters around the mining area, the weakening effect of natural neutralization factors on pollutant migration in the ecosystem is evaluated, effectively reflecting the environmental self-purification ability, and improving the ecological authenticity and reliability of the model. It should be added that by establishing a pollutant-neutralization reaction comparison chart and a spatial distribution chart, the neutralization efficiency can be dynamically quantified, and the impact of the neutralization process on the spatial change of pollutant concentration can be accurately described, enhancing the adaptability and interpretability of the pollution migration behavior model. Finally, by combining the migration frequency data of pollution factors in the mining area and its surrounding areas, an index for identifying the upward trend of non-artificial pollution and correcting false alarms is set, effectively filtering out the interference of environmental fluctuations, improving the accuracy of pollution trend identification, reducing the risk of misjudgment, and enhancing the scientific nature of pollution monitoring and early warning;

[0035] It should also be noted that the present invention realizes the real-time collection of the time series of pollutant factor concentrations in the periphery of the mining area and the multi-dimensional data decomposition by adopting a distributed environmental sensor network, and adjusts the model parameters through a dynamic correction coefficient to ensure that the model has strong adaptability and stability during long-term operation and can sensitively reflect the dynamic changes of pollution. Description of the Drawings

[0036] Figure 1 It is a flowchart of the steps of the disclosed method of the present invention;

[0037] Figure 2 It is a three-dimensional structure diagram of the pollution migration behavior model of the present invention;

[0038] Figure 3 It is the reaction comparison chart disclosed by the present invention;

[0039] Figure 4The concentration curve graph disclosed by the present invention;

[0040] Figure 5 The modified exponential dynamic change curve graph disclosed by the present invention;

[0041] Figure 6 The three-dimensional structure diagram of the updated pollution migration behavior model of the present invention. Detailed implementation manners

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0043] Before understanding the technical solutions proposed in this application, it is necessary to first clarify the meaning of "pollutant behavior migration in mining areas". It should be added that pollutant behavior migration in mining areas specifically refers to the processes of diffusion, transformation, and fate of pollutants in mining areas in various environmental media, mainly including: the seepage migration of heavy metal ions in the hydrogeological unit, the chemical transport of acidic wastewater in the surface runoff process, and the turbulent diffusion of suspended particulate matter in the atmospheric boundary layer. To scientifically predict the environmental impact degree of pollutants in mining areas during the migration process, this application proposes an ecological environment big data processing method based on modeling the migration behavior of mining area pollutants.

[0044] Specifically, referring to Figure 1 it can be seen that the ecological environment big data processing method based on modeling the migration behavior of mining area pollutants includes: step S100 - step S400.

[0045] Step S100: Construct a migration behavior model of mining area pollutants based on the mining area parameter data within the target range and the ecological and geographical environment parameters around the mining area.

[0046] It should be noted that in step S100, the mining area parameter data includes: pollutant concentrations in metal mining areas, coal mining areas, salt mining areas, and rare earth mining areas, and the ecological and geographical environment parameters include: water source characteristic parameter data, terrain characteristic parameter data, climate and meteorological parameter data, soil type parameter data, and location parameter data. Among them, the water source characteristic parameter data is collected by water source monitoring equipment in the existing technology, including the pH value, dissolved oxygen content, temperature, and flow rate of the water body. The terrain characteristic parameter data and location parameter data are used to determine the elevation, slope, surface cover type, and longitude and latitude coordinates around the target mining area through existing satellite stereo images. The climate and meteorological parameter data is determined by historical records and real-time observations from local weather stations to determine precipitation, wind speed, humidity, and temperature. Finally, the soil type parameter data is used to measure the pH value, organic matter content, cation exchange capacity, and heavy metal background value of the soil through soil sampling and analysis in the existing technology.

[0047] Specifically, the method for constructing the migration behavior model of mining area pollutants includes: steps S101 - S104.

[0048] Step S101: Obtain the geodetic coordinate values of the protection points and the mining area within the target range.

[0049] It should be clear that in step S101, the protection points include: residential areas of the masses, ecological protection areas, and water source protection areas. It should be noted that the degree of influence of pollutants on these protection point areas is an important basis for evaluating the migration behavior of mining area pollutants. Therefore, obtaining the geodetic coordinate values of the protection points is to clarify the spatial distribution of these areas, thereby providing spatial reference data for the subsequent construction of the model. In addition, it should be noted that in step S101, the geodetic coordinate values refer to longitude and latitude coordinates and altitude, and the geodetic coordinate values of the mining area, residential areas of the masses, ecological protection areas, and water source protection areas are the longitude and latitude coordinates and altitude at the central axis position within the area.

[0050] Step S102: Determine the maximum diffusion range interval of mining area pollutants based on the geodetic coordinate values of the first group and the geodetic coordinate values of the mining area.

[0051] It should be noted that in step S102, the geodetic coordinate values of the first group specifically refer to the geodetic coordinate values taken for any one type of protection point.

[0052] Step S103: Obtain the pollutant concentration gradient within the maximum diffusion range area.

[0053] It should be noted that in step S103, the method for obtaining the pollutant concentration gradient is to divide the maximum diffusion range area into multiple spatial detection areas of the same volume, and use the concentration monitoring equipment in the existing technology to measure and record the pollutant concentration in each spatial detection area.

[0054] Step S104: Generate a migration behavior model of the mine area pollutants based on the concentration distribution results of the spatial detection areas.

[0055] It should be noted that in step S104, to enhance the dynamic prediction ability of the migration behavior model, it is necessary to integrate the spatial distribution of pollutants with the relationship between the concentration change of pollutants over time to construct a migration behavior model of the mine area pollutants. Specifically, based on the spatial concentration gradient information of pollutants in the maximum diffusion range area obtained in step S103, and combined with the physical and chemical properties of the mine area pollutants, a migration behavior model of the mine area pollutants with concentration changing over time is constructed to reflect the scenarios of pollutant diffusion and natural attenuation in three-dimensional space.

[0056] It should be noted that the functional expression form of the migration behavior model of the mine area pollutants in step S104 is as follows:

[0057] ;

[0058] Where is used to represent the concentration of pollutants at time and spatial position , is used to represent the initial concentration of the pollution source, represents the central position of the pollution source in the three-dimensional space coordinate system, is used to represent the natural attenuation coefficient of pollutants in the target environmental medium, with the unit of , The value of is determined by inputting the mine area parameter data and the ecological and geographical environment parameters around the mine area through Internet technology, and can be regarded as a constant. is used to represent the diffusion coefficient of pollutants in the medium, with the unit of , which is obtained through on-site monitoring or literature data.

[0059] It should be noted that the migration behavior model of the mine area pollutants is used to depict the concentration attenuation and spatial dilution characteristics of pollutants along the diffusion path over time, and can reflect the behavior process of pollutant migration and evolution in the environmental medium over time. It is a time dimension supplement to the static migration behavior model.

[0060] As a preferred embodiment, this embodiment is mainly used to improve the practical application function of the pollutant migration behavior model in the mining area. Specifically, when a heavy metal leakage event occurs in the stacking area of the mining area (taking copper ion Cu² + as a typical pollutant), the pollutant migration behavior model in the mining area quantitatively describes the three-dimensional diffusion behavior of pollutants along the x (horizontal direction), y (vertical surface direction), and z (penetration depth direction) by simulating the three-dimensional space migration process of pollutants in the soil-groundwater system. Its core application goal is to construct the degree of pollution diffusion within a 12-hour emergency response period.

[0061] It should be noted that in this example, the pollution source is located at the origin of coordinates =(0, 0, 0), the initial concentration is set to =500 μg / L. According to the actual parameters of the underground seepage medium, the diffusion coefficient =1.5 , the natural attenuation coefficient of the pollutant is taken as =0.015 , and the time point =12 h is selected as the model running time. At this time, referring to Figure 2 the content, it can be seen that the darker the gray area in the figure, the higher the concentration. The concentration in the area near the pollution source is significantly higher than that in the position far from the source point. Through this figure, the predicted concentration value at any spatial coordinate point at a specific time can be extracted. Taking the target monitoring point (x = 5, y = 5, z = 2) as an example, the calculation is carried out in combination with the migration function model proposed in this application.

[0062] At this time ;

[0063] ;

[0064] ; ;

[0065] .

[0066] It can be seen from this that 12 hours after the leakage of the pollution source, the concentration of copper ions is still as high as 197.24 μg / L, which is significantly higher than the limit value of the groundwater environmental quality standard (such as the "Groundwater Quality Standard" GB / T 14848).

[0067] Step S200: Retrieve the corresponding neutralization item from the ecological and geographical environment parameters around the mining area according to the type of the target mining area, and establish a neutralization efficiency index.

[0068] It should be noted that within step S200, the neutralization efficiency index is used to evaluate the natural weakening effect of the neutralizing item on the pollutant migration behavior.

[0069] As a preferred implementation, this implementation should supplement the natural weakening effect of the neutralizing item on the pollutant migration behavior within step S200.

[0070] Specifically, it includes: step S201 - step S203.

[0071] Step S201: Extract the neutralizing factors corresponding to the pollutants within the ecological geographical environment parameters and establish a reaction control chart.

[0072] It should be noted that step S201 extracts environmental factors with pollution neutralization ability from the ecological geographical parameters already obtained around the mining area, such as high-alkaline soil layers (such as carbonate or calcareous rock layers), biological communities (such as metal-enriched plants), high-pH water sources, etc., and establishes Figure 3 the expressed reaction control chart with the pollutant types (such as acidic, metal ions).

[0073] It should be noted that the reaction control chart has different neutralizing factors corresponding to pollutants represented by acidic solutions (H + , H2SO4) and metal ions (Pb 2+ , Cd 2+ ). Acidic pollutants react chemically in carbonate rock layers to generate harmless substances (H2o, CO2 and Ca 2+ ), and the specific reaction formula is CaCO3 + 2H + →Ca 2+ + CO2 + H2O. At the same time, high-pH water sources neutralize the acidic environment by combining OH - ions with H + to form water (OH - +H + →H2O). On the other hand, heavy metal ions are fixed by being absorbed by the roots of metal-enriched plants, reducing their migration and bioavailability in the environment.

[0074] Step S202: Identify the reaction relationship between the pollutant - neutralizing item within the reaction control chart.

[0075] Step S203: Set the neutralization efficiency index according to the reaction relationship between the pollutant - neutralizing item. The neutralization efficiency index is used to evaluate the natural weakening effect of the neutralizing item on the pollutant migration behavior.

[0076] It should be noted that within step S203, the neutralization efficiency index is determined by establishing a spatial distribution map of the neutralizing item and evaluating the percentage of the intersection area between it and the pollutant migration path in the total area.

[0077] Step S300: Obtain the migration frequency of the pollution factors with the same type as the ecological and geographical environment parameters and the target mining area, and set a correction index based on the migration frequency.

[0078] It should be noted that within step S300, the setting of the correction index is mainly used to reduce the interference of environmental fluctuations on the identification of pollution trends during the actual operation of the migration behavior model. The pollution factor represents the same type of pollution element as the pollutants in the ecological and geographical environment parameters and the target mining area.

[0079] As a preferred implementation, this implementation is mainly used to supplement the setting of the correction index in step S300, specifically including: step S301 - step S303.

[0080] Step S301: Collect the concentration time series data of the target pollution factor within the historical period (at least 3 years) through the distributed environmental sensor network deployed outside the mining area.

[0081] It should be noted that for metal mining areas, it is necessary to focus on monitoring the monthly concentration fluctuations of ionic state pollutants such as Cu 2+ , Pb 2+ , Cd 2+ , and for coal mining areas, focus on the seasonal variation laws of benzene series and polycyclic aromatic hydrocarbon organic pollutants. The obtained concentration time series data is specifically a concentration curve graph, that is Figure 4 within the past three years (only 34 months are shown in the attached figure).

[0082] It should be supplemented that in Figure 4 the content, the Cu²⁺ concentration generally shows a slight upward trend as a whole, and is accompanied by relatively obvious annual periodic fluctuations. The peak generally appears in summer every year. This feature may be related to the evaporation and concentration of water bodies caused by high temperatures, reflecting that copper ions have a certain seasonal accumulation tendency in the natural state. The Pb²⁺ concentration shows a slow downward trend, and at the same time shows a semi-annual cycle fluctuation feature, which may be related to wind direction changes, rainfall frequency or regional settlement processes, indicating that this factor has significant short-term periodic disturbances. The Cd²⁺ concentration is relatively stable as a whole, with a small fluctuation range and weak periodicity. In addition, it should be supplemented that Figure 4 in the content, three full-cycle mean reference lines of pollution factors are also set, corresponding to the average concentration levels of Cu²⁺, Pb²⁺ and Cd²⁺ respectively. These reference lines are used to judge the deviation degree of pollution concentration and help identify whether there is an abnormal upward trend.

[0083] Step S302: Decompose the concentration sequence into a trend term, a seasonal term and a residual term, and set a discrimination threshold. According to the comparison results between the trend term, the seasonal term, the residual term and the discrimination threshold, discriminate the pollution accumulation trend.

[0084] Specifically, the discriminant conditions for the pollution accumulation trend are as follows: when the linear regression slope of the trend term in the concentration curve graph exceeds the discriminant threshold α (such as α = 0.15 μg / (L·month) in the metal mining area), the standard deviation of the amplitude of the seasonal term is greater than the discriminant threshold β (taking twice the standard deviation of the same historical period), and there are six consecutive monitoring periods with the same-direction deviation in the residual term, it is determined that there is a non-artificial pollution upward trend. It should be noted that the non-artificial pollution here is natural disaster pollution.

[0085] It should be added that the discriminant threshold α is obtained by using the monthly pollutant concentration data in the past three years (or longer period) in the concentration curve graph, performing linear regression on the monthly average concentration sequence of the pollutant, calculating the slope of the trend term, and taking the mean + 2 times the standard deviation of the slope distribution at the 95% confidence level as the α threshold. The significance of such a setting is to establish a dynamically benchmark value with statistical significance to effectively distinguish natural fluctuations from abnormal accumulation phenomena. For the determination of the discriminant threshold β, it is determined by extracting twice the absolute value of the standard deviation between the historical seasonal term amplitude data and the real-time seasonal term amplitude data in the concentration curve graph.

[0086] Step S303: Construct a dynamic correction coefficient according to the deviation degree between the residual term and the discriminant threshold.

[0087] Specifically, the calculation function of the correction index is: , where is used to represent the correction coefficient, is used to represent the concentration residual value of the i-th monitoring period, is used to represent the tolerance threshold of the residual term, which is set according to the historical residual standard deviation, is the time weighting factor, which is determined according to the ratio of the current detection sequence to the total number of detection sequences, is used to represent the total number of detection periods.

[0088] As a preferred implementation, this implementation is used for the supplement when the correction index is actually used. Specifically, referring to Figure 5 , it can be seen that by decomposing the monthly copper ion concentration data collected by the sensors outside the mining area into trend terms, seasonal terms and residuals, based on the ratio of the residual to the set tolerance threshold combined with the time weighting factor, the correction index is obtained as a curve that changes dynamically with the monitoring period (month), which is used to dynamically adjust the false alarm risk in the discrimination of the non-artificial pollution upward trend. Among them, Figure 5 the blue smooth curve in represents the change trend of the correction index over time, and the superimposed dots show the actual calculated values for each month. When the correction index value is between 0 and 1, the closer the value is to 1, the smaller the residual fluctuation, the lower the false alarm probability of the pollution trend recognition, and the more reliable the discrimination result; the closer the value is to 0, the larger the residual, the higher the false alarm risk, and stronger correction is required.

[0089] Step S400: The migration behavior model updates the model based on the neutralization efficiency index and the correction index, and outputs a visualization report.

[0090] It should be noted that in step S400, the update method for the migration behavior model includes: step S401 - step S403.

[0091] Step S401: Integrate the neutralization efficiency index and the correction index into the input parameters of the migration behavior model.

[0092] It should be noted that in step S401, the neutralization efficiency index reflects the weakening ability of the natural environment around the mining area on pollutant migration, while the correction index is used to dynamically adjust the false alarm risk in pollution trend identification. By taking the two as supplementary input parameters, the prediction accuracy and adaptability of the model can be enhanced.

[0093] Specifically, after combining the neutralization efficiency index and the correction index, the updated migration behavior model is specifically as follows:

[0094] ;

[0095] where is the updated migration behavior model, is used to represent the neutralization efficiency index, where let

[0096] and are added together because the environment around the mining area contains some natural neutralization items, such as highly alkaline soil and metal-enriched plants. These factors will accelerate the attenuation of pollutants or reduce their effective concentration. This process is similar to enhanced attenuation, not only the natural attenuation of pollutants themselves, but also the reduction of pollutants by the environment. Therefore, the neutralization efficiency index is a supplement to the original attenuation coefficient . In addition, taking as the overall multiplication factor is because taking as the multiplication factor of the concentration prediction result can smoothly adjust the model output. This correction is a global scaling of the model output, rather than a local adjustment.

[0097] Step S402: Recalculate the concentration distribution of pollutants in the spatial and temporal dimensions based on the updated input parameters.

[0098] Specifically, in step S402, by introducing the neutralization efficiency index and the correction index, the model can more accurately simulate the migration path and attenuation process of pollutants in the actual environment. Referring to Figure 6 it can be seen that in the content shown by the updated migration behavior model, relative toFigure 2 The diffusion range of the modeled pollutant for the demonstrated migration behavior is significantly reduced, mainly reflected in the significant decrease in peak concentration, which is attributed to the neutralization efficiency index enhancing the attenuation effect. For example, the highly alkaline soil layer accelerates the chemical neutralization process of Cu²+. At the same time, the correction index smooths the influence of seasonal fluctuations, making the model's prediction in the direction of penetration depth (z-axis) closer to the actual environmental monitoring values and avoiding misjudgment caused by natural background changes.

[0099] Step S403: Generate a visualization report based on the updated migration behavior model.

[0100] It should be added that the generation of the visualization report is achieved by implanting the updated migration behavior model into the data processing tools and visualization software in the prior art. The spatial concentration distribution map in the report adopts a three-dimensional heat map form, intuitively reflecting the concentration differences of pollutants in different regions through the shade of color, while the time series curve shows the concentration change trend of key monitoring points, facilitating the identification of abnormal fluctuations. In addition, the impact analysis charts of the neutralization efficiency and correction index are presented in a combination of bar charts and line charts, clearly showing the actual impact of natural attenuation and false alarm correction on the judgment of pollution trends.

[0101] To further enhance the practical value of the report, the visualization content also supports interactive operations. Users can dynamically view the simulation results of pollutant diffusion by adjusting the time range, spatial coordinates, or specific parameter values. This design not only enhances the flexibility of data analysis but also provides more accurate decision-making support for the environmental management of mining areas. At the same time, the statistical summary of key indicators, including the maximum concentration value, average concentration value, and their corresponding time and spatial positions, is embedded in the report to help users quickly grasp the core characteristics of pollution diffusion.

[0102] It is worth noting that the generation process of the visualization report fully considers the actual needs of mining area ecological environment management. All charts are output in a standardized format and are accompanied by detailed data descriptions and technical annotations to ensure the accuracy and readability of information transmission. This design makes the report applicable not only to in-depth analysis by professional and technical personnel but also to provide intuitive reference for decision-makers without a technical background.

[0103] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended embodiments and their equivalents.

Claims

1. An ecological environment big data processing method based on modeling the migration behavior of pollutants in mining areas, characterized in that include: Obtain the geodetic coordinates of protection points and mining areas within the target range. Protection points include residential areas, ecological protection areas, and water source protection areas. Geodetic coordinates are used to represent latitude, longitude, and altitude. Determine the maximum diffusion range of pollutants in the mining area based on the geodetic coordinate values of the first group and the geodetic coordinate values of the mining area, wherein the geodetic coordinate values of the first group specifically refer to the geodetic coordinate values taken by any protection point type; Obtain the pollutant concentration gradient within the maximum diffusion range; Based on the concentration distribution results of the spatial detection area, a migration behavior model of pollutants in the mining area is generated.

2. The ecological environment big data processing method based on the modeling of pollutant migration behavior in mining areas according to claim 1, wherein: The corresponding neutralization items are retrieved within the ecological and geographical environment parameters around the mining area according to the target mining area type, and a neutralization efficiency index is established. The neutralization efficiency index is used to update the migration behavior model.

3. The ecological environment big data processing method based on the modeling of the migration behavior of pollutants in the mining area according to claim 2, wherein: The method for setting the neutralization efficiency index includes: Extract the corresponding neutralization factors of pollutants within the ecological and geographical environmental parameters and establish a reaction comparison chart; Identify pollutant-neutralizer reaction relationships within reaction control diagrams; The neutralization efficiency index is set according to the reaction relationship between pollutants and neutralization items. The neutralization efficiency index is used to evaluate the natural weakening effect of neutralization items on the migration behavior of pollutants. The neutralization efficiency index is determined by establishing a spatial distribution map of the neutralization item and evaluating the percentage of the intersection area with the pollutant migration path in the total area.

4. The ecological environment big data processing method based on the modeling of pollutant migration behavior in mining areas according to claim 3, characterized in that: The reaction control diagram extracts environmental factors with pollution neutralization capabilities from the ecological and geographical parameters obtained around the mining area. The environmental factors correspond to the pollutants in the mining area and can generate harmless substances through chemical reactions to reduce migration and biological effectiveness in the environment.

5. The ecological environment big data processing method based on the modeling of the migration behavior of pollutants in the mining area according to claim 2, wherein: By obtaining the migration frequency of the same pollution factors of the ecological and geographical environmental parameters and the target mining area type, and setting a correction index based on the migration frequency, the correction index is used to update the migration behavior model, so that the migration behavior model can reduce the interference of environmental fluctuations on pollution trend identification during actual operation.

6. The ecological environment big data processing method based on the modeling of the migration behavior of pollutants in the mining area according to claim 5, characterized in that: The methods for setting the correction index include: Through a distributed environmental sensor network deployed around the mining area, the concentration time series data of target pollution factors over a historical period are collected; The concentration series is decomposed into trend term, seasonal term and residual term, and a discrimination threshold is set. The cumulative trend of pollution is determined based on the comparison results between the trend term, seasonal term and residual term and the discrimination threshold; A dynamic correction coefficient is constructed according to the degree of deviation between the residual term and the discrimination threshold.

7. The ecological environment big data processing method based on the modeling of the migration behavior of pollutants in the mining area according to claim 6, characterized in that: The criteria for judging pollution accumulation trends are: When the linear regression slope of the trend term in the concentration curve exceeds the discrimination threshold α, the amplitude standard deviation of the seasonal term is greater than the discrimination threshold β, and there is a same-direction deviation in the residual term for six consecutive monitoring periods, it is determined that there is an upward trend in non-anthropogenic pollution; The discrimination threshold α is obtained by using the monthly pollutant concentration data in the historical time series of the concentration curve and performing linear regression on the monthly average concentration series of the pollutants to obtain the slope of the trend term. The mean of the slope distribution at the 95% confidence level + 2 times the standard deviation is set as the discrimination threshold α. This is used to establish a dynamic benchmark value with statistical significance and effectively distinguish between natural fluctuations and abnormal accumulation phenomena. For the determination of the discrimination threshold β, it is determined by extracting twice the absolute value of the standard deviation between the historical seasonal amplitude data and the real-time seasonal amplitude data within the concentration curve graph.

8. The ecological environment big data processing method based on the modeling of pollutant migration behavior in mining areas according to claim 5, characterized in that: The migration behavior model updates the model based on both the neutralization efficiency index and the correction index, and outputs a visualization report; Among them, the update method of the migration behavior model includes: Integrate the neutralization efficiency index and the correction index into the input parameters of the migration behavior model; Recalculate the concentration distribution of pollutants in the spatial and temporal dimensions based on the updated input parameters; Generate a visualization report according to the updated migration behavior model.

Images