Method, device and equipment for predicting soil heavy metal accumulation amount, medium and product

Abstract

The invention discloses a soil heavy metal cumulant prediction method, device and equipment, a medium and a product. The method comprises the following steps: in response to a pollution prediction request for a target enterprise emission plan, determining an emission source type according to the target emission plan, and determining a target production stage which can generate pollution emission corresponding to the emission source type in the target emission plan; determining a target heavy metal discharge amount corresponding to the target production stage, and determining a corresponding target diffusion intensity based on a preset diffusion prediction model; and according to the target diffusion intensity and a preset target characteristic variable influencing soil heavy metal accumulation, adopting a pre-trained target pollution prediction model to predict the heavy metal accumulation amount of surrounding soil after emission of the target enterprise. According to the technical scheme, the heavy metal accumulation amount of the surrounding soil after the target enterprise discharges can be accurately predicted, so that the risk prevention and control work of soil heavy metal pollution is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental pollution prevention and control, and particularly to a prediction method, device, equipment, medium and product for the cumulative amount of heavy metals in soil. Background Art

[0002] Non-ferrous metal production enterprises will emit a large amount of heavy metal dust, waste residue and waste water during the production process. If not properly disposed of, they will enter the surrounding soil through dry and wet deposition, surface runoff and sewage irrigation. Heavy metals will continuously accumulate in the soil, and their content is often much higher than the soil background value. At the same time, anthropogenic and natural characteristic variable factors will affect the migration and fate of heavy metals, and thus affect the vertical distribution of heavy metals in soil. Heavy metals in soil can be released and migrate to the food chain, groundwater and surface water for the second time, thus threatening human health. Therefore, the prevention and control of soil heavy metal pollution risk is particularly important.

[0003] Therefore, how to analyze the heavy metal emission amount and diffusion intensity according to the emission plan, and combine with the pollution prediction model to accurately predict the cumulative amount of heavy metals in the surrounding soil after the target enterprise's emission, so as to contribute to the risk prevention and control work of soil heavy metal pollution, is an urgent problem to be solved at present. Summary of the Invention

[0004] The present invention provides a prediction method, device, equipment, medium and product for the cumulative amount of heavy metals in soil to accurately predict the cumulative amount of heavy metals in the surrounding soil after the target enterprise's emission, so as to contribute to the risk prevention and control work of soil heavy metal pollution.

[0005] According to one aspect of the present invention, a prediction method for the cumulative amount of heavy metals in soil is provided, including:

[0006] In response to a pollution prediction request for the emission plan of a target enterprise, determine the emission source category according to the target emission plan, and determine the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category;

[0007] Determine the target heavy metal emission amount corresponding to the target production stage, and determine the corresponding target diffusion intensity based on a preset diffusion prediction model;

[0008] According to the target diffusion intensity and the target characteristic variables preset to affect the cumulative amount of heavy metals in soil, use a pre-trained target pollution prediction model to predict the cumulative amount of heavy metals in the surrounding soil after the target enterprise's emission.

[0009] According to another aspect of the present invention, a prediction device for the cumulative amount of heavy metals in soil is provided, including:

[0010] A first determination module, configured to, in response to a pollution prediction request for a target enterprise's emission plan, determine an emission source category according to the target emission plan, and determine a target production stage in the target emission plan that generates pollution emissions corresponding to the emission source category;

[0011] A second determination module, configured to determine a target heavy metal emission amount corresponding to the target production stage, and determine a corresponding target diffusion intensity based on a preset diffusion prediction model;

[0012] A prediction module, configured to predict the heavy metal accumulation amount in the soil around the target enterprise after emission by using a pre-trained target pollution prediction model according to the target diffusion intensity and a target characteristic variable preset to affect soil heavy metal accumulation.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the method for predicting the heavy metal accumulation amount in the soil according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for predicting the heavy metal accumulation amount in the soil according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, there is also provided a computer program product including a computer program, and when the computer program is executed by a processor, it implements the method for predicting the heavy metal accumulation amount in the soil according to any embodiment of the present invention.

[0019] In the technical solution of the embodiment of the present invention, in response to a pollution prediction request for the emission plan of a target enterprise, according to the target emission plan, the emission source category is determined, and the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category is determined; the target heavy metal emission amount corresponding to the target production stage is determined, and based on a preset diffusion prediction model, the corresponding target diffusion intensity is determined; according to the target diffusion intensity and the target characteristic variables preset to affect the accumulation of heavy metals in the soil, a pre-trained target pollution prediction model is used to predict the accumulation amount of heavy metals in the soil around the target enterprise after emission. By analyzing the heavy metal emission amount and diffusion intensity according to the emission plan and combining with the pollution prediction model, the accumulation amount of heavy metals in the soil around the target enterprise after emission can be accurately predicted, which helps the risk prevention and control work of soil heavy metal pollution.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of a method for predicting the accumulation amount of heavy metals in soil provided in Embodiment 1 of the present invention;

[0023] Figure 2 It is a flowchart of a method for predicting the accumulation amount of heavy metals in soil provided in Embodiment 2 of the present invention;

[0024] Figure 3 It is a structural block diagram of a device for predicting the accumulation amount of heavy metals in soil provided in Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below 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. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "first", "second", "target", "candidate", "alternative", etc. in the specification, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of the data in the technical solution of this application all comply with the relevant regulations of national laws and regulations.

[0028] Embodiment 1

[0029] Figure 1 is a flowchart of a method for predicting the soil heavy metal accumulation amount provided in Embodiment 1 of the present invention; this embodiment is applicable to analyzing the heavy metal emission amount and diffusion intensity according to the emission plan, and combining with the pollution prediction model to accurately predict the situation of the heavy metal accumulation amount in the surrounding soil after the target enterprise emits, especially applicable to predicting the pollution situation of the gas and liquid emissions of non-ferrous metal enterprises in production to the surrounding soil (i.e., predicting the soil heavy metal content). This method can be executed by a device for predicting the soil heavy metal accumulation amount, and the device for predicting the soil heavy metal accumulation amount can be implemented in the form of hardware and / or software. The device for predicting the soil heavy metal accumulation amount can be configured in an electronic device and executed by the pollution prediction system of a non-ferrous metal enterprise in production, such as Figure 1 shown, the method for predicting the soil heavy metal accumulation amount includes:

[0030] S101. In response to a pollution prediction request for the emission plan of the target enterprise, determine the emission source category according to the target emission plan, and determine the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category.

[0031] Among them, the pollution prediction request refers to a request for predicting the heavy metal accumulation amount in the surrounding soil after the target enterprise emits emissions based on the target emission plan. The target emission plan refers to the plan of the target enterprise to specifically emit waste gas and / or waste water to the surrounding area. The target emission plan can characterize the regulations of the target enterprise's expected emission of waste gas and / or waste water in different time periods through different methods. The emission source categories can include gas source type and water source type. The target production stage corresponds to the emission source category. The water source type corresponds to the emissions of various liquid raw material products through pipelines, tanks, etc.

[0032] Optionally, when the pollution prediction system detects the emission plan issued by the target enterprise, it can consider that the pollution prediction request for the target enterprise's emission plan is detected. At this time, in response to the pollution prediction request, it can match in the plan content of the target emission plan to determine the emission source category.

[0033] Optionally, determining the target production stage corresponding to the pollution emissions corresponding to the emission source category in the target emission plan includes: if the emission source category is the gas source type, determining that the target production stages corresponding to the pollution emissions corresponding to the emission source category in the target emission plan are the yard loading, unloading, and transportation stage and the ore crushing process stage; if the emission source category is the water source type, determining that the target production stage corresponding to the pollution emissions corresponding to the emission source category in the target emission plan is the waste water emission stage.

[0034] Among them, the yard loading, unloading, and transportation stage refers to the emission stage corresponding to the unorganized emission of heavy metals during the yard loading, unloading, and transportation process of non-ferrous metal enterprises and the centralized pollutant discharge port during the production process. The ore crushing process stage refers to the ore crushing process that generates heavy metal emissions during non-ferrous metal mining and beneficiation.

[0035] S102. Determine the target heavy metal emission amount corresponding to the target production stage, and based on the preset diffusion prediction model, determine the corresponding target diffusion intensity.

[0036] Among them, the preset diffusion prediction model can be an atmospheric diffusion model and / or a waste water diffusion model. The atmospheric diffusion model can be, for example, the Atmospheric Environmental Research Model (AERMOD). The target diffusion intensity can include the first diffusion intensity corresponding to gas source type diffusion and / or the second diffusion intensity corresponding to water source type diffusion.

[0037] Optionally, determining the target heavy metal emissions corresponding to the target production stage includes: if the emission source category is gas-source type and the target production stage is the yard loading, unloading, and transportation stage and the ore crushing process stage, then determining the first heavy metal emissions corresponding to the yard loading, unloading, and transportation stage according to the total particulate matter emissions and the heavy metal content in the yard dust; determining the second heavy metal emissions corresponding to the ore crushing process stage according to the emission monitoring data of the target enterprise or the data collected by a preset sampler; and determining the target heavy metal emissions corresponding to the target production stage according to the first heavy metal emissions and the second heavy metal emissions.

[0038] Among them, the first heavy metal emissions refer to the heavy metal emissions generated during the yard loading, unloading, and transportation stage, and the second heavy metal emissions refer to the heavy metal emissions generated during the ore crushing process stage. The target heavy metal emissions can be the sum of the first heavy metal emissions and the second heavy metal emissions.

[0039] Exemplarily, according to the total particulate matter emissions and the heavy metal content in the yard dust, the first heavy metal emissions corresponding to the yard loading, unloading, and transportation stage can be determined based on the following formula:

[0040] H i =W y ×C i

[0041] Among them, H i represents the heavy metal emissions during the loading, unloading, and transportation process, that is, the first heavy metal emissions, with the unit of t / a. W y represents the total particulate matter emissions in the yard dust, in t / a, and C i represents the heavy metal content in the yard dust, in mg / kg.

[0042] Optionally, the total particulate matter emissions W in the yard dust can be determined according to the dust particulate matter emission coefficient during the yard loading and unloading process, the material loading and unloading volume during the loading and unloading process, the particulate matter emission coefficient of the stockpile affected by wind erosion, and the surface area of the stockpile y .

[0043] Exemplarily, the total particulate matter emissions W in the yard dust can be determined according to the following formula y :

[0044]

[0045] Among them, E h represents the dust particulate matter emission coefficient during the yard loading and unloading process, in kg / t, M represents the total number of material loading and unloading times, G Yi represents the material loading and unloading volume during the i-th loading and unloading process, and E w represents the particulate matter emission coefficient of the stockpile affected by wind erosion, in kg / m 2 ², and AY Denotes the surface area of the stockpile, m 2 .

[0046] Optionally, the emission factor of fugitive particulate matter during the loading and unloading process of the stockyard can be determined based on the particle size multiplier of the material, the average ground wind speed, the moisture content of the material, and the removal efficiency of fugitive dust.

[0047] Exemplarily, the emission factor of fugitive particulate matter during the loading and unloading process of the stockyard can be determined based on the following formula:

[0048]

[0049] where, E h Denotes the emission factor of fugitive particulate matter during the loading and unloading process of the stockyard, kg / t, k i Denotes the particle size multiplier of the material, u denotes the average ground wind speed, m / s, M denotes the moisture content of the material, %, and δ denotes the removal efficiency of fugitive dust, %.

[0050] Optionally, the emission coefficient of wind erosion fugitive dust from the stockyard can be determined based on the particle size multiplier of the stockpile, the wind erosion potential of the maximum wind speed observed during disturbance, and the removal efficiency of fugitive dust by pollution control technology.

[0051] Exemplarily, the emission coefficient of wind erosion fugitive dust from the stockyard can be determined based on the following formula:

[0052]

[0053] where, E w Denotes the emission coefficient of wind erosion fugitive dust from the stockyard, kg / m 2 ; k i Particle size multiplier of the stockpile; n denotes the number of disturbances the stockpile undergoes per year; P i Denotes the wind erosion potential of the maximum wind speed observed during the i-th disturbance, g / m2; δ denotes the removal efficiency of fugitive dust by pollution control technology, %.

[0054] Exemplarily, the wind erosion potential P of the maximum wind speed observed during the i-th disturbance i Can be calculated by the following formula:

[0055]

[0056] where, u* denotes the friction velocity, m / s; Denotes the threshold friction velocity, i.e., the critical friction velocity for dust generation, m / s.

[0057] Exemplarily, the friction velocity u* can be calculated by the following formula:

[0058]

[0059] Among them, u(z) represents the ground wind speed, in m / s; Z represents the ground wind speed detection height, in m; z0 represents the ground roughness, in m;

[0060] Optionally, during the non-ferrous metal mining and beneficiation process, heavy metal emissions during the non-ferrous metal mining and beneficiation process are mainly generated by the ore crushing process. Therefore, it is possible to monitor the emission rate of particulate matter and the heavy metal content in particulate matter at all particulate matter emission outlets, and then calculate the heavy metal emissions during the non-ferrous metal production process, that is, determine the second heavy metal emissions corresponding to the ore crushing process stage according to the emission monitoring data of the target enterprise; it is also possible to set up atmospheric particulate matter sampling points in the material crushing workshop during the mining and beneficiation process, use an atmospheric particulate matter sampler to collect particulate matter, and measure the heavy metal content in the particulate matter, so as to calculate the heavy metal emissions during the production process, that is, determine the second heavy metal emissions corresponding to the ore crushing process stage according to the collection data of the preset sampler.

[0061] Optionally, determining the target heavy metal emissions corresponding to the target production stage includes: if the emission source category is water source type and the target production stage is the wastewater discharge stage, then determine the heavy metal emissions corresponding to the wastewater discharge stage according to the pipeline length, the pool area of the pond, the pollutant concentration in the wastewater, the discharge operation time, and the leakage coefficient when the target enterprise discharges through the pipeline and the pond under normal conditions; determine the heavy metal emissions corresponding to the wastewater discharge stage as the heavy metal emissions corresponding to the target production stage.

[0062] Among them, the heavy metal emissions corresponding to the wastewater discharge stage may include the leakage amounts corresponding to the wastewater passing through the pipeline and the pond.

[0063] It should be noted that since the acidic wastewater stored in the open air during non-ferrous metal mining and beneficiation is the main source of soil heavy metals, when determining that the emission source category is water source type, the target production stage can correspondingly be determined as the wastewater discharge stage.

[0064] Optionally, it is possible to determine the heavy metal emissions discharged through the pipeline during the wastewater discharge stage according to the discharge operation time, the leakage coefficient when the target enterprise discharges through the pipeline under normal conditions, the pipeline length, and the pollutant concentration in the wastewater; it is possible to determine the heavy metal emissions discharged through the pond during the wastewater discharge stage according to the discharge operation time, the leakage coefficient when the target enterprise discharges through the pond under normal conditions, the pool area of the pond, and the pollutant concentration in the wastewater.

[0065] Exemplarily, the heavy metal emissions discharged through the pipeline and the pond during the wastewater discharge stage can be determined respectively based on the following formula:

[0066] D i，wastewater(pipe) =T×k i，wastewater(pipe) ×L pipe ×ci，wastewater

[0067] D i，wastewater(pond) = T × k i，wastewater(pond) × S pond × c i，wastewater

[0068] Wherein, D i，wastewater(pipe) and D i，wastewater(pond) are respectively the amounts of pollutants discharged into the soil through the pipeline and pond leakage pathways, i.e., the heavy metal emission amounts, k i，wastewater(pipe) is the leakage coefficient of the pipeline under normal operating conditions, k i，wastewater(pond) is the leakage coefficient of the pond under normal operating conditions, L pipe is the pipeline length, S pond is the pond area, c i，wastewater is the pollutant concentration in the wastewater, and T is the discharge operation time.

[0069] Optionally, the sum of the heavy metal emission amounts discharged through the pipeline and the pond during the wastewater discharge stage can be determined as the total wastewater leakage amount, i.e., the heavy metal emission amount corresponding to the target production stage.

[0070] Optionally, based on a preset diffusion prediction model, the corresponding target diffusion intensity is determined, including: according to the target heavy metal emission amount, using a preset atmospheric diffusion model to predict the first diffusion intensity obtained by the target enterprise through atmospheric diffusion; according to the target heavy metal emission amount, using a preset wastewater diffusion model to predict the second diffusion intensity obtained by the target enterprise through wastewater diffusion.

[0071] Wherein, the wastewater diffusion model can be a cellular automaton. The wastewater diffusion of the enterprises in production mainly forms surface runoff through leakage, thereby affecting the surrounding soil environment.

[0072] Optionally, the pollution source parameters (including the target metal emission amount), meteorological data, and terrain data of the research area (i.e., the preset range area around the target enterprise) can be input into a preset atmospheric diffusion model, such as the AERMOD model or the CALPUFF model (three-dimensional non-steady-state Lagrangian diffusion model), to obtain the atmospheric heavy metal diffusion intensity, i.e., the first diffusion intensity.

[0073] Exemplarily, the pollution source parameters may specifically include at least one of the following: chimney location (latitude and longitude coordinates), height (in meters), and outlet diameter (in m), emission rate (in g / s), flue gas temperature (in °C), and heavy metal emissions corresponding to the target production stage; the meteorological data includes surface meteorological data and upper-air sounding data. The surface meteorological data includes air temperature (in °C), wind speed (in m / s), wind direction (in °), relative humidity (in %), and atmospheric pressure (in hPa); the upper-air sounding data includes the vertical distribution of temperature, wind speed, and wind direction with height. The data sources are mainly meteorological observation stations and numerical weather prediction models, and these data are processed by the AERMOD meteorological preprocessing module in the AERMET software to generate the meteorological parameter file (.sfc) required by the model. The terrain data may include slope, aspect, and elevation, covering the latitude and longitude range and projection coordinate system of the simulation area, and these data are processed by the AERMAP terrain preprocessing module to generate the terrain elevation file (.dem) required by the model.

[0074] Exemplarily, after inputting the pollution source parameters (including the target metal emissions), meteorological data, and terrain data into the AERMOD model, by running the AERMOD file, the particulate matter concentration (in g / m³) at different time scales (1 hour, 3 hours, 8 hours, and 24 hours) is output. The output results are copied into Excel to obtain the annual average ground concentration of each grid point relative to the pollution source. Further, the rasterization tool of the ArcGIS software can be used for data processing to obtain the pollutant diffusion situation in raster form, and finally, the diffusion intensities at 1 hour, 3 hours, 8 hours, 24 hours, and annual average (in g / m³) are output.

[0075] Optionally, using a preset wastewater diffusion model, the research area where the target enterprise is located can be divided into grids, and based on the initial point sources within the grids, combined with the distance from the target enterprise, elevation, slope, and surface roughness, the diffusion intensity of heavy metals in the wastewater, that is, the second diffusion intensity, can be calculated:

[0076]

[0077] where Slope represents the slope (0 - 90°) between grid points, Rou represents the roughness, Dis represents the horizontal distance between grids, D i，wastewater represents the leakage volume (in L) of the wastewater, c represents the heavy metal concentration (in mg / L) in the wastewater, and finally the data is standardized. JL i refers to the diffusion intensity of heavy metals in the wastewater, that is, the second diffusion intensity.

[0078] S103. According to the target diffusion intensity and the target characteristic variables preset for affecting the accumulation of heavy metals in soil, use the pre-trained target pollution prediction model to predict the accumulation amount of heavy metals in the soil around the target enterprise after its emission.

[0079] Among them, the target feature variable refers to the factor variable among the candidate feature variables that has a greater impact on soil heavy metal accumulation. The candidate feature variables can represent 26 variable indicators corresponding to 6 major influencing factors (i.e., soil properties, climate, geography, agriculture, vegetation, and socioeconomic).

[0080] Exemplarily, the candidate feature variables corresponding to different influencing factors and their related information can be represented by Table 1 below:

[0081] Table 1: Candidate Feature Variables Corresponding to Different Influencing Factors

[0082]

[0083]

[0084] The target pollution prediction model can refer to a basic learner obtained by integrating learners trained by at least two deep learning algorithms. The deep learning algorithms can include at least two of the following: Extreme Gradient Boosting (XGB), support vector machine (SVM), Random Forest (RF), k-Nearest Neighbor (KNN), Decision Tree (DT), and Artificial Neural Network (ANN).

[0085] Optionally, the genetic algorithm can be used to optimize the parameter configuration of each basic learner to obtain the optimal solution of each learner's model; and the ten-fold cross-validation method can be used to verify the model, and the root mean square error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R 2 ) are used to evaluate the model accuracy.

[0086] Optionally, for the selection of basic learners: the K-Means algorithm can be used to prune the basic learners to remove redundant basic learners with similar prediction results; or the multi-objective programming approach (MOBA) can be used to optimize and select the basic learners to determine the basic learners participating in the final integration.

[0087] Optionally, for the integration of base learners, the "elastic net algorithm" integration strategy can be utilized to integrate the selected base learners by combining the output result weights of the base learners (see the following formula), thereby improving the prediction accuracy and stability of the model.

[0088] e it =|z it -y i |

[0089]

[0090] Wherein, e it represents the absolute error of the prediction result of the t-th base learner for the sample i, z it represents the prediction result of the t-th base learner for the sample i, y i represents the expected result of the sample i, 0.1 represents the smoothing factor, a it represents the weight factor of the t-th base learner for the sample i, and w it represents the importance weight of the prediction result of the base learner.

[0091] Optionally, according to the target diffusion intensity and the preset target characteristic variables affecting the accumulation of heavy metals in soil, a pre-trained target pollution prediction model is used to predict the accumulation amount of heavy metals in the soil around the target enterprise after emission, including: determining the degree of association between the candidate characteristic variables and the accumulation amount of heavy metals in the soil based on a preset statistical test method, and determining the target characteristic variables affecting the accumulation of heavy metals in the soil from the candidate characteristic variables according to the degree of association; inputting the target characteristic variables and the target diffusion intensity into the pre-trained target pollution prediction model to predict the accumulation amount of heavy metals in the soil around the target enterprise after emission. Among them, the preset statistical test method can be the Spearman (Spearman rank correlation coefficient) and Kruskal-Wallis (Kruskal-Wallis test) methods.

[0092] Optionally, the SHAP (SHapley Additive exPlanations) algorithm can be used to predict the local interpretation (the influence of each candidate characteristic variable on the accumulation amount of heavy metals in the soil at a specific spatial location) and the global interpretation (the influence of each candidate characteristic variable on the accumulation amount of heavy metals in the entire region), that is, to determine the degree of association between the candidate characteristic variables and the accumulation amount of heavy metals in the soil.

[0093] It should be noted that SHAP is a model interpretation method based on game theory, which is used to quantify the contribution of feature variables to model prediction. The SHAP method provides a consistent and interpretable assessment of feature importance by calculating the marginal contribution of each feature in all possible feature combinations. Local interpretation is to explain the prediction results of soil heavy metal accumulation at a specific spatial location, that is, the contribution of each independent variable to the predicted value in a certain sample point. For a specific sample point, the SHAP values may show that soil pH and organic matter content have a greater contribution to the prediction results, and the contribution of soil pH is negative, while the contribution of organic matter content is positive. Global interpretation is to explain the prediction results of soil heavy metal accumulation in the entire region, that is, the overall contribution of each independent variable to the predicted value of the entire region. The SHAP summary plot results may show that soil pH and organic matter content have a greater overall contribution to the prediction results of the entire region, and the contribution of soil pH is negative, while the contribution of organic matter content is positive. The SHAP interaction plot may show a significant interaction between soil pH and organic matter content. Through the SHAP algorithm, the independent and interactive effects of feature variables on soil heavy metal accumulation can be quantified.

[0094] Optionally, according to the degree of association and in combination with a preset association threshold, the candidate feature variables with an association degree greater than the association threshold can be determined as the target feature variables affecting soil heavy metal accumulation.

[0095] Optionally, based on the historical atmospheric diffusion intensity, historical wastewater diffusion intensity, historical feature variables, and the corresponding historical soil heavy metal accumulation, the basic learner can be iteratively trained to obtain the target pollution prediction model.

[0096] Optionally, after screening the eligible feature variables from the six major factors and 26 indicators affecting soil heavy metal accumulation, that is, after determining the target feature variables, the pre-trained target pollution prediction model can be used to predict the heavy metal accumulation in the soil around the target enterprise after its emission according to the target feature variables and the target diffusion intensity.

[0097] Exemplarily, the Bootstrap method can be used to generate 5000 samples to evaluate the uncertainty of the model prediction results and calculate the 95% confidence interval of the model estimated value. Specifically, first, through Bootstrap resampling, 5000 Bootstrap samples are randomly generated for the established prediction model and the original data set, and the model is retrained with the 5000 samples. The input data is predicted to obtain the predicted values, and the 2.5% and 97.5% quantiles of the predicted values are directly taken as the upper and lower bounds of the 95% confidence interval.

[0098] In the technical solution of the embodiment of the present invention, in response to a pollution prediction request for the emission plan of a target enterprise, according to the target emission plan, the emission source category is determined, and the target production stage that will generate pollution emissions corresponding to the emission source category in the target emission plan is determined; the target heavy metal emission amount corresponding to the target production stage is determined, and based on a preset diffusion prediction model, the corresponding target diffusion intensity is determined; according to the target diffusion intensity and the target characteristic variables preset to affect soil heavy metal accumulation, a pre-trained target pollution prediction model is used to predict the heavy metal accumulation amount in the soil around the target enterprise after emission. By analyzing the heavy metal emission amount and diffusion intensity according to the emission plan and combining with the pollution prediction model, the heavy metal accumulation amount in the soil around the target enterprise after emission can be accurately predicted, which helps the risk prevention and control work of soil heavy metal pollution.

[0099] Embodiment 2

[0100] Figure 2 is a flowchart of a method for predicting the heavy metal accumulation amount in soil provided by Embodiment 2 of the present invention; on the basis of the above embodiment, this embodiment provides a preferred example for predicting the heavy metal accumulation amount in soil. Specifically, as Figure 2 shown, the method includes the following processes:

[0101] S201. In response to a pollution prediction request for the emission plan of a target enterprise, according to the target emission plan, determine the emission source category.

[0102] S202. If the emission source category is gas-source type, determine that the target production stages that will generate pollution emissions corresponding to the emission source category in the target emission plan are the yard loading, unloading and transportation stage and the ore crushing process stage.

[0103] S203. If the emission source category is water-source type, determine that the target production stage that will generate pollution emissions corresponding to the emission source category in the target emission plan is the wastewater emission stage.

[0104] S204. Determine the target heavy metal emission amount corresponding to the target production stage.

[0105] S205. According to the target heavy metal emission amount, use a preset atmospheric diffusion model to predict the first diffusion intensity obtained by the target enterprise through atmospheric diffusion.

[0106] S206. According to the target heavy metal emission amount, use a preset wastewater diffusion model to predict the second diffusion intensity obtained by the target enterprise through wastewater diffusion.

[0107] S207. Based on a preset statistical test method, determine the degree of association between candidate characteristic variables and soil heavy metal accumulation, and according to the degree of association, determine the target characteristic variables that affect soil heavy metal accumulation from the candidate characteristic variables.

[0108] S208. Input the target feature variable and the target diffusion intensity into a pre-trained target pollution prediction model to predict the heavy metal accumulation in the soil around the target enterprise after its emissions.

[0109] Embodiment III

[0110] Figure 3 FIG. is a structural block diagram of a prediction device for soil heavy metal accumulation provided in Embodiment III of the present invention; this embodiment is applicable to analyzing heavy metal emissions and diffusion intensity according to an emission plan, and combining with a pollution prediction model to accurately predict the heavy metal accumulation in the soil around the target enterprise after its emissions. The prediction device for soil heavy metal accumulation provided in the embodiments of the present invention can execute the prediction method for soil heavy metal accumulation provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method; the prediction device for soil heavy metal accumulation can be implemented in the form of hardware and / or software, and is configured in an electronic device with the function of predicting soil heavy metal accumulation, and is executed by the pollution prediction system of a non-ferrous metal producing enterprise, such as Figure 3 As shown, the prediction device for soil heavy metal accumulation may specifically include:

[0111] The first determination module 301 is configured to, in response to a pollution prediction request for the emission plan of the target enterprise, determine the emission source category according to the target emission plan, and determine the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category.

[0112] The second determination module 302 is configured to determine the target heavy metal emissions corresponding to the target production stage, and determine the corresponding target diffusion intensity based on a preset diffusion prediction model.

[0113] The prediction module 303 is configured to, according to the target diffusion intensity and the target feature variable preset to affect soil heavy metal accumulation, use a pre-trained target pollution prediction model to predict the heavy metal accumulation in the soil around the target enterprise after its emissions.

[0114] In the technical solution of the embodiment of the present invention, in response to a pollution prediction request for the emission plan of a target enterprise, according to the target emission plan, the emission source category is determined, and the target production stage that will generate pollution emissions corresponding to the emission source category in the target emission plan is determined; the target heavy metal emission amount corresponding to the target production stage is determined, and based on a preset diffusion prediction model, the corresponding target diffusion intensity is determined; according to the target diffusion intensity and the target characteristic variables preset to affect the accumulation of heavy metals in the soil, a pre-trained target pollution prediction model is used to predict the heavy metal accumulation amount in the soil around the target enterprise after emission. By analyzing the heavy metal emission amount and diffusion intensity according to the emission plan and combining with the pollution prediction model, the heavy metal accumulation amount in the soil around the target enterprise after emission can be accurately predicted, which helps the risk prevention and control work of soil heavy metal pollution.

[0115] Further, the first determination module 301 may include:

[0116] The first determination unit is used to, if the emission source category is gas source type, determine that the target production stage that will generate pollution emissions corresponding to the emission source category in the target emission plan is the yard loading, unloading and transportation stage and the ore crushing process stage;

[0117] The second determination unit is used to, if the emission source category is water source type, determine that the target production stage that will generate pollution emissions corresponding to the emission source category in the target emission plan is the wastewater emission stage.

[0118] Further, the second determination module 302 is specifically used for:

[0119] If the emission source category is gas source type and the target production stage is the yard loading, unloading and transportation stage and the ore crushing process stage, then according to the total particulate matter emission amount and the heavy metal content in the yard dust, determine the first heavy metal emission amount corresponding to the yard loading, unloading and transportation stage;

[0120] According to the emission monitoring data of the target enterprise or the data collected by a preset sampler, determine the second heavy metal emission amount corresponding to the ore crushing process stage;

[0121] According to the first heavy metal emission amount and the second heavy metal emission amount, determine the target heavy metal emission amount corresponding to the target production stage.

[0122] Further, the second determination module 302 is also used for:

[0123] If the emission source category is water source type and the target production stage is the wastewater emission stage, then according to the pipeline length, the pond area of the pond, the pollutant concentration in the wastewater, the emission operation time, and the leakage coefficient when the target enterprise discharges through the pipeline and the pond under normal conditions, determine the heavy metal emission amount corresponding to the wastewater emission stage;

[0124] Determine the heavy metal emissions corresponding to the wastewater discharge stage as the heavy metal emissions corresponding to the target production stage.

[0125] Further, the second determination module 302 is further configured to:

[0126] According to the target heavy metal emissions, use a preset atmospheric diffusion model to predict the first diffusion intensity obtained by the target enterprise through atmospheric diffusion;

[0127] According to the target heavy metal emissions, use a preset wastewater diffusion model to predict the second diffusion intensity obtained by the target enterprise through wastewater diffusion.

[0128] Further, the prediction module 303 is specifically configured to:

[0129] Based on a preset statistical test method, determine the degree of association between the candidate feature variables and the soil heavy metal accumulation amount, and according to the degree of association, determine the target feature variables that affect the soil heavy metal accumulation from the candidate feature variables;

[0130] Input the target feature variables and the target diffusion intensity into a pre-trained target pollution prediction model to predict the heavy metal accumulation amount in the soil around the target enterprise after emission.

[0131] Embodiment IV

[0132] Figure 4 It is a schematic structural diagram of an electronic device provided in Embodiment IV of the present invention. Figure 4 Shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0133] Such as Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as read-only memory (ROM) 12, random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12, and RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0135] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the prediction method for the soil heavy metal accumulation amount.

[0136] In some embodiments, the prediction method for the soil heavy metal accumulation amount can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the prediction method for the soil heavy metal accumulation amount described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the prediction method for the soil heavy metal accumulation amount in any other appropriate manner (for example, by means of firmware).

[0137] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0138] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0139] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0142] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0143] In one embodiment, the embodiment of the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the prediction method for the soil heavy metal accumulation amount in any embodiment of the present invention.

[0144] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages and also conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, can be connected to an external computer (e.g., by connecting through the Internet using an Internet service provider).

[0145] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0146] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A prediction method for soil heavy metal accumulation amount, characterized in that Including: In response to a pollution prediction request for the target enterprise's emission plan, determine the emission source category according to the target emission plan, and determine the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category; Determine the target heavy metal emissions corresponding to the target production stage, and based on a preset diffusion prediction model, determine the corresponding target diffusion intensity; According to the target diffusion intensity and the preset target characteristic variables affecting soil heavy metal accumulation, use a pre-trained target pollution prediction model to predict the heavy metal accumulation in the soil around the target enterprise after emission.

2. The method according to claim 1, wherein Determine the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category, including: If the emission source category is gas-source type, determine that the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category is the yard loading, unloading and transportation stage and the ore crushing process stage; If the emission source category is water-source type, determine that the target production stage in the target emission plan that will generate pollution emissions corresponding to the emission source category is the wastewater discharge stage.

3. The method according to claim 2, wherein Determine the target heavy metal emissions corresponding to the target production stage, including: If the emission source category is gas-source type, and the target production stage is the yard loading, unloading and transportation stage and the ore crushing process stage, determine the first heavy metal emissions corresponding to the yard loading, unloading and transportation stage according to the total particulate matter emissions and the heavy metal content in the yard dust; Determine the second heavy metal emissions corresponding to the ore crushing process stage according to the emission monitoring data of the target enterprise or the data collected by a preset sampler; Determine the target heavy metal emissions corresponding to the target production stage according to the first heavy metal emissions and the second heavy metal emissions.

4. The method according to claim 2, characterized in that, Determine the target heavy metal emissions corresponding to the target production stage, including: If the emission source category is water-source type, and the target production stage is the wastewater discharge stage, determine the heavy metal emissions corresponding to the wastewater discharge stage according to the pipeline length, the pond area, the pollutant concentration in the wastewater, the discharge operation time, and the leakage coefficient when the target enterprise discharges through the pipeline and the pond under normal conditions; Determine the heavy metal emissions corresponding to the wastewater discharge stage as the heavy metal emissions corresponding to the target production stage.

5. The method according to claim 1, wherein Based on a preset diffusion prediction model, determine the corresponding target diffusion intensity, including: According to the target heavy metal emissions, use a preset atmospheric diffusion model to predict the first diffusion intensity obtained by the target enterprise through atmospheric diffusion; According to the target heavy metal emissions, use a preset wastewater diffusion model to predict the second diffusion intensity obtained by the target enterprise through wastewater diffusion.

6. The method according to claim 1, characterized in that, According to the target diffusion intensity and the preset target characteristic variables affecting soil heavy metal accumulation, use a pre-trained target pollution prediction model to predict the heavy metal accumulation in the soil around the target enterprise after emission, including: Based on a preset statistical test method, determine the correlation degree between the candidate characteristic variables and the soil heavy metal accumulation, and according to the correlation degree, determine the target characteristic variables affecting soil heavy metal accumulation from the candidate characteristic variables; Input the target characteristic variables and the target diffusion intensity into a pre-trained target pollution prediction model to predict the heavy metal accumulation in the soil around the target enterprise after emission.

7. A prediction device for the cumulative amount of heavy metals in soil, characterized in that, Including: A first determination module, configured to, in response to a pollution prediction request for a target enterprise's emission plan, determine an emission source category according to the target emission plan, and determine a target production stage in the target emission plan that generates pollution emissions corresponding to the emission source category; A second determination module, configured to determine a target heavy metal emission amount corresponding to the target production stage, and determine a corresponding target diffusion intensity based on a preset diffusion prediction model; A prediction module, configured to predict the heavy metal accumulation amount in the soil around the target enterprise after emission by using a pre-trained target pollution prediction model according to the target diffusion intensity and a target characteristic variable preset for affecting soil heavy metal accumulation.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the heavy metal accumulation amount in the soil according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the method for predicting the heavy metal accumulation amount in the soil according to any one of claims 1-6 when executed by a processor.

10. A computer program product, characterized in that, The computer program product includes a computer program, and the computer program implements the method for predicting the heavy metal accumulation amount in the soil according to any one of claims 1-6 when executed by a processor.

Images