Soil pollution prediction method and system based on input and output flux of pollution source

Abstract

The application discloses a soil pollution prediction method and system based on input and output fluxes of pollution sources, belongs to the technical field of soil pollution risk early warning, and aims to solve the problems of incomplete flux accounting, low spatial precision and declining long-term prediction accuracy with time step in the prior art; the research area is divided into square grids with a set side length, and parameters such as soil properties, topography and hydrology are collected; a complete mass conservation system including four types of input fluxes such as atmospheric deposition and surface runoff and four types of output fluxes such as groundwater leaching and plant absorption is constructed, an influence coefficient of terrain blocking and distance attenuation weighted fusion is introduced to accurately quantify the spatial contribution of pollution sources; a first-order explicit difference is used to complete preliminary prediction, a correction coefficient is generated by combining the trend intensity ratio and the concentration trend ratio of historical concentration to optimize the result, and finally a pollution degree spatial distribution map is generated; and the application significantly improves the calculation accuracy of soil pollutant concentration and the reliability of long-term prediction.

Description

Technical Field

[0001] This invention relates to the field of soil pollution risk early warning technology, and more specifically, to a method and system for predicting soil pollution based on the input and output fluxes of pollution sources. Background Technology

[0002] With the acceleration of industrialization and urbanization, as well as the continuous advancement of intensive agricultural production, pollutants from multiple sources, such as industrial waste emissions, agricultural non-point source pollution, and atmospheric deposition, are constantly entering the soil environment. This has led to increasingly serious problems of soil heavy metal and persistent organic pollutant accumulation. Soil pollution is characterized by its hidden nature, delayed effects, accumulation, and irreversibility. Once pollution occurs, it not only damages the function of the soil ecosystem but also threatens human health through bioaccumulation in the food chain. Furthermore, subsequent remediation is costly, time-consuming, and difficult.

[0003] Currently, soil pollution prediction methods still have the following technical shortcomings in practical applications: The calculation of pollutant input and output fluxes is incomplete, often focusing only on single pathways such as anthropogenic emissions or atmospheric deposition, while ignoring key processes such as cross-grid migration of surface runoff, groundwater recharge and leaching, plant uptake, and soil biodegradation. This results in an incomplete conservation relationship of soil pollutant mass and a large deviation in concentration calculation. Traditional numerical prediction methods extrapolate based solely on flux conditions at the current moment, failing to fully utilize the pollution evolution patterns contained in long-term historical monitoring data. They cannot correct prediction errors caused by model parameter uncertainties and sudden pollution sources, resulting in a significant decrease in long-term prediction accuracy over time.

[0004] To address this, a method and system for predicting soil pollution based on the input and output fluxes of pollution sources have been developed. Summary of the Invention

[0005] To overcome the above-mentioned deficiencies of the prior art, embodiments of the present invention provide a method and system for predicting soil pollution based on the input and output fluxes of pollution sources.

[0006] To achieve the above objectives, the present invention provides the following technical solution: Soil pollution prediction methods based on pollution source input and output fluxes include: Regional discretization data acquisition: The study area is divided into square grid cells with a side length of L, and basic attribute parameters of each grid cell are collected, including soil property parameters, topographic parameters and hydrological parameters; Input flux calculation: For each grid cell, calculate its total pollutant input flux per unit time, including atmospheric deposition flux, surface runoff input flux, groundwater recharge input flux, and anthropogenic emission flux; Output flux calculation: For each grid cell, calculate its total pollutant output flux per unit time, including surface runoff output flux, groundwater leaching output flux, soil degradation flux, and plant uptake flux. Pollution level classification: For any j-th grid cell, after calculating the concentration of pollutants in the soil, the pollution level of a single grid cell is quantified and a spatial distribution map is generated based on the calculated current pollutant concentration of each grid cell. Pollution level prediction: A first-order explicit difference scheme is used to predict the pollutant concentration of each grid cell j in the future, given a time step. When the prediction is completed, the pollutant concentration is dynamically adjusted by combining the historical concentration change trend and using correction logic, and then used as the final predicted pollution concentration.

[0007] Specifically, soil property parameters include organic matter content, pH value, clay content, sand content, bulk density, and porosity. Topographic parameters include digital elevation, slope, and aspect; Hydrological parameters include groundwater level depth, surface runoff, soil moisture content, and annual precipitation.

[0008] Specifically, total pollutant input flux ; , , , These represent atmospheric deposition flux, surface runoff input flux, groundwater recharge input flux, and anthropogenic emission flux, respectively.

[0009] Specifically, total pollutant output flux ; in , , , These represent surface runoff output flux, groundwater leaching output flux, soil degradation flux, and plant uptake flux, respectively.

[0010] Specifically, for any grid cell j, the change in the total mass of pollutants in the soil within a unit time Δt is equal to the input flux minus the output flux: ; The total mass of pollutants in the soil within grid cell j; Converting mass to concentration, the total mass of soil pollutants within the grid can be represented as follows: ; in The average concentration of soil pollutants within grid j. For soil volume, Soil bulk density; The mass conservation equation then becomes: ,but .

[0011] Specifically, based on the concentration of arbitrary grid cells By using pre-established mapping rules, the pollution level is mapped, and the pollution concentration and level of each grid are assigned to the corresponding grid cell to generate a spatial distribution map of the current pollution level in the study area.

[0012] Specifically, using a first-order explicit difference scheme, given a time step Δt, the concentration update formula from t to Δt is: ; For any grid cell j, extract e historical pollutant concentration values ​​sorted chronologically; denoted as ; After determining the trend intensity ratio and concentration trend ratio, a comprehensive processing is performed to output the concentration change coefficient; Using pre-established mapping rules, the concentration change coefficient is converted into a correction coefficient, and then compared with... Multiply the results to obtain the final predicted pollution concentration.

[0013] Specifically, a single-grid concentration time series line graph is drawn with time as the horizontal axis and the historical pollutant concentration of each group as the vertical axis. Each time node corresponds to a numerical point, and adjacent numerical points are connected to form a numerical line. For each numerical line, compare the concentration values ​​of two sets of numerical points. If the concentration value of the right numerical point in the numerical points formed by the numerical lines is higher than the concentration value of the left numerical point, then mark the slope of the numerical line as the first slope; sum all the first slopes to obtain the concentration increase value. If the concentration value of the rightmost point among the numerical points formed by the numerical line is lower than the concentration value of the leftmost point, then the absolute value of the slope of the numerical line is marked as the second slope. Summing all the second slopes yields the concentration decrease value; using the concentration increase value as the numerator and the concentration decrease value as the denominator, the ratio is calculated, and the trend intensity ratio is output. Will Based on the intermediate time point, the concentration sequences of the first half and the second half are obtained. The arithmetic mean of the two sequences is taken respectively, and the average concentration of the first half and the average concentration of the second half are output. The ratio is calculated by using the average concentration of the second half as the numerator and the average concentration of the first half as the denominator, and the concentration trend ratio is output.

[0014] Soil pollution prediction systems based on pollution source input and output fluxes include: The grid unit parameter acquisition module is used to divide the study area into square grid units with a set side length and collect soil property parameters, topographic parameters, and hydrological parameters corresponding to each grid. The pollutant input flux calculation module is used to calculate the total pollutant input flux of a single grid according to four pathways: atmospheric deposition, surface runoff inflow, groundwater recharge input, and anthropogenic emissions. The pollutant output flux calculation module is used to calculate the total pollutant output flux of a single grid according to four pathways: surface runoff output, groundwater leaching, soil degradation, and plant absorption. The pollution classification and dynamic prediction module calculates the current soil pollutant concentration based on the mass conservation formula, classifies the pollution risk into three levels (low, medium, and high) and generates spatial distribution data; it uses a first-order explicit difference formula to preliminarily predict future pollutant concentrations, extracts multiple sets of historical time-series concentration data to determine correction coefficients to optimize the initial differential concentration calculation, and outputs the final predicted concentration.

[0015] The technical effects and advantages of this invention are as follows: This invention discretizes the study area using a square grid with varying side lengths, comprehensively collecting spatially heterogeneous parameters such as soil properties, topography, and hydrology. It also constructs a mass conservation system encompassing four types of input fluxes: atmospheric deposition, surface runoff input, groundwater recharge input, and anthropogenic emissions; and four types of output fluxes: surface runoff output, groundwater leaching, soil degradation, and plant uptake. For anthropogenic pollution sources, it innovatively introduces a weighted fusion method for calculating the influence coefficient of topographic barrier correction factors and distance attenuation factors. This accurately quantifies the spatial contribution of pollution sources under complex terrain, solving the problems of incomplete flux calculation, low spatial accuracy, and distortion of topographic influence in traditional models. It significantly improves the accuracy of soil pollutant concentration calculation and can accurately identify local high-pollution risk points in key areas, providing reliable support for refined soil environmental management.

[0016] This invention employs a prediction logic that combines mechanism-driven and data-corrected approaches. First, it uses a first-order explicit difference scheme to make a preliminary prediction of pollutant concentrations based on current flux conditions. Then, it extracts multiple sets of historical time-series concentration data and calculates the concentration change coefficient by combining the trend intensity ratio and concentration trend ratio. This coefficient is then converted into a correction coefficient to dynamically adjust the preliminary prediction results. This fully leverages the pollution evolution patterns contained in historical monitoring data, effectively corrects prediction errors caused by model parameter uncertainties and sudden pollution sources, and solves the problem of traditional numerical models where long-term prediction accuracy decreases significantly with time steps. This greatly improves the reliability of long-term soil pollution prediction and provides a scientific basis for soil pollution risk early warning and remediation decisions. Attached Figure Description

[0017] Figure 1 This is a flowchart of the soil pollution prediction method based on the input and output flux of pollution sources according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1 like Figure 1 As shown, the soil pollution prediction method based on the input and output fluxes of pollution sources is as follows: Regional discretization data acquisition: The study area is divided into square grid cells with a side length of L, where L ranges from 5 to 50 m, determined according to the study scale and accuracy requirements; basic attribute parameters of each grid cell are collected, including soil property parameters, topographic parameters, and hydrological parameters; Ordinary Kriging interpolation is used to spatially interpolate soil property parameters at discrete sampling points, generating a continuous spatially distributed raster layer, which is then matched with the grid cells.

[0020] Soil property parameters include organic matter content, pH value, clay content, sand content, bulk density, and porosity. Topographic parameters include digital elevation, slope, and aspect; Hydrological parameters include groundwater level depth, surface runoff, soil moisture content, and annual precipitation.

[0021] Input flux calculation: For each grid cell, calculate its total pollutant input flux per unit time, including atmospheric deposition flux, surface runoff input flux, groundwater recharge input flux, and anthropogenic emission flux; Specifically: Total input flux of pollutants ; , , , These represent atmospheric deposition flux, surface runoff input flux, groundwater recharge input flux, and anthropogenic emission flux, respectively. in ;in P represents the concentration of pollutants in the precipitation, P represents the annual precipitation, and A represents the area of ​​the grid cell.

[0022] ;in Let i be the surface runoff from the i-th upstream grid cell to the j-th current grid cell. The concentration of pollutants in the surface runoff of the i-th grid cell upstream; The path length from the upstream grid to the current grid. This is the preset path attenuation coefficient; ;in Capillary upward flux; This represents the concentration of pollutants in groundwater.

[0023] ;in Let t be the emissions from the t-th individual as a pollution source. This is the influence coefficient of the pollution source on the current grid cell; the influence coefficient is calculated based on the distance between the pollution source and the grid cell and the terrain conditions. The distance decay factor is calculated using negative exponential decay. ;in The distance from pollution element x to the geometric center of grid j is the straight-line distance. The preset distance attenuation coefficient is set according to the type of pollution source, such as industrial sources. Agricultural non-point source ; The greater the distance, the smaller the distance attenuation factor, and the lower the contribution of the pollution source.

[0024] Terrain barrier correction factor ; The average slope of the grid where the pollution source lands. Pollution source slope direction slope with the target grid Difference; The closer the value is to 1, the easier it is for pollutants to migrate to this grid along the slope from upstream and downstream. Too large; The closer to -1, the more the slope, mountain, and terrain impede the diffusion of pollutants. Too small; Range [0,1].

[0025] For terrain barrier correction factor and distance decay factor After weighted fusion processing, the terrain impact index is output. That is, the terrain barrier correction factor and distance decay factor After normalization, the results are multiplied by the corresponding preset weight coefficients and then summed to obtain the terrain impact index.

[0026] The influence coefficient is transformed by utilizing the mapping rule between the topographic influence index and the influence coefficient; To clarify, the influence coefficient is limited to the range of 0.1-0.9. By setting the index intervals corresponding to the terrain influence index, and each index interval corresponding to an influence coefficient, the larger the terrain influence index, the larger the corresponding influence coefficient, and vice versa.

[0027] Output flux calculation: For each grid cell, calculate its total pollutant output flux per unit time, including surface runoff output flux, groundwater leaching output flux, soil degradation flux, and plant uptake flux. Specifically: Total pollutant output flux ; in , , , These represent surface runoff output flux, groundwater leaching output flux, soil degradation flux, and plant uptake flux, respectively. ;in Let J be the surface runoff of the j-th grid cell. This represents the concentration of surface pollutants in the soil of the current grid cell; ;in This refers to the amount of groundwater leaching. This represents the concentration of pollutants in the soil aqueous solution. ;in ; The total annual groundwater recharge volume; The leaching partition coefficient; ;in For soil bulk density, Soil volumetric water content, The preset adsorption partition coefficient is related to the type of pollutant and the content of soil organic matter. The higher the clay content, the stronger the water adsorption and the less downward leaching; the larger the porosity and water content, the more free water there is and the greater the amount of leached water.

[0028] ;in is the first-order degradation rate constant of the pollutant; ; in The degradation rate constant at 20℃ Here is the preset temperature coefficient, and T is the soil temperature. This is a preset reference organic matter content. d and d are preset empirical degradation coefficients; The volume of soil within the grid cell. For soil bulk density, This represents the concentration of pollutants in the soil.

[0029] ;in The concentration of pollutants within the plant is calculated using the bioaccumulation factor. This refers to the annual aboveground biomass of plants. .

[0030] Pollution level classification: For any j-th grid cell, after calculating the concentration of pollutants in the soil, based on the calculated current pollutant concentration of each grid cell and in conjunction with the national soil environmental quality standards, the pollution level of a single grid cell is quantified and a spatial distribution map is generated. Specifically: For any grid cell j, the change in the total mass of pollutants in the soil within a unit time Δt is equal to the input flux minus the output flux: ; The total mass of pollutants in the soil within grid cell j; Converting mass to concentration, the total mass of soil pollutants within the grid can be represented as follows: ; in The average concentration of soil pollutants within grid j. For soil volume, Soil bulk density; The mass conservation equation then becomes: ; Assumption and If it remains unchanged during the forecast period, then ; Concentration based on arbitrary grid cells The pre-established mapping rules are used to map the pollution level, and the pollution concentration and level of each grid are assigned to the corresponding grid cell to generate a spatial distribution map of the current pollution level in the study area. That is, by setting the concentration The three corresponding concentration ranges, each corresponding to a pollution level, are: low pollution risk level, medium pollution risk level, and high pollution risk level.

[0031] Pollution level prediction: A first-order explicit difference scheme is used to predict the pollutant concentration of each grid cell j in the future, given a time step. When the prediction is completed, the pollutant concentration is dynamically adjusted by combining the historical concentration change trend and using correction logic, and then used as the final predicted pollution concentration. Specifically: Using a first-order explicit difference scheme, given a time step Δt, the concentration update formula from t to Δt is: ; and Calculations are performed based on the input conditions at time t; For any grid cell j, extract e historical pollutant concentration values ​​sorted chronologically; where e > 5 and is an even number, the specific settings are determined by technical personnel; denoted as ;in ; Outliers in the sequence (such as outliers caused by monitoring errors) are removed, and missing values ​​are filled in using linear interpolation to ensure the continuity of the time series.

[0032] With time as the horizontal axis and the historical pollutant concentrations of each group as the vertical axis, a single-grid concentration time series line graph is drawn, with each time node corresponding to a numerical point, and adjacent numerical points connected to form a numerical line. For each numerical line, compare the concentration values ​​of two sets of numerical points. If the concentration value of the right numerical point in the numerical points formed by the numerical line is higher than the concentration value of the left numerical point, then mark the slope of the numerical line as the first slope. The concentration increase is obtained by summing all the first slopes; If the concentration value of the rightmost point among the numerical points formed by the numerical line is lower than the concentration value of the leftmost point, then the absolute value of the slope of the numerical line is marked as the second slope. Summing all the second slopes yields the concentration decrease. The ratio is calculated by using the increase in concentration as the numerator and the decrease in concentration as the denominator, and the trend intensity ratio is output. Additional notes and special handling: If the concentration decrease value = 0 (all numerical lines are trending upward), set the trend strength ratio = 10 (representing a sustained strong upward trend); if the concentration increase value = 0 (all numerical lines are trending upward), set the trend strength ratio = 1 (representing a sustained strong downward trend).

[0033] Will Based on the intermediate time point, the concentration sequence of the first half and the concentration sequence of the second half are obtained by segmentation. For the two sets of sequences, take the arithmetic mean and output the mean concentration of the first half and the mean concentration of the second half, respectively. The ratio is calculated by using the mean of the second half of the concentration as the numerator and the mean of the first half of the concentration as the denominator, and the concentration trend ratio is output. After comprehensively processing the trend intensity ratio and concentration trend ratio using correction logic, the concentration change coefficient is output. The specific calculation process is as follows: That is, the ratio of trend strength Concentration trend ratio After normalization, substitute into the formula Weighted calculations were performed to obtain the concentration change coefficient. ; and 2 represents the preset weighting coefficients, and their sum is one; High: There is a high probability that pollution will continue to accumulate in the future, making it more likely to fall into the medium- or high-pollution risk range; Low: As existing pollutants continue to decline, the pollution risk gradually decreases, and it is highly likely to remain at a low level.

[0034] Using pre-established mapping rules, the concentration change coefficient is converted into a correction coefficient, and then compared with... Multiply the results to obtain the final predicted pollution concentration. That is, by setting The corresponding coefficient intervals are defined, and each coefficient interval corresponds to a set of correction coefficients, with the correction coefficient range limited to 0.93-1.18, and the concentration change coefficient... The larger the coefficient, the higher the probability of a matching correction coefficient greater than 1, and the higher the probability of a further match of 1.18; conversely, the smaller the coefficient of concentration change... The smaller the value, the higher the probability that the matching correction coefficient is less than 1.

[0035] Example 2 Based on the soil pollution prediction method based on pollution source input and output fluxes provided in Embodiment 1 of this application, Embodiment 2 of this application proposes a soil pollution prediction system based on pollution source input and output fluxes. Embodiment 2 is merely a preferred embodiment of Embodiment 1, and its implementation will not affect the individual implementation of Embodiment 1.

[0036] Specifically, the soil pollution prediction system based on pollution source input and output fluxes provided in Embodiment 2 of this application includes: The grid unit parameter acquisition module is used to divide the study area into square grid units with a set side length and collect soil property parameters, topographic parameters, and hydrological parameters corresponding to each grid. The pollutant input flux calculation module is used to calculate the total pollutant input flux of a single grid according to four pathways: atmospheric deposition, surface runoff inflow, groundwater recharge input, and anthropogenic emissions. The pollutant output flux calculation module is used to calculate the total pollutant output flux of a single grid according to four pathways: surface runoff output, groundwater leaching, soil degradation, and plant absorption. The pollution classification and dynamic prediction module calculates the current soil pollutant concentration based on the mass conservation formula, classifies the pollution risk into three levels (low, medium, and high) and generates spatial distribution data; it uses a first-order explicit difference formula to preliminarily predict future pollutant concentrations, extracts multiple sets of historical time-series concentration data to determine correction coefficients to optimize the initial differential concentration calculation, and outputs the final predicted concentration.

[0037] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0038] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0039] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0040] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0041] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0042] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0043] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0044] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0045] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A soil pollution prediction method based on pollution source input and output fluxes, characterized in that, include: Regional discretization data acquisition: The study area is divided into square grid cells with a side length of L, and basic attribute parameters of each grid cell are collected, including soil property parameters, topographic parameters and hydrological parameters; Input flux calculation: For each grid cell, calculate its total pollutant input flux per unit time, including atmospheric deposition flux, surface runoff input flux, groundwater recharge input flux, and anthropogenic emission flux; Output flux calculation: For each grid cell, calculate its total pollutant output flux per unit time, including surface runoff output flux, groundwater leaching output flux, soil degradation flux, and plant uptake flux. Pollution level classification: For any j-th grid cell, after calculating the concentration of pollutants in the soil, the pollution level of a single grid cell is quantified and a spatial distribution map is generated based on the calculated current pollutant concentration of each grid cell. Pollution level prediction: A first-order explicit difference scheme is used to predict the pollutant concentration of each grid cell j in the future, given a time step. When the prediction is completed, the pollutant concentration is dynamically adjusted by combining the historical concentration change trend and using correction logic, and then used as the final predicted pollution concentration.

2. The soil pollution prediction method based on pollution source input and output fluxes according to claim 1, characterized in that: Soil property parameters include organic matter content, pH value, clay content, sand content, bulk density, and porosity. Topographic parameters include digital elevation, slope, and aspect; Hydrological parameters include groundwater level depth, surface runoff, soil moisture content, and annual precipitation.

3. The soil pollution prediction method based on pollution source input and output fluxes according to claim 2, characterized in that: Total input flux of pollutants ; , , , These represent atmospheric deposition flux, surface runoff input flux, groundwater recharge input flux, and anthropogenic emission flux, respectively.

4. The soil pollution prediction method based on pollution source input and output fluxes according to claim 3, characterized in that: Total pollutant output flux ; in , , , These represent surface runoff output flux, groundwater leaching output flux, soil degradation flux, and plant uptake flux, respectively.

5. The soil pollution prediction method based on pollution source input and output fluxes according to claim 4, characterized in that: For any grid cell j, the change in the total mass of pollutants in the soil within a unit time Δt is equal to the input flux minus the output flux: ; The total mass of pollutants in the soil within grid cell j; Converting mass to concentration, the total mass of soil pollutants within the grid can be represented as follows: ; in The average concentration of soil pollutants within grid j. For soil volume, Soil bulk density; The mass conservation equation then becomes: ,but .

6. The soil pollution prediction method based on pollution source input and output fluxes according to claim 5, characterized in that: Concentration based on arbitrary grid cells By using pre-established mapping rules, the pollution level is mapped, and the pollution concentration and level of each grid are assigned to the corresponding grid cell to generate a spatial distribution map of the current pollution level in the study area.

7. The soil pollution prediction method based on pollution source input and output fluxes according to claim 6, characterized in that: Using a first-order explicit difference scheme, given a time step Δt, the concentration update formula from t to Δt is: ; For any grid cell j, extract e historical pollutant concentration values ​​sorted chronologically; denoted as ; After determining the trend intensity ratio and concentration trend ratio, a comprehensive processing is performed to output the concentration change coefficient; Using pre-established mapping rules, the concentration change coefficient is converted into a correction coefficient, and then compared with... Multiply the results to obtain the final predicted pollution concentration.

8. The soil pollution prediction method based on pollution source input and output fluxes according to claim 7, characterized in that: With time as the horizontal axis and the historical pollutant concentrations of each group as the vertical axis, a single-grid concentration time series line graph is drawn, with each time node corresponding to a numerical point, and adjacent numerical points connected to form a numerical line. For each numerical line, compare the concentration values ​​of two sets of numerical points. If the concentration value of the right numerical point in the numerical points formed by the numerical lines is higher than the concentration value of the left numerical point, then mark the slope of the numerical line as the first slope; sum all the first slopes to obtain the concentration increase value. If the concentration value of the rightmost point among the numerical points formed by the numerical line is lower than the concentration value of the leftmost point, then the absolute value of the slope of the numerical line is marked as the second slope. Summing all the second slopes yields the concentration decrease value; using the concentration increase value as the numerator and the concentration decrease value as the denominator, the ratio is calculated, and the trend intensity ratio is output. Will Based on the intermediate time point, the concentration sequences of the first half and the second half are obtained. The arithmetic mean of the two sequences is taken respectively, and the average concentration of the first half and the average concentration of the second half are output. The ratio is calculated by using the average concentration of the second half as the numerator and the average concentration of the first half as the denominator, and the concentration trend ratio is output.

9. A soil pollution prediction system based on pollution source input-output fluxes, applied to the soil pollution prediction method based on pollution source input-output fluxes as described in any one of claims 1-8, characterized in that, include: The grid unit parameter acquisition module is used to divide the study area into square grid units with a set side length and collect soil property parameters, topographic parameters, and hydrological parameters corresponding to each grid. The pollutant input flux calculation module is used to calculate the total pollutant input flux of a single grid according to four pathways: atmospheric deposition, surface runoff inflow, groundwater recharge input, and anthropogenic emissions. The pollutant output flux calculation module is used to calculate the total pollutant output flux of a single grid according to four pathways: surface runoff output, groundwater leaching, soil degradation, and plant absorption. The pollution classification and dynamic prediction module calculates the current soil pollutant concentration in the grid based on the mass conservation formula, classifies the pollution risk level into low, medium and high levels and generates spatial distribution data. The first-order explicit difference formula is used to initially predict the future pollutant concentration. Multiple sets of historical time series concentration data are extracted to determine the correction coefficient to optimize the initial concentration calculation of the difference, and the final predicted concentration is output.

Images