Pollutant treatment area identification method, device, equipment, medium and product

Abstract

The present application relates to the technical field of water pollution treatment, and discloses a pollution treatment area identification method, device, equipment, medium and product, the pollution treatment area identification method comprising: constructing a target function according to space-time pollution grid data, pollution value quantile variables and pollution day threshold variable; performing variable optimization according to the constraint condition and the target function, obtaining the pollution value quantile interval and the pollution day threshold interval; performing gradient analysis on the preset pollution treatment determination function based on the pollution value quantile interval and the pollution day threshold interval, obtaining the target pollution value quantile and the target pollution day threshold; identifying the pollution treatment area according to the target pollution value quantile, the target pollution day threshold and the space-time pollution grid data, obtaining the target pollution treatment area, the present application identifies the target pollution treatment area most in need of treatment by parameter optimization and target parameter determination, and improves the accuracy of the target pollution treatment area.

Description

Technical Field

[0001] This invention relates to the field of water pollution control technology, specifically to methods, devices, equipment, media, and products for identifying pollutant treatment areas. Background Technology

[0002] With the shift towards precision in water pollution control, the focus of watershed water quality management is gradually shifting from single-point-source pollution control to refined and systematic comprehensive watershed management. In practice, rigid constraints exist in funding, technical resources, and project timelines, making it impossible to achieve full-watershed, comprehensive management. Therefore, it is necessary to scientifically prioritize management efforts, allocating limited resources to key areas with the greatest environmental benefits.

[0003] However, the method for determining pollutant treatment areas in related technologies involves prioritizing treatment based on pollutant concentrations. However, this method results in overly large treatment areas, requiring the treatment of all areas with high pollutant concentrations. This leads to excessively dispersed resource allocation, failing to maximize environmental benefits and resulting in low treatment efficiency within the designated treatment areas. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for identifying pollutant treatment areas, in order to solve the problems of overly dispersed resource allocation, failure to maximize environmental benefits, and low treatment efficiency of pollutant treatment areas caused by pollutant treatment area determination methods in related technologies.

[0005] In a first aspect, the present invention provides a method for identifying pollutant treatment areas, comprising: acquiring spatiotemporal pollution grid data of a target watershed; constructing an objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables; the objective function being a function that minimizes the difference between the overall pollutant treatment load generated by the overall pollutant treatment area and a preset target treatment load; optimizing the pollution value quantile variables and pollution day threshold variables according to the objective function, constrained by the preset number of grids in the pollutant treatment area, to obtain pollution value quantile intervals and pollution day threshold intervals; performing gradient analysis on a preset pollutant treatment determination function based on the pollution value quantile intervals and pollution day threshold intervals to obtain target pollution value quantiles and target pollution day thresholds; and identifying pollutant treatment areas based on the target pollution value quantiles, target pollution day thresholds, and spatiotemporal pollution grid data to obtain the target pollutant treatment area.

[0006] The method for identifying pollutant treatment areas in this invention acquires spatiotemporal pollution grid data of the target watershed. Based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables, an objective function is constructed. Using spatiotemporal pollution grid data as the basic input, the objective function incorporates two dimensions: pollution value quantiles and pollution days. It considers both pollution concentration and pollution duration as spatiotemporal characteristics, defining the objective function as minimizing the difference between the overall pollutant treatment area's load and the preset target treatment load. This ensures that subsequent identification results accurately align with the watershed's total pollution control and load reduction objectives. This invention uses a preset number of pollutant treatment area grids as a constraint. Based on the objective function, it optimizes the pollution value quantile variables and pollution day threshold variables to obtain pollution value quantile intervals and pollution day threshold intervals. Using the preset number of treatment grids as a constraint, it optimizes the pollution value quantile variables and pollution day threshold variables, outputting the pollution value quantile intervals and pollution day threshold intervals. This eliminates reliance on human experience to directly specify quantile and pollution day parameters, automatically solving for feasible parameter ranges through constraint optimization, reducing subjective bias caused by human parameter setting. This invention performs gradient analysis on a preset pollutant treatment determination function based on the quantile interval of pollution values ​​and the threshold interval of pollution days. This yields the target pollution value quantile and the target pollution day threshold. Further gradient analysis is performed on the optimized parameter interval to select the optimal target pollution value quantile and target pollution day threshold. These are the most sensitive thresholds with the greatest marginal benefit. Based on the target pollution value quantile, the target pollution day threshold, and spatiotemporal pollution grid data, pollutant treatment areas are identified, resulting in the most critical target pollutant treatment areas. This improves the accuracy of identifying target pollutant treatment areas. The target pollutant treatment areas take into account both pollution concentration quantile levels and pollution duration, and the grid size of the areas matches the preset treatment volume. These target pollutant treatment areas are also the areas most in need of pollution treatment, maximizing environmental benefits and improving the treatment efficiency of the pollutant treatment areas.

[0007] In one optional implementation, an objective function is constructed based on spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables. This includes: obtaining a first pollutant treatment area relationship based on the relationship between pollution values ​​and pollution value quantile variables in the spatiotemporal pollution grid data; determining a second pollutant treatment area relationship based on the relationship between the first pollutant treatment area relationship and the pollution day threshold variable; determining a preset pollutant treatment load determination function based on the second pollutant treatment area relationship; and minimizing the difference between the load generated by the overall pollutant treatment area obtained from the preset pollutant treatment load determination function and the preset target treatment load, thereby constructing the objective function.

[0008] In one optional implementation, with a preset number of grids for pollutant treatment areas as a constraint, the pollutant value quantile variables and the polluted days threshold variables are optimized according to the objective function to obtain the pollutant value quantile interval and the polluted days threshold interval. This includes: inputting the preset number of grids for pollutant treatment areas, the objective function, the pollutant value quantile variables, and the polluted days threshold variables into a preset optimization algorithm for optimization to obtain the pollutant value quantile interval and the polluted days threshold interval.

[0009] In one optional implementation, gradient analysis is performed on a preset pollutant treatment determination function based on the pollutant value quantile interval and the polluted days threshold interval to obtain the target pollutant value quantile and the target polluted days threshold. This includes: constructing a gradient vector of the preset pollutant treatment determination function based on the rate of change of the pollutant value quantile in the pollutant value quantile interval and the rate of change of the polluted days threshold in the polluted days threshold interval; performing modulus processing on the gradient vector to obtain multiple discrete gradient moduli; using the pollutant value quantile corresponding to the target discrete gradient moduli among the multiple discrete gradient moduli as the target pollutant value quantile; and using the polluted days threshold corresponding to the target discrete gradient moduli as the target polluted days threshold. The target discrete gradient moduli is the largest moduli among the multiple discrete gradient moduli.

[0010] In one optional implementation, the target pollutant treatment area is identified based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data to obtain the target pollutant treatment area. This includes: inputting the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data into the first pollutant treatment area formula and the second pollutant treatment area formula to obtain the target pollutant treatment area.

[0011] In one optional implementation, the target pollution value quantile, the target pollution day threshold, and spatiotemporal pollution grid data are input into the first pollutant treatment area formula and the second pollutant treatment area formula to obtain the target pollutant treatment area. This includes: determining the target pollution value threshold based on the target pollution value quantile and the spatiotemporal pollution grid data; using the areas in the spatiotemporal pollution grid data corresponding to pollution values ​​greater than the target pollution value threshold as the initial pollutant treatment area; counting the number of pollution days in each grid of the pollutant treatment area to obtain the target pollution days for each grid; and identifying areas where the target pollution days are greater than the target pollution day threshold as the target pollutant treatment area.

[0012] Secondly, this invention provides a device for identifying pollutant treatment areas, comprising: an objective function construction module for acquiring spatiotemporal pollution grid data of a target watershed and constructing an objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables; the objective function is a function that minimizes the difference between the load generated by the overall pollutant treatment area and the preset target treatment load; a variable optimization module for optimizing the pollution value quantile variables and pollution day threshold variables according to the objective function, constrained by the preset number of grids in the pollutant treatment area, to obtain the pollution value quantile interval and the pollution day threshold interval; a gradient analysis module for performing gradient analysis on the preset pollutant treatment determination function based on the pollution value quantile interval and the pollution day threshold interval, to obtain the target pollution value quantile and the target pollution day threshold; and a treatment area identification module for identifying the pollutant treatment area based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data, to obtain the target pollutant treatment area.

[0013] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the pollutant treatment area identification method of the first aspect or any corresponding embodiment described above.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the pollutant treatment area identification method of the first aspect or any corresponding embodiment thereof.

[0015] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the pollutant treatment area identification method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a method for identifying pollutant treatment areas according to an embodiment of the present invention; Figure 3This is a schematic diagram of a second process for identifying a pollutant treatment area according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the method for identifying pollutant treatment areas according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a pollutant treatment area identification device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] As an optional application scenario of this invention, such as Figure 1 As shown, the identification system for the pollutant treatment area may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0022] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0023] Watershed pollution exhibits significant spatial heterogeneity and temporal fluctuations; the pollution contribution of the same area can vary drastically across different water periods. Some areas may experience occasional high pollution levels, but these are not persistent, while others may remain at low to medium pollution levels for extended periods, yet their cumulative contribution is substantial. Traditional static, experience-based management methods struggle to capture and quantify these complex spatiotemporal evolution patterns. Traditional methods for delineating pollution control zones rely primarily on qualitative experience, lacking rigorous mathematical models and quantitative standards. Resource allocation is inefficient; the inability to accurately identify specific areas with high and prolonged pollution contributions leads to overly dispersed resource allocation, failing to maximize environmental benefits. Furthermore, the lack of dynamic adjustment capabilities prevents the rapid calculation and generation of optimal spatial combinations of pollution control solutions based on budget changes or adjustments to policy objectives.

[0024] This invention provides a method for identifying pollutant treatment areas. By optimizing parameters and determining target parameters, the method identifies the target pollutant treatment areas that most need treatment, thereby improving the accuracy of identifying target pollutant treatment areas.

[0025] According to an embodiment of the present invention, an embodiment of a method for identifying pollutant treatment areas is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] This embodiment provides a method for identifying pollutant treatment areas, which can be used with computer equipment. Figure 2 This is a flowchart of a first method for identifying pollutant treatment areas according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain spatiotemporal pollution grid data of the target watershed, and construct an objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables; the objective function is the function that minimizes the difference between the load generated by the overall pollutant treatment area and the preset target treatment load.

[0027] The target watershed is the area of ​​the watershed to be subject to pollution control; the spatiotemporal pollution grid data is obtained by spatially dividing the watershed into several grids, with each grid carrying time-series pollution monitoring values. For example, the spatiotemporal pollution grid data is obtained by reading the time-series stored pollution concentration or load grid data within the target watershed. The spatiotemporal pollution grid data contains 205,664 effective calculation grids (785 rows × 457 columns), covering a time range of 365 days a year.

[0028] In some optional implementations, the consistency of the spatiotemporal contamination grid data is verified, including the number of columns, rows, grid size, and coordinate system, to ensure that the data is strictly aligned in space. This provides a unified baseline map for accurate calculations on a grid-by-grid and time-step basis, avoiding analysis errors caused by data inconsistency. The spatiotemporal contamination grid data used for subsequent objective function construction is the spatiotemporal contamination grid data after consistency verification.

[0029] In some alternative implementations, spatiotemporal contamination grid data can be represented as: , indicating that it is located at the th Line 1 The grid of the column in the first Spatiotemporal contamination grid data at a time step (e.g., days).

[0030] In some alternative implementations, the pollution value quantile variable is the variable to be optimized, representing the quantile of the pollution concentration. For example, 0.75 represents the 75th percentile, which is used to define high pollution concentration levels.

[0031] In some optional implementations, the pollution day threshold variable is a variable to be optimized, representing the number of days the grid exceeds the pollution value threshold within the evaluation period, and is used to characterize the frequency of pollution persistence.

[0032] In some optional implementations, the overall pollutant treatment area generates the total amount of pollutants generated by the grids that meet the pollution conditions, as determined by the pollution value quantile and pollution day threshold; the preset target treatment load is the pre-set amount of load reduction required for watershed pollutant treatment.

[0033] In some optional implementations, an objective function is constructed based on minimizing the difference between the load generated by the overall pollutant treatment area and the preset target treatment load, so that the calculated load generated by the overall pollutant treatment area is as close as possible to the preset target treatment load.

[0034] Step S202: Using the preset number of grids for pollutant treatment areas as a constraint, optimize the quantile variables of pollution values ​​and the threshold variables of pollution days according to the objective function to obtain the quantile interval of pollution values ​​and the threshold interval of pollution days.

[0035] Among them, the pollution value quantile interval is a set of feasible quantile ranges obtained through optimization; the pollution day threshold interval is a set of feasible pollution day ranges obtained through optimization.

[0036] Step S203: Based on the quantile interval of pollution values ​​and the threshold interval of pollution days, perform gradient analysis on the preset pollutant treatment determination function to obtain the target pollution value quantile and the target pollution day threshold.

[0037] Among them, gradient analysis involves calculating the rate of change of the preset pollutant treatment area determination function with respect to quantiles and day thresholds, constructing a gradient, and selecting the point with the maximum gradient magnitude from the feasible interval as the optimal parameter.

[0038] In some optional implementations, the preset pollutant treatment determination function can be a preset pollutant treatment area determination function or a preset pollutant treatment load determination function.

[0039] Step S204: Identify the pollutant treatment area based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data to obtain the target pollutant treatment area.

[0040] Among them, the target pollutant treatment area is the final output set of watershed grids to be treated.

[0041] The pollutant treatment area identification method provided in this embodiment acquires spatiotemporal pollution grid data of the target watershed. Based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables, an objective function is constructed. Using spatiotemporal pollution grid data as the basic input, and introducing two dimensions of variables—pollution value quantiles and pollution days—the objective function is constructed, taking into account both pollution concentration and pollution duration. The objective function is defined as minimizing the difference between the overall pollutant treatment area's load and the preset target treatment load, ensuring that subsequent identification results accurately align with the watershed's total pollution control and load reduction objectives. This embodiment uses a preset number of pollutant treatment area grids as a constraint. Based on the objective function, it optimizes the pollution value quantile variables and pollution day threshold variables to obtain pollution value quantile intervals and pollution day threshold intervals. Using the preset number of treatment grids as a constraint, it optimizes the pollution value quantile variables and pollution day threshold variables, outputting the pollution value quantile intervals and pollution day threshold intervals. This eliminates the reliance on human experience to directly specify quantile and pollution day parameters; by automatically solving for feasible parameter ranges through constraint optimization, it reduces subjective bias caused by human parameter setting. This invention, based on the quantile range of pollution values ​​and the threshold range of pollution days, performs gradient analysis on a preset pollutant treatment determination function to obtain the target pollution value quantile and the target pollution day threshold. Further gradient analysis is performed on the optimized parameter range to select the optimal target pollution value quantile and target pollution day threshold. These are the most sensitive thresholds with the greatest marginal benefit. Therefore, based on the target pollution value quantile, the target pollution day threshold, and spatiotemporal pollution grid data, pollutant treatment areas are identified, resulting in the target pollutant treatment areas most in need of treatment. This improves the accuracy of the target pollutant treatment areas. The target pollutant treatment areas take into account both pollution concentration quantile levels and pollution duration days, and the area grid size fits the preset treatment volume. These target pollutant treatment areas are also the areas most in need of pollution treatment, maximizing environmental benefits and improving the treatment efficiency of the pollutant treatment areas.

[0042] This embodiment provides a method for identifying pollutant treatment areas, which can be used with computer equipment. Figure 3 This is a second flowchart of a method for identifying pollutant treatment areas according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain spatiotemporal pollution grid data of the target watershed, and construct an objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables; the objective function is the function that minimizes the difference between the load generated by the overall pollutant treatment area and the preset target treatment load.

[0043] Specifically, step S301 includes: Step S3011: Based on the relationship between pollution values ​​and pollution value quantile variables in the spatiotemporal pollution grid data, obtain the regional relationship for the treatment of the first pollutant.

[0044] Specifically, for each time step, the pollution values ​​of all effective grids within the target watershed are sorted, and the quantile method is used to determine the grids with pollution values ​​higher than the quantile variable of the pollution value as high pollution intensity grids at that time, thus constructing the relationship of the first pollutant treatment area.

[0045] For example, for each time step According to the quantile variable of pollution values ( Determine the target pollution threshold. Specifically, determine the target pollution threshold. The formula is: ; in, The target pollution threshold, It is a quantile function. For pollution value quantile variables, For the position located at the Line 1 The grid of the column in the first Spatiotemporal contamination grid data with a time step, This represents the total number of rows in the grid. This represents the total number of columns in the grid.

[0046] In some optional implementations, based on the target pollution value threshold and spatiotemporal pollution grid data, the relationship between the treatment areas of the first pollutant can be expressed as: ; in, This is a spatial indicator matrix, representing the regional relationship of the first pollutant treatment area. For the position located at the Line 1 The grid of the column in the first Spatiotemporal contamination grid data with a time step, The target pollution threshold.

[0047] In some optional implementations, the first pollutant treatment area relationship can be understood as follows: when the spatiotemporal pollution grid data of the grid is greater than or equal to the target pollution value threshold, the grid is assigned a value of 1, indicating a high pollution state; when the spatiotemporal pollution grid data of the grid is less than the target pollution value threshold, the grid is assigned a value of 0, indicating a low pollution state.

[0048] In some alternative implementations, dynamic relative thresholds (quantiles) are used instead of absolute thresholds, which can adapt to the background fluctuations of the watershed water environment in different hydrological periods (high, normal, and low water periods), avoiding the bias that fixed thresholds tend to identify most grids as highly polluted during the low water period and are difficult to identify pollution peaks during the high water period.

[0049] Step S3012: Determine the second pollutant treatment area relationship based on the relationship between the first pollutant treatment area relationship and the pollution day threshold variable.

[0050] The frequency matrix is ​​obtained by counting the total number of times each grid is in a high-pollution state throughout the entire assessment period, which can be represented as: ; in, For the first Line 1 The frequency matrix of the column grid. For spatial indicator matrix, For the evaluation period.

[0051] In some alternative implementations, the frequency matrix effectively distinguishes between occasional pollution peaks and continuous pollution emissions, accurately pinpointing the causes of long-term, cumulative impacts on watershed water quality.

[0052] In some optional implementations, grids that simultaneously meet the dual criteria of "high spatial intensity" and "high temporal frequency" are selected based on the pollution day threshold variable, generating a second pollutant treatment area relationship formula, which can be expressed as: ; in, For the first Line 1 Are the grid lines designated as pollutant treatment areas? For the first Line 1 The frequency matrix of the column grid. The threshold variable for the number of polluted days.

[0053] In some optional implementations, the second pollutant treatment area relationship is expressed as follows: when the total number of times a grid is in a high-pollution state is greater than or equal to the pollution day threshold, it is assigned a value of 1; when the total number of times a grid is in a high-pollution state is less than the pollution day threshold, it is assigned a value of 0. The set of grids assigned a value of 1 constitutes the identified target pollutant treatment area.

[0054] Step S3013: Determine the preset pollutant treatment load determination function based on the second pollutant treatment area relationship formula.

[0055] Among them, the pollution values ​​of the preset pollutant treatment area obtained from the relationship of the second pollutant treatment area are statistically analyzed to obtain the preset pollutant treatment load determination function, which can be expressed as: ; in, The function for determining the pre-defined pollutant treatment load (the function for determining the load generated by the overall pollutant treatment area). This represents the total number of rows in the grid. This represents the total number of columns in the grid. To identify the grid area as the pollution control zone, For the position located at the Line 1 The grid of the column in the first Spatiotemporal pollution grid data at a time step, i.e., grid pollution value or load.

[0056] Step S3014: Minimize the difference between the total pollutant treatment load generated by the overall pollutant treatment area obtained by the preset pollutant treatment load determination function and the preset target treatment load, and construct the objective function.

[0057] The preset target treatment load is the amount of load reduction required for the treatment of pollutants in the watershed, which can be determined based on the physical upper limit corresponding to the treatment funds or resources.

[0058] In some alternative implementations, the objective function can be expressed as: ; in, Let be the objective function. The function for determining the pre-defined pollutant treatment load (the function for determining the load generated by the overall pollutant treatment area). To preset the target treatment load, For pollution value quantile variables, The threshold variable for the number of polluted days.

[0059] In some alternative implementations, the quantile variable of the contamination value controls the accuracy of spatial identification. The larger the value, the more stringent the standard for a single identification; the larger the value of the threshold variable for the number of polluted days, the higher the requirement for the persistence of pollution.

[0060] Step S302: Using the preset number of grids for pollutant treatment areas as a constraint, optimize the quantile variables of pollution values ​​and the threshold variables of pollution days according to the objective function to obtain the quantile interval of pollution values ​​and the threshold interval of pollution days.

[0061] Specifically, step S302 includes: Step S3021: Input the preset number of grids for pollutant treatment area, objective function, pollutant value quantile variable and polluted days threshold variable into the preset optimization algorithm for optimization, and obtain the pollutant value quantile interval and the polluted days threshold interval.

[0062] The preset optimization algorithm can be the particle swarm optimization algorithm.

[0063] In some optional implementations, the preset number of grids for pollutant treatment areas, objective function, pollutant value quantile variables, and polluted days threshold variables are input into a preset optimization algorithm. The algorithm automatically searches within a preset parameter space (e.g., spatial quantile threshold range of 0.80-0.95, and time day threshold range of 183-365 days). Each iteration generates a set of candidate parameters, which are then input into the objective function for filtering. After multiple iterations (e.g., 1500 times), the algorithm converges and outputs the pollutant value quantile interval and polluted days threshold interval that satisfy the objective function.

[0064] Step S303: Based on the quantile interval of pollution values ​​and the threshold interval of pollution days, perform gradient analysis on the preset pollutant treatment determination function to obtain the target pollution value quantile and the target pollution day threshold.

[0065] Specifically, step S303 includes: Step S3031: Construct the gradient vector of the preset pollutant treatment determination function based on the rate of change of the quantile of the pollution value in the pollution value quantile interval and the rate of change of the pollution day threshold in the pollution day threshold interval.

[0066] In some optional implementations, comprehensive iterative calculations are performed within the quantile range of pollution values ​​and the threshold range of polluted days to generate a response surface for "parameter combination - number of treatment grids." The gradient rate of change of the number of treatment grids with small parameter variations is analyzed to identify the region of most dramatic change. This point represents the inflection point where the parameters are most sensitive and the marginal benefit is greatest. This inflection point can serve as the technical basis for tiered treatment. For example, before the inflection point, a small parameter adjustment can achieve a significant reduction in the treated area; after the inflection point, further increasing the standards may lead to a sharp decrease in the treated area, but the marginal improvement in ecological benefits may be limited.

[0067] In some optional implementations, a preset pollutant treatment area determination function is constructed based on the second pollutant treatment area relationship. The preset pollutant treatment area determination function can be expressed as: ; in, A function to determine the pre-defined pollutant treatment area (used to determine the overall pollutant treatment area). This represents the total number of rows in the grid. This represents the total number of columns in the grid. To identify the grid area as the pollution control zone, For the first Line 1 The area of ​​the grid in the column.

[0068] In some optional implementations, the preset pollutant treatment determination function can be a preset pollutant treatment area determination function or a preset pollutant treatment load determination function. When the preset pollutant treatment determination function is a preset pollutant treatment area determination function, the formula for constructing the gradient vector of the preset pollutant treatment determination function is: ; in, The gradient vector, A function to determine the pre-defined pollutant treatment area. For pollution value quantile variables, The threshold variable for the number of polluted days.

[0069] Step S3032: Perform modulus processing on the gradient vector to obtain multiple discrete gradient modulus values. Take the pollution value quantile corresponding to the target discrete gradient modulus value among the multiple discrete gradient modulus values ​​as the target pollution value quantile. Take the pollution day threshold corresponding to the target discrete gradient modulus value as the target pollution day threshold. The target discrete gradient modulus value is the maximum modulus value among the multiple discrete gradient modulus values.

[0070] Among them, identification gradient magnitude The position of the largest parameter is used to obtain the target pollution value quantile and the target pollution day threshold.

[0071] In some alternative implementations, in actual discrete data, the quantile variable of contamination values... and the threshold variable for the number of polluted days Only a finite number of discrete values ​​can be taken, let's assume and Given the search step sizes in the two directions, calculate the finite difference to obtain: ; ; in, The relationship between the treatment areas of the second pollutant and the quantile variables of the pollution values. Finite difference in direction, For pollution value quantile variables Search step size in direction, The relationship between the second pollutant treatment area and the threshold variable of the number of polluted days. Finite difference in direction, Threshold variable for number of polluted days The search step size in the direction.

[0072] The discrete gradient magnitude is then approximated as: ; in, For discrete gradient magnitudes, The relationship between the treatment areas of the second pollutant and the quantile variables of the pollution values. Finite difference in direction, For pollution value quantile variables Search step size in direction, The relationship between the second pollutant treatment area and the threshold variable of the number of polluted days. Finite difference in direction, Threshold variable for number of polluted days The search step size in the direction.

[0073] In some alternative implementations, the formula for determining the target discrete gradient magnitude is: ; in, For the target discrete gradient magnitude, The relationship between the treatment areas of the second pollutant and the quantile variables of the pollution values. Finite difference in direction, For pollution value quantile variables Search step size in direction, The relationship between the second pollutant treatment area and the threshold variable of the number of polluted days. Finite difference in direction, Threshold variable for number of polluted days The search step size in the direction.

[0074] In some alternative implementations, the maximum magnitude among multiple discrete gradient magnitudes is taken as the target discrete gradient magnitude. At the target discrete gradient magnitude, a small perturbation of the parameters will cause the most drastic change in the number of overall pollutant treatment areas. The target discrete gradient magnitude is the critical point where watershed pollution transitions from local extremely high values ​​to general medium and low values, representing the point where the marginal benefit of treatment resource input is maximized.

[0075] In some optional implementations, when the preset pollutant treatment determination function is the preset pollutant treatment load determination function, the preset pollutant treatment area determination function in the above gradient analysis process is used. Replace with a preset pollutant treatment load determination function That's all.

[0076] Step S304: Identify the pollutant treatment area based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data to obtain the target pollutant treatment area.

[0077] Specifically, step S304 includes: Step S3041: Input the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data into the first pollutant treatment area relation and the second pollutant treatment area relation to obtain the target pollutant treatment area.

[0078] In some optional implementations, the target pollution value quantile, the target pollution day threshold, and spatiotemporal pollution grid data are input into the first pollutant treatment area formula and the second pollutant treatment area formula to obtain the target pollutant treatment area. This includes: determining the target pollution value threshold based on the target pollution value quantile and the spatiotemporal pollution grid data; using the areas in the spatiotemporal pollution grid data corresponding to pollution values ​​greater than the target pollution value threshold as the initial pollutant treatment area; counting the number of pollution days in each grid of the pollutant treatment area to obtain the target pollution days for each grid; and identifying areas where the target pollution days are greater than the target pollution day threshold as the target pollutant treatment area.

[0079] The process of determining the target pollution value threshold based on the target pollution value quantiles and spatiotemporal pollution grid data includes: inputting the target pollution value quantiles into the threshold determination process. The formula is used to obtain the target pollution threshold.

[0080] In some optional implementations, the region corresponding to the pollution value in the spatiotemporal pollution grid data that is greater than the target pollution value threshold is taken as the initial pollutant treatment region, including: inputting the spatiotemporal pollution grid data and the target pollution value threshold into the first pollutant treatment region relationship to obtain the initial pollutant treatment region.

[0081] In some optional implementations, the number of polluted days in each grid within the pollutant treatment area is counted to obtain the target number of polluted days for each grid, including obtaining the target number of polluted days for each grid using a frequency matrix.

[0082] In some optional implementations, areas with a target number of polluted days greater than a target number of polluted days threshold are identified as target pollutant treatment areas, including: inputting the target number of polluted days and the target number of polluted days threshold into a second pollutant treatment area relationship formula to obtain the target pollutant treatment area.

[0083] The pollutant treatment area identification method provided in this embodiment can accurately pinpoint the specific grid set that contributes the most to pollution across the entire watershed and has the longest duration of impact, significantly improving the targeting of treatment projects. All screening logic is based on spatiotemporal monitoring data, eliminating the randomness of human judgment and improving the accuracy of pollutant treatment area identification. Through reverse optimization and inflection point analysis, it ensures that the combination of treatment areas with the highest environmental benefits is selected under limited area transformation constraints. It can quantitatively predict the reduction ratio of pollution peaks and the coverage rate of key pollution periods by the treatment plan before implementation. A dual screening mechanism based on spatial quantile ranking and temporal persistence proportion is established, achieving accurate definition of watershed pollution hotspots. The particle swarm optimization algorithm is introduced to achieve the reverse solution from preset treatment objectives to optimal technical parameters. A gradient-based marginal benefit identification technique is introduced, and by calculating parameter sensitivity, the critical point of treatment scale change is identified, providing scientific evidence for maximizing resource utilization efficiency.

[0084] This embodiment provides a method for identifying pollutant treatment areas, which can be used with computer equipment. Figure 4 This is a third flowchart of a method for identifying pollutant treatment areas according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Acquire spatiotemporal pollution grid data for the target watershed; when simply identifying target pollutant treatment areas, select high-pollution areas from the spatiotemporal pollution grid data based on the coupled logic of spatial intensity determination and temporal frequency determination; when faced with treatment area or budget constraints, use particle swarm optimization to obtain the target pollution value quantile and target pollution day threshold; when the most cost-effective and refined adjustment criteria are needed, calculate and analyze the gradient change rate of the treatment grid number with small parameter changes to identify the areas with the most drastic changes; output a report consisting of high-pollution areas, target pollution value quantiles, target pollution day thresholds, and the areas with the most drastic changes.

[0085] The method for identifying pollutant treatment areas in this invention allows each step to be processed independently, resulting in different analysis results from different perspectives. It integrates data verification, forward identification, reverse optimization, inflection point identification, and automatic report generation functions, realizing a complete transformation process from raw spatiotemporal data to the final treatment plan.

[0086] This embodiment also provides a device for identifying pollutant treatment areas. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0087] This embodiment provides a device for identifying pollutant treatment areas, such as... Figure 5 As shown, it includes: The objective function construction module 501 is used to obtain spatiotemporal pollution grid data of the target watershed and construct an objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables. The objective function is the function that minimizes the difference between the load generated by the overall pollutant treatment area and the preset target treatment load.

[0088] The variable optimization module 502 is used to optimize the quantile variables of pollution values ​​and the threshold variables of pollution days according to the objective function, with the preset number of grids for pollutant treatment areas as constraints, to obtain the quantile interval of pollution values ​​and the threshold interval of pollution days.

[0089] The gradient analysis module 503 is used to perform gradient analysis on the preset pollutant treatment determination function based on the quantile interval of pollution value and the threshold interval of pollution days, so as to obtain the target pollution value quantile and the target pollution day threshold.

[0090] The treatment area identification module 504 is used to identify the pollutant treatment area based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data, so as to obtain the target pollutant treatment area.

[0091] In some optional implementations, the objective function construction module 501 includes: The first relational determination unit is used to obtain the first pollutant treatment area relational formula based on the relationship between the pollution value and the pollution value quantile variable in the spatiotemporal pollution grid data.

[0092] The second relational determination unit is used to determine the second pollutant treatment area relational formula based on the relationship between the first pollutant treatment area relational formula and the pollution day threshold variable.

[0093] The preset function determination unit is used to determine the preset pollutant treatment load determination function based on the second pollutant treatment area relationship formula.

[0094] The objective function construction unit is used to minimize the difference between the load generated by the overall pollutant treatment area obtained by the function based on the preset pollutant treatment load and the preset target treatment load, and to construct the objective function.

[0095] In some alternative implementations, the variable optimization module 502 includes: The variable optimization unit is used to input the preset number of grids for pollutant treatment area, objective function, pollutant value quantile variable, and polluted days threshold variable into the preset optimization algorithm for optimization, so as to obtain the pollutant value quantile interval and the polluted days threshold interval.

[0096] In some alternative implementations, the gradient analysis module 503 includes: The gradient vector determination unit is used to construct the gradient vector of the preset pollutant treatment determination function based on the rate of change of the quantile of the pollution value in the quantile interval and the rate of change of the threshold of the number of pollution days in the threshold interval.

[0097] The target threshold determination unit is used to perform modulus processing on the gradient vector to obtain multiple discrete gradient magnitudes. The pollution value quantile corresponding to the target discrete gradient magnitude among the multiple discrete gradient magnitudes is taken as the target pollution value quantile. The pollution day threshold corresponding to the target discrete gradient magnitude is taken as the target pollution day threshold. The target discrete gradient magnitude is the maximum magnitude among the multiple discrete gradient magnitudes.

[0098] In some optional implementations, the governance area identification module 504 includes: The treatment area identification unit is used to input the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data into the first pollutant treatment area relationship formula and the second pollutant treatment area relationship formula to obtain the target pollutant treatment area.

[0099] In some optional implementations, the governance area identification unit includes: The threshold determination subunit is used to determine the target pollution value threshold based on the target pollution value quantile and spatiotemporal pollution grid data.

[0100] The initial treatment area determination sub-unit is used to identify the areas in the spatiotemporal pollution grid data that correspond to pollution values ​​greater than the target pollution value threshold as the initial pollutant treatment area.

[0101] The polluted days determination sub-unit is used to count the number of polluted days in each grid within the pollutant treatment area, and to obtain the target number of polluted days for each grid.

[0102] The treatment area identification sub-unit is used to identify areas where the number of target polluted days is greater than the target polluted day threshold as target pollutant treatment areas.

[0103] The pollutant treatment area identification device provided in this embodiment of the invention can execute the pollutant treatment area identification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0104] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0105] The following is a detailed reference. Figure 6This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0106] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0107] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the pollutant treatment area identification method of the embodiments of the present invention.

[0108] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0109] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for identifying pollutant treatment areas shown in the above embodiments is implemented.

[0110] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0111] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for identifying pollutant treatment areas, characterized in that, The method includes: Spatiotemporal pollution grid data of the target watershed is obtained, and an objective function is constructed based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables; the objective function is a function that minimizes the difference between the load generated by the overall pollutant treatment area and the preset target treatment load. With the preset number of grids for pollutant treatment areas as a constraint, the pollutant value quantile variable and the polluted days threshold variable are optimized according to the objective function to obtain the pollutant value quantile interval and the polluted days threshold interval. Based on the pollution value quantile interval and the pollution day threshold interval, gradient analysis is performed on the preset pollutant treatment determination function to obtain the target pollution value quantile and the target pollution day threshold. The target pollutant treatment area is identified based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data.

2. The method according to claim 1, characterized in that, The construction of the objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables includes: Based on the relationship between the pollution values ​​in the spatiotemporal pollution grid data and the quantile variables of the pollution values, the relationship formula for the treatment area of ​​the first pollutant is obtained; Based on the relationship between the first pollutant treatment area relationship formula and the pollution day threshold variable, the second pollutant treatment area relationship formula is determined; Based on the second pollutant treatment area relationship formula, determine the preset pollutant treatment load determination function; The objective function is constructed by minimizing the difference between the total pollutant treatment load generated in the overall pollutant treatment area obtained by the preset pollutant treatment load determination function and the preset target treatment load.

3. The method according to claim 1 or 2, characterized in that, The process, constrained by a preset number of grid cells for pollutant treatment areas, optimizes the quantile variables of pollution values ​​and the threshold variables of pollution days according to the objective function to obtain the quantile intervals of pollution values ​​and the threshold intervals of pollution days, including: The preset number of grids for pollutant treatment areas, the objective function, the quantile variable of pollution value, and the threshold variable of pollution days are input into a preset optimization algorithm for optimization to obtain the quantile interval of pollution value and the threshold interval of pollution days.

4. The method according to claim 1 or 2, characterized in that, The step of performing gradient analysis on a preset pollutant treatment determination function based on the pollution value quantile interval and the pollution day threshold interval to obtain the target pollution value quantile and the target pollution day threshold includes: Based on the rate of change of the quantile of the pollution value in the quantile interval and the rate of change of the threshold of the pollution days in the pollution days threshold interval, the gradient vector of the preset pollutant treatment determination function is constructed. The gradient vector is subjected to modulus processing to obtain multiple discrete gradient moduli. The pollution value quantile corresponding to the target discrete gradient moduli among the multiple discrete gradient moduli is taken as the target pollution value quantile. The pollution day threshold corresponding to the target discrete gradient moduli is taken as the target pollution day threshold. The target discrete gradient moduli is the maximum modulus among the multiple discrete gradient moduli.

5. The method according to claim 2, characterized in that, The process of identifying pollutant treatment areas based on the target pollution value quantile, the target pollution days threshold, and the spatiotemporal pollution grid data, to obtain the target pollutant treatment area, includes: The target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data are input into the first pollutant treatment area relation and the second pollutant treatment area relation to obtain the target pollutant treatment area.

6. The method according to claim 5, characterized in that, The step of inputting the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data into the first pollutant treatment area relation and the second pollutant treatment area relation to obtain the target pollutant treatment area includes: The target pollution value threshold is determined based on the target pollution value quantile and the spatiotemporal pollution grid data; The region corresponding to the pollution value greater than the target pollution value threshold in the spatiotemporal pollution grid data is taken as the initial pollutant treatment region; The number of polluted days in each grid within the pollutant treatment area is counted to obtain the target number of polluted days for each grid. The area where the number of target polluted days is greater than the target polluted days threshold is identified as the target pollutant treatment area.

7. A device for identifying a pollutant treatment area, characterized in that, The device includes: The objective function construction module is used to acquire spatiotemporal pollution grid data of the target watershed, and construct an objective function based on the spatiotemporal pollution grid data, pollution value quantile variables, and pollution day threshold variables; the objective function is a function that minimizes the difference between the load generated by the overall pollutant treatment area and the preset target treatment load. The variable optimization module is used to optimize the pollution value quantile variable and the pollution day threshold variable according to the objective function, with the preset number of grids for pollutant treatment areas as constraints, to obtain the pollution value quantile interval and the pollution day threshold interval. The gradient analysis module is used to perform gradient analysis on the preset pollutant treatment determination function based on the pollution value quantile interval and the pollution day threshold interval to obtain the target pollution value quantile and the target pollution day threshold. The treatment area identification module is used to identify the pollutant treatment area based on the target pollution value quantile, the target pollution day threshold, and the spatiotemporal pollution grid data, thereby obtaining the target pollutant treatment area.

8. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for identifying pollutant treatment areas as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the method for identifying pollutant treatment areas as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the method for identifying pollutant treatment areas as described in any one of claims 1 to 6.

Images