An intelligent assessment method and system for land pollution based on water quality big data analysis

Abstract

The present invention discloses an intelligent assessment method and system for land pollution based on water quality big data analysis, which relates to the technical field of environmental monitoring and assessment, and is used to solve the problems of uneven integration of multi-source water quality monitoring data and decision-making delay. By collecting multi-dimensional data related to water quality and land pollution, preprocessing the collected data, analyzing the spatio-temporal characteristics and spatial correlation of pollution, calculating the pollution complexity and allocating governance tasks, then based on the task simulation results and budget data, evaluating the feasibility of governance goals and calculating resource balance and action priorities, and finally executing or adjusting governance tasks according to the evaluation results, realizing intelligent decision-making and dynamic optimization of water and soil pollution governance.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring and assessment, and more specifically, to an intelligent land pollution assessment method and system based on water quality big data analysis. Background Art

[0002] With the continuous development of environmental monitoring technologies, water quality monitoring and land pollution assessment have gradually become important research directions in the field of environmental protection. Intelligent land pollution assessment methods and systems based on big data analysis are gradually becoming research hotspots in this field due to their high efficiency and accuracy. However, existing related technical solutions still have significant deficiencies in data collection, processing, and application, making it difficult to meet the requirements of efficient and accurate land pollution assessment.

[0003] The existing technologies have the following deficiencies:

[0004] Currently, there are still obvious deficiencies in the comprehensive application of multi-source data collection, big data analysis capabilities, and land pollution assessment. Especially in the face of complex environmental monitoring scenarios, existing technologies are difficult to integrate and analyze multi-source water quality monitoring data, nor can they build a comprehensive and accurate land pollution assessment model. Therefore, an intelligent land pollution assessment method and system based on water quality big data analysis are proposed.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] To overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an intelligent land pollution assessment method and system based on water quality big data analysis, which evaluate the pollution complexity by comprehensively considering the pollution diffusion coefficient and the regional correlation index to solve the problems raised in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution. An intelligent land pollution assessment system based on water quality big data analysis includes a data collection module, a complexity analysis module, a resource assessment module, and a task optimization module, and the modules are connected by signals;

[0008] The data collection module is used to obtain water quality data and land pollution data of the polluted area;

[0009] The complexity analysis module preprocesses the collected data, analyzes the spatio-temporal heterogeneity of land pollution and calculates the pollution diffusion coefficient, combines the water quality spatial correlation, and calculates the regional correlation index using the multi-dimensional weight distribution method, and accordingly determines the pollution complexity and assigns governance tasks;

[0010] The resource evaluation module conducts simulations based on the assigned tasks, obtains the planned treatment duration and operation requirements, and calculates the cost difference, resource difference, and resource balance coefficient in combination with the budget data in the database, comprehensively analyzing the feasibility and priority of the treatment objectives;

[0011] The task optimization module determines whether to implement or adjust the tasks according to the evaluation results and executes the final treatment plan.

[0012] In a preferred embodiment, the data collection module accesses the water resource monitoring platform to obtain the water body pollutant concentration and flow velocity in the implementation area, accesses the flowmeter to detect the flow rate in the implementation area in real time, accesses the geological monitoring database to obtain the geological structure stability in the implementation area, counts the vegetation coverage rate in the implementation area, and separately counts the concentrations of heavy metals, organic substances, and inorganic salt pollutants to calculate the soil pollutant ratio, and sets a period of time as the environmental change analysis time to collect the ecological change data in the implementation area.

[0013] In a preferred embodiment, the complexity analysis module preprocesses the water quality data and land pollution data. The specific steps are as follows: For the water quality data, the result obtained by subtracting the maximum value from the minimum value of the chemical oxygen demand, total nitrogen, and total phosphorus is used as the standardized result, which is respectively marked as x, y, and z. For the flow velocity and flow rate, multiple historical time periods of the same length as the sample time are selected as the analysis time with the time interval of the collected flow rate as the sample time, and the maximum flow velocity, minimum flow velocity, maximum flow rate, and minimum flow rate within the analysis time are obtained, and the Min-Max normalization method is used to process them. The normalized result of the flow velocity is used as the flow velocity coefficient, and the normalized result of the flow rate is used as the flow rate coefficient. The water temperature is the ratio of the water body temperature in the implementation area to the standard temperature, and its numerical range is limited between 0 and 1, which is used as the water temperature coefficient;

[0014] For the land pollution data, the vegetation coverage rate is calculated according to the ratio of the vegetation coverage area to the total area in the implementation area, and the concentrations of heavy metals, organic substances, and inorganic salt pollutants are standardized to obtain the heavy metal pollutant ratio, organic substance pollutant ratio, and inorganic salt pollutant ratio respectively.

[0015] In a preferred embodiment, the complexity analysis module uses the non-linear mapping method to analyze the spatial correlation. The specific steps are as follows: First, determine what type of pollution the evaluation unit belongs to, and construct a non-linear mapping model with the standardized result of the pollutant concentration of the corresponding pollution type and the corresponding flow parameter coefficient;

[0016] When the non-linear mapping calculation result exceeds the preset spatial correlation threshold, it is determined that the spatial correlation of the evaluation unit is high. When the non-linear mapping calculation result is lower than the preset spatial correlation threshold, it is determined that the spatial correlation of the evaluation unit is low.

[0017] In a preferred embodiment, the complexity analysis module calculates the regional correlation index using the multi-dimensional weight allocation method. The specific steps are as follows:

[0018] Divide the implementation area into N unit spatial areas, classify them into chemical oxygen demand areas, total nitrogen areas, and total phosphorus areas according to pollution types respectively, obtain the non-linear mapping calculation results, sum the products of the results and the standardized results of the corresponding pollutant concentrations as the weight coefficients, set the pollution weights using the analytic hierarchy process, and calculate the regional correlation index by weighted summing the standardized results of pollutant concentrations and the pollution weights.

[0019] In a preferred embodiment, the complexity analysis module analyzes the spatio-temporal heterogeneity and calculates the pollution diffusion coefficient using the dynamic clustering method. The specific steps are as follows:

[0020] Divide the environmental change analysis time into two time intervals with the same length, marked as the early stage and the late stage respectively. Calculate the average ecological changes in the two time periods and take the absolute value of the difference as the ecological change coefficient. Judge the spatio-temporal heterogeneity of the implementation area by comparing the ecological change coefficient with the preset ecological difference threshold.

[0021] If the ecological change coefficient exceeds the ecological difference threshold, it is judged that the spatio-temporal heterogeneity of the implementation area is high; otherwise, it is judged that the spatio-temporal heterogeneity of the implementation area is low. Construct a dynamic clustering model, solve the system of equations by taking the partial derivative of the sum of squared residuals and setting the partial derivative equal to 0 to obtain the regression coefficients of the corresponding variables, and then calculate the pollution diffusion coefficient.

[0022] In a preferred embodiment, when the pollution complexity is low, the complexity analysis module optimizes the governance tasks using the dynamic weighted allocation method. The specific steps are as follows:

[0023] Take the regional correlation index and the pollution diffusion coefficient as inputs, and the governance priority coefficient as the output. Establish a dynamic weighted model. Use the distance weighted method to calculate the local weighted coefficient, and set its weight function using the exponential kernel function. Set the allocation ratio after calculating the governance priority coefficient, calculate the average value of the governance dataset, and use the calculation result obtained by dividing the governance priority coefficient of each evaluation unit by the average value of the governance dataset as the allocation ratio, and allocate the task volume for each governance task according to the allocation ratio.

[0024] In a preferred embodiment, the resource assessment module automatically calculates the planned governance duration and the planned operation resource requirements for each evaluation unit, and accesses the database to obtain the planned governance duration budget and the planned operation resource configuration.

[0025] The difference between the governance duration budget and the planned governance duration is standardized in the same way as the ecological change coefficient. The result after standardizing the difference between the governance duration budget and the planned governance duration is used as the cost difference coefficient. The resource balance coefficient is calculated using the multi-factor combination decision formula. The result after standardizing the difference between the operating resource allocation and the planned operating resource demand is used as the operating difference coefficient. The sum average of the operating difference coefficient and the cost difference coefficient is obtained as the governance action coefficient, denoted as r. The governance action coefficient is compared with the preset action threshold to analyze the feasibility of the target.

[0026] In a preferred embodiment, the resource evaluation module randomly selects N evaluation units in the implementation area, and calculates the governance action coefficient and the resource balance coefficient of each evaluation unit respectively;

[0027] The governance action coefficients and resource balance coefficients of the N evaluation units are respectively combined into a governance action data set and a resource balance data set, and the execution priority is calculated using the multi-factor decision method. When the execution priority exceeds the preset execution threshold, it is determined that the governance task is executable. When the execution priority is lower than the preset execution threshold, it is determined that the governance task is not executable.

[0028] An intelligent evaluation method for land pollution based on water quality big data analysis includes S1: collecting water quality data and land pollution data of the polluted area and performing preprocessing;

[0029] S2: Analyze the spatio-temporal heterogeneity of land pollution and calculate the pollution diffusion coefficient. Combining the water quality spatial correlation, use the multi-dimensional weight allocation method to calculate the regional correlation index, and accordingly determine the pollution complexity and allocate governance tasks;

[0030] S3: Based on the allocated tasks, perform simulations to obtain the planned governance duration and operating requirements, and combine the budget data in the database to calculate the cost difference, resource difference and resource balance coefficient, and comprehensively analyze the feasibility and priority of the governance target;

[0031] S4; Judge whether to implement or adjust the task according to the evaluation result, and execute the final governance plan

[0032] The technical effects and advantages of the present invention:

[0033] 1. The present invention collects multi-dimensional data related to water quality and land pollution, preprocesses the collected data, analyzes the spatio-temporal characteristics and spatial correlation of pollution, calculates the pollution complexity and allocates governance tasks, and then based on the task simulation results and budget data, evaluates the feasibility of the governance target and calculates the resource balance and action priority. Finally, according to the evaluation results, execute or adjust the governance task to achieve intelligent decision-making and dynamic optimization of water and soil pollution control. Brief Description of the Drawings

[0034] Figure 1Schematic diagram of the modules of an intelligent land pollution assessment system based on water quality big data analysis according to the present invention;

[0035] Figure 2 Method flowchart of an intelligent land pollution assessment method based on water quality big data analysis according to the present invention. Specific embodiments

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Embodiment 1

[0037] The present invention provides an intelligent land pollution assessment method and system based on water quality big data analysis, the core of which is to integrate water quality big data and land pollution monitoring data, and through a series of complex calculation and analysis processes, realize the intelligent assessment of land pollution and optimize the governance task allocation. The following combines the attached Figure 1 module diagram to describe the specific embodiments of the present invention in detail;

[0038] Attached Figure 1 shows the module structure of the system, including a data acquisition module, a complexity analysis module, a resource assessment module, and a task optimization module. The modules are connected by signals, and the entire process from data acquisition to the implementation and adjustment of governance tasks is further refined through a flowchart:

[0039] In specific implementation, first, the data acquisition module completes the collection of water quality data and land pollution data.

[0040] The water quality data mainly includes the concentration of water pollutants and flow parameters. Among them, the concentration of water pollutants covers chemical oxygen demand (COD), total nitrogen (TN), and total phosphorus (TP), while the flow parameters include flow velocity, flow rate, and water temperature.

[0041] In order to obtain data, the data acquisition module accesses the water resources monitoring platform to obtain the concentration of water pollutants and flow velocity information in the implementation area, simultaneously accesses the flowmeter to detect the flow data in the implementation area in real time, and accesses the geological monitoring database to obtain the geological structure stability information in the implementation area.

[0042] In addition, the data acquisition module also counts the vegetation coverage rate in the implementation area, and calculates the concentration ratio of heavy metals, organic matters, and inorganic salt pollutants respectively, so as to obtain the soil pollutant ratio.

[0043] The data acquisition module also sets a period of time as the environmental change analysis time for collecting ecological change data in the implementation area. After being sorted out, these data are sent to the complexity analysis module for further processing.

[0044] After receiving the water quality data and land pollution data, the complexity analysis module first preprocesses the data.

[0045] For water quality data, the complexity analysis module uses the maximum-minimum normalization method to standardize the chemical oxygen demand (COD), total nitrogen (TN), and total phosphorus (TP). The result obtained by subtracting the minimum value from the maximum value is used as the standardized result, which is marked as x, y, and z respectively.

[0046] For flow velocity and flow rate, the complexity analysis module takes the time interval of collecting the flow rate as the sample time, selects multiple historical time periods of the same length as the sample time as the analysis time, obtains the maximum flow velocity, minimum flow velocity, maximum flow rate, and minimum flow rate during the analysis time, and uses the Min-Max normalization method to process them. The normalized result of the flow velocity is used as the flow velocity coefficient, and the normalized result of the flow rate is used as the flow rate coefficient.

[0047] The water temperature is calculated by the ratio of the water body temperature in the implementation area to the standard temperature, and its value range is limited between 0 and 1, which is used as the water temperature coefficient.

[0048] For land pollution data, the complexity analysis module calculates the vegetation coverage rate according to the ratio of the vegetation coverage area to the total area in the implementation area, and standardizes the concentrations of heavy metals, organic substances, and inorganic salt pollutants to obtain the heavy metal pollutant ratio, organic pollutant ratio, and inorganic salt pollutant ratio respectively.

[0049] After completing the data preprocessing, the complexity analysis module uses the dynamic clustering method to calculate the pollution diffusion coefficient for analyzing spatio-temporal heterogeneity.

[0050] The specific steps are as follows:

[0051] The complexity analysis module divides the environmental change analysis time into two time intervals of the same length, which are marked as the early stage and the later stage respectively. It calculates the average ecological change in the two time periods respectively and takes the absolute value of the difference, and uses this value as the ecological change coefficient.

[0052] By comparing the ecological change coefficient with the preset ecological difference threshold, the spatio-temporal heterogeneity situation of the implementation area is judged.

[0053] If the ecological change coefficient exceeds the ecological difference threshold, it is judged that the spatio-temporal heterogeneity of the implementation area is high; otherwise, it is judged that the spatio-temporal heterogeneity of the implementation area is low.

[0054] Subsequently, the complexity analysis module constructs a dynamic clustering model to calculate the pollution diffusion coefficient.

[0055] The model expression is:

[0056] y = h0 - h1x1 + h2x2 + h3x3 + h4x4 + d;

[0057] Where y is the pollution diffusion coefficient, x1 is the vegetation coverage rate, x2 is the ratio of heavy metal pollutants, x3 is the ratio of organic pollutants, x4 is the ratio of inorganic salt pollutants, d is the random error term, and h1, h2, h3, and h4 are the regression coefficients of the corresponding variables respectively.

[0058] When solving the regression coefficients, the complexity analysis module obtains a system of equations consisting of 5 linear equations by taking the partial derivative of the sum of squared residuals and setting the partial derivative equal to 0, and solving the system of equations can obtain the regression coefficients of the corresponding variables, and then calculate the pollution diffusion coefficient;

[0059] Meanwhile, the complexity analysis module also uses the nonlinear mapping method to analyze the spatial correlation.

[0060] The specific steps are as follows: The complexity analysis module first determines what type of pollution the evaluation unit belongs to. After confirmation, a nonlinear mapping model is constructed with the standardized result of the pollutant concentration of the corresponding pollution type and the corresponding flow parameter coefficient. The model expression is:

[0061] M = f(P, Q);

[0062] Where M is the result of the nonlinear mapping calculation, f is the nonlinear function, P is the standardized result of the pollutant concentration of the corresponding pollution type, and Q is the corresponding flow parameter coefficient.

[0063] The complexity analysis module obtains the pollution type ratio of the evaluation unit and classifies the pollution type of the evaluation unit by obtaining the three-dimensional coordinate range of the evaluation unit, and takes the type with the largest pollution type ratio as the reference type.

[0064] For example, if the proportion of chemical oxygen demand in the evaluation unit is the largest, the corresponding pollution type is chemical oxygen demand, and the corresponding flow parameter is the flow velocity coefficient, that is, P is the standardized result of chemical oxygen demand, and Q is the flow velocity coefficient.

[0065] When the result of the nonlinear mapping calculation exceeds the preset spatial correlation threshold, it is judged that the spatial correlation of the evaluation unit is high; when the result of the nonlinear mapping calculation is lower than the preset spatial correlation threshold, it is judged that the spatial correlation of the evaluation unit is low;

[0066] After completing the analysis of spatio-temporal heterogeneity and spatial correlation, the complexity analysis module comprehensively evaluates the pollution complexity based on the results of both.

[0067] When the spatial correlation of the evaluation units is high and the spatio-temporal heterogeneity of the implementation area is low, it is judged that the pollution complexity is low; otherwise, it is judged that the pollution complexity is high.

[0068] When the pollution complexity is low, the complexity analysis module uses the dynamic weighted allocation method to optimize the governance tasks.

[0069] The specific steps are as follows: First, determine the input and output, taking the regional correlation index and the pollution diffusion coefficient as the input, and the governance priority coefficient as the output.

[0070] Subsequently, prepare the spatial data by collecting the spatial location information of each evaluation unit in the implementation area, such as longitude and latitude coordinates.

[0071] Then, establish a dynamic weighted model, and the model expression is:

[0072] Z = β0(ui, vi) - β1(ui, vi)α1 + β2(ui, vi)α2 + ε;

[0073] Among them, Z is the governance priority coefficient, β0, β1, and β2 are local weighted coefficients, (ui, vi) is the coordinate of the i-th evaluation unit, α1 is the regional correlation index, α2 is the pollution diffusion coefficient, and ε is the random error term.

[0074] The complexity analysis module uses the distance weighted method to calculate the local weighted coefficients, and its weight function is set using the exponential kernel function.

[0075] When calculating the governance priority coefficient, use the calculated local weighted coefficients to calculate the governance priority coefficient Z of all evaluation units through the dynamic weighted model, and merge them into the governance data set.

[0076] When setting the allocation ratio, calculate the average value of the governance data set, and use the calculation result obtained by dividing the governance priority coefficient of each evaluation unit by the average value of the governance data set as the allocation ratio.

[0077] Finally, allocate the task volume for each governance task according to the allocation ratio. The formula is T = α × T, where α is the allocation ratio, T is the governance task evenly distributed to each evaluation unit in the entire implementation area, and T is the governance task of each evaluation unit.

[0078] The resource evaluation module is responsible for collecting budget data and simulation operation data, and analyzing the feasibility of the governance goal through the budget data and simulation operation data.

[0079] The budget data includes the governance duration budget and the operation resource allocation, and the simulation operation data includes the planned governance duration budget and the planned operation resource allocation.

[0080] The resource evaluation module simulates according to the governance tasks assigned by the complexity analysis module, and automatically calculates the proposed governance duration budget and the proposed operation resource allocation.

[0081] Subsequently, the resource evaluation module accesses the database to obtain the proposed governance duration budget and the proposed operation resource allocation, subtracts the governance duration budget from the proposed governance duration, and then performs the same standardization processing with the ecological change coefficient. The result after standardizing the difference between the governance duration budget and the proposed governance duration is used as the cost difference coefficient.

[0082] The resource evaluation module calculates the resource balance coefficient using the multi-factor combination decision formula. The formula is:

[0083] f = u × 1 + v × 2;

[0084] Where f is the resource balance coefficient, u is the cost difference coefficient, and v is the result after standardizing the ecological change coefficient.

[0085] When the cost difference coefficient or the ecological change coefficient is larger, the task implementation duration is more lenient, and the resource balance coefficient is larger.

[0086] At the same time, the resource evaluation module uses the result after standardizing the difference between the operation resource allocation and the proposed operation resource requirement as the operation difference coefficient, and sums and averages the operation difference coefficient and the cost difference coefficient to obtain the governance action coefficient, denoted as r.

[0087] Compare the governance action coefficient with the preset action threshold to analyze the target feasibility. When the governance action coefficient exceeds the action threshold, it is judged that the target feasibility is high; otherwise, it is judged that the target feasibility is low.

[0088] The resource evaluation module randomly selects N evaluation units in the implementation area, and calculates the governance action coefficient and the resource balance coefficient of each evaluation unit respectively.

[0089] It should be noted that the duration budget data and operation feedback data of each unit are formulated based on the average budget data of each evaluation unit and the allocation ratio of the governance tasks of each evaluation unit. For example, if the allocation ratio of a certain unit is 1.2, and the average budget duration of each evaluation unit is 2000 seconds and the average operation configuration is 5 monitoring devices, then the corresponding unit budget cost is 2400 seconds, and the corresponding unit budget operation configuration is 6 monitoring devices; when calculating the operation configuration according to the ratio, the calculation result is rounded up.

[0090] It should be noted that the limitation of the operation configuration can be monitoring devices or operation configurations such as drone monitoring. The specific type of operation configuration is not limited and will not be elaborated here;

[0091] Combine the governance action coefficients and resource balance coefficients of N evaluation units into a governance action data set and a resource balance data set respectively.

[0092] Use the multi-factor decision-making method to calculate the execution priority for the comprehensive governance action data set and the resource balance data set. The specific steps are as follows: First, construct a linear combination for calculating the execution priority. The formula is:

[0093] s = w1r + w2f;

[0094] Where s is the execution priority, r is the average value of the governance action data set, f is the average value of the resource balance data set, w1 is the optimal coefficient of r, and w2 is the optimal coefficient of f.

[0095] Sum the governance action coefficients and resource balance coefficients obtained for each evaluation unit. S = r + f. Use the multi-factor decision formula to calculate w1 and w2. The formula is min(1 / 2N × (S - (w1r + w2f))^2 + γ × (|w1| + |w2|)), where γ is the regularization parameter.

[0096] When w1 and w2 make the calculation result minimum using the multi-factor decision formula, w1 and w2 are the optimal coefficients of r and f respectively.

[0097] Compare the calculated execution priority with the preset execution threshold. When the execution priority exceeds the preset execution threshold, it is determined that the governance task is executable, and the resource evaluation module sends a confirmation governance task signal to the task optimization module;

[0098] When the execution priority is lower than the preset execution threshold, it is determined that the governance task is not executable, and the resource evaluation module sends the calculated execution priority and an adjusted governance task signal to the task optimization module;

[0099] The task optimization module is responsible for receiving the signals sent by the resource evaluation module and implementing the governance task content or implementing it after adjusting the governance task content.

[0100] When the task optimization module receives the confirmation governance task signal, it implements the evaluation unit governance task given by the complexity analysis module; when it receives the adjusted governance task content, it adjusts the allocation ratio according to the execution priority. The product of the allocation ratio and the execution priority can be used as the new allocation ratio, and the evaluation unit governance task is allocated and implemented according to the new allocation ratio.

[0101] Specifically, the following water pollution source detection methods can be adopted before evaluation:

[0102] Synchronously collect water body environment data during the collection of acoustic disturbance data, including four indicators: water temperature, pH value, dissolved oxygen concentration, and flow velocity.

[0103] The first set of the water environment data is four types of indicators (water temperature, pH value, dissolved oxygen concentration and flow velocity) at the sediment; the second set of the water environment data is four types of indicators at 5 cm vertically upward from the sediment; the third set of the water environment data is four types of indicators at 15 cm vertically upward from the sediment; the fourth set of the water environment data is four types of indicators at 50 cm vertically upward from the sediment.

[0104] Such a setting is because when the sediment is disturbed, only the composition of the sediment is often considered, and the diffusion situation of the sediment and the actual non-linear pollution behavior cannot be reflected in time. By setting the water environment data with gradient heights, the change situation in the short-distance range after the sediment is disturbed can be reflected preferentially, and as the diffusion range increases, the set gradient gradually increases, effectively preventing the collection of invalid data or unobvious data and facilitating the accuracy of subsequent analysis.

[0105] Calculate the water environment gradient data based on the water environment data; let the water environment data be ; is the group number of the water environment data, = 1, 2, 3, 4 are the first, second, third and fourth groups of the water environment data respectively; is the category identifier of the water environment data, = 1, 2, 3, 4 represent water temperature, pH value, dissolved oxygen concentration and flow velocity respectively; the water environment gradient data is:

[0106] In the formula, = 1;

[0107] The water environment gradient data is also four groups; each group is a three-dimensional vector; the collection of the water environment gradient data is to improve the sensitivity to pollution release abnormal events; the traditional collection and analysis of sediment only exist in the laboratory, which is far from enough if the timely response ability of the environmental protection department needs to be improved. By obtaining the water environment gradient data and amplifying the gradient influence of sediment disturbance, it is beneficial to detect and warn water pollution in a timely and real-time manner. The vector method can reflect the gradient trend better than single data.

[0108] Introduce the water environment gradient data and the acoustic disturbance data into the time synchronization mechanism. The time synchronization mechanism is to stamp the water environment gradient data and the acoustic disturbance data with a unified time stamp accurate to seconds. The information of the time stamp includes the collection date, hour, minute, second and quarter identifier, which is used to construct the time series input feature matrix subsequently. The quarter information is automatically determined by the built-in calendar module of the system. The introduction of time features can improve the model's recognition ability for periodic disturbance events and seasonal pollution release trends.

[0109] In summary, the present invention integrates water quality big data and land pollution monitoring data, and combines algorithms such as dynamic clustering method, non-linear mapping method, dynamic weighted allocation method and multi-factor decision-making method to realize the intelligent evaluation of land pollution and the optimal allocation of governance tasks. Through the above specific implementation manners, problems such as unreasonable allocation of governance tasks and overrun of governance duration can be effectively reduced, which has important practical application value. Embodiment 2

[0110] Please refer to Figure 2 , an intelligent evaluation method for land pollution based on water quality big data analysis, including:

[0111] S1: Collect water quality data and land pollution data of the polluted area and perform preprocessing;

[0112] S2: Analyze the spatio-temporal heterogeneity of land pollution and calculate the pollution diffusion coefficient. Combine the water quality spatial correlation, and use the multi-dimensional weight allocation method to calculate the regional correlation index, and accordingly determine the pollution complexity and allocate governance tasks;

[0113] S3: Based on the allocated tasks, perform simulations to obtain the planned governance duration and operation requirements, and combine the budget data in the database to calculate the cost difference, resource difference and resource balance coefficient, and comprehensively analyze the feasibility and priority of the governance objectives;

[0114] S4; Judge whether to implement or adjust the tasks according to the evaluation results, and execute the final governance plan;

[0115] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0116] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of 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, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. 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 by wired or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0117] It should be understood that in various embodiments of the present application, the order numbers of the above processes do not indicate the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0118] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0119] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0120] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0123] If the functions are implemented in the form of software function 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 part of this 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 for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0124] As described above, only the specific implementation manners of this application are provided, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An intelligent land pollution assessment system based on water quality big data analysis, characterized in that: Including: A data acquisition module, a complexity analysis module, a resource evaluation module, and a task optimization module, with signal connections between the modules; The data acquisition module is used to obtain water quality data and land pollution data of the polluted area; The complexity analysis module preprocesses the collected data, analyzes the spatio-temporal heterogeneity of land pollution and calculates the pollution diffusion coefficient, combines the water quality spatial correlation, uses the multi-dimensional weight distribution method to calculate the regional correlation index, and determines the pollution complexity and assigns governance tasks according to the pollution diffusion coefficient and the regional correlation index; The resource evaluation module conducts simulations based on the assigned tasks, obtains the planned treatment duration and operation requirements, and calculates the cost difference, resource difference, and resource balance coefficient in combination with the budget data in the database, and comprehensively analyzes the feasibility and priority of the governance objectives; The task optimization module determines whether to implement or adjust the task according to the evaluation results and executes the final governance plan; The steps of calculating the regional correlation index using the multi-dimensional weight distribution method include: dividing the implementation area into N unit spatial areas, classifying them according to pollution types respectively, obtaining the non-linear mapping calculation result and multiplying it by the corresponding pollutant concentration standardization result and then summing as the weight coefficient, setting the pollution weight using the analytic hierarchy process, and calculating the regional correlation index by weighted summing of the pollutant concentration standardization result and the pollution weight; among them, the steps of obtaining the non-linear mapping calculation result include: first determining which pollution type the evaluation unit belongs to, constructing a non-linear mapping model with the pollutant concentration standardization result of the corresponding pollution type and the corresponding flow parameter coefficient, and obtaining the non-linear mapping calculation result through the constructed non-linear mapping model; The steps of calculating the pollution diffusion coefficient include: dividing the environmental change analysis time into two time intervals with the same time, calculating the average ecological change of the two time periods and taking the absolute value of the difference as the ecological change coefficient, and judging the spatio-temporal heterogeneity of the implementation area by comparing the ecological change coefficient with the preset ecological difference threshold; if the ecological change coefficient exceeds the ecological difference threshold, it is judged that the spatio-temporal heterogeneity of the implementation area is high, otherwise it is judged that the spatio-temporal heterogeneity of the implementation area is low, constructing a dynamic clustering model, solving the system of equations by taking the partial derivative of the sum of squared residuals and setting the partial derivative equal to 0 to obtain the regression coefficients of the corresponding variables, and then calculating the pollution diffusion coefficient.

2. The intelligent land pollution assessment system based on water quality big data analysis according to claim 1, wherein: The data acquisition module accesses the water resource monitoring platform to obtain the water body pollutant concentration and flow rate of the implementation area, accesses the flow meter to detect the flow rate of the implementation area in real time, accesses the geological monitoring database to obtain the geological structure stability of the implementation area, counts the vegetation coverage rate of the implementation area and respectively counts the pollutant concentrations of heavy metals, organic substances, and inorganic salts to calculate the soil pollutant ratio, and sets a period of time as the environmental change analysis time to collect the ecological change data of the implementation area.

3. The intelligent land pollution assessment system based on water quality big data analysis according to claim 2, characterized in that: The specific steps for the complexity analysis module to preprocess water quality data and land pollution data are as follows: For water quality data, the results obtained by subtracting the minimum value from the maximum value of chemical oxygen demand, total nitrogen, and total phosphorus are used as the standardized results, which are respectively labeled as x, y, and z. For flow velocity and flow rate, multiple historical time periods of the same length as the sample time are selected as the analysis time with the time interval of the collected flow rate as the sample time. The maximum flow velocity, minimum flow velocity, maximum flow rate, and minimum flow rate within the analysis time are obtained, and the Min-Max normalization method is used to process them. The normalized result of the flow velocity is used as the flow velocity coefficient, and the normalized result of the flow rate is used as the flow rate coefficient. The water temperature is the ratio of the water temperature in the implementation area to the standard temperature, and its value range is limited between 0 and 1, which is used as the water temperature coefficient. For land pollution data, the vegetation coverage rate is calculated based on the ratio of the vegetation coverage area to the total area in the implementation area, and the concentrations of heavy metal, organic, and inorganic salt pollutants are standardized to obtain the heavy metal pollutant ratio, organic pollutant ratio, and inorganic salt pollutant ratio respectively.

4. An intelligent land pollution assessment system based on water quality big data analysis according to claim 1, characterized in that: After obtaining the non-linear mapping calculation result, when the non-linear mapping calculation result exceeds the preset spatial correlation threshold, it is determined that the spatial correlation of the evaluation unit is high; when the non-linear mapping calculation result is lower than the preset spatial correlation threshold, it is determined that the spatial correlation of the evaluation unit is low.

5. An intelligent land pollution assessment system based on water quality big data analysis according to claim 1, characterized in that: The specific steps for the complexity analysis module to calculate the regional correlation index using the multi-dimensional weight allocation method are as follows: The implementation area is divided into N unit spatial regions, which are classified according to pollution types, specifically as chemical oxygen demand regions, total nitrogen regions, and total phosphorus regions.

6. The intelligent land pollution assessment system based on water quality big data analysis according to claim 1, characterized in that: The environmental change analysis time is divided into two time intervals of the same length, which are respectively labeled as the early stage and the late stage.

7. An intelligent land pollution assessment system based on water quality big data analysis according to claim 1, characterized in that: When the pollution complexity is low, the complexity analysis module uses the dynamic weighted allocation method to optimize the governance tasks. The specific steps are as follows: Taking the regional correlation index and the pollution diffusion coefficient as inputs and the governance priority coefficient as the output, a dynamic weighted model is established. The distance weighted method is used to calculate the local weighted coefficient, and its weight function is set using the exponential kernel function. After calculating the governance priority coefficient, the allocation ratio is set, and the average value of the governance data set is calculated. The calculation result obtained by dividing the governance priority coefficient of each evaluation unit by the average value of the governance data set is used as the allocation ratio, and the task volume of each governance task is allocated according to the allocation ratio.

8. An intelligent land pollution assessment system based on water quality big data analysis according to claim 7, characterized in that: The resource evaluation module automatically calculates the planned governance duration and the required planned operating resources for each evaluation unit and accesses the database to obtain the planned governance duration budget and the planned operating resource configuration. The difference between the governance duration budget and the planned governance duration is subjected to the same standardization process as the ecological change coefficient. The standardized result of the difference between the governance duration budget and the planned governance duration is used as the cost difference coefficient. The resource balance coefficient is calculated using the multi-factor combination decision formula. The standardized result of the difference between the operating resource configuration and the required planned operating resources is used as the operating difference coefficient. The sum of the operating difference coefficient and the cost difference coefficient is averaged to obtain the governance action coefficient, which is labeled as r. The governance action coefficient is compared with the preset action threshold to analyze the feasibility of the target.

9. An intelligent land pollution assessment system based on water quality big data analysis according to claim 8, characterized in that: The resource evaluation module randomly selects N evaluation units in the implementation area, and calculates the governance action coefficient and resource balance coefficient of each evaluation unit respectively; The governance action coefficients and resource balance coefficients of the N evaluation units are respectively combined into a governance action data set and a resource balance data set, and the execution priority is calculated using the multi-factor decision-making method. When the execution priority exceeds the preset execution threshold, it is determined that the governance task is executable; when the execution priority is lower than the preset execution threshold, it is determined that the governance task is not executable.

10. An intelligent land pollution assessment method based on water quality big data analysis, which is used to implement an intelligent land pollution assessment system according to any one of claims 1-9, and is characterized in that: It includes: S1: Collect water quality data and land pollution data in the polluted area and perform preprocessing; S2: Analyze the spatio-temporal heterogeneity of land pollution and calculate the pollution diffusion coefficient. Combining the water quality spatial correlation, use the multi-dimensional weight allocation method to calculate the regional correlation index, and accordingly determine the pollution complexity and allocate governance tasks; S3: Based on the allocated tasks, perform simulations to obtain the planned governance duration and operation requirements, and calculate the cost difference, resource difference and resource balance coefficient in combination with the budget data in the database, and comprehensively analyze the feasibility and priority of the governance objectives; S4: Judge whether to implement or adjust the tasks according to the evaluation results, and execute the final governance plan.

Images