Intelligent evaluation method and system for water and soil pollution based on multi-source data

Abstract

The invention discloses an intelligent evaluation method and system for water and soil pollution based on multi-source data, relates to the technical field of environment monitoring and intelligent evaluation, and is used for solving the problem of insufficient precision of multi-source data fusion and pollution dynamic monitoring. The method comprises the following steps: dividing a monitoring space into a plurality of independent but correlated evaluation units, calculating a pollutant concentration gradient, combining the pollutant concentration gradient with a pollution diffusion rate obtained by detecting equipment working frequency and sampling precision, comprehensively judging whether a pollution state needs to be evaluated again or not, calculating a pollution correlation degree and a pollution trend prediction value between the unit and other units, and calculating a prediction result. According to the method, evaluation resources are redistributed, different evaluation priorities are set for adjacent units, more detection capabilities are distributed for high-priority units, energy consumption of low-priority units is reduced, comprehensive evaluation efficiency is calculated, and according to the comprehensive evaluation efficiency and the change frequency of environmental parameters, the updating period of an evaluation strategy is dynamically adjusted. The operation efficiency of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring and intelligent assessment, and more specifically, to a method and system for intelligent assessment of water and soil pollution based on multi-source data. Background Art

[0002] With the continuous development of environmental monitoring technology, the intelligent assessment method and system of water and soil pollution based on multi-source data have shown important application value in the field of environmental protection. The existing relevant technical solutions still have some shortcomings in data fusion, intelligent analysis and real-time monitoring capabilities, which affects their assessment accuracy and applicability.

[0003] The prior art has the following deficiencies: At present, the existing intelligent sensors and data processing systems still need to be improved in terms of multi-source data fusion, dynamic pollution monitoring and comprehensive assessment capabilities. Therefore, an intelligent assessment method and system for water and soil pollution based on multi-source data is proposed.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for intelligent assessment of water and soil pollution based on multi-source data, which solves the problems raised in the above-mentioned background technology through multi-dimensional monitoring, intelligent analysis and precise assessment of water and soil pollution.

[0006] To achieve the above object, the present invention provides the following technical solution: a method and system for intelligent assessment of water and soil pollution based on multi-source data, comprising a data acquisition module, a dynamic analysis module, a priority allocation module and an update optimization module, and signal connections between the modules; The data acquisition module collects environmental parameters through a distributed sensor network, generates a basic pollution assessment model based on the processing results, and dynamically adjusts the working frequency and sampling accuracy of the detection equipment; The dynamic analysis module divides the monitoring space into multiple independent but interrelated evaluation units. When the pollution status of a unit changes significantly, the pollutant concentration gradient is calculated and combined with the pollution diffusion rate obtained by the working frequency and sampling accuracy of the detection equipment to comprehensively determine whether the pollution status needs to be re-evaluated; The priority allocation module calculates the pollution correlation between the unit and other units and the pollution trend prediction value, reallocates the evaluation resources, sets different evaluation priorities for adjacent units, allocates more detection capabilities to high-priority units, reduces the energy consumption of low-priority units, and calculates the comprehensive evaluation efficiency; The update optimization module dynamically adjusts the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of changes in environmental parameters.

[0007] In a preferred embodiment, the data acquisition module collects multiple environmental parameters in real time through a distributed sensor network, including pollutant concentration, soil moisture, water flow velocity, and air pressure, and transmits them to the central processing unit through the sensor network.

[0008] In a preferred embodiment, the dynamic analysis module divides the entire monitoring space into different preliminary evaluation units according to functional zoning, so that the detection equipment in each evaluation unit can operate and adjust independently. When the detection equipment of the unit cannot be controlled independently, these units are merged into one evaluation unit, and the sensor network is used to perform real-time environmental detection on each unit. The environmental detection data includes pollutant concentration and air pressure. The pollutant concentration gradient is calculated using the pollutant diffusion equation based on the environmental detection data.

[0009] In a preferred embodiment, the pollutant concentration gradient is calculated by the pollutant diffusion equation; The pollution diffusion rate is affected by the working frequency of the detection equipment, sampling accuracy and data transmission rate. The pollution diffusion rate is modeled through a multi-factor function. Set thresholds for pollutant concentration gradient and pollution diffusion rate respectively, and comprehensively judge whether it is necessary to re-evaluate the pollution status: Combined with the changes in pollutant concentration gradient and pollution diffusion rate, the following judgment rules are formulated: When the pollutant concentration gradient is greater than or equal to the pollutant concentration gradient threshold, or the pollution diffusion rate is less than or equal to the pollution diffusion rate threshold, the pollution status needs to be reassessed; When the pollutant concentration gradient is less than the pollutant concentration gradient threshold and the pollution diffusion rate is higher than the pollution diffusion rate threshold, there is no need to re-evaluate the pollution status.

[0010] In a preferred embodiment, the priority allocation module uses a sensor network to perform real-time environmental detection on each unit, and the environmental detection data includes pollutant concentration and soil moisture. The pollution correlation between the unit and other units is calculated using cosine similarity based on the environmental detection data; Calculate the cosine similarity between each pair of units, evaluate the contamination correlation of each pair of units, and average the cosine similarity between each pair of units and record it as the final contamination correlation; The pollution trend is predicted using a time series prediction model. The time series prediction model in this embodiment adopts an LSTM model. The pollution trend is predicted when it is determined that the current initialization evaluation resource allocation is unreasonable. Furthermore, the specific steps for predicting pollution trends through the time series prediction model are as follows: Step C1, obtaining prediction data; Step C2, building an LSTM model; Step C3, using gradient descent method to optimize LSTM model parameters; Step C4, verifying the effect of the fitting model and checking the goodness of fit of the model by the mean square error method; Step C5, using the fitted model to predict the future pollution trend, and taking the maximum value of the prediction result as the highest point of the pollution trend in the future time period; Specifically, the prediction data include the water flow velocity and pollution diffusion rate data corresponding to each time point; Pollution trend data refers to historical pollution trend data, whose data are used as the main variables of the time series; In step C3, α, W1, and U1 are calculated by the gradient descent method; Dynamically predict pollution trends by predicting the maximum, minimum and average values ​​of the results.

[0011] In a preferred embodiment, after receiving the final pollution correlation degree and the pollution trend, the final pollution correlation degree and the pollution trend are defined as input variables, and they are divided into different fuzzy sets respectively; Define the priority as the output variable and divide it into fuzzy sets; Formulate fuzzy rules to describe the final pollution correlation and the impact of pollution trends on priorities; Perform fuzzy reasoning based on fuzzy rules to determine priorities; The priority ranking results are synthesized to obtain a priority ranking table, and the evaluation resources are reallocated according to the priority ranking, with the evaluation resources being allocated to units with higher levels first; After the evaluation resources are reallocated, the detection output and energy consumption input of each unit are recorded, and the evaluation efficiency of each unit is calculated respectively. The evaluation efficiency is the ratio of the detection output and the energy consumption input. The comprehensive evaluation efficiency is obtained by taking the weighted average of the evaluation efficiencies of each unit.

[0012] In a preferred embodiment, the update optimization module collects pollutant concentration and soil moisture environmental parameters in real time through a sensor network, designs a threshold for pollutant concentration and soil moisture data, and counts it as one time when the threshold is exceeded. The change frequency of the environmental parameters is represented by the ratio of the total number of changes to the total time; Dynamically adjust the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of change of environmental parameters, use particle filters to smooth the dynamic changes of the comprehensive evaluation efficiency and the frequency of change of environmental parameters, update the evaluation strategy through the observed noise data, extract and comprehensively evaluate the trend slope of efficiency and environmental parameters from the noise data, and infer the change rate; Comprehensively evaluate the change frequency of efficiency and environmental parameters, and calculate the trend slope of the change frequency of comprehensive evaluation efficiency and environmental parameters; The update period is adjusted according to the calculated rate of change: when the rate of change is faster, the update period is shortened; when the rate of change is slower, the update period is lengthened.

[0013] In a preferred embodiment, the distributed sensing network in the data acquisition module is composed of multiple sensor nodes, which are deployed at different locations in the monitoring area to collect pollutant concentration, soil moisture, water flow velocity, and air pressure data. The sensor nodes are connected to the central processing unit via a wireless communication protocol and transmit the collected data to the central processing unit for processing.

[0014] An intelligent assessment method for water and soil pollution based on multi-source data includes: S1: collecting environmental parameters through a distributed sensor network and dynamically adjusting the working frequency and sampling accuracy of the detection equipment; S2: Divide the monitoring space into multiple independent but interrelated evaluation units, calculate the pollutant concentration gradient and the pollution diffusion rate obtained by the working frequency and sampling accuracy of the detection equipment, and comprehensively judge whether the pollution status needs to be re-evaluated; S3: Calculate the pollution correlation between the unit and other units and the pollution trend prediction value, reallocate the evaluation resources, set different evaluation priorities for adjacent units, allocate more detection capabilities to high-priority units, reduce the energy consumption of low-priority units, and calculate the comprehensive evaluation efficiency; S4: Dynamically adjust the update cycle of the evaluation strategy based on the comprehensive evaluation efficiency and the frequency of changes in environmental parameters.

[0015] Technical effects and advantages of the present invention: 1. The present invention collects environmental parameters through a distributed sensor network, divides the monitoring space into a plurality of independent but interrelated evaluation units, calculates the pollutant concentration gradient and the pollution diffusion rate obtained by the working frequency of the detection equipment and the sampling accuracy, comprehensively judges whether it is necessary to re-evaluate the pollution status, calculates the pollution correlation between the unit and other units and the pollution trend prediction value, reallocates the evaluation resources, sets different evaluation priorities for adjacent units, allocates more detection capabilities to high-priority units, reduces the energy consumption of low-priority units, calculates the comprehensive evaluation efficiency, dynamically adjusts the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of changes in environmental parameters, reasonably allocates detection resources, reduces energy consumption, and improves the operation efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a module of an intelligent water and soil pollution assessment system based on multi-source data according to the present invention; Figure 2 This is a method flow chart of an intelligent water and soil pollution assessment method based on multi-source data of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1

[0019] The present invention provides an intelligent assessment system for water and soil pollution based on multi-source data. Figure 1 The module structure diagram shown in the figure is described in detail. Figure 1 The four core modules of the system and their connection relationships are demonstrated, including data acquisition module, dynamic analysis module, priority allocation module and update optimization module. Each module realizes information exchange through signal connection and jointly completes the intelligent assessment task of water and soil pollution; The data acquisition module is the basic part of the whole system. Its main function is to realize the real-time acquisition of various environmental parameters through a distributed sensor network.

[0020] The distributed sensing network consists of multiple sensor nodes, which are deployed at different locations in the monitoring area to collect environmental parameters such as pollutant concentration, soil moisture, water flow velocity, and air pressure.

[0021] The sensor nodes are connected to the central processing unit through wireless communication protocols and transmit the collected data to the central processing unit for processing.

[0022] The data acquisition module also includes the implementation process of the adaptive filtering algorithm, which generates a basic model for pollution assessment through real-time processing of the collected data and dynamically adjusts the working frequency and sampling accuracy of the detection equipment.

[0023] Specifically, first, assume that the environmental parameter set H contains n samples, each sample j has m features fj1, fj2, fj3...fjm, and the target variable is the pollution assessment basic model kj.

[0024] Then the data is normalized, 70% of the data set H is randomly divided into a training set and 30% is randomly divided into a test set, satisfying p+q=n. Then three parallel filters are constructed. For each filter, a sample set of size p is extracted with replacement in the training set, and b features are randomly selected from m features at each filtering point.

[0025] Use the trained filter to predict the training set or test set data and output a prediction result k.

[0026] Finally, the prediction results of all filters are processed comprehensively as the basic model for pollution assessment, including the operating frequency and sampling accuracy of the detection equipment.

[0027] The output results of the data acquisition module are transmitted to the dynamic analysis module through signal connection to provide data support for its subsequent processing.

[0028] The dynamic analysis module divides the monitoring space into multiple independent but interrelated evaluation units according to the pollution characteristics. The detection equipment in each unit can operate and adjust independently.

[0029] When the detection equipment of a unit cannot be controlled independently, the units are combined into one evaluation unit.

[0030] The dynamic analysis module obtains environmental detection data in real time through the sensor network, including pollutant concentration and air pressure, and calculates the pollutant concentration gradient based on the pollutant diffusion equation.

[0031] The formula for the pollutant concentration gradient is: ; in, is the pollutant concentration gradient, is the number of moles of pollutant, is the diffusion coefficient of the pollutant, C1 and C2 are the initial and final pollutant concentrations, P1 and P2 are the initial and final gas pressures, and R is the gas constant.

[0032] In addition, the pollution diffusion rate fd is jointly affected by the working frequency fw of the detection equipment, the sampling accuracy fs and the data transmission rate ft, and is modeled by a multi-factor function as follows: ; in, , , is the adjustment coefficient, which indicates the degree of influence of each parameter on the pollution diffusion rate; The dynamic analysis module sets thresholds for pollutant concentration gradient and pollution diffusion rate respectively. and , and formulate judgment rules: When the pollutant concentration gradient is greater than or equal to the pollutant concentration gradient threshold, or the pollution diffusion rate is less than or equal to the pollution diffusion rate threshold, the pollution status needs to be reassessed; When the pollutant concentration gradient is less than the pollutant concentration gradient threshold and the pollution diffusion rate is higher than the pollution diffusion rate threshold, there is no need to re-evaluate the pollution status.

[0033] The output results of the dynamic analysis module are transmitted to the priority allocation module through signal connection to provide a basis for its resource allocation.

[0034] The priority allocation module reallocates assessment resources based on pollution correlation and pollution trend prediction values.

[0035] The priority allocation module obtains environmental detection data in real time through the sensor network, including pollutant concentration and soil moisture, and uses cosine similarity to calculate the pollution correlation between the unit and other units.

[0036] The cosine similarity formula is: ; in, and are the environmental data of two units respectively. After calculating the cosine similarity between each pair of units, the average value is taken as the final pollution correlation.

[0037] In addition, the priority allocation module uses the time series prediction model LSTM to predict pollution trends; The specific steps include obtaining prediction data, establishing an LSTM model, optimizing model parameters using the gradient descent method, verifying the effect of the fitted model, and using the fitted model to predict future pollution trends.

[0038] The prediction data include the water flow velocity and pollution diffusion rate data corresponding to each time point. The basic form of the LSTM model is: ; in, is the pollution trend at the current time point, is the bias term, For the The hidden layer weights, is the number of hidden layers, For the The weight of the input layer, is the number of input layers, is a random noise term, is the hidden state at the previous moment, is the input variable.

[0039] The specific process of optimizing model parameters by gradient descent includes defining the loss function: ; and derive the loss function to get the gradient , and , and then update the parameter value by gradient descent method , , .

[0040] The maximum, minimum and average values ​​of the prediction results are used to dynamically predict pollution trends.

[0041] After receiving the final pollution correlation and pollution trend, the priority allocation module divides them into different fuzzy sets and formulates fuzzy rules to describe the impact of the two on the priority.

[0042] After determining the priority through fuzzy reasoning, a priority ranking table is generated, and resource reallocation is evaluated based on the priority ranking.

[0043] The priority allocation module records the detection output and energy consumption input of each unit, calculates the evaluation efficiency Ei of each unit, and calculates the comprehensive evaluation efficiency through weighted average: ; in, is the weight of each unit, is the total number of units.

[0044] The output result of the priority allocation module is transmitted to the update optimization module through signal connection, providing a basis for its strategy adjustment.

[0045] The update optimization module collects pollutant concentration and soil moisture environmental parameters in real time through the sensor network, and designs thresholds to statistically analyze the frequency of changes in environmental parameters.

[0046] The frequency of change is expressed as the ratio of the total number of changes to the total time. The update optimization module dynamically adjusts the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of change of environmental parameters, and uses a particle filter to smooth the dynamic changes of the comprehensive evaluation efficiency and the frequency of change of environmental parameters.

[0047] The state space model of particle filtering can be expressed as: , ; in, is the state vector of the system, is the state transition matrix, is the control input matrix, is the control input, is the process noise, is the observed value, is the observation matrix, is the observation noise.

[0048] Update optimization module to calculate the trend slope of comprehensive evaluation efficiency and frequency of change of environmental parameters ; in, is the slope of the trend, is the sampling interval.

[0049] The update period is adjusted according to the calculated change rate, shortening the update period when the change rate is faster and extending the update period when the change rate is slower.

[0050] The specific adjustment method rules are defined as , in, is the trend slope of the frequency of change of environmental parameters, is the trend slope of the comprehensive evaluation efficiency; is a function, set up as follows: ; in, and is the adjustment coefficient, which controls the update period for faster and slower changes respectively; The above four modules realize information exchange through signal connection and together constitute an intelligent water and soil pollution assessment system based on multi-source data.

[0051] The data acquisition module collects environmental parameters through a distributed sensor network and generates a basic model for pollution assessment; The dynamic analysis module divides the evaluation units according to the pollution characteristics and calculates the pollutant concentration gradient and diffusion rate; The priority allocation module reallocates assessment resources based on pollution correlation and trend prediction values; The update optimization module dynamically adjusts the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of changes in environmental parameters.

[0052] The modules work together to ensure that the system can complete the intelligent assessment task of water and soil pollution efficiently and accurately.

[0053] In order to enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is supplemented below in combination with a specific application scenario.

[0054] In a water and soil pollution monitoring project in an industrial park, the system deploys multiple sensor nodes to form a distributed sensor network. These sensor nodes are distributed in different areas of the park and are used to collect environmental parameters such as pollutant concentration, soil moisture, water flow velocity and air pressure in real time.

[0055] The data acquisition module transmits the collected data to the central processing unit, processes the data in real time using an adaptive filtering algorithm, generates a basic model for pollution assessment, and dynamically adjusts the operating frequency and sampling accuracy of the detection equipment.

[0056] For example, if a significant increase in pollutant concentration is detected in a certain area, the system will automatically increase the operating frequency and sampling accuracy of the sensors in that area to ensure the accuracy of the data. At the same time, the data acquisition module will pass the processed data to the dynamic analysis module to provide support for subsequent analysis.

[0057] The dynamic analysis module divides the monitoring area into multiple independent but interrelated evaluation units according to the pollution characteristics.

[0058] For example, when the pollutant concentration gradient in a unit exceeds the set threshold, module 2 will calculate the pollutant diffusion rate and comprehensively determine whether it is necessary to re-evaluate the pollution status of the unit.

[0059] Assuming that the pollutant concentration detected in a unit rises rapidly from the initial value C1 to the final value C2, and the air pressure drops from P1 to P2, module 2 calculates the pollutant concentration gradient based on the pollutant diffusion equation Δ, and further analyzes it in combination with the pollution diffusion rate formula. If the pollutant concentration gradient is greater than or equal to the threshold Or the pollution diffusion rate is less than or equal to the threshold , then the re-evaluation mechanism is triggered.

[0060] The dynamic analysis module transmits the analysis results to the priority allocation module to provide a basis for resource allocation.

[0061] The priority allocation module reallocates the evaluation resources of each unit based on the pollution correlation and pollution trend prediction value.

[0062] For example, the pollution correlation between a unit and other units is calculated using the cosine similarity formula, and the LSTM model is used to predict the pollution trend.

[0063] In a specific scenario, assuming that the pollution trend prediction results of a certain unit show that the pollutant concentration will continue to rise in the future, the priority allocation module will increase the priority of the unit and allocate more detection resources to it.

[0064] At the same time, the priority allocation module records the detection output and energy consumption input of each unit, calculates the evaluation efficiency of each unit, and calculates the comprehensive evaluation efficiency through the weighted average formula. The priority allocation module passes the comprehensive evaluation efficiency to the update optimization module to provide a basis for strategy adjustment.

[0065] The update optimization module dynamically adjusts the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of changes in environmental parameters.

[0066] For example, when the pollutant concentration in a certain area changes rapidly, the update optimization module smoothes the change frequency of the comprehensive evaluation efficiency and environmental parameters through a particle filter, and adjusts the update cycle according to the trend slope.

[0067] Assuming that the pollutant concentration in a certain area changes at a faster rate, the update optimization module will shorten the evaluation strategy update cycle for that area to ensure the timeliness and accuracy of monitoring.

[0068] On the contrary, if the rate of change is slow, the update cycle is extended to save resources. The specific adjustment rules are defined as ,in, is the slope of the frequency trend of environmental parameters, To comprehensively evaluate the efficiency trend slope, is the adjustment function, and are the adjustment coefficients for faster and slower changes, respectively.

[0069] The present invention achieves the intelligent assessment task of soil and water pollution through the collaborative work of the above four modules. In practical applications, the system can efficiently deal with the problem of multi-source data fusion in complex environments, and realize multi-dimensional monitoring, intelligent analysis and accurate assessment of soil and water pollution. For example, in the long-term monitoring of industrial parks, the system significantly improves the accuracy and real-time performance of pollution assessment by dynamically adjusting the working frequency and sampling accuracy of detection equipment; through the priority allocation mechanism, it reasonably allocates detection resources and reduces energy consumption; and by dynamically adjusting the update cycle, it improves the operating efficiency of the system.

[0070] The realization of these functions depends on the close collaboration between modules and the comprehensive processing capabilities of multi-source data.

[0071] Specifically, the following water pollution source detection methods can be used before the assessment: When collecting acoustic disturbance data, water environment data are collected simultaneously, including four indicators: water temperature, pH value, dissolved oxygen concentration and flow rate.

[0072] The first group of water environment data is four types of indicators at the bottom mud (water temperature, pH value, dissolved oxygen concentration and flow rate); the second group of water environment data is four types of indicators 5 cm vertically upward from the bottom mud; the third group of water environment data is four types of indicators 15 cm vertically upward from the bottom mud; the fourth group of water environment data is four types of indicators 50 cm vertically upward from the bottom mud.

[0073] This setting is because when the sediment is disturbed, only the composition of the sediment is often considered, which cannot timely reflect the diffusion of the sediment and the actual nonlinear pollution behavior. By setting the water environment data of the gradient height, the changes in the close range after the sediment disturbance can be reflected first, and as the diffusion range increases, the set gradient gradually increases, which effectively prevents the collection of invalid or unclear data and facilitates the accuracy of subsequent analysis.

[0074] Calculate water environment gradient data based on water environment data; suppose water environment data is ; is the water environment data group number, =1, 2, 3, 4 are the first, second, third and fourth groups of water environment data respectively; is the water environment data category identifier, =1, 2, 3, 4 represent water temperature, pH value, dissolved oxygen concentration and flow rate respectively; the water environment gradient data are: In the formula, =1; The water environment gradient data also consists of four groups; each group is a three-dimensional vector; the collection of water environment gradient data is to improve the sensitivity to abnormal pollution release events; traditional sediment collection and analysis only exist in the laboratory, which is far from enough if the timely response capability of the environmental protection department needs to be improved. By obtaining water environment gradient data and amplifying the gradient impact of sediment disturbance, it is conducive to timely and real-time detection and early warning of water pollution. The vector method can better reflect the gradient trend than single data.

[0075] The water environment gradient data and acoustic disturbance data are introduced into the time synchronization mechanism, which gives the water environment gradient data and acoustic disturbance data a unified timestamp, accurate to seconds. The timestamp information includes the acquisition date, hour, minute, second and quarterly identification, which is used to subsequently construct the time series input feature matrix. The quarterly information is automatically determined by the system's built-in calendar module. The introduction of time features can enhance the model's ability to identify periodic disturbance events and seasonal pollution release trends.

[0076] Example 2 See also Figure 2 , an intelligent assessment method for water and soil pollution based on multi-source data, including: S1: Collect environmental parameters through a distributed sensor network and dynamically adjust the working frequency and sampling accuracy of the detection equipment; S2: Divide the monitoring space into multiple independent but interrelated evaluation units, calculate the pollutant concentration gradient and the pollution diffusion rate obtained by the working frequency and sampling accuracy of the detection equipment, and comprehensively judge whether the pollution status needs to be re-evaluated; S3: Calculate the pollution correlation between this unit and other units and the pollution trend prediction value, reallocate the evaluation resources, set different evaluation priorities for adjacent units, allocate more detection capabilities to high-priority units, reduce the energy consumption of low-priority units, and calculate the comprehensive evaluation efficiency S4: Dynamically adjust the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of changes in environmental parameters; The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0077] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. 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 process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0078] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0079] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0080] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0081] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0082] 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 aforementioned method embodiments and will not be repeated here.

[0083] In the several embodiments provided in the present 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0086] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0087] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent water and soil pollution assessment system based on multi-source data, characterized by: include: Data acquisition module, dynamic analysis module, priority allocation module and update optimization module, and signal connections between modules; The data acquisition module collects environmental parameters through a distributed sensor network, generates a basic pollution assessment model based on the processing results, and dynamically adjusts the working frequency and sampling accuracy of the detection equipment; The dynamic analysis module divides the monitoring space into multiple independent but interrelated evaluation units. When the pollution status of a unit changes significantly, the pollutant concentration gradient is calculated and combined with the pollution diffusion rate obtained by the working frequency and sampling accuracy of the detection equipment to comprehensively determine whether the pollution status needs to be re-evaluated; The priority allocation module calculates the pollution correlation between the unit and other units and the pollution trend prediction value, reallocates the evaluation resources, sets different evaluation priorities for adjacent units, allocates more detection capabilities to high-priority units, reduces the energy consumption of low-priority units, and calculates the comprehensive evaluation efficiency; The update optimization module dynamically adjusts the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of changes in environmental parameters.

2. The intelligent water and soil pollution assessment system based on multi-source data according to claim 1 is characterized by: The data acquisition module collects a variety of environmental parameters in real time through a distributed sensor network, including pollutant concentration, soil moisture, water flow velocity, and air pressure, and transmits them to the central processing unit through the sensor network.

3. The intelligent water and soil pollution assessment system based on multi-source data according to claim 2 is characterized by: The dynamic analysis module divides the entire monitoring space into different preliminary evaluation units according to functional zoning, so that the detection equipment in each evaluation unit can operate and adjust independently. When the detection equipment of the unit cannot be controlled independently, these units are merged into one evaluation unit. The sensor network is used to perform real-time environmental detection on each unit. The environmental detection data includes pollutant concentration and air pressure. The pollutant diffusion equation is used to calculate the pollutant concentration gradient based on the environmental detection data.

4. The intelligent water and soil pollution assessment system based on multi-source data according to claim 3 is characterized by: The pollutant concentration gradient is calculated using the pollutant diffusion equation; The pollution diffusion rate is affected by the working frequency of the detection equipment, sampling accuracy, and data transmission rate. The pollution diffusion rate is modeled through a multi-factor function. Set thresholds for pollutant concentration gradient and pollution diffusion rate respectively, and comprehensively judge whether it is necessary to re-evaluate the pollution status: Combined with the changes in pollutant concentration gradient and pollution diffusion rate, the following judgment rules are formulated: When the pollutant concentration gradient is greater than or equal to the pollutant concentration gradient threshold, or the pollution diffusion rate is less than or equal to the pollution diffusion rate threshold, the pollution status needs to be reassessed; When the pollutant concentration gradient is less than the pollutant concentration gradient threshold and the pollution diffusion rate is higher than the pollution diffusion rate threshold, there is no need to re-evaluate the pollution status.

5. The intelligent water and soil pollution assessment system based on multi-source data according to claim 4 is characterized by: The priority allocation module uses the sensor network to perform real-time environmental detection on each unit. The environmental detection data includes pollutant concentration and soil moisture. The pollution correlation between the unit and other units is calculated using cosine similarity based on the environmental detection data. Calculate the cosine similarity between each pair of units, evaluate the contamination correlation of each pair of units, and average the cosine similarity between each pair of units and record it as the final contamination correlation; The pollution trend is predicted using a time series prediction model. The time series prediction model in this embodiment adopts an LSTM model. The pollution trend is predicted when it is determined that the current initialization evaluation resource allocation is unreasonable. Furthermore, the specific steps for predicting pollution trends through the time series prediction model are as follows: Step C1, obtaining prediction data; Step C2, building an LSTM model; Step C3, using gradient descent method to optimize LSTM model parameters; Step C4, verifying the effect of the fitting model and checking the goodness of fit of the model by the mean square error method; Step C5, using the fitted model to predict the future pollution trend, and taking the maximum value of the prediction result as the highest point of the pollution trend in the future time period; Specifically, the prediction data include the water flow velocity and pollution diffusion rate data corresponding to each time point; Pollution trend data refers to historical pollution trend data, whose data are used as the main variables of the time series; In step C3, α, W1, and U1 are calculated by the gradient descent method; Dynamically predict pollution trends by predicting the maximum, minimum and average values ​​of the results.

6. The intelligent water and soil pollution assessment system based on multi-source data according to claim 5 is characterized by: After receiving the final pollution correlation degree and pollution trend, the final pollution correlation degree and pollution trend are defined as input variables, and they are divided into different fuzzy sets respectively; Define the priority as the output variable and divide it into fuzzy sets; Formulate fuzzy rules to describe the final pollution correlation and the impact of pollution trends on priorities; Perform fuzzy reasoning based on fuzzy rules to determine priorities; The priority ranking results are synthesized to obtain a priority ranking table, and the evaluation resources are reallocated according to the priority ranking, with the evaluation resources being allocated to units with higher levels first; After the evaluation resources are reallocated, the detection output and energy consumption input of each unit are recorded, and the evaluation efficiency of each unit is calculated respectively. The evaluation efficiency is the ratio of the detection output and the energy consumption input. The comprehensive evaluation efficiency is obtained by taking the weighted average of the evaluation efficiencies of each unit.

7. The intelligent water and soil pollution assessment system based on multi-source data according to claim 6 is characterized by: The update optimization module collects pollutant concentration and soil moisture environmental parameters in real time through the sensor network, and designs thresholds for pollutant concentration and soil moisture data. If the threshold is exceeded, it is counted as one time. The change frequency of environmental parameters is expressed by the ratio of the total number of changes to the total time. Dynamically adjust the update cycle of the evaluation strategy according to the comprehensive evaluation efficiency and the frequency of change of environmental parameters, use particle filters to smooth the dynamic changes of the comprehensive evaluation efficiency and the frequency of change of environmental parameters, update the evaluation strategy through the observed noise data, extract and comprehensively evaluate the trend slope of efficiency and environmental parameters from the noise data, and infer the change rate; Comprehensively evaluate the change frequency of efficiency and environmental parameters, and calculate the trend slope of the change frequency of comprehensive evaluation efficiency and environmental parameters; The update period is adjusted according to the calculated rate of change: when the rate of change is faster, the update period is shortened; when the rate of change is slower, the update period is lengthened.

8. The intelligent water and soil pollution assessment system based on multi-source data according to claim 1 is characterized by: The distributed sensor network in the data acquisition module is composed of multiple sensor nodes, which are deployed at different locations in the monitoring area to collect pollutant concentration, soil moisture, water flow velocity, and air pressure data. The sensor nodes are connected to the central processing unit through a wireless communication protocol and transmit the collected data to the central processing unit for processing.

9. A method for intelligent assessment of soil and water pollution based on multi-source data, used to implement the intelligent assessment system for soil and water pollution based on multi-source data as claimed in any one of claims 1 to 8, characterized in that: include: S1: Collect environmental parameters through a distributed sensor network and dynamically adjust the working frequency and sampling accuracy of the detection equipment; S2: Divide the monitoring space into multiple independent but interrelated evaluation units, calculate the pollutant concentration gradient and the pollution diffusion rate obtained by the working frequency and sampling accuracy of the detection equipment, and comprehensively judge whether the pollution status needs to be re-evaluated; S3: Calculate the pollution correlation between the unit and other units and the pollution trend prediction value, reallocate the evaluation resources, set different evaluation priorities for adjacent units, allocate more detection capabilities to high-priority units, reduce the energy consumption of low-priority units, and calculate the comprehensive evaluation efficiency; S4: Dynamically adjust the update cycle of the evaluation strategy based on the comprehensive evaluation efficiency and the frequency of changes in environmental parameters.

Images