Environmental protection water ecological monitoring method and system based on big data

Abstract

The present invention discloses an environmental water ecological monitoring method and system based on big data, which relates to the technical field of water ecological monitoring, including obtaining geographical information of water ecological areas, calculating a comprehensive index based on terrain complexity and water body coverage, and determining the initial arrangement nodes of sensors. The method of the present invention ensures the effective coverage of the sensor network through multi-scale analysis, sorts the sensor node arrangement by comprehensive index, maximizes the network coverage, and ensures that the sensor can effectively cover more areas and reduce monitoring blind spots through the combination of multi-scale analysis and hybrid frog leaping strategy. By constructing a two-dimensional pollution diffusion model, the model can more accurately describe the diffusion behavior of pollutants in water bodies, and combines the two-dimensional diffusion model with the dynamic time variation coefficient, which not only enhances the adaptability of the model, but also improves the prediction accuracy of the pollutant diffusion path.

Description

Technical Field

[0001] The present invention relates to the technical field of water ecology monitoring, and in particular to an environmental protection water ecology monitoring method and system based on big data. Background Art

[0002] The protection and monitoring of water ecosystems is an important part of nature conservation. Traditional water quality monitoring methods are mainly based on sampling and laboratory analysis. Although this method has high accuracy, it has problems such as long sampling time, long monitoring cycle, and limited spatial coverage, making it difficult to reflect the dynamic changes of water pollution in real time.

[0003] The existing big data obtained by deploying a large number of sensors is used for real-time analysis and monitoring of water quality conditions. Although it has achieved good detection results, there are still certain limitations in sensor layout, data processing and pollution source positioning under complex water ecological environments. It is inconvenient to fully consider and optimize the layout of sensors according to the terrain. At the same time, it is inconvenient to predict the spread of polluted water and pollution sources in a timely manner. It usually relies on experience and simple rules, which limits the effectiveness and accuracy of monitoring coverage, reduces the flexibility and adaptability of monitoring, and makes it difficult to cope with complex pollution diffusion processes. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing environmental water ecological monitoring methods and systems based on big data, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that under complex water ecological environments, there are still certain limitations in sensor layout, data processing and pollution source positioning. It is inconvenient to fully consider and optimize the layout of sensors according to the terrain. At the same time, it is inconvenient to predict the spread of polluted water and pollution sources in a timely manner. It usually relies on experience and simple rules, which limits the effectiveness and accuracy of monitoring coverage, reduces the flexibility and adaptability of monitoring, and makes it difficult to cope with complex pollution diffusion processes.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an environmental water ecological monitoring method based on big data, which includes:

[0007] Obtain geographic information of the water ecological area, calculate a comprehensive index based on multi-scale analysis through terrain complexity and water coverage, and determine the initial layout nodes of sensors;

[0008] The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensors, the optimal location of the sensor layout nodes is determined through the objective function, and a planning diagram is generated;

[0009] Based on the planning map, sensors are deployed to collect environmental water ecological data, a two-dimensional pollution diffusion model is constructed, a dynamic time coefficient of variation is introduced, partial differential equations are solved to calculate the distribution of pollutant concentrations and visualize them;

[0010] Compare the visualized pollutant concentration distribution with the pollutant concentration data collected by the sensor, minimize the error and mark the pollution source location. Use the two-dimensional pollution diffusion model based on the pollution source location to predict the diffusion path, generate a risk map, and issue a pollutant concentration warning for the water ecological environment according to the pollution threshold.

[0011] As a preferred solution of the environmental water ecological monitoring method based on big data of the present invention, wherein: the acquisition of geographical information of the water ecological area, calculation of the comprehensive index based on multi-scale analysis through terrain complexity and water body coverage, and determination of the initial arrangement nodes of the sensor include:

[0012] Based on GIS geographic information system, the terrain undulation information of the monitoring area is obtained through the digital elevation model DEM, and the river flow direction and basin range data are extracted;

[0013] Provide remote sensing data platform with remote sensing images to obtain lake boundary and area information, and extract water body boundaries within the monitoring area;

[0014] Obtain land use and cover information, including agricultural land, industrial areas, and urbanized areas;

[0015] Calibrate based on the acquired terrain, river flow direction and lake distribution data, and overlay the vector information of the data;

[0016] Use GIS to identify areas with high pollution risks downstream of lakes and rivers, near industrial areas, and around urban sewage outlets, and preliminarily determine the scope of water ecological monitoring;

[0017] The slope and elevation change rate of each geographic unit were calculated using DEM data, and the terrain complexity coefficient was calculated using Euclidean distance.

[0018] Water body cells were determined based on remote sensing data and divided by the total area of ​​the region to calculate water body coverage;

[0019] Based on multi-scale analysis, terrain complexity and water coverage are calculated at different scales, and the sum of terrain complexity and water coverage is used as a comprehensive index.

[0020] The comprehensive indexes of all cells are sorted by value, and the initial layout cells of the sensors are determined according to the calculated priorities, and the center points of the cells are selected as the initial layout nodes.

[0021] As a preferred solution of the environmental water ecological monitoring method based on big data described in the present invention, wherein: the hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensor, the optimal position of the sensor layout nodes is determined by the objective function, and a planning diagram is generated, including:

[0022] The population size N is determined based on the number of units in the monitoring area, the number of iterations T is determined based on the historical mean, and the step size is determined based on 5% of the average distance between all nodes. ;

[0023] The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensor. The set of all layout nodes is defined as X. The objective function is defined by dividing the coverage of the initial layout nodes of the sensor by the average communication distance between the nodes, which is expressed as:

[0024] ;in The objective function of the node set X, represents the coverage of the node set X, represents the average communication distance between the deployed nodes;

[0025] Calculate the position of each node i based on the objective function The corresponding objective function value is calculated and compared with the objective function values ​​of all nodes, and the largest node position is selected as the optimal position of population N;

[0026] The position of each sensor node is iteratively calculated and optimized, which is expressed as: ;

[0027] ;in represents the position of node i at the t+1th iteration, represents the position of node i in the tth iteration, represents the random node position in the tth iteration, represents the initial random factor, usually set to 0.05, represents the random factor of the iteration number t, and T represents the total number of iterations;

[0028] After T iterations, each sensor location node will converge, and the final node layout will be verified using the objective function to confirm that the location can maximize the coverage while minimizing the communication distance between nodes;

[0029] Record the location information of all nodes and generate a network deployment plan.

[0030] As a preferred solution of the environmental water ecological monitoring method based on big data described in the present invention, wherein: the sensors are deployed based on the planning map to collect environmental water ecological data, a two-dimensional pollution diffusion model is constructed, a dynamic time coefficient of variation is introduced, partial differential equations are solved to calculate the pollutant concentration distribution and visualize it, including:

[0031] Based on the baseline diffusion velocity of pollutants, the dynamic time variation coefficient is introduced to adapt to the pollution diffusion characteristics under different environmental conditions, which is expressed as:

[0032] ; ; ;

[0033] in and represent the base diffusion speed in the x and y directions respectively, represents the time coefficient of variation, Indicates the time e flow rate and the reference flow rate The difference, Indicates the current temperature and the reference temperature The difference, and They represent the diffusion speed of pollutants in the x and y directions at time e, respectively;

[0034] Based on the planning map, sensors are deployed to collect environmental water ecological data, and a two-dimensional pollution diffusion model is constructed to describe the diffusion and migration of pollutants in the water body through partial differential equations;

[0035] The boundary condition is defined as the pollutant concentration is 0;

[0036] Use the finite difference method FDM to discretize partial differential equations in time and space;

[0037] The discretized equations are numerically solved using the numerical computing library SciPy in Python to obtain the distribution of pollutants at different time points and spatial locations in the entire monitoring area, which are then visualized using GIS tools.

[0038] As a preferred solution of the environmental water ecological monitoring method based on big data described in the present invention, wherein: the comparison of the visualized pollutant concentration distribution and the pollutant concentration data collected by the sensor, the error minimization positioning, and the marking of the pollution source location include:

[0039] The pollutant concentration distribution data visualized by GIS tools is compared with the pollutant concentration data collected by sensors to minimize errors and locate the pollutants;

[0040] The location of the pollution source calculated by minimizing the error The pollution source is located and marked on the visual display map.

[0041] As a preferred solution of the environmental water ecological monitoring method based on big data described in the present invention, wherein: the two-dimensional pollution diffusion model is used based on the location of the pollution source to predict the diffusion path and generate a risk map, including:

[0042] Based on the location of the pollution source, the two-dimensional pollution diffusion model is used again through partial differential equations, combined with the time variation coefficient right and The impact of each time step Update the concentration distribution of pollutants, numerically solve the discretized equations through the numerical calculation library SciPy in Python, calculate the diffusion direction and speed of pollutants, and predict the diffusion path;

[0043] Through iterative calculation, the pollutant concentration distribution at future moments is gradually generated;

[0044] Generate future time steps based on the predicted pollutant diffusion path The pollution risk map uses GIS tools to visualize the map and mark the pollution risk areas with different colors.

[0045] As a preferred solution of the environmental water ecological monitoring method based on big data of the present invention, the pollutant concentration early warning of the water ecological environment according to the pollution threshold includes:

[0046] After the risk map is generated, the real-time sensor data is immediately compared with the pollutant concentration distribution data visualized by the GIS tool to confirm the high-risk areas. The water ecological pollutant concentration warning value stipulated by the relevant departments is used as the pollution threshold. If the pollutant concentration distribution data visualized by the GIS tool exceeds the pollution threshold, the generated warning information will be automatically sent to the relevant departments and key contacts in the affected areas.

[0047] Another object of the present invention is to provide a system for environmental water ecological monitoring method based on big data, which includes:

[0048] Geographic information analysis module, which obtains geographic information of the water ecological area and determines the initial layout nodes of the sensors based on multi-scale analysis methods;

[0049] The sensor node optimization module uses a hybrid frog leaping strategy to optimize the initially arranged sensor nodes and determines the optimal sensor arrangement location through the objective function;

[0050] The pollution diffusion prediction module constructs a two-dimensional pollution diffusion model, introduces the dynamic time coefficient of variation, solves partial differential equations, and calculates the pollutant concentration distribution;

[0051] Pollution diffusion path prediction: locate and mark the location of pollution sources through error minimization method, and use two-dimensional pollution diffusion model to predict the diffusion path of pollutants;

[0052] The pollutant concentration warning module provides pollutant concentration warning for the water ecological environment based on the risk map and the set pollution threshold.

[0053] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned environmental water ecological monitoring method based on big data when executing the computer program.

[0054] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned environmental water ecological monitoring method based on big data.

[0055] The beneficial effects of the present invention are as follows: through multi-scale analysis, effective coverage of the sensor network is ensured; through the arrangement of sensor nodes sorted by comprehensive index, the network coverage is maximized; through the combination of multi-scale analysis and hybrid frog leaping strategy, it is ensured that the sensor can effectively cover more areas and reduce monitoring blind spots; by constructing a two-dimensional pollution diffusion model, the model can more accurately describe the diffusion behavior of pollutants in water bodies; combining the two-dimensional diffusion model with the dynamic time coefficient of variation not only enhances the adaptability of the model, but also improves the prediction accuracy of the pollutant diffusion path; through the error minimization positioning method, the spatial position of the pollution source can be accurately identified, the pollution source can be accurately located in a complex environment, and the pollution source can be quickly identified; by calculating the pollutant diffusion path through a model based on partial differential equations, the future diffusion behavior of the pollutant can be accurately predicted at each time step. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0057] Figure 1 This is a flow chart of the environmental water ecological monitoring method based on big data.

[0058] Figure 2 This is a structural diagram of the environmental water ecological monitoring system based on big data. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides an environmental water ecological monitoring method based on big data. The environmental water ecological monitoring method based on big data includes:

[0063] S1, obtain the geographical information of the water ecological area, calculate the comprehensive index through terrain complexity and water body coverage based on multi-scale analysis, and determine the initial layout nodes of the sensors;

[0064] Preferably, the geographical information of the water ecological area is obtained, and the comprehensive index is calculated based on the multi-scale analysis through the terrain complexity and water body coverage to determine the initial layout nodes of the sensor, including:

[0065] Based on GIS geographic information system, the terrain undulation information of the monitoring area is obtained through the digital elevation model DEM, and the river flow direction and basin range data are extracted;

[0066] Provide remote sensing data platform with remote sensing images to obtain lake boundary and area information, and extract water body boundaries within the monitoring area;

[0067] Obtaining land use and cover information, including agricultural land, industrial areas, and urbanized areas, which are often significant sources of pollution;

[0068] Calibrate based on the acquired terrain, river flow direction and lake distribution data, and overlay the vector information of the data;

[0069] Use GIS to identify areas with high pollution risks downstream of lakes and rivers, near industrial areas, and around urban sewage outlets, and preliminarily determine the scope of water ecological monitoring;

[0070] The slope and elevation change rate of each geographic unit are calculated using DEM data, and the terrain complexity coefficient is calculated using Euclidean distance, which is expressed as:

[0071] ;

[0072] ;

[0073] ;

[0074] in represents the elevation difference, represents the horizontal distance, and Respectively represent the maximum and minimum elevation of the area, Represents a cell The area of ​​the region, represents the calculation of the inverse tangent function, Represents a cell The terrain complexity coefficient is Represents a cell The slope of the geographic unit, Represents a cell The rate of change of elevation;

[0075] Water body cells were determined based on remote sensing data and divided by the total area of ​​the region to calculate water body coverage;

[0076] Based on multi-scale analysis, terrain complexity and water coverage are calculated at different scales, such as 1 km, 10 km, and 100 km, and the sum of terrain complexity and water coverage is used as a comprehensive index;

[0077] The comprehensive indexes of all cells are sorted by value, and the initial layout cells of the sensors are determined according to the calculated priorities, and the center points of the cells are selected as the initial layout nodes.

[0078] By superimposing terrain, river flow, lake distribution and land use information through the GIS system, it is possible to accurately identify areas with higher pollution risks in the monitoring area. By calculating terrain complexity and water coverage and combining multi-scale analysis, the effective coverage of the sensor network is ensured, and the detection accuracy of environmental changes in the monitoring area is improved. Through comprehensive index sorting, sensor nodes are arranged in the center of the cell with the highest priority, which maximizes the network coverage while ensuring the effective utilization of sensor resources, improving the coverage efficiency of the monitoring system, and reducing redundant deployment. In the layout of environmental monitoring sensors, terrain complexity and water coverage are analyzed in combination with different spatial scales. Compared with traditional single-scale information, it reveals the complex characteristics of the environmental system at different scales, providing a more scientific basis for sensor layout. By integrating GIS system, DEM data processing and remote sensing technology, the initial sensor deployment for the water ecological environment is more reasonable, and it can more flexibly respond to the monitoring needs of environmental changes and emerging pollution sources, so as to achieve effective utilization of sensor resources, reduce redundancy and waste, optimize monitoring costs and resource inputs, and achieve a balance between high efficiency and low cost.

[0079] S2, using the hybrid frog leaping strategy to optimize the initial layout nodes of the sensors, determining the optimal location of the sensor layout nodes through the objective function, and generating a planning diagram;

[0080] Preferably, a hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensors, the optimal positions of the sensor layout nodes are determined by the objective function, and a planning diagram is generated, including:

[0081] The population size N is determined based on the number of units in the monitoring area, the number of iterations T is determined based on the historical mean, and the step size is determined based on 5% of the average distance between all nodes. ;

[0082] The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensor. The set of all layout nodes is defined as X. The objective function is defined by dividing the coverage of the initial layout nodes of the sensor by the average communication distance between the nodes, which is expressed as:

[0083] ;

[0084] ;

[0085] ;

[0086] in The objective function of the node set X, represents the coverage of the node set X, represents the average communication distance between the deployed nodes, N represents the population size, represents the coverage area of ​​the ith node, and Respectively represent the coordinate positions of node i and node j;

[0087] The objective function takes into account the coverage and communication distance, and ensures that the network coverage performance and communication efficiency are balanced by maximizing the coverage area and minimizing the communication distance between nodes;

[0088] Calculate the position of each node i based on the objective function The corresponding objective function value is calculated and the objective function values ​​of all nodes are compared. The largest node position is selected as the optimal position of the population N, which is expressed as:

[0089] ;

[0090] in represents the optimal position in the population N in the tth iteration, represents the objective function value of the node i position in the tth iteration;

[0091] The position of each sensor node is iteratively calculated and optimized, which is expressed as:

[0092] ;

[0093] ;

[0094] in represents the position of node i at the t+1th iteration, represents the position of node i in the tth iteration, represents the random node position in the tth iteration, represents the initial random factor, usually set to 0.05, represents the random factor of the iteration number t, and T represents the total number of iterations;

[0095] After T iterations, each sensor location node will converge, and the final node layout will be verified using the objective function to confirm that the location can maximize the coverage while minimizing the communication distance between nodes;

[0096] Record the location information of all nodes and generate a network deployment plan.

[0097] Through the iterative optimization calculation of the sensor node position, the concepts of particle swarm optimization and frog leaping algorithm are integrated. Guide the node position to the current optimal position to ensure that the entire network gradually converges to the global optimal solution. The rationality of this part is that it enables each node to gradually move closer to the global optimal position. At the same time, random perturbation calculations are introduced into the optimization calculation. By introducing appropriate randomness, nodes can explore different areas, thereby improving the global search capability. The formula not only ensures that the node moves in the direction of the global optimal solution, but also avoids premature convergence to the local optimal solution.

[0098] Through the combination of multi-scale analysis and hybrid frog leaping strategy, the entire sensor network achieves maximum coverage, ensuring that sensors can effectively cover more areas, reducing monitoring blind spots, and improving the comprehensiveness of environmental monitoring. The communication distance between sensor nodes is taken into account in the optimization process. By rationally arranging node positions, the communication distance and energy consumption of data transmission are reduced, the service life of sensor nodes is extended, and the operating cost of the entire system is reduced. In the actual calculation and optimization of sensor deployment positions, random disturbances are introduced to avoid the system from falling into local optimality, enhance the robustness and global search capabilities of the sensor network, and provide an efficient and intelligent solution for environmental monitoring.

[0099] S3, based on the planning map, deploy sensors to collect environmental water ecological data, build a two-dimensional pollution diffusion model, introduce the dynamic time coefficient of variation, solve the partial differential equation to calculate the pollutant concentration distribution and visualize it;

[0100] Preferably, sensors are deployed based on the planning map to collect environmental water ecological data, a two-dimensional pollution diffusion model is constructed, a dynamic time coefficient of variation is introduced, partial differential equations are solved to calculate the distribution of pollutant concentrations and visualize them, including:

[0101] Based on the baseline diffusion velocity of pollutants, the dynamic time variation coefficient is introduced to adapt to the pollution diffusion characteristics under different environmental conditions, which is expressed as:

[0102] ;

[0103] ;

[0104] ;

[0105] in and represent the base diffusion speed in the x and y directions respectively, represents the time coefficient of variation, Indicates the time e flow rate and the reference flow rate The difference, Indicates the current temperature and the reference temperature The difference, and They represent the diffusion speed of pollutants in the x and y directions at time e, respectively;

[0106] Based on the planning map, sensors are deployed to collect environmental water ecological data, and a two-dimensional pollution diffusion model is constructed. The diffusion and migration of pollutants in the water body are described by partial differential equations, which is expressed as:

[0107] ;

[0108] Where C represents the pollutant concentration, represents the rate of change of pollutant concentration over time, and They represent the curvature of the pollutant concentration with the position in the x-direction and the y-direction, respectively. The second-order spatial derivative of the pollutant concentration with the x-direction and the y-direction can represent the degree of diffusion. v represents the water body willow. It represents the release intensity of the pollution source at the location (x, y) at time e;

[0109] For example, for heavy metal pollutants such as lead (Pb) or cadmium (Cd) from industrial wastewater outlets, It can be defined as a fixed point source, whose emission intensity is usually stable over time. The release of heavy metal pollutants is usually related to the process of industrial production, so its emission rate can be regarded as a constant;

[0110] For nitrogen fertilizers used in agriculture (such as nitrate NO3 - ) enters the water body through runoff with rainfall. This pollution source is usually dispersed, and the emission intensity is closely related to rainfall. It can be expressed as a distribution function related to time and location, expressed as:

[0111] ;

[0112] in represents the runoff intensity caused by rainfall at time e, which can be obtained through rainfall data or runoff model. It indicates the distribution density of agricultural runoff in different geographical locations, reflecting the release intensity of pollutants in different areas;

[0113] The boundary condition is defined as the pollutant concentration is 0;

[0114] The finite difference method FDM is used to discretize the partial differential equation in time and space, which can be expressed as:

[0115] ;

[0116] ;

[0117] ;

[0118] ;

[0119] in represents the time step, which represents the discrete increment of simulation time during calculation. represents the pollutant concentration at the time position (x, y), represents the pollutant concentration at the position (x, y) after the time step, and They represent the pollutant concentration after time e is shifted by one step in the x direction and y direction, respectively. and They represent the pollutant concentration after a step shift in the reverse direction along the x direction and the y direction, Indicates the time t position pollutants in the area;

[0120] The discretized equations are numerically solved using the numerical computing library SciPy in Python to obtain the distribution of pollutants at different time points and spatial locations in the entire monitoring area, which are then visualized using GIS tools.

[0121] By constructing a two-dimensional pollution diffusion model, the model can more accurately describe the diffusion behavior of pollutants in water bodies. Compared with one-dimensional models, two-dimensional models can capture more complex diffusion patterns and are suitable for diffusion simulation of pollutants in complex water environments such as lakes and rivers. By introducing the dynamic time variation coefficient, the model can dynamically adjust the diffusion calculation according to the real-time monitored environmental parameters, thereby improving the accuracy and reliability of predicting the diffusion path of pollutants. The introduction of the dynamic time variation coefficient makes the system more flexible and can respond to changes in environmental parameters in real time. For example, when the flow rate increases or the temperature changes, the model can automatically adjust the diffusion coefficient to more accurately reflect the actual diffusion situation. Compared with traditional pollution Physical diffusion models often use static diffusion coefficients. Combining the two-dimensional diffusion model with the dynamic time variation coefficient not only enhances the adaptability of the model, but also greatly improves the prediction accuracy of the pollutant diffusion path. By considering real-time environmental data and dynamically adjusting the diffusion coefficient, the model's adaptability to actual complex environments is significantly improved. The finite difference method is used for time and space discretization, and the solution is performed through the SciPy library in Python. The concentration distribution of pollutants in the monitoring area can be quickly generated, and effective response measures can be taken at the early stage of pollutant diffusion to reduce environmental hazards. By combining GIS tools for visualization, not only the intuitiveness of the model results is improved, but also the application scenarios of the model are expanded.

[0122] S4, compares the visual pollutant concentration distribution with the pollutant concentration data collected by the sensor, performs error minimization positioning, marks the location of the pollution source, uses a two-dimensional pollution diffusion model based on the location of the pollution source to predict the diffusion path, generates a risk map, and issues pollutant concentration warnings for the water ecological environment based on the pollution threshold;

[0123] Preferably, the visualized pollutant concentration distribution is compared with the pollutant concentration data collected by the sensor, the error is minimized, and the location of the pollution source is marked, including:

[0124] The pollutant concentration distribution data visualized by GIS tools is compared with the pollutant concentration data collected by sensors to minimize the error, which is expressed as:

[0125] ;

[0126] in represents the location of the pollution source, M represents the total number of observation points, Indicates time e position The sensors collect pollutant concentrations. Indicates time e position Visual display of pollutant concentrations;

[0127] The location of the pollution source calculated by minimizing the error The pollution source is located and marked on the visual display map.

[0128] Through the error minimization positioning method, the spatial position of the pollution source can be accurately identified, and the pollution source can be accurately located in a complex environment, helping to quickly identify the pollution source. By comparing the errors between the actual observation data and the model prediction data, the prediction model can be automatically adjusted and gradually approach the actual pollution source location. The error minimization method can not only be used for preliminary positioning, but also can be dynamically adjusted when the pollution source characteristics change (such as fluctuations in emission intensity or changes in environmental conditions) to ensure that the positioning results always remain accurate, which helps to quickly take response measures in the early stages of pollution incidents. Through accurate pollution source positioning, monitoring and emergency resources can be more reasonably allocated. Through systematic error evaluation, the optimal pollution source location can be identified, rather than simply relying on a single observation or prediction data. The reliability of the positioning results is improved through the global optimal approach.

[0129] Furthermore, a two-dimensional pollution diffusion model is used to predict the diffusion path based on the location of the pollution source and generate a risk map, including:

[0130] Based on the location of the pollution source, the two-dimensional pollution diffusion model is used again through partial differential equations, combined with the time variation coefficient right and The impact of each time step Update the concentration distribution of pollutants, numerically solve the discretized equations through the numerical calculation library SciPy in Python, calculate the diffusion direction and speed of pollutants, and predict the diffusion path, which is expressed as:

[0131] ;

[0132] Through iterative calculation, the pollutant concentration distribution at future moments is gradually generated;

[0133] Generate future time steps based on the predicted pollutant diffusion path The pollution risk map uses GIS tools to visualize the map and mark the pollution risk areas with different colors.

[0134] By calculating the pollutant diffusion path based on the partial differential equation model, the future diffusion behavior of pollutants can be accurately predicted at each time step, and the concentration distribution map of pollutants can be updated in real time, so as to identify potential pollution risk areas in advance. By introducing the time variation coefficient, the system can adapt to changes in environmental conditions (such as flow velocity, wind speed, etc.), and adjust the pollutant diffusion prediction path in real time, which improves the reliability of the prediction. The risk map generated by the path prediction results can effectively identify areas affected by pollution in the future. The pollution risk levels of different areas can be intuitively displayed through visualization tools, providing decision makers with timely early warning information. Through the reuse of dynamic time variation coefficient and two-dimensional pollution diffusion model, the model can flexibly respond to pollution diffusion behavior under different environmental conditions. Through iterative calculation, the future pollutant distribution is gradually approached, showing the high complexity and comprehensiveness of the model. The path prediction is combined with real-time risk assessment to generate a pollution risk map, so that the system can not only predict the pollution diffusion path, but also evaluate potential risk areas in real time and provide visual early warning information, achieving good use value.

[0135] Furthermore, according to the pollution threshold, the water ecological environment is given a pollutant concentration warning, including:

[0136] After the risk map is generated, the real-time sensor data is immediately compared with the pollutant concentration distribution data visualized by the GIS tool to confirm the high-risk areas. The water ecological pollutant concentration warning value stipulated by the relevant departments is used as the pollution threshold. If the pollutant concentration distribution data visualized by the GIS tool exceeds the pollution threshold, the generated warning information will be automatically sent to the relevant departments and key contacts in the affected areas.

[0137] By comparing real-time sensor data with the predicted distribution of pollutant concentrations, high-risk areas can be quickly identified. When the detected pollutant concentration exceeds the predetermined pollution threshold, the system will immediately generate and send an early warning message, reducing the time and error risk of manual intervention and improving the response speed and accuracy of the early warning system. The automated early warning mechanism can ensure that key decision makers obtain accurate information in the shortest time possible and take appropriate emergency measures immediately to reduce the impact of pollution spread.

[0138] Example 2, reference Figure 2 , which is the second embodiment of the present invention. This embodiment is different from the previous embodiment and provides a system for environmental water ecological monitoring method based on big data, including:

[0139] Geographic information analysis module, which obtains geographic information of the water ecological area and determines the initial layout nodes of the sensors based on multi-scale analysis methods;

[0140] The sensor node optimization module uses a hybrid frog leaping strategy to optimize the initially arranged sensor nodes and determines the optimal sensor arrangement location through the objective function;

[0141] The pollution diffusion prediction module constructs a two-dimensional pollution diffusion model, introduces the dynamic time coefficient of variation, solves partial differential equations, and calculates the pollutant concentration distribution;

[0142] Pollution diffusion path prediction: locate and mark the location of pollution sources through error minimization method, and use two-dimensional pollution diffusion model to predict the diffusion path of pollutants;

[0143] The pollutant concentration warning module provides pollutant concentration warning for the water ecological environment based on the risk map and the set pollution threshold.

[0144] 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 invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0146] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0147] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An environmental water ecological monitoring method based on big data, characterized by: include, Obtain geographic information of the water ecological area, calculate a comprehensive index based on multi-scale analysis through terrain complexity and water coverage, and determine the initial layout nodes of sensors; The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensors, the optimal location of the sensor layout nodes is determined through the objective function, and a planning diagram is generated; Based on the planning map, sensors are deployed to collect environmental water ecological data, a two-dimensional pollution diffusion model is constructed, a dynamic time coefficient of variation is introduced, partial differential equations are solved to calculate the distribution of pollutant concentrations and visualize them; Compare the visual pollutant concentration distribution with the pollutant concentration data collected by the sensor, minimize the error and locate the pollution source. Use the two-dimensional pollution diffusion model based on the pollution source location to predict the diffusion path, generate a risk map, and issue a pollutant concentration warning for the water ecological environment according to the pollution threshold. The method of obtaining geographical information of the water ecological area, calculating a comprehensive index based on multi-scale analysis through terrain complexity and water body coverage, and determining the initial arrangement nodes of the sensor includes: Based on GIS geographic information system, the terrain undulation information of the monitoring area is obtained through the digital elevation model DEM, and the river flow direction and basin range data are extracted; Provide remote sensing data platform with remote sensing images to obtain lake boundary and area information, and extract water body boundaries within the monitoring area; Obtain land use and cover information, including agricultural land, industrial areas, and urbanized areas; Calibrate based on the acquired terrain, river flow direction and lake distribution data, and overlay the vector information of the data; Use GIS to identify areas with high pollution risks downstream of lakes and rivers, near industrial areas, and around urban sewage outlets, and preliminarily determine the scope of water ecological monitoring; The slope and elevation change rate of each geographic unit were calculated using DEM data, and the terrain complexity coefficient was calculated using Euclidean distance. Water body cells were determined based on remote sensing data and divided by the total area of ​​the region to calculate water body coverage; Based on multi-scale analysis, terrain complexity and water coverage are calculated at different scales, and the sum of terrain complexity and water coverage is used as a comprehensive index. Sort the comprehensive indexes of all cells by value, determine the initial layout cell of the sensor according to the calculated priority, and select the center point of the cell as the initial layout node; The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensor, the optimal position of the sensor layout nodes is determined by the objective function, and a planning diagram is generated, including: The population size N is determined based on the number of units in the monitoring area, the number of iterations T is determined based on the historical mean, and the step size is determined based on 5% of the average distance between all nodes. ; The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensor. The set of all layout nodes is defined as X. The objective function is defined by dividing the coverage of the initial layout nodes of the sensor by the average communication distance between the nodes, which is expressed as: ;in The objective function of the node set X, represents the coverage of the node set X, represents the average communication distance between the deployed nodes; Calculate the position of each node i based on the objective function The corresponding objective function value is calculated and compared with the objective function values ​​of all nodes, and the largest node position is selected as the optimal position of population N; The position of each sensor node is iteratively calculated and optimized, which is expressed as: ; ;in represents the position of node i at the t+1th iteration, represents the position of node i in the tth iteration, represents the random node position in the tth iteration, represents the initial random factor, represents the random factor of the iteration number t, T represents the total number of iterations, represents the optimal position in the population N in the tth iteration; After T iterations, each sensor location node will converge, and the final node layout will be verified using the objective function to confirm that the location can maximize the coverage while minimizing the communication distance between nodes; Record the location information of all nodes and generate a network deployment plan; The method deploys sensors based on the planning map to collect environmental water ecological data, constructs a two-dimensional pollution diffusion model, introduces a dynamic time coefficient of variation, solves partial differential equations to calculate the distribution of pollutant concentrations and visualizes them, including: Based on the baseline diffusion velocity of pollutants, the dynamic time variation coefficient is introduced to adapt to the pollution diffusion characteristics under different environmental conditions, which is expressed as: ; ; ;in and represent the base diffusion speed in the x and y directions respectively, represents the time coefficient of variation, Indicates the time e flow rate and the reference flow rate The difference, Indicates the current temperature and the reference temperature The difference, and They represent the diffusion speed of pollutants in the x and y directions at time e, respectively; Based on the planning map, sensors are deployed to collect environmental water ecological data, and a two-dimensional pollution diffusion model is constructed to describe the diffusion and migration of pollutants in the water body through partial differential equations; The boundary condition is defined as the pollutant concentration is 0; Use the finite difference method FDM to discretize partial differential equations in time and space; The discretized equations are numerically solved using the numerical computing library SciPy in Python to obtain the distribution of pollutants at different time points and spatial locations in the entire monitoring area, which are then visualized using GIS tools.

2. The environmental water ecological monitoring method based on big data as claimed in claim 1, characterized in that: The comparison of the visualized pollutant concentration distribution and the pollutant concentration data collected by the sensor to minimize the error and mark the location of the pollution source includes: The pollutant concentration distribution data visualized by GIS tools is compared with the pollutant concentration data collected by sensors to minimize errors and locate the pollutants; The location of the pollution source calculated by minimizing the error The pollution source is located and marked on the visual display map.

3. The environmental water ecological monitoring method based on big data as claimed in claim 2, characterized in that: The two-dimensional pollution diffusion model is used to predict the diffusion path based on the location of the pollution source to generate a risk map. include, Based on the location of the pollution source, the two-dimensional pollution diffusion model is used again through partial differential equations, combined with the time variation coefficient right and The impact of each time step Update the concentration distribution of pollutants, numerically solve the discretized equations through the numerical calculation library SciPy in Python, calculate the diffusion direction and speed of pollutants, and predict the diffusion path; Through iterative calculation, the pollutant concentration distribution at future moments is gradually generated; Generate future time steps based on the predicted pollutant diffusion path The pollution risk map uses GIS tools to visualize the map and mark the pollution risk areas with different colors.

4. The environmental water ecological monitoring method based on big data as claimed in claim 3 is characterized by: The pollutant concentration warning for the water ecological environment is carried out according to the pollution threshold. include, After the risk map is generated, the real-time sensor data is immediately compared with the pollutant concentration distribution data visualized by the GIS tool to confirm the high-risk areas. The water ecological pollutant concentration warning value stipulated by the relevant departments is used as the pollution threshold. If the pollutant concentration distribution data visualized by the GIS tool exceeds the pollution threshold, the generated warning information will be automatically sent to the relevant departments and key contacts in the affected areas.

5. A system based on the environmental water ecological monitoring method based on big data according to any one of claims 1 to 4, characterized in that: include, Geographic information analysis module, which obtains geographic information of the water ecological area and determines the initial layout nodes of the sensors based on multi-scale analysis methods; The sensor node optimization module uses a hybrid frog leaping strategy to optimize the initially arranged sensor nodes and determines the optimal sensor arrangement location through the objective function; The pollution diffusion prediction module constructs a two-dimensional pollution diffusion model, introduces the dynamic time coefficient of variation, solves partial differential equations, and calculates the pollutant concentration distribution; Pollution diffusion path prediction: locate and mark the location of pollution sources through error minimization method, and use two-dimensional pollution diffusion model to predict the diffusion path of pollutants; The pollutant concentration early warning module provides pollutant concentration early warning for the water ecological environment based on the risk map and the set pollution threshold; Determine the initial layout nodes of sensors, including: Based on GIS geographic information system, the terrain undulation information of the monitoring area is obtained through the digital elevation model DEM, and the river flow direction and basin range data are extracted; Provide remote sensing data platform with remote sensing images to obtain lake boundary and area information, and extract water body boundaries within the monitoring area; Obtain land use and cover information, including agricultural land, industrial areas, and urbanized areas; Calibrate based on the acquired terrain, river flow direction and lake distribution data, and overlay the vector information of the data; Use GIS to identify areas with high pollution risks downstream of lakes and rivers, near industrial areas, and around urban sewage outlets, and preliminarily determine the scope of water ecological monitoring; The slope and elevation change rate of each geographic unit were calculated using DEM data, and the terrain complexity coefficient was calculated using Euclidean distance. Water body cells were determined based on remote sensing data and divided by the total area of ​​the region to calculate water body coverage; Based on multi-scale analysis, terrain complexity and water coverage are calculated at different scales, and the sum of terrain complexity and water coverage is used as a comprehensive index. Sort the comprehensive indexes of all cells by value, determine the initial layout cell of the sensor according to the calculated priority, and select the center point of the cell as the initial layout node; The optimal sensor placement is determined by the objective function, including: The population size N is determined based on the number of units in the monitoring area, the number of iterations T is determined based on the historical mean, and the step size is determined based on 5% of the average distance between all nodes. ; The hybrid frog leaping strategy is used to optimize the initial layout nodes of the sensor. The set of all layout nodes is defined as X. The objective function is defined by dividing the coverage of the initial layout nodes of the sensor by the average communication distance between the nodes, which is expressed as: ;in The objective function of the node set X, represents the coverage of the node set X, represents the average communication distance between the deployed nodes; Calculate the position of each node i based on the objective function The corresponding objective function value is calculated and compared with the objective function values ​​of all nodes, and the largest node position is selected as the optimal position of population N; The position of each sensor node is iteratively calculated and optimized, which is expressed as: ; ;in represents the position of node i at the t+1th iteration, represents the position of node i in the tth iteration, represents the random node position in the tth iteration, represents the initial random factor, represents the random factor of the iteration number t, T represents the total number of iterations, represents the optimal position in the population N in the tth iteration; After T iterations, each sensor location node will converge, and the final node layout will be verified using the objective function to confirm that the location can maximize the coverage while minimizing the communication distance between nodes; Record the location information of all nodes and generate a network deployment plan; Calculate the pollutant concentration distribution, include, Based on the baseline diffusion velocity of pollutants, the dynamic time variation coefficient is introduced to adapt to the pollution diffusion characteristics under different environmental conditions, which is expressed as: ; ; ;in and represent the base diffusion speed in the x and y directions respectively, represents the time coefficient of variation, Indicates the time e flow rate and the reference flow rate The difference, Indicates the current temperature and the reference temperature The difference, and They represent the diffusion speed of pollutants in the x and y directions at time e, respectively; Based on the planning map, sensors are deployed to collect environmental water ecological data, and a two-dimensional pollution diffusion model is constructed to describe the diffusion and migration of pollutants in the water body through partial differential equations; The boundary condition is defined as the pollutant concentration is 0; Use the finite difference method FDM to discretize partial differential equations in time and space; The discretized equations are numerically solved using the numerical computing library SciPy in Python to obtain the distribution of pollutants at different time points and spatial locations in the entire monitoring area, which are then visualized using GIS tools.

6. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the environmental water ecological monitoring method based on big data described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the environmental water ecology monitoring method based on big data described in any one of claims 1 to 4 are implemented.

Images