Bay water quality monitoring station location layout optimization method

Abstract

The invention discloses a bay water quality monitoring station layout optimization method, and the method comprises the steps: carrying out the grid division of a research region, and obtaining data points; determining an initial range of algorithm search according to the characteristic values of the data points; the optimal step length of data point updating is determined by calculating gradient and curvature information of a target function, the position of the data point is updated based on the comparison result of the actual decline amount and the predicted decline amount of the target function, loop iteration is carried out until the preset convergence condition is reached, and the finally obtained position of the data point is the bay water quality monitoring station site. On the basis of the trust region mapping method, the site selection and layout problem of the bay water quality monitoring stations is rapidly solved through the particle swarm optimization algorithm, the appropriate number of stations can be given according to requirements when the number of the monitoring stations is not restrained, calculation reasonability is high, and the method has high application value.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of water quality monitoring station layout, and in particular to a bay water quality monitoring station layout optimization method. Background Art

[0002] The bay is a clear spatial area, a collection of various environmental elements such as the ocean, rivers entering the sea, soil and vegetation, and a gathering area for human activities. As the final receptor of the input of various elements, seawater bodies are affected by multiple factors in different spatial ranges, and their water quality usually has obvious temporal and spatial variability. Obviously, fully understanding the temporal and spatial changes in water quality status under the conditions of limited funds and time is the basis and prerequisite for carrying out research and application work such as development, protection and restoration in the bay, and this requires research on the layout of water quality monitoring stations, the focus of which is to determine the number and spatial location of stations in a scientific, reasonable and repeatable manner. However, this is a long-term challenge in any region, and no unified technical standards or processes have been established. If the monitoring stations are not properly laid out, it is likely that the collected water quality data will be of little value, resulting in significant financial or time losses.

[0003] It is generally believed that the fundamental purpose of the layout of seawater monitoring stations in a limited area is to find a minimum cost under various constraints to optimize the overall or average performance. Currently, there are two main challenges in solving this type of problem: one is how to achieve layout optimization analysis within a limited time; the other is how to obtain a global optimization solution. Based on these two challenges, this application proposes a bay water quality monitoring station layout optimization method. Summary of the invention

[0004] Technical Purpose In order to solve at least one of the technical problems mentioned in the above background technology, the purpose of the present invention is to provide a method for optimizing the layout of water quality monitoring stations in the bay. By collecting historical water quality data in the bay area, a comprehensive analysis of the bay's hydrological, meteorological, topographic and geomorphological environmental factors is conducted, and key factors affecting water quality are extracted through data mining technology to establish a corresponding water quality model. On this basis, an optimization algorithm is further used to optimize the layout of monitoring stations, and the number and location of stations are dynamically adjusted according to the water quality model and actual monitoring needs to achieve the best balance between monitoring efficiency and cost. This solution can not only effectively reflect the temporal and spatial variation characteristics of the bay's water quality, but also adapt to changes in different monitoring targets and conditions, providing strong technical support for environmental management, pollution control and ecological restoration in the bay.

[0005] Technical Solution A method for optimizing the layout of bay water quality monitoring stations, comprising: S1. Grid the study area to obtain data points; the characteristic values ​​of the data points include the future water quality change trend predicted based on the historical monitoring data of the existing monitoring stations; S2, determine the initial range of the algorithm search based on the characteristic value of the data point; S3, determining the optimal step size for updating the data point by calculating the gradient and curvature information of the objective function, and updating the data point position based on the comparison result between the actual decrease amount and the predicted decrease amount of the objective function, and iterating in a loop; S4. When the preset convergence condition is reached, the location of the data point finally obtained is the location of the bay water quality monitoring station.

[0006] Furthermore, in step S1, the characteristic values ​​of the data points need to consider the following factors: ① The interaction between the bay ecosystem and seawater quality; ② The role of water exchange rate in promoting the improvement of seawater quality; ③ Pollution discharge points caused by human activities that have a significant negative impact on water quality.

[0007] Furthermore, by building a decision tree, the key features in the historical monitoring data of existing monitoring stations that have the greatest impact on water quality changes are determined, and the future water quality change trend is predicted based on the spatial distribution information in the grid division, including: collecting historical monitoring data from existing monitoring stations, and processing missing values ​​and outliers in the data; extracting feature data based on factors such as the bay ecosystem and water exchange rate, and determining the key features that have the greatest impact on the prediction results; building a decision tree through the random forest algorithm, and adjusting the number of trees, tree depth, etc.

[0008] Furthermore, the feature importance in random forest is calculated by average impurity reduction, and the calculation formula is as follows:

[0009] in, is the number of trees; is the impurity before feature segmentation; is the impurity after feature segmentation.

[0010] Furthermore, a water quality model is constructed according to the future trend of water quality changes. The water quality model and the hydrodynamic model are coupled to simulate the effect of water exchange rate on the improvement of seawater quality. The hydrodynamic model equations are expressed as follows: (1); (2); In formula (1) and formula (2), for water depth; For time; is the flow velocity vector; is the gradient of the velocity vector; is the potential energy of the fluid; is the gradient of fluid potential energy; is the density of water; is the kinematic viscosity coefficient; For the Coriolis force.

[0011] By simulating the role of water exchange rate in promoting the improvement of seawater quality, water quality monitoring stations can be determined more scientifically, ensuring the representativeness and comprehensiveness of monitoring data, helping to identify key monitoring areas, optimize the allocation of monitoring resources, and improve the efficiency and benefits of water quality monitoring.

[0012] Furthermore, in step S3, an optimal step length is found near the current data point to minimize the objective function while keeping the step length within the trust region radius. The optimal step length solution formula is expressed as formula (3): (3); In formula (3), It means finding a step size to minimize the model function under the constraint of the trust region radius; is the objective function value of the current point; is the gradient of the current point; is transposed; is the step vector; is the Hessian matrix; is the norm; is the trust region adjustment factor, which is used to adjust the size of the trust region; is the trust region radius.

[0013] Furthermore, the size of the trust region radius is determined according to the actual decrease of the objective function.

[0014] The application of the trust region mapping method enables the particle swarm optimization algorithm to perform a more refined search when approaching the optimal solution, improving the search accuracy of the algorithm. By dynamically adjusting the size of the trust region, the algorithm can balance the needs of global search and local search, thereby accelerating the convergence speed and improving the convergence stability.

[0015] Furthermore, in step S3, the data point position and velocity update formulas are expressed as follows: (4); (5); In formula (4) and formula (5), For the Data points in iterations In the Speed ​​in dimension; For the Data points in iterations In the Speed ​​in dimension; For the Data points in iterations In the Position on the dimension; For the Data points in iterations The best historical position is Position on the dimension; For the Data points in iterations In the Position on the dimension; For the The global optimal position in the first iteration is Position on the dimension; is the inertia weight; is the first acceleration constant; is the second acceleration constant; and is a random number between 0 and 1; is the proportional factor, which is used to control the intensity of chaotic disturbance; is a chaotic function, which is used to introduce nonlinearity and randomness in velocity update; and Different from the concept of speed in physics, it is an abstract concept in the search space, which indicates the change in the position of a data point during the iteration process.

[0016] It is simple and easy to implement, and has a fast convergence speed. In the process of optimizing the layout of bay water quality monitoring stations, it can play a role in quickly finding the approximately optimal layout of monitoring stations. It combines the local search characteristics of the trust region method with the global search capability of the particle swarm optimization algorithm, thus improving the efficiency of the optimization process and the quality of the solution.

[0017] Furthermore, if the actual decrease in the objective function is close to the predicted decrease and the step size is within the trust region radius, the position of the data point is updated.

[0018] Furthermore, in step S4, the preset convergence conditions are: the position change of the data point is less than a certain threshold, the maximum number of iterations has been reached, or the norm of the gradient is small enough.

[0019] A computer-readable storage medium stores a computer program executable by a processor, wherein the computer program, when executed by the processor, runs at least one step of the aforementioned bay water quality monitoring station layout optimization method.

[0020] A computer device, comprising a memory, a processor, a communication interface and a communication bus; wherein: The memory, processor, and communication interface communicate with each other via the communication bus; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory, and when the processor executes the computer program, at least one step of the aforementioned method for optimizing the layout of bay water quality monitoring stations is implemented.

[0021] Beneficial Effects By implementing the bay water quality monitoring station layout optimization method provided by the present invention, the following technical effects are achieved: This application collects historical water quality data in the bay area, conducts a comprehensive analysis of the bay's hydrological, meteorological, topographic and other environmental factors, and extracts key factors affecting water quality through data mining technology to establish a corresponding water quality model. On this basis, the optimization algorithm is further used to optimize the layout of the monitoring stations, and the number and location of the stations are dynamically adjusted according to the water quality model and actual monitoring needs to achieve the best balance between monitoring efficiency and cost. This application can more scientifically determine the water quality monitoring stations by simulating the promotion of water exchange rate on the improvement of seawater quality, ensure the representativeness and comprehensiveness of monitoring data, help identify key monitoring areas, optimize the allocation of monitoring resources, and improve the efficiency and benefits of water quality monitoring. Its algorithm is simple and easy to implement, with a fast convergence speed. In the process of optimizing the layout of the bay water quality monitoring stations, it can quickly find the approximate optimal monitoring station layout scheme, combine the local search characteristics of the trust region method with the global search ability of the particle swarm optimization algorithm, and improve the efficiency of the optimization process and the quality of the solution. This indirectly shows that the calculation results of this application are relatively stable and reasonable, and the research results can be well applied in other bays and even open seas. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to make the above-mentioned bay water quality monitoring station layout optimization method of the present invention more obvious and easy to understand, the drawings required for use in the specific implementation of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 A schematic diagram showing the optimization method of the layout of water quality monitoring stations in the bay; Figure 2 Schematic diagram showing the iterative process of data points; Figure 3 A block diagram representing a structure of a computer-readable storage medium. DETAILED DESCRIPTION

[0024] Those skilled in the art can refer to the content of this article and appropriately replace and / or modify the process parameters to achieve the same. However, it should be particularly noted that all similar replacements and / or modifications are obvious to those skilled in the art and are considered to be included in the present invention. The products and preparation methods described in the present invention have been described through preferred examples. It is obvious that relevant personnel can modify or appropriately change and combine the products and preparation methods described herein without departing from the content, spirit and scope of the present invention to implement and apply the technology of the present invention.

[0025] Unless otherwise defined, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention belongs. The present invention uses the methods and materials described herein; however, other suitable methods and materials known in the art may also be used. The materials, methods, and examples described herein are illustrative only and are not intended to be limiting. All publications, patent applications, patents, provisional applications, database entries, and other references mentioned herein are incorporated herein by reference in their entirety. In the event of a conflict, the present specification, including definitions, shall prevail.

[0026] Unless specifically stated, the materials, methods, and examples described herein are illustrative only and not limiting. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of the present invention, suitable methods and materials are still described herein.

[0027] The present invention is described in detail below.

[0028] Embodiment 1: This embodiment uses a lagoon as a research area to provide a bay water quality monitoring station layout optimization method. The bay water quality monitoring station layout optimization method is as follows: Figure 1 As shown in the figure, the lagoon is a typical tropical coastal lagoon with a water area of ​​about 10 square kilometers. It has many typical ecosystems. According to relevant research, there are many human activities around the lagoon, including shallow-water cage aquaculture, coastal fishery aquaculture, direct discharge of urban sewage, farmland planting, animal husbandry and tourism destinations.

[0029] Considering the calculation needs, the spatial map was projected to the Gauss Krige plane coordinates. Combined with the data accuracy, the fishnet function in ArcGIS 10.2 was used to divide the study area into 200m × 200m. In this way, 250 grids, i.e. 250 data points, were obtained. These data points were assigned .

[0030] Several factors need to be considered when determining appropriate seawater monitoring stations within the lagoon area: ① The interaction between the bay ecosystem and seawater quality; ② The role of water exchange rate in promoting the improvement of seawater quality; ③ Pollution discharge points caused by human activities that have a significant negative impact on water quality.

[0031] By building a decision tree, the key features in the historical monitoring data of existing monitoring stations that have the greatest impact on water quality changes are determined, and the future water quality change trend is predicted based on the spatial distribution information in the grid division. Specifically, the historical monitoring data of existing monitoring stations are collected, and missing values ​​and outliers in the data are processed; characteristic data are extracted based on factors such as the bay ecosystem and water exchange rate, and the key features that have the greatest impact on the prediction results are determined; a decision tree is built through the random forest algorithm, and the number of trees, tree depth, etc. are adjusted.

[0032] Feature importance in random forests is calculated by average impurity reduction, which is calculated as follows:

[0033] in, is the number of trees; is the impurity before feature segmentation; is the impurity after feature segmentation.

[0034] Assuming there are 100 trees, the average impurity reduction values ​​of each feature across all trees include temperature 2.5, dissolved oxygen 3.0, pH 2.0, turbidity 1.5, and vegetation cover 4.0; The total average impurity reduction is: 2.5 + 3.0 + 2.0 + 1.5 + 4.0 = 13.0; Among them, the importance of temperature is The importance of dissolved oxygen is The importance of pH is The importance of turbidity is The importance of vegetation coverage is ; According to the above calculation results, vegetation coverage has the highest importance, followed by dissolved oxygen.

[0035] According to the future trend of water quality changes, a water quality model is constructed. The water quality model and the hydrodynamic model are coupled to simulate the effect of water exchange rate on the improvement of seawater quality. The hydrodynamic model equations are expressed as follows: (1); (2); In formula (1) and formula (2), for water depth; For time; is the flow velocity vector; is the gradient of the velocity vector; is the potential energy of the fluid; is the gradient of fluid potential energy; is the density of water; is the kinematic viscosity coefficient; For the Coriolis force.

[0036] Embodiment 2: On the basis of the above-mentioned embodiment, an optimal step length is found near the current data point to minimize the objective function while keeping the step length within the trust region radius. The optimal step length solution formula is expressed as formula (3): (3); In formula (3), It means finding a step size to minimize the model function under the constraint of the trust region radius; is the objective function value of the current point; is the gradient of the current point; is transposed; is the step vector; is the Hessian matrix; is the norm; is the trust region adjustment factor, which is used to adjust the size of the trust region; is the trust region radius.

[0037] The size of the trust region radius is determined according to the actual decrease in the objective function.

[0038] The data point position and velocity update formulas are shown in equations (4) and (5): (4); (5); In formula (4) and formula (5), For the Data points in iterations In the Speed ​​in dimension; For the Data points in iterations In the Speed ​​in dimension; For the Data points in iterations In the Position on the dimension; For the Data points in iterations The best historical position is Position on the dimension; For the Data points in iterations In the Position on the dimension; For the The global optimal position in the first iteration is Position on the dimension; is the inertia weight; is the first acceleration constant; is the second acceleration constant; and is a random number between 0 and 1; is the proportional factor, which is used to control the intensity of chaotic disturbance; is a chaotic function, which is used to introduce nonlinearity and randomness in velocity update; and Different from the concept of speed in physics, it is an abstract concept in the search space, which indicates the change in the position of a data point during the iteration process.

[0039] For example, suppose for , the objective function is , data point size is 2, number of iterations is 5, inertia weight is 0.7, the first acceleration constant is 2, the second acceleration constant is 2, the scale factor is 0.5, and the location of the initial data point is is 0, 6.

[0040] In the first iteration, , , the best in history , , the global optimal ; For data point 1: ; For data point 2: ; Update the position, for data point 1: , for data point 2: ; After 5 iterations, the objective function is found. Minimized value.

[0041] If the actual decrease in the objective function is close to the predicted decrease, and the step size is within the trust region radius, the position of the data point is updated. The data point iteration process is as follows: Figure 2As shown in the figure, the particle swarm optimization algorithm can effectively maintain a balance between global search and local search, and at the same time use the chaotic perturbation term to increase the randomness of the search, so as to find a better solution in the layout optimization problem of the bay water quality monitoring station. This optimization method can not only improve the quality of the solution, but also shorten the time of the optimization process and improve the efficiency of the optimization process.

[0042] Figure 2 In the figure, with the increase of the number of iterations, the number of representative points of data points is also slowly decreasing. However, the 15 most stable representative points of data points obtained after iteration 110 all appear in the range of better representative points screened out in the previous iteration, indicating that with the increase of the number of iterations, some representative points of data points remain unchanged, indicating that the algorithm scheme and algorithm results of the present application are very stable, there will be no sudden jump in the screening points, the rationality is relatively high, and it can be well adapted to other lagoons, bays, sea areas, etc.

[0043] The preset convergence conditions are: the position change of the data point is less than a certain threshold, the maximum number of iterations has been reached, or the norm of the gradient is small enough.

[0044] Embodiment 3: A computer readable storage medium such as Figure 3 As shown, the computer-readable storage medium stores a computer program that can be executed by a processor. When the computer program is executed by the processor, the various steps in the aforementioned bay water quality monitoring station layout optimization method are run, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0045] Embodiment 4: A computer device, comprising a memory, a processor, a communication interface and a communication bus; wherein the memory, the processor and the communication interface communicate with each other via the communication bus; the memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory, and when the processor executes the computer program, each step in the aforementioned method for optimizing the layout of bay water quality monitoring stations can be implemented, and the same technical effect can be achieved, which will not be described here to avoid repetition.

[0046] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PR AM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0047] The conventional techniques in the above embodiments are prior arts known to those skilled in the art, and thus will not be described in detail here.

[0048] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may substitute the specific embodiments described in a similar manner without departing from the spirit of the present invention or exceeding the scope defined by the appended claims.

[0049] Although the present invention has been described in detail and some specific embodiments have been cited, it is obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the present invention.

[0050] Although the above-mentioned specific embodiments have been shown, described and pointed out the novel features applied to various embodiments, it should be understood that, without departing from the spirit of the present disclosure, various omissions, substitutions and changes can be made to the form and details of the described device or method. In addition, the above-mentioned various features and methods can be used independently of each other, or can be combined in various ways. All possible combinations and sub-combinations are intended to fall within the scope of the present disclosure. Many of the above-mentioned embodiments include similar components, and therefore, these similar components are interchangeable in different embodiments. Although the present invention has been disclosed in the context of certain embodiments and examples, it should be understood by those skilled in the art that the present invention can extend to other alternative embodiments and / or applications and equivalents beyond the specifically disclosed embodiments. Therefore, the present invention is not intended to be limited by the specific disclosure of the preferred embodiments herein.

[0051] Matters not covered in the present invention are all known technologies.

Claims

1. A method for optimizing the layout of bay water quality monitoring stations, characterized in that: include: S1. Grid the study area and obtain data points; The characteristic values ​​of the data points include the future water quality change trends predicted based on the historical monitoring data of existing monitoring stations; S2, determine the initial range of the algorithm search based on the characteristic value of the data point; S3, determining the optimal step size for updating the data point by calculating the gradient and curvature information of the objective function, and updating the data point position based on the comparison result between the actual decrease amount and the predicted decrease amount of the objective function, and iterating in a loop; S4. When the preset convergence condition is reached, the location of the data point finally obtained is the location of the bay water quality monitoring station.

2. The method for optimizing the layout of bay water quality monitoring stations according to claim 1, characterized in that: In step S1, the characteristic values ​​of the data points also need to consider the following factors: ① The interaction between the bay ecosystem and seawater quality; ② The role of water exchange rate in promoting the improvement of seawater quality; ③ Pollution discharge points caused by human activities that have a significant negative impact on water quality.

3. The method for optimizing the layout of bay water quality monitoring stations according to claim 2, characterized in that: By building a decision tree, the key features that have the greatest impact on water quality changes in the historical monitoring data of existing monitoring stations are determined, and the future water quality change trend is predicted based on the spatial distribution information in the grid division.

4. The method for optimizing the layout of bay water quality monitoring stations according to claim 2, characterized in that: A water quality model is constructed according to the future trend of water quality changes. The water quality model and the hydrodynamic model are coupled to simulate the effect of water exchange rate on the improvement of seawater quality. The hydrodynamic model equations are expressed as follows: (1)； (2)； In formula (1) and formula (2), for water depth; For time; is the flow velocity vector; is the gradient of the velocity vector; is the potential energy of the fluid; is the gradient of fluid potential energy; is the density of water; is the kinematic viscosity coefficient; For the Coriolis force.

5. The method for optimizing the layout of bay water quality monitoring stations according to any one of claims 1 to 4, characterized in that: In step S3, an optimal step length is found near the current data point to minimize the objective function while keeping the step length within the trust region radius. The optimal step length solution formula is expressed as follows: (3)； In formula (3), It means finding a step size to minimize the model function under the constraint of the trust region radius; is the objective function value of the current point; is the gradient of the current point; is transposed; is the step vector; is the Hessian matrix; is the norm; is the trust region adjustment factor, which is used to adjust the size of the trust region; is the trust region radius.

6. The method for optimizing the layout of bay water quality monitoring stations according to claim 5, characterized in that: The size of the trust region radius is determined according to the actual decrease in the objective function.

7. The method for optimizing the layout of bay water quality monitoring stations according to claim 6, characterized in that: In step S3, the data point position and velocity update formulas are expressed as follows: (4)； (5)； In formula (4) and formula (5), For the Data points in iterations In the Speed ​​in dimension; For the Data points in iterations In the Speed ​​in dimension; For the Data points in iterations In the Position on the dimension; For the Data points in iterations The best historical position is Position on the dimension; For the Data points in iterations In the Position on the dimension; For the The global optimal position in the first iteration is Position on the dimension; is the inertia weight; is the first acceleration constant; is the second acceleration constant; and is a random number between 0 and 1; is the proportional factor, which is used to control the intensity of chaotic disturbance; is a chaotic function, which is used to introduce nonlinearity and randomness in velocity update; and Different from the concept of speed in physics, it is an abstract concept in the search space, which indicates the change in the position of a data point during the iteration process.

8. The method for optimizing the layout of bay water quality monitoring stations according to claim 7, characterized in that: If the actual decrease in the objective function is close to the predicted decrease and the step size is within the trust region radius, the position of the data point is updated.

9. A computer-readable storage medium, wherein a computer program executable by a processor is stored in the computer-readable storage medium, characterized in that: When the computer program is executed by a processor, at least one step of the method according to any one of claims 1 to 8 is performed.

10. A computer device, comprising a memory, a processor, a communication interface and a communication bus; wherein: The memory, processor, and communication interface communicate with each other via the communication bus; the memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory, and is characterized in that: when the processor executes the computer program, it implements at least one step of the method described in any one of claims 1-8.

Images