Drainage basin water resource multi-scale multi-target configuration decision support system

Abstract

The invention discloses a drainage basin water resource multi-scale multi-target configuration decision support system. The system comprises a front-end module, an interaction module, a rear-end module and a database, the front-end module is used for interacting with a user, receiving user input and displaying a system output result; the interaction module is used for data exchange between the front-end module and the rear-end module; the back-end module is used for making a basin water resource configuration decision based on the data input by the user; the database is used for storing data. According to the method, the technical problem faced by agricultural producers in water resource allocation decision making is effectively solved, a simple and clear guiding mode is provided, the agricultural producers are helped to understand and apply policy schemes, the planting structure is optimized, and the economic benefit is maximized.

Description

Technical Field

[0001] The present invention relates to the field of water resources management, and in particular to a multi-scale and multi-objective configuration decision support system for water resources in a river basin. Background Art

[0002] The water demand of inland river basin planting industry is relatively large. Taking the Heihe River Basin as an example, the agricultural producers in the basin have limited understanding and interpretation of policy options, and need a more concise and clear way to guide their own agricultural production and provide positive opinions for agricultural producers' planting structure decisions to maximize economic benefits. The design of a multi-scale and multi-objective configuration decision support system for water resources in the basin can provide positive opinions for agricultural producers' planting structure decisions. Summary of the invention

[0003] In order to solve the technical problems in the above background, the present invention aims to guide agricultural producers in their understanding and reading of policies in a concise and clear manner, provide positive opinions for their planting structure decisions, and maximize economic benefits.

[0004] To achieve the above-mentioned purpose, the present invention provides a basin water resources multi-scale multi-objective configuration decision support system, comprising: a front-end module, an interaction module, a back-end module and a database;

[0005] The front-end module is used to interact with the user, receive user input and display system output results;

[0006] The interaction module is used for data exchange between the front-end module and the back-end module;

[0007] The back-end module is used to make basin water resources allocation decisions based on user input data;

[0008] The database is used to store data.

[0009] Preferably, the front-end module uses Hypertext Markup Language to define the structure and content of the page; uses Cascading Style Sheets to beautify the page; uses CSS to set the border style, font color and size of the data table; at the same time, the front-end module also uses JavaScript to dynamically modify the page content, control multimedia, and achieve animation effects; the front-end module uses the Bootstrap front-end framework to design page response.

[0010] Preferably, the interaction module uses FetchAPI to implement data exchange between the front-end module and the back-end module. FetchAPI allows the front-end module to exchange data with the back-end module without reloading the entire page.

[0011] Preferably, the back-end module uses the Spring Boot framework to build services; at the same time, the Python programming language is used to build a decision model, which includes a planting structure prediction model, an ecological water demand threshold prediction model, and a water distribution prediction model for each irrigation area.

[0012] Preferably, the decision model is solved by converting multiple objectives into a single objective, selecting a minimum deviation method to convert the multi-objective model into a single objective model, and then using a multi-layer tolerance method to solve it.

[0013] Preferably, the planting prediction model includes:

[0014] ln y =r0+r1ln P y-1 +r2ln A y-1 +μ y

[0015] In the formula, y represents the year; μ y A represents the random residual in the y time period; y P represents the predicted planting area for the year; y-1 A represents the price in the y-1 time period; y-1 It represents the crop planting area in the time period y-1;

[0016] The following relationship exists between expected price and actual price:

[0017]

[0018] and represents the expected price in time y and y-1; β represents the adjustment coefficient or expected price formation coefficient in the range of [0, 1];

[0019] Based on the relationship between expected price and actual price, we further propose a linear function hypothesis that the planting area is affected by the expected price:

[0020]

[0021] Among them, α0 and α1 represent linear coefficients.

[0022] Preferably, the back-end module is also used to manage the database, including data storage, retrieval and update; through efficient interaction with the database, the integrity and consistency of the system data are ensured, accurate data support is provided for the front-end module, and stable operation and functional realization of the entire system are achieved.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The invention effectively solves the technical problems faced by agricultural producers in water resource allocation decision-making, and provides a concise and clear guidance method to help them understand and apply policy options, optimize planting structures, and maximize economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0026] Figure 1 A schematic diagram of the system structure of an embodiment of the present invention;

[0027] Figure 2 It is a global ER diagram of the physical model of an embodiment of the present invention;

[0028] Figure 3 This is a physical logic diagram of the physical model of an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Embodiment 1

[0032] like Figure 1 As shown, it is a schematic diagram of the system structure of this embodiment, including: a front-end module, an interaction module, a back-end module and a database; the front-end module is used to interact with the user, receive user input and display the system output results; the interaction module is used for data exchange between the front-end module and the back-end module; the back-end module is used to make basin water resources allocation decisions based on the data input by the user; the database is used to store data.

[0033] The following will describe in detail how the present invention solves the technical problems in practical work in conjunction with this embodiment.

[0034] The front-end module is mainly responsible for interacting with users, receiving user input and displaying system output results. When displaying results to users, the front-end module focuses on user experience and ease of operation, so its design uses a series of advanced technologies and frameworks to achieve this. Specifically, the front-end module uses Hypertext Markup Language (HTML) to define the structure and content of the page, providing a basic framework for the entire page. When constructing a water resources data display page, various HTML tags are used to organize the page layout. Labels are used to divide different areas.

[0035]

[0036]

[0037]

[0038]

[0039]

[0040]

[0041]

[0042]

[0043]

[0044]

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] y y-1 y-1 y

[0051] y y y-1 y-1

[0052]

[0053]

[0054]

[0055]

[0056]

[0057]

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064]

[0065]

[0066]

[0067]

[0068]

[0069]

[0070]

[0071]

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088]

[0089]

[0090]

[0091] m

[0092]

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099]

[0100]

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113] t tk

[0114]

[0115]

[0116]

[0117]

[0118]

[0119]

[0120]

[0121] t tk

[0122] t t

[0123] ik

[0124]

[0125]

[0126]

[0127]

[0128]

[0129]

[0130]

[0131]

[0132]

[0133] Figure 2 Figure 3

[0134]

[0135]

[0136] Tags display data tables, etc. The front-end module also uses Cascading Style Sheets (CSS) to beautify the page and set the style of HTML elements, including layout, color, font and animation. Through CSS, the border style, font color and size of the data table can be set to make the data display clearer and easier to read; for the charts in the system, CSS can control their colors, line thickness and other styles to enhance the visualization effect. At the same time, CSS can also achieve responsive layout to ensure that the page can be adaptively displayed on different screen sizes and devices. For example, on mobile phones and tablets, page elements can automatically adjust the size and position to facilitate user operation. JavaScript is a key technology for the front-end module to achieve interactivity. It is used to dynamically modify page content, control multimedia, and achieve animation effects. When users enter crop-related data, JavaScript can verify the validity of the data in real time. If the input is wrong, a prompt box will pop up immediately to inform the user; when displaying the water distribution plan, JavaScript is used to realize the dynamic drawing of the chart, so that users can more intuitively understand the distribution of water resources in different industries and irrigation areas; for the guidance of some operation processes, JavaScript can control animation effects, such as gradually displaying the operation steps, guiding users to complete complex operations, and improving user experience. In terms of page responsiveness, it is mainly achieved with the help of the Bootstrap front-end framework. The framework uses CSS media query technology to automatically adjust the page layout and style according to the device screen size. On large-screen devices, the display of water resource allocation plans may adopt a multi-column layout to display various data in detail; on small-screen devices, it automatically switches to a single-column layout to highlight key information and avoid overcrowding of information. The elastic layout ensures that page elements can reasonably allocate space under different screen sizes and maintain good visual effects. Scalable images and media resources can also automatically adjust the size according to the screen resolution to ensure clear image quality. For example, the watershed map image can be displayed completely and clearly on different devices, making it convenient for users to view the distribution of water resources. The interactive module realizes data interaction between the front-end module and the back-end module through FetchAPI. When the user operates in the front-end module (such as entering data, clicking the query button, etc.), FetchAPI allows the front-end module application to exchange data with the back-end module server without reloading the entire page. After agricultural producers input data such as crop prices and planting areas in the front-end module, FetchAPI sends this data to the back-end module, which performs calculations and analysis and returns results such as planting recommendations or water distribution plans. After receiving the data, the front-end module dynamically updates the page content through JavaScript and displays the results to the user. This method improves the user experience and the response speed of the application, and users can get the latest information without waiting for the page to refresh. In addition, FetchAPI can also be used in combination with technologies such as WebSocket to implement server-side event push or real-time communication.When the backend module updates the real-time water resource data (such as changes in upstream water volume, real-time water use in irrigation areas, etc.), it can be pushed to the frontend module in real time through WebSocket. The frontend module updates the page display in time, allowing users to keep abreast of the dynamic changes in water resources in the basin. The backend module is the core of the entire system, responsible for processing complex business logic, data calculation and storage management, and providing stable and reliable data services for the frontend. The backend module uses the Spring Boot framework to build services. The automatic configuration feature of the framework greatly simplifies the development process and reduces the tedious manual configuration work. When configuring the database connection, Spring Boot can automatically complete the relevant settings according to the predefined configuration file. The embedded server function makes the deployment of the application more convenient. The backend service can be quickly deployed and run without the need to install additional complex server software. At the same time, Spring Boot has the characteristics of production readiness, which can ensure the stable and reliable operation of the backend service in high concurrency and large-scale data processing scenarios. In the process of water resource allocation decision-making, multiple users may simultaneously process prediction requests for different irrigation areas and different crop planting structures and water distribution plan calculation requests. The Spring Boot framework can effectively manage the backend resources, ensure the stable operation of the system, quickly respond to user requests, and provide users with timely and accurate water distribution plans and related information. The backend uses programming languages ​​such as Python to implement decision model calculations, improve the efficiency and accuracy of data analysis, realize automated decision-making and prediction, monitor and respond to water resource changes in real time, optimize and personalize services, and reduce the probability of human errors. The decision model is an important part of the backend, including the planting structure prediction model, the ecological water demand threshold prediction model, and the water allocation prediction model for each irrigation area. These models provide a scientific basis for the rational allocation of water resources through the analysis and calculation of a large amount of data. The planting structure prediction model is designed based on the concept of multi-layer multi-objective planning and contains three layers of objective functions. The first layer of objective function takes into account factors such as industrial economic benefits, COD (chemical oxygen demand) emission control, and water allocation guarantee for key departments from the perspective of regional managers. In practical applications, for example, when formulating a water resource allocation plan, it is necessary to weigh the water demand and economic benefits of different industries (agriculture, industry, etc.) to ensure the efficient use of water resources, while reducing pollution emissions and ensuring the water demand of key departments (such as domestic water supply departments). The second objective function is mainly based on irrigation district managers, and is committed to optimizing the internal water resource allocation of the irrigation district, and achieving fairness among various water users by minimizing the Gini coefficient; at the same time, it controls leakage, improves water resource utilization efficiency, and ensures water allocation in key irrigation areas. The third objective function is based on the interests of farmers, pursuing the maximization of crop economic benefits, maximization of yield, and sufficient water allocation during the key growth period.The constraints of the model include equality constraints (such as water quantity relationship, corresponding relationship of crop water use ratio in irrigation area, etc.) and inequality constraints (including water quantity constraint, food security constraint, water allocation constraint, etc.), ensuring that the model calculation results meet the requirements of actual water resources management. The decision model solution method adopts the strategy of converting multiple objectives into a single objective, selects the minimum deviation method to convert the multi-objective model into a single objective model, and then uses the multi-layer tolerance method to solve it. The specific steps are: first calculate the optimal and worst values ​​of each objective value of each layer, then use the analytic hierarchy process (AHP) to obtain the weight of each decision layer objective, then use the minimum deviation method to integrate multiple objectives into a single objective, calculate the optimized objective value and decision variables of each layer model, establish the membership function by setting the maximum tolerance of each layer decision variable change, set the tolerance for each decision layer and obtain the membership function of each decision layer, and finally establish a single objective model with the maximum satisfaction as the goal, and solve the model by programming to obtain the final result. In actual operation, for example, for the planting structure prediction model, the required parameters are input into the formula for regression to obtain the Nerlove model parameters of each crop in different administrative regions. The model fitting effect is tested by the deterministic coefficient R2 and the joint hypothesis test (F-test). According to the experience of the model simulation effect on different crops, the planting area of ​​each crop is reasonably calculated to achieve the optimization of the planting structure. The model operation database stores a large amount of data related to water resources management, such as irrigation area, crop yield, irrigation quota, canal water utilization coefficient, field water utilization coefficient, maximum single water output value, single water benefit, net water demand, effective rainfall, crop water production function, whether there is a lining channel length, allowable water flow, COD emission concentration and sewage discharge coefficient of each water-using department, minimum water demand of each water-using department, net water benefit penalty coefficient of each water-using department, and hydrological year probability. These data provide basic support for model calculation. When calculating the water allocation plan for each irrigation area, data such as irrigation area, crop planting structure, and irrigation quota are needed to determine the reasonable water allocation; by analyzing data such as effective rainfall and net water demand, the ecological water demand threshold can be predicted more accurately. The detailed formulas of the above content are as follows: (1) Planting structure prediction model Planting structure prediction Nerlove theory assumes that producers adjust their expectations of current prices based on the degree to which the expected price of the previous period deviates from the actual price of the previous period. ln A=r0+r1ln P+r2ln A+μ In the formula, y represents the year; μ represents the random residual in the y time period; A represents the predicted planting area of ​​the year; P represents the price in the y-1 time period; A represents the crop planting area in the y-1 time period; there is the following relationship between the expected price and the actual price: and represents the expected price in the y and y-1 time periods; β represents the adjustment coefficient or expected price formation coefficient in the range of [0, 1]; based on the relationship between the expected price and the actual price, the linear function hypothesis of the planting area affected by the expected price is further proposed: where α0 and α1 represent linear coefficients.With the help of the Nerlove model and related historical data, the future crop planting area can be predicted, which can effectively help regional managers plan agricultural production. (2) Specific content of the model First-level objective function (regional manager): industry i, region m. Goal 1: Maximum economic benefit Goal 2: Minimum carbon emissions Goal 3: Maximum water allocation for key departments Second-level objective function (irrigation district manager): time t irrigation district n Goal 1: Maximum water use efficiency Goal 2: Highest water use efficiency Under different known conditions, channel leakage can be calculated in different ways: The channel leakage calculation method can be selected according to the data: Method ① By collecting the channel leakage coefficient, the corresponding infiltration volume can be calculated, and the calculation is simple. Method ② requires the leakage coefficient, water diversion volume, channel length, lining conditions, etc. of each channel, and finally the comprehensive channel leakage is obtained. This value is affected by many factors and is more accurate. Objective 3: Maximum water allocation in key irrigation areas Third-level objective function (farmers): Crop type j Objective 1: Maximize economic benefits Yield can be calculated by any of the following formulas: Objective 2: Maximize yield Objective 3: Maximize water allocation in key growth period of crops Constraints: Equality constraint (water quantity relationship) The first administrative district contains D1 irrigation districts: The second administrative district contains D2 irrigation districts: The mth administrative district contains D irrigation districts: Corresponding relationship between water use ratio of irrigation district crops: Corresponding relationship between water use ratio of irrigation district crops: Inequality constraint 1. Water quantity Agricultural available groundwater constraint 2. Food security (there are J1 types of food crops) 3. Water allocation constraint 4. Non-negative constraint The explanation of each character in the above formula is shown in Table 1. Table 1 In terms of solution, the back-end module converts the multi-objective strategy into a single-objective strategy to solve the decision model, selects the minimum deviation method to convert the multi-objective model into a single-objective model, and then uses the multi-layer tolerance method to solve. The specific steps are as follows: Input the required parameters into formula (3-1) for regression, and the Nerlove model parameters (r0, r1, r2) of each crop in different administrative districts can be obtained. The model is tested using the coefficient of certainty R2 and the joint hypothesis test (F-test). The larger the R2, the better the fitting effect. P is the F-test test result, and 1-P reflects the possibility that the obtained model is the true model. According to previous experience, the Nerlove model has a better simulation effect on corn and vegetables, but the simulation effect on wheat is not in line with expectations. Therefore, the total planting area is subtracted from the planting area of ​​corn and vegetables to obtain the wheat planting area. Solution method for multi-layer multi-objective planning model of water resources in arid agricultural areas ① Convert the multi-objective of each decision layer into a single objective. ② Solve the multi-layer single-objective model. Select the minimum deviation method, convert the multi-objective model into a single-objective model, and then use the multi-layer tolerance method to solve it.The steps of solving the MLMOSP model are as follows: Calculate the optimal and worst values ​​of each target value at each layer. Use the AHP method to obtain the weight of each decision layer target; Use the minimum deviation method to integrate multiple targets of each decision layer into a single target in the following form: Calculate the optimization target value F′ and decision variable x′ of each layer model; By setting the maximum tolerance MTt of the change of decision variables at each layer, establish the membership function for the decision variable as follows: Set the tolerance for each decision layer and obtain the membership function of each decision layer: Establish a single-target model with maximum satisfaction as the goal, and the model is as follows: Maxθ Constraint θ≤γ(x)θ≤γ(F)x∈X Where θ represents satisfaction; X represents the initial constraint set of the MLMOSP model. Programming the above model in LINGO software to solve the model can obtain the solution of the model. If you are satisfied with the solution obtained, the solution stops and the optimization result is output. If you are not satisfied, adjust the satisfaction of the upper and middle layers and solve again. The back-end module is also used to manage the database, including data storage, retrieval and update; through efficient interaction with the database, the integrity and consistency of the system data are ensured, accurate data support is provided for the front-end module, and the stable operation and function realization of the entire system are realized. Embodiment 2 As a supplement to Embodiment 1, this embodiment will give an overview of the database of the present invention and explain the physical model design. 1) Database Overview The present invention uses the database MySQL to store user data and calculation results. In order to improve performance and scalability, and also for security and organizational reasons, multiple databases are used to store different data. The database helps organize data through tables, indexes and other data structures, making data storage and retrieval more efficient and conducive to user use. 2) Physical Model Design In this water resource management system, the dependency between entities is mainly reflected in the interrelationship between the hydrological year, irrigation area, crop planting structure and water distribution plan. The hydrological year records the water resource status of a certain year, including the upstream water volume, the available water volume in the middle reaches, etc., as the basis for formulating the water distribution plan. The irrigation area is the main water-using area in the system, which is associated with its available water volume and irrigation area. Each irrigation area has a corresponding crop planting structure, namely crop type, planting area, etc. These data affect the calculation of water demand. The water distribution plan comprehensively considers the data of the hydrological year and the water demand of each irrigation area, formulates a water distribution plan, and evaluates its economic benefits and ecological impact. Each entity in the system has a timestamp field to record the time of creation and update to ensure the timeliness and validity of the data. Its conceptual model is shown in Table 2, the global ER diagram is shown in the figure, and the physical logic diagram is shown in the figure. The embodiments described in Table 2 are only descriptions of the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by ordinary technicians in this field to the technical solution of the present invention should fall within the scope of protection determined by the claims of the present invention.

Claims

1. A multi-scale and multi-objective decision support system for water resources in a river basin, characterized in that: include: Front-end module, interactive module, back-end module and database; The front-end module is used to interact with the user, receive user input and display system output results; The interaction module is used for data exchange between the front-end module and the back-end module; The back-end module is used to make basin water resources allocation decisions based on user input data; The database is used to store data.

2. The basin water resources multi-scale and multi-objective configuration decision support system according to claim 1 is characterized in that: The front-end module uses Hypertext Markup Language to define the structure and content of the page; uses Cascading Style Sheets to beautify the page; uses CSS to set the border style, font color and size of the data table; at the same time, the front-end module also uses JavaScript to dynamically modify the page content, control multimedia, and achieve animation effects; the front-end module uses the Bootstrap front-end framework to design page response.

3. The basin water resources multi-scale and multi-objective configuration decision support system according to claim 1 is characterized in that: The interactive module uses FetchAPI to implement data exchange between the front-end module and the back-end module. FetchAPI allows the front-end module to exchange data with the back-end module without reloading the entire page.

4. The basin water resources multi-scale and multi-objective configuration decision support system according to claim 1 is characterized in that: The backend module uses the Spring Boot framework to build services; at the same time, the Python programming language is used to build a decision model, which includes a planting structure prediction model, an ecological water demand threshold prediction model, and a water distribution prediction model for each irrigation area.

5. The basin water resources multi-scale and multi-objective configuration decision support system according to claim 4 is characterized in that: The decision model adopts the strategy of converting multiple objectives into a single objective to solve the problem, selects the minimum deviation method to convert the multi-objective model into a single objective model, and then uses the multi-layer tolerance method to solve the problem.

6. The basin water resources multi-scale and multi-objective configuration decision support system according to claim 4 is characterized in that: The planting prediction model includes: ln A y r0+r1 ln P y-1 +r2 ln A y-1 +µ y In the formula, y represents the year; μ y A represents the random residual in the y time period; y P represents the predicted planting area for the year; y-1 A represents the price in the y-1 time period; y-1 It represents the crop planting area in the time period y-1; The following relationship exists between expected price and actual price: and represents the expected price in time y and y-1; β represents the adjustment coefficient or expected price formation coefficient in the range of [0, 1]; Based on the relationship between expected price and actual price, we further propose a linear function hypothesis that the planting area is affected by the expected price: Among them, α0 and α1 represent linear coefficients.

7. The basin water resources multi-scale and multi-objective configuration decision support system according to claim 1 is characterized in that: The back-end module is also used to manage the database, including data storage, retrieval and update; through efficient interaction with the database, it ensures the integrity and consistency of system data, provides accurate data support for the front-end module, and realizes the stable operation and functional realization of the entire system.

Images