Agricultural non-point source pollution prediction method and system based on plateau lake

Abstract

The invention discloses an agricultural non-point source pollution prediction method and system based on plateau lakes, and relates to the technical field of pollution monitoring, and the method starts from two different perspectives of agricultural land pollutant concentration and environmental pollutant concentration, on one hand, pollutant parameters are analyzed from the inside, and on the other hand, pollutant parameters are analyzed from the outside. Parameters used by internal analysis are completely different from parameters used by external analysis, so that the collinearity problem does not exist, the pollutant concentration indexes obtained through analysis are more comprehensively considered, data are more accurate, and the method has the advantages that the method is simple and easy to implement, and the method is suitable for large-scale popularization and application. And finally, further calculating the non-point source pollution output of the region through dynamic simulation such as MATLAB / simulink. According to the method, linear regression prediction is introduced, the function of predicting the non-point source pollution output is achieved, the agricultural non-point source pollution output is quantified, the dosage can be further standardized, and perspectiveness is provided for follow-up treatment.

Description

Technical Field

[0001] The present application relates to the technical field of pollution monitoring, and particularly relates to a method and system for predicting agricultural non-point source pollution based on plateau lakes. Background Technique

[0002] Farmland non-point source pollution refers to environmental pollution formed by nutrients such as nitrogen and phosphorus, pesticides, and other organic or inorganic pollutants during farmland production activities, along with precipitation or irrigation, through surface runoff and farmland seepage of farmland, mainly including chemical fertilizer pollution, pesticide pollution, livestock and poultry manure pollution, etc. The migration process of non-point source pollutants requires water as a carrier, so agricultural non-point source pollution is greatly affected by rainfall. Currently, agricultural non-point source pollution is one of the important reasons for water eutrophication. Compared with farmland point source pollution, farmland non-point source pollution has the characteristics of instability in location, path, and quantity, large randomness, wide distribution range, and difficult treatment.

[0003] Due to the characteristics of highly random spatio-temporal pollutant output, highly discrete occurrence areas, and prevention and control involving thousands of households in agricultural non-point source pollution, these characteristics make the identification and prevention of agricultural non-point source pollution very difficult, increasing the difficulty of treatment. At the same time, since most of the plateau lake basins are agricultural intensive areas, the application rates of chemical fertilizers and pesticides are higher, resulting in more serious agricultural non-point source pollution. Moreover, factors such as generally large planting areas, high rotation intensity, high multiple cropping index, and high application intensity of pesticides and chemical fertilizers in the plateau lake basins make the pollution sources extensive and complex, further increasing the difficulty of treatment. Summary of the Invention

[0004] The main purpose of the present application is to provide a method and system for predicting agricultural non-point source pollution based on plateau lakes to solve the problem of greater difficulty in treating agricultural non-point source pollution in the plateau lake basin in the prior art.

[0005] To achieve the above purpose, the present application provides the following technical solutions:

[0006] A method for predicting agricultural non-point source pollution based on plateau lakes, the agricultural non-point source pollution prediction method is applied to agricultural land adjacent to the plateau lake, and the agricultural non-point source pollution prediction method includes:

[0007] Step S1, obtaining the cultivated area, water consumption, pesticide application amount, fertilizer application amount, and pollutant concentration of the agricultural land based on a plurality of preset time periods;

[0008] Step S2, defining the cultivated area, water consumption, pesticide application amount, fertilizer application amount, and pollutant concentration of a preset time period as a data of a pesticide application cycle;

[0009] Step S3: Calculate the future agricultural land pollutant concentration of the agricultural land based on all medication cycle data, and obtain a future agricultural land pollutant concentration based on a preset prediction step count.

[0010] Step S4: Obtain the environmental temperature, environmental humidity, agricultural land water body temperature, and agricultural land water body flow rate of the agricultural land based on several preset time periods.

[0011] Step S5: Define the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of a preset time period as an environmental cycle data.

[0012] Step S6: Analyze the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data through a multiple linear regression model.

[0013] Step S7: Predict the future environmental pollutant concentration of the agricultural land based on the preset prediction step count through the environmental linear regression relationship.

[0014] Step S8: Obtain the pollution emission coefficient and comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located.

[0015] Step S9: Calculate the agricultural non-point source pollution generation amount based on the current future environmental pollutant concentration, the pollution emission coefficient, and the comprehensive runoff coefficient for the current future preset step count.

[0016] As a further improvement of the present application, Step S3: Calculate the future agricultural land pollutant concentration of the agricultural land based on all medication cycle data, and obtain a future agricultural land pollutant concentration based on a preset prediction step count, including:

[0017] Step S31: Perform standard normalization processing on all medication cycle data.

[0018] Step S32: Define the pollutant concentration of the current medication cycle data as a medication dependent variable.

[0019] Step S33: Define the cultivated area, water consumption, medication amount, and fertilization amount of the current medication cycle data as a group of medication independent variables.

[0020] Step S34: Define the to-be-solved medication linear regression relationship between all medication dependent variables and all medication independent variables according to the multiple linear regression model.

[0021] Step S35: Solve all medication linear regression coefficients of the to-be-solved medication linear regression relationship through the least squares method.

[0022] Step S36: Substitute all the obtained medication linear regression coefficients into the to-be-solved medication linear regression relationship to obtain a pollutant concentration prediction model.

[0023] Step S37: Obtain the future pollutant concentrations of the agricultural land based on a number of preset prediction steps according to the pollutant concentration prediction model.

[0024] As a further improvement of this application, in step S6, analyze the environmental linear regression relationship between all future pollutant concentrations of the agricultural land and all environmental cycle data through a multiple linear regression model, including:

[0025] Step S61: Perform standard normalization processing on all environmental cycle data.

[0026] Step S62: Define each future pollutant concentration of the agricultural land as an environmental dependent variable respectively.

[0027] Step S63: Define the environmental temperature, environmental humidity, agricultural land water temperature, agricultural land water flow rate, plateau lake water temperature, and plateau lake water flow rate of one environmental cycle data as a set of environmental independent variables.

[0028] Step S64: Define the to-be-solved environmental linear regression relationship between all environmental dependent variables and all environmental independent variables according to the multiple linear regression model.

[0029] Step S65: Solve all environmental linear regression coefficients of the to-be-solved environmental linear regression relationship by the least squares method.

[0030] As a further improvement of this application, in step S8, obtain the pollution emission coefficient and comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located, including:

[0031] Step S81: Obtain a number of rainfall data of the area based on a number of preset time periods.

[0032] Step S82: Perform precipitation simulation on the area through dynamic simulation based on all rainfall data to obtain the effective load of the area.

[0033] Step S83: Assign a pollution emission coefficient to the effective load according to a preset strategy.

[0034] Step S84: Crawl the comprehensive runoff coefficient matching the geology of the area through a crawler script in public channels.

[0035] As a further improvement of this application, in step S82, perform precipitation simulation on the area through dynamic simulation based on all rainfall data to obtain the effective load of the area, including:

[0036] Step S821: Obtain the point cloud data of the area through remote sensing interpretation;

[0037] Step S822: Construct a finite element model of the area through the point cloud data;

[0038] Step S823: Assign a preset unit precipitation amount to the finite element model to obtain the total precipitation amount when the finite element model starts to overflow;

[0039] Step S824: Obtain the remaining amount of the total precipitation amount at preset time intervals;

[0040] Step S825: Obtain the difference between the total precipitation amount and the remaining amount, and define the difference as the effective load.

[0041] As a further improvement of the present application, in step S83, assign a pollution emission coefficient to the effective load according to a preset strategy, including:

[0042] Step S831: Obtain the total drainage system assembly of the finite element model;

[0043] Step S832: Obtain the drainage pipe network layout of the total drainage system assembly;

[0044] Step S833: Obtain the combined flow length and the split flow length of the drainage pipe network layout;

[0045] Step S834: Obtain the length ratio of the combined flow length to the split flow length;

[0046] Step S835: When the length ratio is 0, assign a first pollution emission coefficient to the effective load;

[0047] Step S836: When the length ratio is in the range of (0%, 20%], assign a second pollution emission coefficient to the effective load;

[0048] Step S837: When the length ratio is in the range of (20%, 100%], assign a third pollution emission coefficient to the effective load.

[0049] As a further improvement of the present application, in step S9, calculate the agricultural non-point source pollution generation amount based on the current and future environmental pollutant concentrations, the pollution emission coefficient, and the comprehensive runoff coefficient for a preset number of steps in the current and future, including:

[0050] Step S91: Calculate the agricultural non-point source pollution generation amount according to formula (1):

[0051] fh = H·ΔF·a·q·c·10 -9 (1);

[0052] Among them, fh is the agricultural non-point source pollution generation amount, H is the average annual precipitation of the region, ΔF is the difference between the total precipitation and the remainder, a is the comprehensive runoff coefficient, q is one of the first pollution emission coefficient, the second pollution emission coefficient, and the third pollution emission coefficient, and c is the current and future environmental pollutant concentration.

[0053] To achieve the above object, the present application also provides the following technical solutions:

[0054] An agricultural non-point source pollution prediction system based on a plateau lake, the agricultural non-point source pollution prediction system is applied to the agricultural non-point source pollution prediction method as described above, and the agricultural non-point source pollution prediction system includes:

[0055] An agricultural land medication parameter acquisition module, configured to acquire the cultivated area, water consumption, medication amount, fertilization amount, and pollutant concentration of the agricultural land based on a plurality of preset time periods;

[0056] A medication cycle data definition module, configured to define the cultivated area, water consumption, medication amount, fertilization amount, and pollutant concentration of a preset time period as a medication cycle data;

[0057] A future agricultural land pollutant concentration prediction module, configured to calculate the future agricultural land pollutant concentration of the agricultural land based on all medication cycle data, and obtain a future agricultural land pollutant concentration based on a preset prediction step number;

[0058] An agricultural land environmental parameter acquisition module, configured to acquire the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of the agricultural land based on a plurality of preset time periods;

[0059] An environmental cycle data definition module, configured to define the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of a preset time period as an environmental cycle data;

[0060] An environmental linear regression relationship analysis module, configured to analyze the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data through a multiple linear regression model;

[0061] A future environmental pollutant concentration prediction module, configured to predict the future environmental pollutant concentration of the agricultural land based on the preset prediction step number through the environmental linear regression relationship;

[0062] A regional emission and runoff coefficient acquisition module, configured to acquire the pollution emission coefficient and the comprehensive runoff coefficient of the region where the agricultural land and the plateau lake are located;

[0063] An agricultural non-point source pollution generation amount calculation module, which is used to calculate the agricultural non-point source pollution generation amount based on the current and future environmental pollutant concentrations, the pollution emission coefficient, and the comprehensive runoff coefficient for a preset number of steps in the current and future.

[0064] To achieve the above object, the present application also provides the following technical solutions:

[0065] An electronic device, comprising a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the agricultural non-point source pollution prediction method as described above is implemented.

[0066] To achieve the above object, the present application also provides the following technical solutions:

[0067] A storage medium, the storage medium stores program instructions, and when the program instructions are executed by a processor, the agricultural non-point source pollution prediction method as described above can be implemented.

[0068] The present application obtains the cultivated area, water consumption, drug dosage, fertilizer dosage, and pollutant concentration of agricultural land based on several preset time periods; defines the cultivated area, water consumption, drug dosage, fertilizer dosage, and pollutant concentration of a preset time period as a drug use cycle data; calculates the future agricultural land pollutant concentration based on all drug use cycle data, and obtains a future agricultural land pollutant concentration based on a preset prediction step; obtains the ambient temperature, ambient humidity, water body temperature, and water body flow rate of agricultural land based on several preset time periods; defines the ambient temperature, ambient humidity, and water body temperature of a preset time period as a drug use cycle data; calculates the future agricultural land pollutant concentration based on all drug use cycle data, and obtains a future agricultural land pollutant concentration based on a preset prediction step; obtains the ambient temperature, ambient humidity, and water body temperature of agricultural land based on several preset time periods; defines the ambient temperature, ambient humidity, and water body flow rate of a preset time period as a drug use cycle data; calculates the future agricultural land pollutant concentration based on all drug use cycle data; calculates the future agricultural land pollutant concentration based on a preset prediction step; calculates the future agricultural land pollutant concentration based on a preset prediction step; calculates the future agricultural land pollutant concentration based on a preset time period ... , agricultural land water temperature, agricultural land water flow rate, plateau lake water temperature, plateau lake water flow rate are defined as an environmental cycle data; the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data is analyzed through a multivariate linear regression model; the future environmental pollutant concentration of agricultural land based on a preset prediction step is predicted through the environmental linear regression relationship; the pollution emission coefficient and the comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located are obtained; the amount of agricultural non-point source pollution based on the current future preset step is calculated based on the current future environmental pollutant concentration, the pollution emission coefficient, and the comprehensive runoff coefficient. This application starts from two different angles: agricultural land pollutant concentration and environmental pollutant concentration. On the one hand, the pollutant parameters are analyzed from the inside (agricultural land), and on the other hand, the pollutant parameters are analyzed from the outside (plateau lake basin), and then the linear regression relationship between the two is combined to predict the future pollutant concentration. Since the parameters used for internal analysis are completely different from those used for external analysis, there is no collinearity problem, so that the pollutant concentration index obtained by analysis is more comprehensive and the data is more accurate. Finally, the amount of non-point source pollution in the area is further calculated through dynamic simulation such as MATLAB / simu link. Since this application introduces linear regression prediction, it can realize the prediction function of the amount of non-point source pollution generated. At the same time, by obtaining the precipitation effective load of agricultural land, the amount exceeding the effective load is calculated, and the excess amount is defined as the amount of agricultural non-point source pollution generated. The amount of agricultural non-point source pollution generated in this application is not only quantified, but also can further standardize the amount of medicine used and provide foresight for subsequent governance. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 This is a schematic diagram of the process steps of an embodiment of the method for predicting agricultural non-point source pollution based on plateau lakes in this application;

[0070] Figure 2 This is a functional module diagram of an embodiment of the agricultural non-point source pollution prediction system based on plateau lakes of this application;

[0071] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0072] Figure 4 This is a schematic structural diagram of an embodiment of the storage medium of the present application. Specific embodiments

[0073] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0074] The terms "first", "second", and "third" in the present application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0075] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0076] As Figure 1 shown, this embodiment provides an embodiment of a method for predicting agricultural non-point source pollution based on plateau lakes. In this embodiment, the method for predicting agricultural non-point source pollution is applied to agricultural land adjacent to plateau lakes.

[0077] Preferably, this embodiment is more applicable to modern farmland that has undergone rainwater and sewage diversion transformation, and has more quantitative significance compared to traditional farmland.

[0078] Preferably, the agricultural land around plateau lakes mainly exhibits the following characteristics:

[0079] High altitude and low temperature: Plateau lakes are usually located in areas with high altitudes, so the agricultural land around them is correspondingly at high altitudes. Due to the high altitude, the temperature in these areas is usually low, which poses certain limitations to the growth of crops. This low-temperature environment requires crops to have strong cold tolerance and also affects the growth cycle and yield of crops.

[0080] Flat terrain and fertile soil: Although the agricultural land around plateau lakes is at high altitudes, in some river valleys or near lakes, the terrain is relatively flat and the soil is relatively fertile. These areas usually have good tillage conditions and are suitable for the growth of crops. For example, the river valley areas on the Qinghai-Tibet Plateau, such as the Yarlung Zangbo River Valley and the Huangshui River Valley, are typical agriculturally developed areas.

[0081] Adequate water source and convenient irrigation: As important water sources, plateau lakes provide sufficient water resources for the agricultural land around them. These water resources not only meet the needs of crop growth but also facilitate irrigation. In areas close to lakes or rivers, farmers can use these water sources for effective irrigation to improve the yield and quality of crops.

[0082] Adequate sunlight and large temperature difference between day and night: Plateau areas usually have sufficient sunlight resources, which are very beneficial to the photosynthesis and growth of crops.

[0083] Specifically, the agricultural non-point source pollution prediction method includes the following steps:

[0084] Step S1, obtain the cultivated area, water consumption, pesticide application amount, fertilizer application amount, and pollutant concentration of agricultural land based on several preset time periods.

[0085] Preferably, the preset time period can be set to a natural day, a natural week, a natural month, etc., and the step size of the preset prediction steps in the following text can be unified with the preset time period.

[0086] Step S2, define the cultivated area, water consumption, pesticide application amount, fertilizer application amount, and pollutant concentration of a preset time period as a pesticide application cycle data.

[0087] Preferably, the consumption of consumables in Step S2 can be obtained through direct statistics.

[0088] Step S3, calculate the future pollutant concentration of agricultural land based on all pesticide application cycle data, and obtain a future pollutant concentration of agricultural land based on a preset prediction step.

[0089] Step S4: Obtain the ambient temperature, ambient humidity, agricultural land water temperature, and agricultural land water flow rate of the agricultural land based on several preset time periods.

[0090] Preferably, the environmental parameters in step S4 can be obtained through direct measurement.

[0091] Step S5: Define the ambient temperature, ambient humidity, agricultural land water temperature, agricultural land water flow rate, plateau lake water temperature, and plateau lake water flow rate of a preset time period as an environmental cycle data.

[0092] Preferably, the significance of measuring the farmland water temperature and the lake water temperature in step S5 is that the flowing water in the same place is usually cooler than the static water. This is because the flowing water will continuously exchange heat with the surrounding environment during the flow process, resulting in a slight decrease in the water temperature. At the same time, the flowing water will also carry away a part of the heat, making the overall temperature of the water body decrease. In contrast, the heat transfer of static water mainly relies on convection and heat conduction, and the heat exchange speed is relatively slow, so the temperature change of static water is not significant. Therefore, under the same environmental conditions, the temperature of flowing water is usually slightly lower than that of static water.

[0093] Step S6: Analyze the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data through a multiple linear regression model.

[0094] Preferably, the environmental linear regression relationship and the medication linear regression relationship in the following text are linear regression relationships calculated based on the same linear regression model. In this embodiment, only different names are used to distinguish different application scenarios.

[0095] Step S7: Predict the future environmental pollutant concentration of the agricultural land based on the preset prediction steps through the environmental linear regression relationship.

[0096] Preferably, the step size of the preset prediction steps can be unified with the preset time period into a natural unit time such as a natural day, a natural week, or a natural month.

[0097] Preferably, in order to prevent the multiple linear regression model from overfitting and resulting in inaccurate objective functions of the model, the following methods can be used to avoid it:

[0098] ① Increase the number of training set sample points.

[0099] ② Reduce the model complexity, that is, the model order.

[0100] ③ Regularization.

[0101] ④ Shorten the number of training epochs or reduce the precision limit, and stop training the model before the model overfits.

[0102] ⑤Data augmentation and adding noise.

[0103] ⑥Deep learning: Dropout and Dropconnect.

[0104] Step S8, obtain the pollution emission coefficient and the comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located.

[0105] Step S9, calculate the agricultural non-point source pollution generation amount based on the current future environmental pollutant concentration, pollution emission coefficient, and comprehensive runoff coefficient for a preset number of future steps.

[0106] Furthermore, in step S3, calculate the future agricultural land pollutant concentration of the agricultural land based on all the medication cycle data, and obtain a future agricultural land pollutant concentration based on a preset prediction number of steps, including the following steps:

[0107] Step S31, perform standard normalization processing on all the medication cycle data.

[0108] Preferably, in this embodiment, the zero-mean normalization (Z-score standardization) normalization method is preferably used. This method standardizes the data based on the mean and standard deviation of the original data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. For the normalization method, batch normalization can also be used in this embodiment.

[0109] Step S32, define the pollutant concentration of the current medication cycle data as a medication dependent variable.

[0110] Step S33, define the cultivated area, water consumption, medication amount, and fertilization amount of the current medication cycle data as a set of medication independent variables.

[0111] Step S34, define the to-be-solved medication linear regression relationship between all the medication dependent variables and all the medication independent variables according to the multiple linear regression model.

[0112] Preferably, the multiple linear regression equation set is shown as the following formula:

[0113]

[0114] Among them, y i is the dependent variable of the i-th preset time period, n is the number of all preset time periods, β0 is the intercept of all linear regression relationships, β1 is the linear regression coefficient of all cultivated areas, β2 is the linear regression coefficient of all water consumption amounts, β3 is the linear regression coefficient of all medication amounts, β4 is the linear regression coefficient of all fertilization amounts, x 1,iis the cultivated area data for the i-th preset time period, x 2,i is the water consumption data for the i-th preset time period, x 3,i is the amount of medicine used data for the i-th preset time period, x 4,i is the fertilization amount data for the i-th preset time period, and δ is the random error of all linear regression relationships.

[0115] Step S35, solve all the drug linear regression coefficients of the drug linear regression relationship to be solved by the least squares method.

[0116] Preferably, the least squares method is represented by the following formula:

[0117]

[0118] Among them, is the estimated value of β j , j = 1, 2, 3, 4, corresponding to β1, β2, β3, β4, X is the matrix of all drug independent variables, X T is the transpose matrix of matrix X.

[0119] It should be noted that the formulas in the above additional content are for principle explanations, and the symbol meanings of the formulas are not interoperable with other formulas.

[0120] Step S36, substitute all the obtained drug linear regression coefficients into the drug linear regression relationship to be solved to obtain the pollutant concentration prediction model.

[0121] Preferably, the significance test of the linear regression model refers to testing whether the linear relationship between the independent variable and the dependent variable in the linear regression model is significant through statistical methods. The significance test mainly includes the following methods:

[0122] ① F-test: used to test the significance of the entire regression equation. The hypothesis of the F-test is that at least one regression coefficient is not zero. Calculate the F statistic and compare it with the critical value. If the F value is less than the significance level (such as 0.05), then reject the original hypothesis and consider the regression equation significant, that is, there is a significant linear relationship between the independent variable and the dependent variable.

[0123] ② t-test: used to test the significance of a single regression coefficient. The hypothesis of the t-test is that a certain regression coefficient is zero. Calculate the t statistic and compare it with the critical value. If the t value is less than the significance level (such as 0.05), then reject the original hypothesis and consider that the regression coefficient is significantly not zero.

[0124] Step S37, obtain the future agricultural land pollutant concentration of the agricultural land based on several preset prediction steps according to the pollutant concentration prediction model.

[0125] Further, in step S6, analyze the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data through a multiple linear regression model, including the following steps:

[0126] Step S61, perform standard normalization processing on all environmental cycle data.

[0127] Step S62, define each future agricultural land pollutant concentration as an environmental dependent variable respectively.

[0128] Step S63, define the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of an environmental cycle data as a set of environmental independent variables.

[0129] Step S64, define the to-be-solved environmental linear regression relationship between all environmental dependent variables and all environmental independent variables according to the multiple linear regression model.

[0130] Step S65, solve all environmental linear regression coefficients of the to-be-solved environmental linear regression relationship through the least squares method.

[0131] Preferably, the multiple linear regression model used in steps S62 to S65 is the same as the multiple linear regression model used in steps S32 to S35, so the calculation principle is the same, and the calculation process will not be elaborated here.

[0132] Further, in step S8, obtain the pollution emission coefficient and comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located, including the following steps:

[0133] Step S81, obtain several rainfall data of the area based on several preset time periods.

[0134] Preferably, the rainfall data can be directly obtained from the local meteorological bureau.

[0135] Step S82, perform precipitation simulation on the area through dynamic simulation based on all rainfall data to obtain the effective load of the area.

[0136] Preferably, the preset software can be set to one of StormDesk, InfoWorks ICM, SWMM, XP-SWMM, XP2D.

[0137] Among them, StormDesk is a drainage system model analysis software, which focuses on the research and solutions of waterlogging and black and odorous water body problems, and provides functions such as waterlogging accumulation simulation, rain and sewage mixing connection analysis, and rapid pipe network design.

[0138] InfoWorks ICM is a comprehensive integrated catchment drainage model analysis software. It realizes the integration of the drainage pipe network system and the river model, can simulate the rainwater circulation system, and is applicable to the current situation assessment of the drainage system, renovation planning, and the design and planning of new drainage systems. This software combines a one-dimensional hydraulic model and a two-dimensional flood inundation model within an independent simulation engine.

[0139] SWMM is a dynamic precipitation-runoff simulation model analysis software, mainly used to simulate a single precipitation event or long-term water quantity and water quality. This software can handle complex precipitation-runoff problems and is applicable to various types of drainage systems, including combined and separate systems.

[0140] XP-SWMM is a dynamic simulation software for rainwater, sewage, and river systems, applicable to various complex precipitation events and water quality simulations. This software provides detailed simulation and analysis functions and is applicable to the design and optimization of drainage systems.

[0141] XP2D is an integrated one-dimensional and two-dimensional dynamic hydraulic simulation software, which can analyze the inundation situation more accurately. This software is applicable to various complex flood simulation scenarios and provides detailed simulation and analysis functions.

[0142] In summary, the above-mentioned software can all perform precipitation simulations and obtain the effective load of the preset area. Just input the finite element model in the following text into the software and then set the precipitation amount.

[0143] Step S83: Assign a pollution emission coefficient to the effective load according to the preset strategy.

[0144] Step S84: Crawl the comprehensive runoff coefficient matching the geology of the area through a crawler script in public channels.

[0145] Preferably, under the condition of the same rainfall amount, the runoff volume of farmland increases with the increase of rainfall intensity. Specifically, at three rainfall intensities of 10 mm / h, 15 mm / h, and 25 mm / h, the total runoff volumes generated are 197.07 m 3 / hm 2 , 381.92 m 3 / hm 2 , 649.45 m 3 / hm 2 , and the corresponding runoff coefficients are 0.20, 0.38, and 0.65 respectively.

[0146] Preferably, the runoff coefficient of farmland can be directly obtained by querying the existing technology, such as the Journal of Agricultural Resources and Environment.

[0147] Further, in step S82, precipitation simulation is performed on the area based on all rainfall data through dynamic simulation to obtain the effective load of the area, including the following steps:

[0148] Step S821, obtain the point cloud data of the area through remote sensing interpretation.

[0149] Preferably, the point cloud data can also be directly obtained through one or a combination of digital model acquisition strategies such as on-site surveying and mapping, UAV photogrammetry, and 3D laser scanning.

[0150] Step S822, construct a finite element model of the area through the point cloud data.

[0151] Step S823, assign a preset unit precipitation amount to the finite element model to obtain the total precipitation amount when the finite element model starts to overflow.

[0152] Step S824, obtain the remaining amount of the total precipitation amount at preset time intervals.

[0153] Step S825, obtain the difference between the total precipitation amount and the remaining amount, and define the difference as the effective load.

[0154] Further, in step S83, assign a pollution emission coefficient to the effective load according to a preset strategy, including the following steps:

[0155] Step S831, obtain the total drainage system assembly of the finite element model.

[0156] Step S832, obtain the drainage pipe network layout of the total drainage system assembly.

[0157] Step S833, obtain the combined length and the divided length of the drainage pipe network layout.

[0158] Step S834, obtain the length ratio of the combined length to the divided length.

[0159] Step S835, when the length ratio is 0, assign a first pollution emission coefficient to the effective load.

[0160] Step S836, when the length ratio is in the range of (0%, 20%], assign a second pollution emission coefficient to the effective load.

[0161] Step S837, when the length ratio is in the range of (20%, 100%], assign a third pollution emission coefficient to the effective load.

[0162] Preferably, the pollution emission coefficient can be divided into 3 to 5 levels according to the rain and sewage diversion situation in the preset area, and the pollution emission coefficient is assigned based on each level. Please refer to Table 1 below (Pollution Emission Coefficient Comparison Table). The higher the coefficient, the greater the contrast before and after the transformation, and the greater the reduction benefit of the newly generated pollution load after the transformation.

[0163] Ratio value of the diversion length to the confluence length Pollution emission coefficient 0 (sewer and sewage pipe with complete diversion) 0.19 (0％,20％] 0.32 (20％,100％] 1

[0164] Table 1: Pollution Emission Coefficient Comparison Table

[0165] As can be seen from the above, the first pollution emission coefficient is 0.19, the second pollution emission coefficient is 0.32, and the third pollution emission coefficient is 1.

[0166] Furthermore, in step S9, the agricultural non-point source pollution generation amount based on the current future preset number of steps is calculated based on the current future environmental pollutant concentration, pollution emission coefficient, and comprehensive runoff coefficient, including:

[0167] Step S91, calculate the agricultural non-point source pollution generation amount according to formula (1):

[0168] fh = H·ΔF·a·q·c·10 -9 (1).

[0169] Among them, fh is the agricultural non-point source pollution generation amount, H is the annual average precipitation in the area where it is located, ΔF is the difference between the total precipitation and the remainder, a is the comprehensive runoff coefficient, q is one of the first pollution emission coefficient, the second pollution emission coefficient, and the third pollution emission coefficient, and c is the current future environmental pollutant concentration.

[0170] This embodiment obtains the cultivated area, water consumption, pesticide dosage, fertilizer dosage, and pollutant concentration of agricultural land based on several preset time periods; defines the cultivated area, water consumption, pesticide dosage, fertilizer dosage, and pollutant concentration of a preset time period as a pesticide cycle data; calculates the future agricultural land pollutant concentration of the agricultural land based on all the pesticide cycle data, and obtains a future agricultural land pollutant concentration based on a preset prediction step number; obtains the ambient temperature, ambient humidity, water body temperature, and water body flow rate of the agricultural land based on several preset time periods; defines the ambient temperature, ambient humidity, and water body temperature of a preset time period as a pesticide cycle data; calculates the future agricultural land pollutant concentration of the agricultural land based on all the pesticide cycle data, and obtains a future agricultural land pollutant concentration based on a preset prediction step number; obtains the ambient temperature, ambient humidity, and water body temperature of the agricultural land as well as the water body flow rate of the agricultural land based on several preset time periods; defines the ambient temperature, ambient humidity, and water body temperature of a preset time period as a pesticide cycle data; calculates the future agricultural land pollutant concentration of the agricultural land based on all the pesticide cycle data; calculates the future agricultural land pollutant concentration of the agricultural land as a pesticide cycle data; calculates the future agricultural land pollutant concentration ... The temperature of agricultural land water, the flow rate of agricultural land water, the temperature of plateau lake water, and the flow rate of plateau lake water are defined as an environmental cycle data; the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data is analyzed through a multivariate linear regression model; the future environmental pollutant concentration of agricultural land based on a preset prediction step is predicted through an environmental linear regression relationship; the pollution emission coefficient and the comprehensive runoff coefficient of the area where agricultural land and plateau lakes are located are obtained; the amount of agricultural non-point source pollution based on the current future preset step number is calculated based on the current future environmental pollutant concentration, the pollution emission coefficient, and the comprehensive runoff coefficient. This embodiment starts from two different angles: the concentration of agricultural land pollutants and the concentration of environmental pollutants. On the one hand, the pollutant parameters are analyzed from the inside (agricultural land), and on the other hand, the pollutant parameters are analyzed from the outside (plateau lake basin), and then the linear regression relationship between the two is combined to predict the future pollutant concentration. Since the parameters used for the internal analysis are completely different from the parameters used for the external analysis, there is no collinearity problem, so that the pollutant concentration index obtained by the analysis is more comprehensive and the data is more accurate. Finally, the amount of non-point source pollution in the area is further calculated through dynamic simulation such as MATLAB / simu link. Since this embodiment introduces linear regression prediction, it can realize the prediction function of the amount of non-point source pollution generated. At the same time, by obtaining the precipitation effective load of agricultural land, the amount exceeding the effective load is calculated, and the excess amount is defined as the amount of agricultural non-point source pollution generated. The amount of agricultural non-point source pollution generated in this embodiment is not only quantified, but also can further standardize the amount of medicine used and provide foresight for subsequent governance.

[0171] like Figure 2 As shown, this embodiment provides an embodiment of an agricultural non-point source pollution prediction system based on plateau lakes. In this embodiment, the agricultural non-point source pollution prediction system is applied to the agricultural non-point source pollution prediction method in the above-mentioned embodiment.

[0172] Specifically, the agricultural non-point source pollution prediction system includes an agricultural land medication parameter acquisition module 1, a medication cycle data definition module 2, a future agricultural land pollutant concentration prediction module 3, an agricultural land environmental parameter acquisition module 4, an environmental cycle data definition module 5, an environmental linear regression relationship analysis module 6, a future environmental pollutant concentration prediction module 7, a regional emission and runoff coefficient acquisition module 8, and an agricultural non-point source pollution generation amount calculation module 9, which are electrically connected in sequence.

[0173] Among them, the agricultural land medication parameter acquisition module 1 is used to acquire the cultivated area, water consumption, medication amount, fertilization amount, and pollutant concentration of agricultural land based on several preset time periods; the medication cycle data definition module 2 is used to define the cultivated area, water consumption, medication amount, fertilization amount, and pollutant concentration of a preset time period as a medication cycle data; the future agricultural land pollutant concentration prediction module 3 is used to calculate the future agricultural land pollutant concentration of agricultural land based on all medication cycle data, and obtain a future agricultural land pollutant concentration based on a preset prediction step; the agricultural land environmental parameter acquisition module 4 is used to acquire the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of agricultural land based on several preset time periods; the environmental cycle data definition module 5 is used to define the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of a preset time period as an environmental cycle data; the environmental linear regression relationship analysis module 6 is used to analyze the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data through a multiple linear regression model; the future environmental pollutant concentration prediction module 7 is used to predict the future environmental pollutant concentration of agricultural land based on a preset prediction step through the environmental linear regression relationship; the regional emission and runoff coefficient acquisition module 8 is used to acquire the pollution emission coefficient and comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located; the agricultural non-point source pollution generation amount calculation module 9 is used to calculate the agricultural non-point source pollution generation amount based on the current future environmental pollutant concentration, pollution emission coefficient, and comprehensive runoff coefficient for the current future preset steps.

[0174] Furthermore, the future agricultural land pollutant concentration prediction module 3 specifically includes a first future agricultural land pollutant concentration prediction sub-module, a second future agricultural land pollutant concentration prediction sub-module, a third future agricultural land pollutant concentration prediction sub-module, a fourth future agricultural land pollutant concentration prediction sub-module, a fifth future agricultural land pollutant concentration prediction sub-module, a sixth future agricultural land pollutant concentration prediction sub-module, and a seventh future agricultural land pollutant concentration prediction sub-module that are electrically connected in sequence; the first future agricultural land pollutant concentration prediction sub-module is electrically connected to the medication cycle data definition module 2, and the seventh future agricultural land pollutant concentration prediction sub-module is electrically connected to the agricultural land environmental parameter acquisition module 4.

[0175] Among them, the first future agricultural land pollutant concentration prediction sub-module is used to perform standard normalization processing on all medication cycle data; the second future agricultural land pollutant concentration prediction sub-module is used to define the pollutant concentration of the current medication cycle data as a medication dependent variable; the third future agricultural land pollutant concentration prediction sub-module is used to define the cultivated area, water consumption, medication amount, and fertilization amount of the current medication cycle data as a set of medication independent variables; the fourth future agricultural land pollutant concentration prediction sub-module is used to define the to-be-solved medication linear regression relationship between all medication dependent variables and all medication independent variables according to the multiple linear regression model; the fifth future agricultural land pollutant concentration prediction sub-module is used to solve all medication linear regression coefficients of the to-be-solved medication linear regression relationship by the least squares method; the sixth future agricultural land pollutant concentration prediction sub-module is used to substitute all the solved medication linear regression coefficients into the to-be-solved medication linear regression relationship to obtain a pollutant concentration prediction model; the seventh future agricultural land pollutant concentration prediction sub-module is used to obtain the future agricultural land pollutant concentration of the agricultural land based on several preset prediction steps according to the pollutant concentration prediction model.

[0176] Furthermore, the environmental linear regression relationship analysis module 6 specifically includes a first environmental linear regression relationship analysis sub-module, a second environmental linear regression relationship analysis sub-module, a third environmental linear regression relationship analysis sub-module, a fourth environmental linear regression relationship analysis sub-module, and a fifth environmental linear regression relationship analysis sub-module that are electrically connected in sequence; the first environmental linear regression relationship analysis sub-module is electrically connected to the environmental cycle data definition module 5, and the fifth environmental linear regression relationship analysis sub-module is electrically connected to the future environmental pollutant concentration prediction module 7.

[0177] Among them, the first environmental linear regression relationship analysis sub-module is used to perform standard normalization processing on all environmental cycle data; the second environmental linear regression relationship analysis sub-module is used to define the pollutant concentration of each future agricultural land as an environmental dependent variable respectively; the third environmental linear regression relationship analysis sub-module is used to define the environmental temperature, environmental humidity, agricultural land water temperature, agricultural land water flow velocity, plateau lake water temperature, and plateau lake water flow velocity of an environmental cycle data as a set of environmental independent variables; the fourth environmental linear regression relationship analysis sub-module is used to define the to-be-solved environmental linear regression relationship between all environmental dependent variables and all environmental independent variables according to the multiple linear regression model; the fifth environmental linear regression relationship analysis sub-module is used to solve all environmental linear regression coefficients of the to-be-solved environmental linear regression relationship by the least squares method.

[0178] Further, the regional emission and runoff coefficient acquisition module 8 specifically includes a first regional emission and runoff coefficient acquisition sub-module, a second regional emission and runoff coefficient acquisition sub-module, a third regional emission and runoff coefficient acquisition sub-module, and a fourth regional emission and runoff coefficient acquisition sub-module that are electrically connected in sequence; the first regional emission and runoff coefficient acquisition sub-module is electrically connected to the future environmental pollutant concentration prediction module 7, and the fourth regional emission and runoff coefficient acquisition sub-module is electrically connected to the agricultural non-point source pollution generation amount calculation module 9.

[0179] Among them, the first regional emission and runoff coefficient acquisition sub-module is used to obtain several rainfall data of the region based on several preset time periods; the second regional emission and runoff coefficient acquisition sub-module is used to perform precipitation simulation on the region through dynamic simulation based on all rainfall data to obtain the effective load of the region; the third regional emission and runoff coefficient acquisition sub-module is used to assign a pollution emission coefficient to the effective load according to a preset strategy; the fourth regional emission and runoff coefficient acquisition sub-module is used to crawl the comprehensive runoff coefficient matching the geology of the region through a crawler script in a public channel.

[0180] Further, the second regional emission and runoff coefficient acquisition sub-module specifically includes a first regional emission and runoff coefficient acquisition unit, a second regional emission and runoff coefficient acquisition unit, a third regional emission and runoff coefficient acquisition unit, a fourth regional emission and runoff coefficient acquisition unit, and a fifth regional emission and runoff coefficient acquisition unit that are electrically connected in sequence; the first regional emission and runoff coefficient acquisition unit is electrically connected to the first regional emission and runoff coefficient acquisition sub-module, and the fifth regional emission and runoff coefficient acquisition unit is electrically connected to the third regional emission and runoff coefficient acquisition sub-module.

[0181] Among them, the first regional emission and runoff coefficient acquisition unit is used to obtain the point cloud data of the region through remote sensing interpretation; the second regional emission and runoff coefficient acquisition unit is used to construct the finite element model of the region through the point cloud data; the third regional emission and runoff coefficient acquisition unit is used to assign a preset unit precipitation amount to the finite element model to obtain the total precipitation amount when the finite element model starts to overflow; the fourth regional emission and runoff coefficient acquisition unit is used to obtain the remaining amount of the total precipitation amount at preset time intervals; the fifth regional emission and runoff coefficient acquisition unit is used to obtain the difference between the total precipitation amount and the remaining amount and define the difference as the effective load.

[0182] Further, the third regional emission and runoff coefficient acquisition sub-module specifically includes a sixth regional emission and runoff coefficient acquisition unit, a seventh regional emission and runoff coefficient acquisition unit, an eighth regional emission and runoff coefficient acquisition unit, a ninth regional emission and runoff coefficient acquisition unit, a tenth regional emission and runoff coefficient acquisition unit, an eleventh regional emission and runoff coefficient acquisition unit, and a twelfth regional emission and runoff coefficient acquisition unit that are electrically connected in sequence; the sixth regional emission and runoff coefficient acquisition unit is electrically connected to the fifth regional emission and runoff coefficient acquisition unit, and the twelfth regional emission and runoff coefficient acquisition unit is electrically connected to the fourth regional emission and runoff coefficient acquisition sub-module.

[0183] Among them, the sixth regional emission and runoff coefficient acquisition unit is used to obtain the total drainage system of the finite element model; the seventh regional emission and runoff coefficient acquisition unit is used to obtain the drainage pipe network layout of the total drainage system; the eighth regional emission and runoff coefficient acquisition unit is used to obtain the combined flow length and the split flow length of the drainage pipe network layout; the ninth regional emission and runoff coefficient acquisition unit is used to obtain the length ratio of the combined flow length to the split flow length; the tenth regional emission and runoff coefficient acquisition unit is used to assign the first pollution emission coefficient to the effective load when the length ratio is 0; the eleventh regional emission and runoff coefficient acquisition unit is used to assign the second pollution emission coefficient to the effective load when the length ratio is in the range of (0%, 20%]; the twelfth regional emission and runoff coefficient acquisition unit is used to assign the third pollution emission coefficient to the effective load when the length ratio is in the range of (20%, 100%].

[0184] Further, the agricultural non-point source pollution generation amount calculation module 9 is specifically used to calculate the agricultural non-point source pollution generation amount according to Equation (1):

[0185] fh = H·ΔF·a·q·c·10 -9 (1).

[0186] Among them, fh is the generation amount of agricultural non-point source pollution, H is the average annual precipitation in the region where it is located, ΔF is the difference between the total precipitation and the remainder, a is the comprehensive runoff coefficient, q is one of the first pollution emission coefficient, the second pollution emission coefficient, and the third pollution emission coefficient, and c is the concentration of environmental pollutants in the current and future.

[0187] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For the preferred, extended, limited, exemplified, and principle description parts of this embodiment, refer to the above embodiment, and this embodiment will not be elaborated here.

[0188] This embodiment obtains the cultivated area, water consumption, chemical application amount, fertilization amount, and pollutant concentration of agricultural land based on several preset time periods; defines the cultivated area, water consumption, chemical application amount, fertilization amount, and pollutant concentration in one preset time period as one set of chemical application cycle data; calculates the future pollutant concentration of agricultural land based on all sets of chemical application cycle data, and obtains a future pollutant concentration of agricultural land based on one preset prediction step; obtains the environmental temperature, environmental humidity, water temperature of agricultural land, and water flow velocity of agricultural land of agricultural land based on several preset time periods; defines the environmental temperature, environmental humidity, water temperature of agricultural land, water flow velocity of agricultural land, water temperature of plateau lakes, and water flow velocity of plateau lakes in one preset time period as one set of environmental cycle data; analyzes the environmental linear regression relationship between all future pollutant concentrations of agricultural land and all sets of environmental cycle data through a multiple linear regression model; predicts the future environmental pollutant concentration of agricultural land based on the preset prediction step through the environmental linear regression relationship; obtains the pollution emission coefficient and comprehensive runoff coefficient of the region where the agricultural land and the plateau lakes are located; calculates the generation amount of agricultural non-point source pollution based on the current and future environmental pollutant concentration, pollution emission coefficient, and comprehensive runoff coefficient for the current and future preset steps. This embodiment starts from two different perspectives of the pollutant concentration of agricultural land and the environmental pollutant concentration. On the one hand, it analyzes the pollutant parameters from the inside (agricultural land), and on the other hand, it analyzes the pollutant parameters from the outside (plateau lake basin), and then combines the linear regression relationship between the two to predict the future pollutant concentration. Since the parameters used for internal analysis are completely different from those used for external analysis, there is no collinearity problem, making the pollutant concentration indicators obtained by the analysis more comprehensive and the data more accurate. Finally, the generation amount of non-point source pollution in this region is further calculated through dynamic simulation such as MATLAB / simulink. Since this embodiment introduces linear regression prediction, it can realize the prediction function of the generation amount of non-point source pollution. At the same time, by obtaining the effective precipitation load of agricultural land to calculate the generation amount exceeding the effective load, and defining the excess amount as the generation amount of agricultural non-point source pollution, the generation amount of agricultural non-point source pollution in this embodiment is not only quantified, but also the chemical application amount can be further standardized, and it provides foresight for subsequent treatment.

[0189] Figure 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As Figure 3 shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0190] The memory 102 stores program instructions for implementing the fault detection method of an oil-immersed transformer according to any one of the above embodiments.

[0191] The processor 101 is configured to execute the program instructions stored in the memory 102 to perform fault detection on the oil-immersed transformer.

[0192] Among them, the processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0193] Furthermore, Figure 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application. Refer to Figure 4 , the storage medium 11 of the embodiment of the present application stores program instructions 111 capable of implementing all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods according to various embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0194] In several embodiments provided in the present application, it should be understood that the disclosed systems, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the system or unit can be in electrical, mechanical, or other forms.

[0195] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. The above is only the implementation manner of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, is equally included in the patent protection scope of the present application.

Claims

1. A prediction method for agricultural non-point source pollution based on plateau lakes, the agricultural non-point source pollution prediction method being applied to agricultural land adjacent to the plateau lakes, characterized in that, The agricultural non-point source pollution prediction method includes: Step S1, obtaining the cultivated area, water consumption, chemical application amount, fertilizer application amount, and pollutant concentration of the agricultural land based on a number of preset time periods; Step S2, defining the cultivated area, water consumption, chemical application amount, fertilizer application amount, and pollutant concentration of a preset time period as a chemical application cycle data; Step S3, calculating the future pollutant concentration of the agricultural land based on all chemical application cycle data, and obtaining a future pollutant concentration of the agricultural land based on a preset prediction step number; Step S4, obtaining the environmental temperature, environmental humidity, water temperature of the agricultural land, and water flow velocity of the agricultural land of the agricultural land based on a number of preset time periods; Step S5, defining the environmental temperature, environmental humidity, water temperature of the agricultural land, water flow velocity of the agricultural land, water temperature of the plateau lake, and water flow velocity of the plateau lake of a preset time period as an environmental cycle data; Step S6, analyzing the environmental linear regression relationship between all future pollutant concentrations of the agricultural land and all environmental cycle data through a multiple linear regression model; Step S7, predicting the future environmental pollutant concentration of the agricultural land based on the preset prediction step number through the environmental linear regression relationship; Step S8, obtaining the pollution emission coefficient and the comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located; Step S9, calculating the agricultural non-point source pollution generation amount based on the current future environmental pollutant concentration, the pollution emission coefficient, and the comprehensive runoff coefficient for the current future preset step number.

2. The agricultural non-point source pollution prediction method according to claim 1, wherein Step S3, calculating the future pollutant concentration of the agricultural land based on all chemical application cycle data, and obtaining a future pollutant concentration of the agricultural land based on a preset prediction step number, including: Step S31, performing standard normalization processing on all chemical application cycle data; Step S32, defining the pollutant concentration of the current chemical application cycle data as a chemical application dependent variable; Step S33, defining the cultivated area, water consumption, chemical application amount, and fertilizer application amount of the current chemical application cycle data as a group of chemical application independent variables; Step S34, defining the to-be-solved chemical application linear regression relationship between all chemical application dependent variables and all chemical application independent variables according to the multiple linear regression model; Step S35, solving all chemical application linear regression coefficients of the to-be-solved chemical application linear regression relationship by the least squares method; Step S36, substituting all the solved chemical application linear regression coefficients into the to-be-solved chemical application linear regression relationship to obtain a pollutant concentration prediction model; Step S37, obtaining the future pollutant concentration of the agricultural land based on a number of preset prediction step numbers according to the pollutant concentration prediction model.

3. The agricultural non-point source pollution prediction method according to claim 1, wherein Step S6, analyzing the environmental linear regression relationship between all future pollutant concentrations of the agricultural land and all environmental cycle data through a multiple linear regression model, including: Step S61, performing standard normalization processing on all environmental cycle data; Step S62, respectively defining each future pollutant concentration of the agricultural land as an environmental dependent variable; Step S63: Define the environmental temperature, environmental humidity, agricultural land water temperature, agricultural land water flow rate, plateau lake water temperature, and plateau lake water flow rate of an environmental cycle data as a set of environmental independent variables; Step S64: Define the to-be-solved environmental linear regression relationship between all environmental dependent variables and all environmental independent variables according to the multiple linear regression model; Step S65: Solve all environmental linear regression coefficients of the to-be-solved environmental linear regression relationship by the least squares method.

4. The agricultural non-point source pollution prediction method according to claim 1, wherein Step S8: Obtain the pollution emission coefficient and comprehensive runoff coefficient of the area where the agricultural land and the plateau lake are located, including: Step S81: Obtain several rainfall data of the area based on several preset time periods; Step S82: Perform precipitation simulation on the area through dynamic simulation based on all rainfall data to obtain the effective load of the area; Step S83: Assign a pollution emission coefficient to the effective load according to a preset strategy; Step S84: Crawl the comprehensive runoff coefficient matching the geology of the area through a crawler script in public channels.

5. The agricultural non-point source pollution prediction method according to claim 4, characterized in that Step S82: Perform precipitation simulation on the area through dynamic simulation based on all rainfall data to obtain the effective load of the area, including: Step S821: Obtain the point cloud data of the area through remote sensing interpretation; Step S822: Construct a finite element model of the area through the point cloud data; Step S823: Assign a preset unit precipitation amount to the finite element model to obtain the total precipitation amount when the finite element model starts to overflow; Step S824: Obtain the remaining amount of the total precipitation amount at intervals of a preset time period; Step S825: Obtain the difference between the total precipitation amount and the remaining amount, and define the difference as the effective load.

6. The agricultural non-point source pollution prediction method according to claim 5, characterized in that Step S83: Assign a pollution emission coefficient to the effective load according to a preset strategy, including: Step S831: Obtain the drainage system assembly of the finite element model; Step S832: Obtain the drainage pipe network layout of the drainage system assembly; Step S833: Obtain the combined flow length and split flow length of the drainage pipe network layout; Step S834: Obtain the length ratio of the combined flow length and the split flow length; Step S835: When the length ratio is 0, assign a first pollution emission coefficient to the effective load; Step S836: When the length ratio is in the range of (0%, 20%], assign a second pollution emission coefficient to the effective load; Step S837: When the length ratio is in the range of (20%, 100%], assign a third pollution emission coefficient to the effective load.

7. The agricultural non-point source pollution prediction method according to claim 6, wherein Step S9: Calculate the agricultural non-point source pollution generation amount based on the current future environmental pollutant concentration, the pollution emission coefficient, and the comprehensive runoff coefficient for a preset number of steps in the current future, including: Step S91: Calculate the agricultural non-point source pollution generation amount according to Equation (1): fh = H·ΔF·a·q·c·10 -9 (1); Among them, fh is the agricultural non-point source pollution generation amount, H is the average annual precipitation of the region, ΔF is the difference between the total precipitation and the remainder, a is the comprehensive runoff coefficient, q is one of the first pollution emission coefficient, the second pollution emission coefficient, and the third pollution emission coefficient, and c is the current and future environmental pollutant concentration.

8. An agricultural non-point source pollution prediction system based on plateau lakes, wherein the agricultural non-point source pollution prediction system is applied to the agricultural non-point source pollution prediction method according to any one of claims 1 to 7, and is characterized in that, The agricultural non-point source pollution prediction system includes: An agricultural land medication parameter acquisition module, configured to acquire the cultivated area, water consumption, medication amount, fertilization amount, and pollutant concentration of the agricultural land based on a plurality of preset time periods; A medication cycle data definition module, configured to define the cultivated area, water consumption, medication amount, fertilization amount, and pollutant concentration of a preset time period as a medication cycle data; A future agricultural land pollutant concentration prediction module, configured to calculate the future agricultural land pollutant concentration of the agricultural land based on all medication cycle data, and obtain a future agricultural land pollutant concentration based on a preset prediction step number; An agricultural land environmental parameter acquisition module, configured to acquire the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of the agricultural land based on a plurality of preset time periods; An environmental cycle data definition module, configured to define the environmental temperature, environmental humidity, agricultural land water body temperature, agricultural land water body flow rate, plateau lake water body temperature, and plateau lake water body flow rate of a preset time period as an environmental cycle data; An environmental linear regression relationship analysis module, configured to analyze the environmental linear regression relationship between all future agricultural land pollutant concentrations and all environmental cycle data through a multiple linear regression model; A future environmental pollutant concentration prediction module, configured to predict the future environmental pollutant concentration of the agricultural land based on the preset prediction step number through the environmental linear regression relationship; A regional emission and runoff coefficient acquisition module, configured to acquire the pollution emission coefficient and the comprehensive runoff coefficient of the region where the agricultural land and the plateau lake are located; An agricultural non-point source pollution generation amount calculation module, configured to calculate the agricultural non-point source pollution generation amount based on the current and future environmental pollutant concentration, the pollution emission coefficient, and the comprehensive runoff coefficient for the current and future preset step numbers.

9. An electronic device, characterized in that, It includes a processor and a memory coupled to the processor, and the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the agricultural non-point source pollution prediction method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores program instructions, and when the program instructions are executed by the processor, they can implement the agricultural non-point source pollution prediction method according to any one of claims 1 to 7.

Images