Intelligent monitoring and coupling analysis system for water and soil elements in inland river basin

Abstract

The invention relates to the technical field of environment monitoring, in particular to an inland river basin water and soil element intelligent monitoring and coupling effect analysis system which comprises a data acquisition module, a data processing module, a coupling analysis model building module, a coupling effect analysis module, a decision support module and a visual display module. The data acquisition module acquires water and soil element data in real time, the data processing module preprocesses the acquired data, the coupling analysis model building module predicts the future trend of water and soil elements, and the coupling effect analysis module analyzes the coupling effect between the water and soil elements in combination with a geographic information system and a hydrological model. The decision support module provides water resource configuration, agricultural irrigation and environmental protection optimization suggestions by using a multiple regression analysis and decision tree algorithm, and the visual display module visualizes various data and analysis results; scientific basis is provided for water and soil resource management of the inland river basin, the resource utilization efficiency is improved, and ecological environment protection is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to an intelligent monitoring and coupling analysis system for water and soil elements in an inland river basin. Background Art

[0002] As an important ecosystem and water supply source, inland river basins have a vital impact on regional agricultural production, ecological protection, and social and economic development. With climate change, population growth, and the continuous changes in human activities, the management of water and soil resources in inland river basins faces increasingly complex challenges. In particular, water pollution, soil degradation, and unbalanced use of water and soil resources have become important factors restricting the sustainable development of river basins.

[0003] However, the existing inland river basin water and soil element monitoring and management system has certain technical problems, mainly reflected in the low data collection accuracy, poor real-time performance, and the coupling relationship between multiple water and soil elements has not been effectively analyzed. Traditional water quality monitoring and soil monitoring equipment often lack the ability to process and analyze real-time data, and the collected data usually cannot accurately reflect the interaction between water and soil elements. Most of the existing coupling analysis methods and prediction models rely on the assumption of linear relationships and cannot effectively capture the complex nonlinear coupling relationship between water and soil elements. In addition, traditional decision support systems lack intelligence, usually rely on manual experience, and lack scientific decision-making basis based on big data analysis. Summary of the invention

[0004] Based on the above purpose, the present invention provides an intelligent monitoring and coupling analysis system for water and soil elements in inland river basins.

[0005] The intelligent monitoring and coupling analysis system of water and soil elements in inland river basins includes data acquisition module, data processing module, coupling analysis model building module, coupling effect analysis module, decision support module and visualization display module, among which;

[0006] The data acquisition module collects water and soil element data in real time through a multi-point sensor network deployed in the inland river basin, and the water and soil element data includes water quality parameters, soil parameters and meteorological data;

[0007] The data processing module is used to preprocess the collected water and soil element data, the preprocessing includes data cleaning and data standardization, and to extract features from the preprocessed water and soil element data;

[0008] The coupling analysis model building module uses the long short-term memory network algorithm to build a coupling analysis model. The coupling analysis model is learned based on historical water and soil element data to capture the nonlinear coupling relationship between water and soil elements, predict the future trend of water and soil elements, and identify their interaction rules.

[0009] The coupling effect analysis module analyzes the coupling effects between water and soil elements based on the prediction results of the coupling analysis model, combined with the geographic information system and the hydrological model, including the impact of water quality changes on soil fertility and the effect of soil moisture changes on the diffusion of water pollutants;

[0010] The decision support module provides corresponding decision suggestions based on the analysis results of the coupling effect analysis module through multiple regression analysis and decision tree algorithm. The decision suggestions include optimizing water resource allocation, agricultural irrigation strategies and environmental protection measures to improve the utilization efficiency of water and soil resources and the level of environmental protection;

[0011] The visualization display module is used to visualize the collected water and soil element data, the prediction results of the coupling analysis model, the analysis results of the coupling effect, and the decision-making suggestions.

[0012] Optionally, the data acquisition module includes:

[0013] Deploy a multi-point sensor network: Select multiple representative monitoring locations in the inland river basin and deploy a series of sensors to collect water and soil element data, including water quality parameters, soil parameters and meteorological data;

[0014] The water quality parameters include water temperature, pH value, dissolved oxygen content, and nitrogen and phosphorus content;

[0015] The soil parameters include soil moisture, soil temperature, soil pH value and organic matter content;

[0016] The meteorological data includes temperature, precipitation and wind speed.

[0017] Optionally, the data processing module includes:

[0018] Data reception: The data processing module receives the water and soil element data collected by the data collection module;

[0019] Data cleaning: Data cleaning is performed on the received water and soil element data, including missing value processing, outlier detection and data format verification;

[0020] Data standardization: standardize the cleaned water and soil element data;

[0021] Feature extraction: Feature extraction is performed based on standardized water and soil element data.

[0022] Optionally, the coupling analysis model building module specifically includes:

[0023] Data preparation: receiving the water and soil element data processed by the data processing module;

[0024] Model construction: Based on the long short-term memory network algorithm, a coupling analysis model is constructed;

[0025] Model training: Use historical water and soil element data to train the coupled analysis model;

[0026] Model prediction: Use the trained coupling analysis model to predict the changing trend of water and soil elements in the future;

[0027] Model evaluation: Evaluate the coupled analysis model to measure the prediction performance of the model. The evaluation indicators include mean square error, mean absolute error and determination coefficient.

[0028] Optionally, the coupling effect analysis module analyzes the impact of water quality changes on soil fertility, specifically including:

[0029] Data input: receiving the change trends of water quality parameters and soil parameters predicted by the coupled analysis model, the change trends including water quality parameters and soil parameters, and combining spatial data in the geographic information system and output data of the hydrological model;

[0030] Data association analysis: Based on the spatial data of land use and soil distribution in the geographic information system, water quality parameters and soil parameters are matched according to geographic space to establish spatial correspondence;

[0031] Correlation analysis: Pearson correlation coefficient was used to evaluate the correlation between water quality parameters (such as nitrogen and phosphorus content, dissolved oxygen) and soil fertility indicators (such as organic matter content, soil pH);

[0032] Analysis of impact mechanism: Based on the coupling relationship between water quality and soil, analyze the impact of nitrogen and phosphorus content in water bodies on soil organic matter accumulation through irrigation or runoff transport. Combined with literature data or experimental results, verify the effect of nitrogen and phosphorus transformation processes in soil (such as nitrification and denitrification) on soil fertility improvement or weakening.

[0033] Coupling model construction: Construct a coupling model of water quality and soil fertility;

[0034] Output results: Based on the constructed coupling model of water quality and soil fertility and input data, the analysis results are output to show the influence of water quality parameters on soil fertility, such as the contribution rate of increased nitrogen and phosphorus content to soil organic matter, and the spatial distribution changes of soil fertility in different regions are visualized through the geographic information system;

[0035] Application suggestions: Based on the analysis results, optimization suggestions for water resource management and soil protection are put forward, such as formulating reasonable irrigation and fertilization plans to improve soil fertility.

[0036] Optionally, the coupling effect analysis module analyzes the effect of soil moisture changes on the diffusion of water pollutants, including:

[0037] Data input: receiving the change trends of soil moisture and water quality parameters predicted by the coupled analysis model, including soil moisture, water quality parameters (such as dissolved oxygen content, nitrogen and phosphorus content, turbidity) and hydrological model output data (such as runoff, infiltration rate), and combining with terrain and watershed network data in the geographic information system;

[0038] Matching soil moisture with water quality data: Using geographic information system spatial analysis, soil moisture data is associated with the corresponding water body location, and the hydrological characteristics of the watershed (such as rainfall intensity and runoff) are matched with water quality data to establish the spatial connection between soil moisture change trends and water quality pollutant diffusion trends;

[0039] Correlation analysis: Pearson correlation coefficient was used to evaluate the correlation between soil moisture change trend and water pollutant diffusion, and to quantify the impact of soil moisture change on water pollutant diffusion;

[0040] Diffusion mechanism analysis: Based on the impact of soil moisture changes on runoff and infiltration rate, analyze how it changes the diffusion rate of water pollutants;

[0041] Pollutant diffusion model construction: Construct a pollutant diffusion model based on soil moisture change trends;

[0042] Coupling effect analysis report: Based on the pollutant diffusion model and input data, output the quantitative analysis results of the impact of soil moisture change trend on the diffusion of water pollutants;

[0043] Application recommendations: Based on the analysis results, water and soil resource management measures can be proposed, such as optimizing soil moisture control methods (such as irrigation and drainage measures) to reduce the risk of pollutant diffusion.

[0044] Optionally, the decision support module is used to optimize water resource allocation, specifically including:

[0045] Input data: Receive the analysis results provided by the coupling effect analysis module, which include the changing trends of water quality parameters and soil parameters, the prediction data of coupling effects (such as the impact of water quality changes on soil fertility, the effect of soil moisture changes on the diffusion of water pollutants), as well as the spatial data provided by the geographic information system and the output data of the hydrological model;

[0046] Multiple regression analysis: Based on the data of water resources, soil fertility and water quality trends, a multiple regression model is constructed to determine the impact of each factor on water resource allocation;

[0047] Optimization model establishment: Based on the regression analysis results, combined with the actual water resource demand and the distribution of water and soil resources in the basin, a water resource allocation optimization model is constructed;

[0048] Application of simulated annealing algorithm: Use simulated annealing algorithm to find the optimal solution for water resources allocation;

[0049] Optimization result output: Output the optimal solution based on the simulated annealing algorithm, that is, the configuration plan that maximizes the efficiency of water resource utilization.

[0050] Output decision recommendations: Provide specific water resource allocation plans based on the configuration plan that maximizes water resource utilization efficiency.

[0051] Optionally, the decision support module is used to optimize agricultural irrigation strategies and environmental protection measures, specifically including:

[0052] Input data: Receive the analysis results provided by the coupling effect analysis module, which include the changing trends of water quality parameters and soil parameters, the prediction data of coupling effects, and the impact data of environmental protection needs and external factors of climate change.

[0053] Model construction: Based on the prediction results of the coupling effect analysis module (such as water quality and soil change trends), a decision tree algorithm is used to build a decision model for agricultural irrigation strategies and environmental protection measures;

[0054] Agricultural irrigation strategy: Provide agricultural irrigation recommendations based on the output of the decision-making model;

[0055] Environmental protection measures: Based on the output of the decision-making model, make recommendations on environmental protection measures;

[0056] Optimize agricultural irrigation: Based on the output of the decision-making model and the characteristics of regional water and soil resources, provide accurate agricultural irrigation optimization solutions to reduce water waste and ensure agricultural production needs.

[0057] Optionally, the visual display module includes:

[0058] Water and soil element data display: Display the time changes of water quality parameters, soil parameters and meteorological data through line graphs or bar graphs;

[0059] Prediction result display: The change trend of water and soil elements predicted by the coupling analysis model is displayed through time series graph;

[0060] Coupling effect display: Display the coupling effect analysis results through heat maps or regional distribution maps, such as the impact of water quality changes on soil fertility;

[0061] Decision suggestion display: Decision suggestions are displayed through pie charts or bar charts, such as the optimization results of water resource allocation and irrigation strategy;

[0062] Interactive display: Provides interactive chart functions to support users to view water and soil element data and prediction results at different times and in different regions.

[0063] Beneficial effects of the present invention:

[0064] The present invention collects data including key parameters such as water quality, soil and meteorology in real time by deploying a multi-point sensor network in inland river basins, thereby ensuring the comprehensiveness and real-time nature of data collection. The data acquisition module can accurately obtain multi-dimensional water and soil element data such as water temperature, pH value, dissolved oxygen, nitrogen and phosphorus content, soil moisture, soil temperature, etc., and through a variety of sensor types, such as water quality sensors, soil sensors and meteorological sensors, it ensures high-precision collection of various types of data. The data processing module further performs cleaning, standardization and feature extraction to optimize data quality and provide a reliable basis for subsequent analysis. In this way, the system can monitor the changes in water and soil elements in real time and provide data support for timely response to environmental changes.

[0065] In the present invention, the coupling analysis module constructs a coupling analysis model based on the long short-term memory network algorithm, and captures the nonlinear coupling relationship between water and soil elements by learning historical water and soil element data, so as to accurately predict the future trend of water and soil elements and identify the interaction law between water and soil elements. This provides an accurate basis for the dynamic assessment of the ecosystem, and can evaluate the changing trend of water and soil resources at different time and space scales. The coupling effect analysis module further combines the geographic information system and the hydrological model to conduct a multi-factor coupling analysis of the impact of water quality changes on soil fertility and the effect of soil moisture changes on the diffusion of water pollutants, providing decision makers with a basis for water and soil resource management decisions based on scientific data. The decision support module generates optimized water resource allocation plans, agricultural irrigation strategies and environmental protection measures through multiple regression analysis and simulated annealing algorithms to help improve the utilization efficiency of water and soil resources and the level of environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0068] Figure 2 The figure is a schematic diagram of the module flow of the coupling analysis model construction according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0070] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0071] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0072] like Figure 1-Figure 2 As shown, the intelligent monitoring and coupling analysis system of water and soil elements in inland river basins includes data acquisition module, data processing module, coupling analysis model building module, coupling effect analysis module, decision support module and visualization display module, among which;

[0073] The data acquisition module collects water and soil element data in real time through a multi-point sensor network deployed in inland river basins. The water and soil element data include water quality parameters, soil parameters and meteorological data.

[0074] The data processing module is used to preprocess the collected water and soil element data, including data cleaning and data standardization, and to extract features from the preprocessed water and soil element data;

[0075] The coupling analysis model building module uses the long short-term memory network algorithm to build a coupling analysis model. The coupling analysis model is based on historical water and soil element data for learning, capturing the nonlinear coupling relationship between water and soil elements, predicting the future trend of water and soil elements, and identifying their interaction laws, providing an accurate basis for the dynamic assessment of the river basin ecosystem.

[0076] The coupling effect analysis module analyzes the coupling effects between water and soil elements based on the prediction results of the coupling analysis model, combined with the geographic information system and the hydrological model, including the impact of water quality changes on soil fertility and the role of soil moisture changes on the diffusion of water pollutants. Through multi-factor coupling analysis, it provides decision-makers with a basis for decision-making on water and soil resource management;

[0077] The decision support module provides corresponding decision suggestions based on the analysis results of the coupling effect analysis module through multiple regression analysis and decision tree algorithm. The decision suggestions include optimizing water resource allocation, agricultural irrigation strategies and environmental protection measures to improve the utilization efficiency of water and soil resources and the level of environmental protection;

[0078] The visualization module is used to visualize the collected water and soil element data, the prediction results of the coupling analysis model, the analysis results of the coupling effect, and the decision-making recommendations.

[0079] The data acquisition module includes:

[0080] Deploy a multi-point sensor network: Select multiple representative monitoring locations in the inland river basin and deploy a series of sensors to collect water and soil element data, including water quality parameters, soil parameters and meteorological data;

[0081] Water quality parameters include water temperature, pH value, dissolved oxygen content, and nitrogen and phosphorus content. The water temperature is measured by a PT100 temperature sensor, the pH value is measured by a solid-state pH sensor, the dissolved oxygen content is measured by a polarographic dissolved oxygen sensor, and the nitrogen and phosphorus content is measured by an ion-selective electrode sensor;

[0082] Soil parameters include soil moisture, soil temperature, soil pH value and organic matter content. Soil moisture is measured by a capacitive soil moisture sensor, soil temperature is measured by an NTC thermistor sensor, soil pH value is measured by a glass electrode pH sensor, and organic matter content is measured by an infrared spectrum sensor;

[0083] Meteorological data include air temperature, precipitation, and wind speed. The air temperature is measured by a thermistor sensor, the precipitation is measured by a vibrating rain gauge, and the wind speed is measured by a rotating cup anemometer.

[0084] The data processing module includes:

[0085] Data reception: The data processing module receives the water and soil element data collected by the data collection module;

[0086] Data cleaning: Data cleaning is performed on the received water and soil element data, including missing value processing, outlier detection and data format validation, including;

[0087] Missing value processing: For the missing data that may exist in the collection process, linear interpolation or deletion of missing values ​​is used to process them. If the missing values ​​exceed a certain proportion (such as more than 10%), the interpolation algorithm is used to fill the data;

[0088] Outlier detection: Perform outlier detection on the received water and soil element data to identify and remove data that does not meet the expected range. The outlier detection uses the Z-score method for identification;

[0089] Data format verification: ensure the consistency of data types and units, perform standardized conversion on data that does not conform to the format, and uniformly convert the units of timestamps and sensor values ​​to ensure the comparability and availability of data;

[0090] Data standardization: The cleaned water and soil element data are standardized to ensure that different types of water and soil element data can be compared and analyzed on the same scale. The standardization process uses the Min-Max standardization method to map the data to the [0,1] interval;

[0091] Feature extraction: Based on the standardized water and soil element data, feature extraction is performed. The purpose of feature extraction is to extract effective information from the original data that is helpful for subsequent coupling analysis and decision support, including:

[0092] Water quality feature extraction: Based on the time series characteristics of water quality parameters, periodic features (such as daily water temperature fluctuations, dissolved oxygen change trends) and fluctuation features (such as sharp changes in nitrogen and phosphorus concentrations) are extracted.

[0093] Soil feature extraction: Extract trend features (such as daily change trend of soil moisture) and volatility features (such as seasonal change of soil pH) based on the change trend of soil moisture, temperature and pH value data;

[0094] Meteorological feature extraction: Extract climate features closely related to changes in water and soil elements from meteorological data, such as the correlation characteristics of temperature, precipitation and water quality changes, and the changing patterns of wind speed and soil moisture.

[0095] The coupled analysis model building modules include:

[0096] Data preparation: receiving the water and soil element data processed by the data processing module;

[0097] Model construction: Based on the long short-term memory network algorithm, a coupling analysis model is constructed, which includes the following steps:

[0098] (1) Input data preparation: The preprocessed water and soil element data are divided into input data sequences {x t} and the target output sequence {y t}, where xt is the input data at the current moment, y t is the corresponding output prediction value;

[0099] The input data sequence x t Convert to a format suitable for long short-term memory networks, including standardizing the data at each moment to ensure that the data scale is consistent.

[0100] (2) LSTM network design: The LSTM network model consists of several LSTM network units. Each LSTM network unit contains three main parts: input gate, forget gate, output gate, and a unit state for storing memory.

[0101] The LSTM network is used to learn the temporal relationship and nonlinear coupling effect between water and soil elements. The model structure includes an input layer, multiple LSTM hidden layers, and an output layer.

[0102] (3) Network parameter initialization: Randomly initialize the weight matrix of the long short-term memory network model (including the weights of the forget gate, input gate, and output gate), and set the bias term;

[0103] Model training: Use historical water and soil element data to train the coupling analysis model. The specific steps are as follows:

[0104] (1) Dataset division: All historical water and soil element data are divided into training set, validation set and test set according to the time step. Usually 80% of the data is used for training, 10% for validation and 10% for testing.

[0105] (2) Definition of loss function: The mean square error (MSE) is used as the loss function to evaluate the difference between the model prediction result and the actual value:

[0106]

[0107] Among them, L is the loss value, n is the number of samples, is the predicted value of the model, y t is the true value.

[0108] (3) Training process: Use the back-propagation algorithm to calculate the gradient of the loss function, and adjust the weights and bias terms of the LSTM network model through an optimization algorithm (such as the Adam optimizer) to minimize the loss function;

[0109] During the training process, cross-validation and early stopping techniques were used to prevent overfitting, and model hyperparameters were adjusted based on the performance of the validation set;

[0110] Model prediction: Use the trained coupling analysis model to predict the changing trend of water and soil elements in the future, including the future changes of water quality, soil and meteorological parameters. Specifically, input the water and soil element data at the current time, and calculate the corresponding prediction value through the coupling analysis model;

[0111] Model evaluation: Evaluate the coupled analysis model and measure the prediction performance of the model. The evaluation indicators include mean square error, mean absolute error and determination coefficient.

[0112] Adjust the model structure or optimize the training process based on the evaluation results to ensure that the model has good generalization ability.

[0113] The coupling effect analysis module analyzes the impact of water quality changes on soil fertility, including:

[0114] Data input: receiving the changing trends of water quality parameters and soil parameters predicted by the coupled analysis model, which includes water quality parameters and soil parameters, and combining the spatial data in the geographic information system and the output data of the hydrological model;

[0115] Data association analysis: Based on the spatial data of land use and soil distribution in the geographic information system, water quality parameters and soil parameters are matched according to geographic space to establish spatial correspondence to ensure that water quality changes in different areas of the basin are associated with soil parameters in the corresponding areas;

[0116] Correlation analysis: The Pearson correlation coefficient was used to evaluate the correlation between water quality parameters (such as nitrogen and phosphorus content, dissolved oxygen) and soil fertility indicators (such as organic matter content, soil pH value) to quantify the direct impact of water quality changes on soil fertility. The Pearson correlation coefficient calculation formula is:

[0117]

[0118] Among them, r is the Pearson correlation coefficient, n is the number of data points, x is the water quality parameter change trend dataset, and y is the soil fertility parameter change trend dataset;

[0119] Analysis of impact mechanism: Based on the coupling relationship between water quality and soil, analyze the impact of nitrogen and phosphorus content in water bodies on soil organic matter accumulation through irrigation or runoff transport. Combined with literature data or experimental results, verify the effect of nitrogen and phosphorus transformation processes in soil (such as nitrification and denitrification) on soil fertility improvement or weakening.

[0120] Coupling model construction: Construct a coupling model of water quality and soil fertility. The model expression is:

[0121] F=α1N+α2P+β1W+β2pH+γ;

[0122] Among them, F is the soil fertility level, N is the nitrogen content in the soil, p is the phosphorus content in the soil, W is the soil moisture, pH is the acidity and alkalinity of the soil, α1, α2, β1, β2, γ are model parameters determined by regression analysis;

[0123] Output results: Based on the constructed coupling model of water quality and soil fertility and input data, the analysis results are output to show the influence of water quality parameters on soil fertility, such as the contribution rate of increased nitrogen and phosphorus content to soil organic matter, and the spatial distribution changes of soil fertility in different regions are visualized through the geographic information system;

[0124] Application suggestions: Based on the analysis results, optimization suggestions for water resource management and soil protection are put forward, such as formulating reasonable irrigation and fertilization plans to improve soil fertility.

[0125] The coupling effect analysis module analyzes the effect of soil moisture changes on the diffusion of water pollutants, including:

[0126] Data input: receiving the changing trends of soil moisture and water quality parameters predicted by the coupled analysis model, including soil moisture, water quality parameters (such as dissolved oxygen content, nitrogen and phosphorus content, turbidity) and hydrological model output data (such as runoff, infiltration rate), and combining with terrain and watershed network data in the geographic information system;

[0127] Matching soil moisture with water quality data: Using geographic information system spatial analysis, soil moisture data is associated with the corresponding water body location, and the hydrological characteristics of the watershed (such as rainfall intensity and runoff) are matched with water quality data to establish the spatial connection between soil moisture change trends and water quality pollutant diffusion trends;

[0128] Correlation analysis: Pearson correlation coefficient was used to evaluate the correlation between soil moisture change trend and water pollutant diffusion, and to quantify the impact of soil moisture change on water pollutant diffusion;

[0129] Diffusion mechanism analysis: Based on the impact of soil moisture changes on runoff and infiltration rate, analyze how it changes the diffusion rate of water pollutants. Combined with experimental or literature data, establish the impact path between soil moisture changes and pollutant diffusion;

[0130] Pollutant diffusion model construction: Construct a pollutant diffusion model based on the soil moisture change trend. The model expression is:

[0131]

[0132] Where C(x,t) is the pollutant concentration at position x and time t, M is the initial pollutant mass, D is the diffusion coefficient, which depends on the change of soil moisture, and v is the propagation speed of the pollutant with runoff;

[0133] Coupling effect analysis report: Based on the pollutant diffusion model and input data, output the quantitative analysis results of the impact of soil moisture change trend on the diffusion of water quality pollutants, such as the proportion of water quality pollutant diffusion increased due to soil moisture decrease, and use geographic information system to visualize the diffusion dynamics of pollutants in the basin;

[0134] Application recommendations: Based on the analysis results, water and soil resource management measures can be proposed, such as optimizing soil moisture control methods (such as irrigation and drainage measures) to reduce the risk of pollutant diffusion.

[0135] The decision support module is used to optimize water resource allocation, including:

[0136] Input data: Receive the analysis results provided by the coupling effect analysis module, which include the change trends of water quality parameters and soil parameters, the prediction data of coupling effects (such as the impact of water quality changes on soil fertility, the effect of soil moisture changes on the diffusion of water pollutants), as well as the spatial data provided by the geographic information system and the output data of the hydrological model;

[0137] Multiple regression analysis: Based on the data of water resources, soil fertility and water quality change trends, a multiple regression model was constructed to determine the impact of various factors on water resources allocation. The model expression is:

[0138] W resource =α0+α1W quality +α2S fertility +α3T humidity +…+ε;

[0139] Among them, W resource is the water resource allocation, W quality is the changing trend of water quality parameters, S fertility is the changing trend of soil fertility, T humidity is the changing trend of soil moisture, α0, α1, α2, α3 are regression coefficients, and ε is the error term;

[0140] Using optimization algorithms such as the least squares method, the regression model is trained with historical data to obtain the regression coefficients of each parameter and quantify the impact of different factors on water resource allocation;

[0141] Optimization model establishment: Based on the regression analysis results, combined with the actual water resource demand and the distribution of water and soil resources in the basin, a water resource allocation optimization model is constructed. The goal is to maximize the efficiency of water resource use and reasonably allocate it to different areas or uses. The optimization objective function is expressed as:

[0142]

[0143] Among them, f(W resource ) is the optimization objective function of water resources allocation, Ci is the water resource utilization efficiency of region i, W resource,i is the water resource allocation amount for region i;

[0144] Application of simulated annealing algorithm: Use simulated annealing algorithm to solve the optimal solution of water resource allocation. The basic steps of simulated annealing algorithm include:

[0145] (1) Initialization: Select the initial solution (For example, initialize based on existing water resource configuration)

[0146] (2) Neighborhood solution generation: Generate neighborhood solutions by perturbing the current solution

[0147] (3) Calculate the energy difference: Calculate the energy difference between the current solution and the neighboring solution. The energy difference is the difference in the objective function value, expressed as:

[0148]

[0149] (4) Acceptance criteria: If ΔE≤0, accept the neighborhood solution; if ΔE>0, accept the neighborhood solution with probability p=e -ΔE / T Accept the neighborhood solution, where T is the current temperature and ΔE is the energy difference;

[0150] (5) Cooling process: The temperature T is gradually reduced according to the set cooling plan, and the neighborhood solutions and acceptance criteria are repeatedly generated until the temperature drops to the preset stop temperature T stop ;

[0151] Optimization result output: Based on the simulated annealing algorithm, the optimal solution is output, that is, the configuration plan that maximizes the efficiency of water resource utilization. This plan can be used to optimize the reasonable allocation of water resources and ensure the scientificity and efficiency of resource allocation while considering factors such as water quality changes and soil moisture.

[0152] Output decision recommendations: Based on the configuration plan that maximizes the efficiency of water resource use, provide specific water resource allocation plans, such as recommending water resource usage in different areas of the basin, guiding the allocation of water resources between regions, and ensuring the efficient use of water resources.

[0153] The decision support module is used to optimize agricultural irrigation strategies and environmental protection measures, including:

[0154] Input data: Receive the analysis results provided by the coupling effect analysis module, which include the changing trends of water quality parameters and soil parameters, the prediction data of coupling effects, and the impact data of environmental protection needs and external factors of climate change.

[0155] Model construction: Based on the prediction results of the coupling effect analysis module (such as water quality and soil change trends), a decision tree algorithm is used to build a decision model for agricultural irrigation strategies and environmental protection measures. The decision tree construction process includes:

[0156] Use historical data to train decision tree models to build relationships between factors such as water quality, soil moisture, precipitation, and irrigation needs and environmental protection measures;

[0157] Different decision rules are set according to the branch conditions of the tree. For example, if the soil moisture is below a certain threshold and the water quality is poor, the decision tree recommends strengthening irrigation and taking measures to improve water quality;

[0158] Decision tree generation: Use CART (Classification and Regression Tree) algorithm or ID3, C4.5 algorithm to generate a decision tree based on historical data and analysis results. Each leaf node represents a specific agricultural irrigation or environmental protection measure;

[0159] Agricultural irrigation strategy: Based on the output of the decision model, provide agricultural irrigation suggestions, such as recommending irrigation water volume, irrigation method and irrigation timing under different meteorological conditions. For example, when the temperature is too high and the soil moisture is low, the decision tree can recommend increasing the irrigation volume;

[0160] Environmental protection measures: Based on the output of the decision-making model, environmental protection measures are proposed, including control measures to reduce water pollution (such as setting up interception belts, reducing farmland drainage) or measures to improve water quality (such as strengthening water purification, implementing farmland water conservancy construction, etc.);

[0161] Optimize agricultural irrigation: Based on the output of the decision-making model and the characteristics of regional water and soil resources, provide accurate agricultural irrigation optimization solutions to reduce water waste and ensure agricultural production needs;

[0162] Provide specific environmental protection plans, such as strengthening water quality monitoring, soil protection measures, environmental impact assessments within the basin, to ensure the sustainable use of water and soil resources.

[0163] The visualization module includes:

[0164] Water and soil element data display: Display the time changes of water quality parameters, soil parameters and meteorological data through line graphs or bar graphs;

[0165] Prediction result display: The change trend of water and soil elements predicted by the coupling analysis model is displayed through time series graph;

[0166] Coupling effect display: Display the coupling effect analysis results through heat maps or regional distribution maps, such as the impact of water quality changes on soil fertility;

[0167] Decision suggestion display: Decision suggestions are displayed through pie charts or bar charts, such as the optimization results of water resource allocation and irrigation strategy;

[0168] Interactive display: Provides interactive chart functions to support users to view water and soil element data and prediction results at different times and in different regions.

[0169] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0170] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Intelligent monitoring and coupling analysis system of water and soil elements in inland river basins, characterized by: It includes data acquisition module, data processing module, coupling analysis model building module, coupling effect analysis module, decision support module and visualization display module, among which; The data acquisition module collects water and soil element data in real time through a multi-point sensor network deployed in the inland river basin, and the water and soil element data includes water quality parameters, soil parameters and meteorological data; The data processing module is used to preprocess the collected water and soil element data, the preprocessing includes data cleaning and data standardization, and to extract features from the preprocessed water and soil element data; The coupling analysis model building module uses the long short-term memory network algorithm to build a coupling analysis model. The coupling analysis model is learned based on historical water and soil element data to capture the nonlinear coupling relationship between water and soil elements, predict the future trend of water and soil elements, and identify their interaction rules. The coupling effect analysis module analyzes the coupling effects between water and soil elements based on the prediction results of the coupling analysis model, combined with the geographic information system and the hydrological model, including the impact of water quality changes on soil fertility and the effect of soil moisture changes on the diffusion of water pollutants; The decision support module provides corresponding decision suggestions based on the analysis results of the coupling effect analysis module through multiple regression analysis and decision tree algorithm. The decision suggestions include optimizing water resource allocation, agricultural irrigation strategies and environmental protection measures; The visualization display module is used to visualize the collected water and soil element data, the prediction results of the coupling analysis model, the analysis results of the coupling effect, and the decision-making suggestions.

2. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 1 is characterized in that: The data acquisition module comprises: Deploy a multi-point sensor network: Select multiple monitoring locations in the inland river basin and deploy a series of sensors to collect water and soil element data, including water quality parameters, soil parameters and meteorological data; The water quality parameters include water temperature, pH value, dissolved oxygen content, and nitrogen and phosphorus content; The soil parameters include soil moisture, soil temperature, soil pH value and organic matter content; The meteorological data includes temperature, precipitation and wind speed.

3. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 2 is characterized in that: The data processing module comprises: Data reception: The data processing module receives the water and soil element data collected by the data collection module; Data cleaning: Data cleaning is performed on the received water and soil element data, including missing value processing, outlier detection and data format verification; Data standardization: standardize the cleaned water and soil element data; Feature extraction: Feature extraction is performed based on standardized water and soil element data.

4. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 3 is characterized in that: The coupling analysis model building module specifically includes: Data preparation: receiving the water and soil element data processed by the data processing module; Model construction: Based on the long short-term memory network algorithm, a coupling analysis model is constructed; Model training: Use historical water and soil element data to train the coupled analysis model; Model prediction: Use the trained coupling analysis model to predict the changing trend of water and soil elements in the future; Model evaluation: Evaluate the coupled analysis model to measure the prediction performance of the model. The evaluation indicators include mean square error, mean absolute error and determination coefficient.

5. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 4 is characterized in that: The coupling effect analysis module analyzes the impact of water quality changes on soil fertility, specifically including: Data input: receiving the change trends of water quality parameters and soil parameters predicted by the coupled analysis model, the change trends including water quality parameters and soil parameters, and combining spatial data in the geographic information system and output data of the hydrological model; Data association analysis: Based on the spatial data of land use and soil distribution in the geographic information system, water quality parameters and soil parameters are matched according to geographic space to establish spatial correspondence; Correlation analysis: Pearson correlation coefficient was used to evaluate the correlation between water quality parameters and soil fertility indicators; Analysis of impact mechanism: Based on the coupling relationship between water quality and soil, analyze the impact of nitrogen and phosphorus content in water bodies on soil organic matter accumulation through irrigation or runoff transport. Combined with literature data or experimental results, verify the effect of nitrogen and phosphorus conversion in soil on soil fertility improvement or weakening. Coupling model construction: Construct a coupling model of water quality and soil fertility; Output results: Based on the constructed coupling model of water quality and soil fertility and input data, the analysis results are output to show the influence of water quality parameters on soil fertility, and the spatial distribution changes of soil fertility in different regions are visualized through the geographic information system; Application suggestions: Based on the analysis results, make optimization suggestions for water resource management and soil protection.

6. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 5 is characterized in that: The coupling effect analysis module analyzes the effect of soil moisture changes on the diffusion of water pollutants, including: Data input: receiving the change trends of soil moisture and water quality parameters predicted by the coupled analysis model, which include soil moisture, water quality parameters and hydrological model output data, combined with terrain and watershed network data in the geographic information system; Matching soil moisture with water quality data: Using geographic information system spatial analysis, soil moisture data is associated with the corresponding water body locations, the hydrological characteristics of the watershed are matched with water quality data, and the spatial connection between soil moisture change trends and water quality pollutant diffusion trends is established; Correlation analysis: Pearson correlation coefficient was used to evaluate the correlation between soil moisture trend and water pollutant diffusion; Diffusion mechanism analysis: Based on the impact of soil moisture changes on runoff and infiltration rate, analyze how it changes the diffusion rate of water pollutants; Pollutant diffusion model construction: Construct a pollutant diffusion model based on soil moisture change trends; Coupling effect analysis report: Based on the pollutant diffusion model and input data, output the quantitative analysis results of the impact of soil moisture change trend on the diffusion of water pollutants; Application suggestions: Propose water and soil resource management measures based on the analysis results.

7. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 6 is characterized in that: The decision support module is used to optimize water resource allocation, specifically including: Input data: Receive the analysis results provided by the coupling effect analysis module, which include the change trends of water quality parameters and soil parameters, the prediction data of coupling effects, as well as the spatial data provided by the geographic information system and the output data of the hydrological model; Multiple regression analysis: Based on the data of water resources, soil fertility and water quality trends, a multiple regression model is constructed to determine the impact of each factor on water resource allocation; Optimization model establishment: Based on the regression analysis results, combined with the actual water resource demand and the distribution of water and soil resources in the basin, a water resource allocation optimization model is constructed; Application of simulated annealing algorithm: Use simulated annealing algorithm to find the optimal solution for water resources allocation; Optimization result output: Output the optimal solution based on the simulated annealing algorithm, that is, the configuration plan that maximizes the efficiency of water resource use; Output decision recommendations: Provide specific water resource allocation plans based on the configuration plan that maximizes water resource utilization efficiency.

8. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 7 is characterized in that: The decision support module is used to optimize agricultural irrigation strategies and environmental protection measures, specifically including: Input data: Receive the analysis results provided by the coupling effect analysis module, which include the change trends of water quality parameters and soil parameters, the prediction data of coupling effects, and the impact data of environmental protection needs and external factors of climate change; Model construction: Based on the prediction results of the coupling effect analysis module, a decision tree algorithm is used to build a decision model for agricultural irrigation strategies and environmental protection measures; Agricultural irrigation strategy: Provide agricultural irrigation recommendations based on the output of the decision-making model; Environmental protection measures: Based on the output of the decision-making model, make recommendations on environmental protection measures; Optimize agricultural irrigation: Provide agricultural irrigation optimization solutions based on the output of the decision-making model and the characteristics of regional water and soil resources.

9. The intelligent monitoring and coupling analysis system for water and soil elements in inland river basins according to claim 8 is characterized in that: The visual display module includes: Water and soil element data display: Display the time changes of water quality parameters, soil parameters and meteorological data through line graphs or bar graphs; Prediction result display: The change trend of water and soil elements predicted by the coupling analysis model is displayed through time series graph; Coupling effect display: display the coupling effect analysis results through thermal maps or regional distribution maps; Decision suggestion presentation: Present decision suggestions through pie charts or bar charts; Interactive display: Provides interactive chart functions to support users to view water and soil element data and prediction results at different times and in different regions.

Images