Sensor-based saline-alkali soil water-salt migration characteristic data analysis processing method and system

Abstract

The invention discloses a sensor-based saline-alkali soil water-salt migration characteristic data analysis processing method and system. The method comprises the following steps: acquiring monitoring data of a saline-alkali soil water-salt migration process by adopting a multi-source heterogeneous sensor; preprocessing the monitoring data to obtain processed data; constructing a water-salt migration characteristic data set based on the processed data; constructing a water-salt migration characteristic analysis model based on the water-salt migration characteristic data set; analyzing and processing the water-salt migration characteristic data of the saline-alkali soil by using the water-salt migration characteristic analysis model. According to the method, a water-salt migration characteristic data set with a unified temporal-spatial resolution is constructed. Key characteristic parameters are extracted through a wavelet analysis method, and a water-salt migration characteristic analysis model is constructed by adopting a decision tree algorithm, so that accurate analysis processing of the saline-alkali soil water-salt migration characteristics is realized. The method not only improves the accuracy and efficiency of data processing, but also contributes to optimizing the water-salt regulation and control measures of the saline-alkali soil, and is of great significance to accurately grasp the water-salt migration rule of the saline-alkali soil.

Description

Technical Field

[0001] The invention relates to the field of water-salt migration analysis, and in particular to a sensor-based method and system for analyzing and processing characteristic data of water-salt migration in saline-alkali land. Background Art

[0002] The water-salt migration process in saline-alkali land has obvious spatiotemporal multi-scale characteristics, and the laws and characteristics of water-salt migration at different spatiotemporal scales are significantly different. The existing sensor monitoring data vary greatly in temporal and spatial resolution, and the monitoring data of different sensors are heterogeneous in format, accuracy, frequency, etc. Directly applying these multi-source heterogeneous monitoring data to water-salt migration analysis will lead to large errors. In addition, the water-salt migration processes at different spatiotemporal scales affect each other, and the monitoring data at a single spatiotemporal scale cannot fully characterize the overall characteristics of water-salt migration. Therefore, it is urgent to study targeted multi-source heterogeneous sensor data processing methods to achieve unified expression and fusion of monitoring data at temporal and spatial scales, and to construct a water-salt migration characteristic analysis model under a unified spatiotemporal framework. At the same time, it is also necessary to study the interaction mechanism of water-salt migration processes at different spatiotemporal scales, establish a multi-spatiotemporal scale water-salt migration joint analysis model, and realize a comprehensive analysis of water-salt migration characteristics from local to overall and from micro to macro. The solution to the above technical problems is of great significance for accurately grasping the laws of water-salt migration in saline-alkali land and optimizing control measures. Summary of the invention

[0003] In order to solve the technical problems in the above background, the present invention provides the following solutions:

[0004] A sensor-based method for analyzing and processing characteristic data of water and salt migration in saline-alkali land, comprising the following steps:

[0005] Use multi-source heterogeneous sensors to obtain monitoring data on water and salt migration in saline-alkali land;

[0006] Preprocessing the monitoring data to obtain processed data;

[0007] Based on the processed data, construct a water-salt migration characteristic data set;

[0008] Based on the water-salt migration characteristic data set, a water-salt migration characteristic analysis model is constructed;

[0009] The water-salt migration characteristic analysis model is used to complete the analysis and processing of saline-alkali land water-salt migration characteristic data.

[0010] Preferably, a Kalman filter algorithm is used to eliminate the heterogeneity of the monitoring data of different sensors in format, accuracy and frequency, and obtain a standardized monitoring data set. The Kalman filter process includes:

[0011] Status prediction:

[0012]

[0013]

[0014] Status Update:

[0015]

[0016]

[0017] P k|k =(IK k H k ) k|k-1

[0018] in, represents the state estimate at time step k based on the information predicted at time step k-1; F k represents the state transfer matrix; B k represents the control input matrix; u k represents the control input at time step k; P k|k-1 represents the error covariance of the prediction; Q k represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the actual measurement value at time step k; H k represents the observation matrix; R k represents the measurement noise covariance matrix; At time step k, the state estimate is updated based on the latest measurement; P k|k represents the updated error covariance.

[0019] Preferably, based on Kalman filtering, Kriging interpolation is used to convert the standardized monitoring data set into monitoring data with uniform spatiotemporal resolution to obtain the processed data;

[0020] The Kriging interpolation process is as follows:

[0021]

[0022] in, represents the estimated value of position u; Z(u i ) represents the value of a known data point; λ i Represents the interpolation weight.

[0023] In the estimation process, the condition of unbiased estimation needs to be met, that is, the expectation of the estimated value is equal to the true value. The formula is as follows:

[0024]

[0025] The goal of Kriging interpolation is to minimize the estimation error, that is, to minimize the variance between the predicted value and the true value:

[0026]

[0027] In the formula, J represents the cost function; Var represents the variance function; represents the estimated value of position u; Z(u) represents the true value of position u.

[0028] Preferably, the key characteristic parameters reflecting the water-salt migration process are extracted by wavelet analysis method to construct the water-salt migration characteristic data set, wherein the key characteristic parameters include: water content, salinity, groundwater level and evapotranspiration; the expression of the wavelet analysis is as follows:

[0029]

[0030] Among them, x(t) represents the original signal; ψ represents the wavelet basis function; a represents the scale parameter; and b represents the location parameter.

[0031] Preferably, the water-salt migration characteristic analysis model is constructed using a decision tree algorithm.

[0032] The present invention also provides a sensor-based saline-alkali land water and salt migration characteristic data analysis and processing system, the system is used to implement the above method, including: an acquisition module, a processing module, a data set construction module, a model construction module and an analysis module;

[0033] The acquisition module is used to acquire monitoring data of the water and salt migration process in saline-alkali land using multi-source heterogeneous sensors;

[0034] The processing module is used to pre-process the monitoring data to obtain processed data;

[0035] The data set construction module is used to construct a water-salt migration characteristic data set based on the processed data;

[0036] The model building module is used to build a water-salt migration characteristic analysis model based on the water-salt migration characteristic data set;

[0037] The analysis module is used to complete the analysis and processing of the water-salt migration characteristic data of saline-alkali land using the water-salt migration characteristic analysis model.

[0038] Preferably, the workflow of the processing module includes: using a Kalman filter algorithm to eliminate the heterogeneity of the monitoring data of different sensors in format, accuracy and frequency to obtain a standardized monitoring data set, and the Kalman filter process includes:

[0039] Status prediction:

[0040]

[0041]

[0042] Status Update:

[0043]

[0044]

[0045] P k|k =(IK k H k ) k|k-1

[0046] in, represents the state estimate at time step k based on the information predicted at time step k-1; F k represents the state transfer matrix; B k represents the control input matrix; u k represents the control input at time step k; P k|k-1 represents the error covariance of the prediction; Q k represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the actual measurement value at time step k; H k represents the observation matrix; R k represents the measurement noise covariance matrix; At time step k, the state estimate is updated based on the latest measurement; P k|k represents the updated error covariance.

[0047] Preferably, the workflow of the processing module further includes: based on Kalman filtering, using Kriging interpolation to convert the standardized monitoring data set into monitoring data with uniform spatiotemporal resolution to obtain the processed data;

[0048] The Kriging interpolation process is as follows:

[0049]

[0050] in, represents the estimated value of position u; Z(u i ) represents the value of a known data point; λ i Represents the interpolation weight.

[0051] In the estimation process, the condition of unbiased estimation needs to be met, that is, the expectation of the estimated value is equal to the true value. The formula is as follows:

[0052]

[0053] The goal of Kriging interpolation is to minimize the estimation error, that is, to minimize the variance between the predicted value and the true value:

[0054]

[0055] In the formula, J represents the cost function; Var represents the variance function; represents the estimated value of position u; Z(u) represents the true value of position u.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0057] The patent of this invention uses multi-source heterogeneous sensors to obtain monitoring data of the water and salt migration process in saline-alkali land, and uses the Kalman filter algorithm and Kriging interpolation technology to pre-process and standardize the data, thereby constructing a water and salt migration characteristic data set with a unified temporal and spatial resolution. The key characteristic parameters are extracted by wavelet analysis, and a water and salt migration characteristic analysis model is constructed using a decision tree algorithm, thereby achieving accurate analysis and processing of the water and salt migration characteristics of saline-alkali land. This method not only improves the accuracy and efficiency of data processing, but also helps to optimize water and salt regulation measures in saline-alkali land, which is of great significance for accurately grasping the laws of water and salt migration in saline-alkali land. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0059] Figure 1 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0062] Embodiment 1

[0063] like Figure 1 FIG. 1 is a schematic diagram of the method flow of this embodiment, and the steps include:

[0064] S1. Use multi-source heterogeneous sensors to obtain monitoring data on water and salt migration in saline-alkali land.

[0065] According to the spatiotemporal multi-scale characteristics of the water and salt migration process in saline-alkali land, multi-source heterogeneous sensors are used to obtain monitoring data with different spatiotemporal resolutions. In this embodiment, these data include: soil moisture and salinity data once an hour, and groundwater level and mineralization data once a day.

[0066] S2. Preprocess the monitoring data to obtain processed data.

[0067] The collected monitoring data is cleaned and preprocessed. Specifically, the Kalman filter algorithm is used to eliminate the heterogeneity of the monitoring data of different sensors in terms of format, accuracy, frequency, etc., and a standardized monitoring data set with a time resolution of hours and a spatial resolution of 1 square meter is obtained. The Kalman filter process is as follows:

[0068] Status prediction:

[0069]

[0070]

[0071] Status Update:

[0072]

[0073]

[0074] P k|k =(IK k H k ) k|k-1

[0075] in, represents the state estimate at time step k based on the information predicted at time step k-1; F k represents the state transfer matrix; B k represents the control input matrix; u k represents the control input at time step k; P k|k-1 represents the error covariance of the prediction; Q k represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the actual measurement value at time step k; H k represents the observation matrix; R k represents the measurement noise covariance matrix; At time step k, the state estimate is updated based on the latest measurement; P k|k represents the updated error covariance.

[0076] On this basis, Kriging interpolation was used to convert the standardized monitoring data set into unified spatiotemporal resolution monitoring data with a temporal resolution of days and a spatial resolution of 10 square meters, i.e. processed data. The Richards flow equation was used to simulate and calculate the spatiotemporal distribution of soil water potential, water content, and salt concentration at different spatiotemporal scales. By comparing with the water-salt regulation threshold of saline-alkali land, the water-salt migration process of each 10 square meter grid unit was analyzed every day.

[0077] The Kriging interpolation process is as follows:

[0078]

[0079] in, represents the estimated value of position u; Z(u i ) represents the value of a known data point; λ i Represents the interpolation weight.

[0080] In the estimation process, the condition of unbiased estimation needs to be met, that is, the expectation of the estimated value is equal to the true value. The formula is as follows:

[0081]

[0082] The goal of Kriging interpolation is to minimize the estimation error, that is, to minimize the variance between the predicted value and the true value:

[0083]

[0084] In the formula, J represents the cost function; Var represents the variance function; represents the estimated value of position u; Z(u) represents the true value of position u.

[0085] The Richards equation is the basic equation describing water flow in unsaturated porous media. It combines the conservation of mass and the Darcy-Buckingham flow relationship. Its formula is as follows:

[0086]

[0087] Where θ represents volumetric water content; ψ represents the matrix component of soil water potential; t represents time; K(θ) represents the unsaturated hydraulic conductivity function; R(θ) represents the source-sink term; Represents the divergence operator.

[0088] The Darcy flow q is driven by the potential gradient and is expressed as:

[0089]

[0090] Here, z represents the vertical coordinate.

[0091] Substituting Darcy's law into the continuity equation, we can obtain the mixed form of Richards' equation:

[0092]

[0093] Where φ represents the pore water content; p represents the pore water pressure; and K(φ) represents the hydraulic conductivity related to the saturation.

[0094] S3. Based on the processed data, construct a water and salt migration characteristic dataset.

[0095] In view of the differences in spatiotemporal resolution of different monitoring data, the monitoring data from different sources were unified into a standard spatiotemporal framework with a spatial resolution of 30m and a temporal resolution of 1h by constructing a spatiotemporal scale conversion matrix, eliminating the errors caused by the inconsistency of the spatiotemporal scales of the monitoring data. Based on the unified monitoring data, the key characteristic parameters reflecting the water and salt migration process were extracted using the wavelet analysis method (Continuous Wavelet Transform, CWT), including soil moisture, salinity, groundwater level, evapotranspiration, etc., and a water and salt migration characteristic data set containing 42 characteristic variables was constructed.

[0096] Wavelet analysis is used to extract the time-frequency characteristics of a signal by convolving the signal with a series of scaled and translated wavelet functions. Select a suitable wavelet basis function, and through continuous wavelet transform, convolve the signal with wavelet basis functions of different scales and positions to obtain wavelet coefficients, which describe the characteristics of the signal at each scale. The expression of wavelet analysis is as follows:

[0097]

[0098] Among them, x(t) represents the original signal; ψ represents the wavelet basis function; a represents the scale parameter; and b represents the location parameter.

[0099] S4. Based on the water-salt migration characteristic dataset, a water-salt migration characteristic analysis model is constructed.

[0100] Under the unified spatiotemporal framework, the spatiotemporal evolution law and key influencing factors of water and salt migration process are explored to construct a water and salt migration characteristic analysis model. In this embodiment, the decision tree algorithm is selected to construct the water and salt migration characteristic analysis model:

[0101] First, the water-salt migration feature dataset constructed by S3 is used as the basis for building a decision tree. The features that best reflect the water-salt migration process are selected as nodes of the decision tree. When classifying, the decision tree recursively divides the data set according to the order of feature selection until all samples belong to the same category or the preset stop condition is reached. The classification effect of the decision tree is evaluated by cross-validation, confusion matrix and other methods, and the decision tree with higher accuracy is selected for subsequent analysis.

[0102] When classifying, the extracted results are classified through a decision tree to obtain a classification result. Generally speaking, the goal of decision tree classification is to group samples of the same category together and separate samples of different categories as much as possible.

[0103] S5. Use the water-salt migration characteristic analysis model to complete the analysis and processing of the water-salt migration characteristic data of saline-alkali land.

[0104] Embodiment 2

[0105] The present embodiment also provides a sensor-based saline-alkali land water and salt migration characteristic data analysis and processing system, including: an acquisition module, a processing module, a data set construction module, a model construction module and an analysis module; the acquisition module is used to obtain monitoring data of the water and salt migration process of saline-alkali land using multi-source heterogeneous sensors; the processing module is used to pre-process the monitoring data to obtain processed data; the data set construction module is used to construct a water-salt migration characteristic data set based on the processed data; the model construction module is used to construct a water-salt migration characteristic analysis model based on the water-salt migration characteristic data set; the analysis module is used to complete the analysis and processing of the saline-alkali land water and salt migration characteristic data using the water-salt migration characteristic analysis model.

[0106] The workflow of the acquisition module includes: data cleaning and preprocessing of the collected monitoring data. Specifically, the Kalman filter algorithm is used to eliminate the heterogeneity of the monitoring data of different sensors in terms of format, accuracy, frequency, etc., and obtain a standardized monitoring data set with a time resolution of hours and a spatial resolution of 1 square meter. The Kalman filter process is as follows:

[0107] The workflow of the processing module includes: using the Kalman filter algorithm to eliminate the heterogeneity of the monitoring data of different sensors in format, accuracy and frequency, and obtain a standardized monitoring data set. The Kalman filter process includes:

[0108] Status prediction:

[0109]

[0110]

[0111] Status Update:

[0112]

[0113] in, represents the state estimate at time step k based on the information predicted at time step k-1; F k represents the state transfer matrix; B k represents the control input matrix; u k represents the control input at time step k; P k|k-1 represents the error covariance of the prediction; Q k represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the actual measurement value at time step k; H k represents the observation matrix; R k represents the measurement noise covariance matrix; At time step k, the state estimate is updated based on the latest measurement; P k|k represents the updated error covariance.

[0114] On this basis, Kriging interpolation was used to convert the standardized monitoring data set into unified spatiotemporal resolution monitoring data with a temporal resolution of days and a spatial resolution of 10 square meters, i.e. processed data. The Richards flow equation was used to simulate and calculate the spatiotemporal distribution of soil water potential, water content, and salt concentration at different spatiotemporal scales. By comparing with the water-salt regulation threshold of saline-alkali land, the water-salt migration process of each 10 square meter grid unit was analyzed every day.

[0115] The Kriging interpolation process is as follows:

[0116]

[0117] in, represents the estimated value of position u; Z(u i ) represents the value of a known data point; λ i Represents the interpolation weight.

[0118] In the estimation process, the condition of unbiased estimation needs to be met, that is, the expectation of the estimated value is equal to the true value. The formula is as follows:

[0119]

[0120] The goal of Kriging interpolation is to minimize the estimation error, that is, to minimize the variance between the predicted value and the true value:

[0121]

[0122] In the formula, J represents the cost function; Var represents the variance function; represents the estimated value of position u; Z(u) represents the true value of position u.

[0123] The Richards equation is the basic equation describing water flow in unsaturated porous media. It combines the conservation of mass and the Darcy-Buckingham flow relationship. Its formula is as follows:

[0124]

[0125] Where θ represents volumetric water content; ψ represents the matrix component of soil water potential; t represents time; K(θ) represents the unsaturated hydraulic conductivity function; R(θ) represents the source-sink term; Represents the divergence operator.

[0126] The Darcy flow q is driven by the potential gradient and is expressed as:

[0127]

[0128] Here, z represents the vertical coordinate.

[0129] Substituting Darcy's law into the continuity equation, we can obtain the mixed form of Richards' equation:

[0130]

[0131] Where φ represents the pore water content; p represents the pore water pressure; and K(φ) represents the hydraulic conductivity related to the saturation.

[0132] The dataset construction module aims to unify the monitoring data from different sources into a standard spatiotemporal framework with a spatial resolution of 30m and a temporal resolution of 1h by constructing a spatiotemporal scale conversion matrix in view of the differences in spatiotemporal resolution of different monitoring data, thus eliminating the errors caused by the inconsistency of spatiotemporal scales of monitoring data. Based on the unified monitoring data, the wavelet analysis method (Continuous Wavelet Transform, CWT) was used to extract the key characteristic parameters reflecting the water and salt migration process, including soil moisture, salinity, groundwater level, evapotranspiration, etc., and a water and salt migration characteristic dataset containing 42 characteristic variables was constructed.

[0133] Wavelet analysis is used to extract the time-frequency characteristics of a signal by convolving the signal with a series of scaled and translated wavelet functions. Select a suitable wavelet basis function, and through continuous wavelet transform, convolve the signal with wavelet basis functions of different scales and positions to obtain wavelet coefficients, which describe the characteristics of the signal at each scale. The expression of wavelet analysis is as follows:

[0134]

[0135] Among them, x(t) represents the original signal; ψ represents the wavelet basis function; a represents the scale parameter; and b represents the location parameter.

[0136] The model building module explores the spatiotemporal evolution laws and key influencing factors of water and salt migration in a unified spatiotemporal framework, and builds a water and salt migration characteristic analysis model. In this embodiment, the decision tree algorithm is selected to build a water and salt migration characteristic analysis model:

[0137] First, the water-salt migration feature dataset constructed by the dataset construction module is used as the basis for decision tree construction. The features that best reflect the water-salt migration process are selected as nodes of the decision tree. When classifying, the decision tree recursively divides the dataset according to the order of feature selection until all samples belong to the same category or the preset stop condition is reached. The classification effect of the decision tree is evaluated by cross-validation, confusion matrix and other methods, and the decision tree with higher accuracy is selected for subsequent analysis.

[0138] When classifying, the extracted results are classified through a decision tree to obtain a classification result. Generally speaking, the goal of decision tree classification is to group samples of the same category together and separate samples of different categories as much as possible.

[0139] Finally, the analysis module uses the water-salt migration characteristic analysis model to complete the analysis and processing of the water-salt migration characteristic data of saline-alkali land.

[0140] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A sensor-based method for analyzing and processing characteristic data of water and salt migration in saline-alkali land, characterized in that the steps include: Use multi-source heterogeneous sensors to obtain monitoring data on water and salt migration in saline-alkali land; Preprocessing the monitoring data to obtain processed data; Based on the processed data, construct a water-salt migration characteristic data set; Based on the water-salt migration characteristic data set, a water-salt migration characteristic analysis model is constructed; The water-salt migration characteristic analysis model is used to complete the analysis and processing of saline-alkali land water-salt migration characteristic data.

2. The sensor-based saline-alkali land water and salt migration characteristic data analysis and processing method according to claim 1 is characterized in that: The Kalman filter algorithm is used to eliminate the heterogeneity of the monitoring data of different sensors in format, accuracy and frequency, and obtain a standardized monitoring data set. The Kalman filter process includes: Status prediction: Status Update: in, represents the state estimate at time step k based on the information predicted at time step k-1; F k represents the state transfer matrix; B k represents the control input matrix; u k represents the control input at time step k; P k|k-1 represents the error covariance of the prediction; Q k represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the actual measurement value at time step k; H k represents the observation matrix; R k represents the measurement noise covariance matrix; At time step k, the state estimate is updated based on the latest measurement; P k|k represents the updated error covariance.

3. The sensor-based saline-alkali land water and salt migration characteristic data analysis and processing method according to claim 2 is characterized in that: Based on Kalman filtering, Kriging interpolation is used to convert the standardized monitoring data set into monitoring data with uniform spatiotemporal resolution to obtain the processed data; The Kriging interpolation process is as follows: in, represents the estimated value of position u; Z(u i ) represents the value of a known data point; λ i represents the interpolation weight; In the estimation process, the condition of unbiased estimation needs to be met, that is, the expectation of the estimated value is equal to the true value; the formula is as follows: The goal of Kriging interpolation is to minimize the estimation error, that is, to minimize the variance between the predicted value and the true value: In the formula, J represents the cost function; Var represents the variance function; represents the estimated value of position u; Z(u) represents the true value of position u.

4. The sensor-based saline-alkali land water and salt migration characteristic data analysis and processing method according to claim 1 is characterized in that: The wavelet analysis method is used to extract key characteristic parameters reflecting the water-salt migration process and construct the water-salt migration characteristic data set. The key characteristic parameters include: water content, salinity, groundwater level and evapotranspiration. The expression of the wavelet analysis is as follows: Among them, x(t) represents the original signal; ψ represents the wavelet basis function; a represents the scale parameter; and b represents the location parameter.

5. The sensor-based saline-alkali land water and salt migration characteristic data analysis and processing method according to claim 1 is characterized in that: The water-salt migration characteristic analysis model is constructed using a decision tree algorithm.

6. A sensor-based saline-alkali land water and salt migration characteristic data analysis and processing system, the system being used to implement the method according to any one of claims 1 to 5, characterized in that: include: Acquisition module, processing module, data set construction module, model construction module and analysis module; The acquisition module is used to acquire monitoring data of the water and salt migration process in saline-alkali land using multi-source heterogeneous sensors; The processing module is used to pre-process the monitoring data to obtain processed data; The data set construction module is used to construct a water-salt migration characteristic data set based on the processed data; The model building module is used to build a water-salt migration characteristic analysis model based on the water-salt migration characteristic data set; The analysis module is used to complete the analysis and processing of the water-salt migration characteristic data of saline-alkali land using the water-salt migration characteristic analysis model.

7. The sensor-based saline-alkali land water and salt migration characteristic data analysis and processing system according to claim 6 is characterized in that: The workflow of the processing module includes: using the Kalman filter algorithm to eliminate the heterogeneity of the monitoring data of different sensors in terms of format, accuracy and frequency, and obtain a standardized monitoring data set. The Kalman filter process includes: Status prediction: Status Update: in, represents the state estimate at time step k based on the information predicted at time step k-1; F k represents the state transfer matrix; B k represents the control input matrix; u k represents the control input at time step k; P k|k-1 represents the error covariance of the prediction; Q k represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the actual measurement value at time step k; H k represents the observation matrix; R k represents the measurement noise covariance matrix; At time step k, the state estimate is updated based on the latest measurement; P k|k represents the updated error covariance.

8. The sensor-based saline-alkali land water and salt migration characteristic data analysis and processing system according to claim 7 is characterized in that: The workflow of the processing module also includes: based on Kalman filtering, using Kriging interpolation to convert the standardized monitoring data set into monitoring data with uniform spatiotemporal resolution to obtain the processed data; The Kriging interpolation process is as follows: in, represents the estimated value of position u; Z(u i ) represents the value of a known data point; λ i represents the interpolation weight; In the estimation process, the condition of unbiased estimation needs to be met, that is, the expectation of the estimated value is equal to the true value; the formula is as follows: The goal of Kriging interpolation is to minimize the estimation error, that is, to minimize the variance between the predicted value and the true value: In the formula, J represents the cost function; Var represents the variance function; represents the estimated value of position u; Z(u) represents the true value of position u.

Images