Desert sand stabilization monitoring and management system based on data analysis

Abstract

The invention discloses a desert sand stabilization monitoring and management system based on data analysis, which belongs to the technical field of desert sand stabilization data analysis, and is characterized in that an acquisition instruction is sent to a sensor deployed in an implementation area through the Internet of Things, monitoring data is acquired, and the monitoring data is stored in a cache area after being subjected to integrity check and preliminary abnormal value check; obtaining a newly added monitoring index characteristic value through missing value processing, abnormal value processing and region division, and constructing a newly added monitoring index value set; performing spatial-temporal characteristic analysis on the monitoring index value set, and positioning an abnormal solid sand area; adjusting the collection frequency of the sensor in the abnormal solid sand area, sending a collection instruction through the Internet of Things technology, and monitoring the ecological benefit change trend in the abnormal solid sand area; the monitoring data of the sand stabilization area can be efficiently collected, processed and analyzed, the abnormal area is positioned according to the analysis result, and the acquisition frequency of the sensor is intelligently adjusted to optimize the monitoring process.

Description

Technical Field

[0001] The present invention relates to the technical field of desert sand fixation data analysis, and more specifically to a desert sand fixation monitoring and management system based on data analysis. Background Art

[0002] Traditional desert environment monitoring mainly relies on manual field investigations and a small number of fixed-point monitoring devices. Manual monitoring not only consumes a large amount of manpower, material resources and time, but also has a limited monitoring range and is difficult to comprehensively cover the vast desert area. At the same time, due to the low frequency of manual monitoring, it is impossible to obtain real-time change information of the desert environment in a timely manner. In the face of a complex desert environment, monitoring devices are easily affected by conditions such as sandstorms, high temperatures and low temperatures, resulting in inaccurate data collection or equipment failures. In addition, due to relatively backward data transmission and processing methods, monitoring data often has a large delay and is difficult to provide timely and effective support for sand fixation decision-making.

[0003] Although the existing sand barrier sand fixation function monitoring technology can improve efficiency and reduce costs, there are still deficiencies, including: insufficient comprehensiveness in monitoring, only focusing on wind accumulation and wind erosion amounts, and unable to comprehensively obtain multi-dimensional ecological benefit data such as soil, meteorology, and vegetation; poor real-time performance, relying on periodic drone operations and being difficult to track the dynamics of sand fixation areas in a timely manner; lack of intelligent decision-making ability, unable to automatically adjust strategies based on monitoring data, and also unable to provide comprehensive decision-making support for sand fixation management and timely early warning responses to abnormal situations. Therefore, to overcome these limitations, the present invention proposes a desert sand fixation monitoring and management system based on data analysis. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a desert sand fixation monitoring and management system based on data analysis, which solves the technical problems of how to efficiently collect, process and analyze the monitoring data of sand fixation areas, and accurately locate abnormal areas and intelligently adjust the sensor collection frequency based on the analysis results to optimize monitoring. The data collection module sets the sensor collection frequency according to the characteristics of different monitoring indicators, sends instructions to various sensors in the implementation area of the sand fixation project to collect monitoring data, checks the integrity and outliers of the data and stores them in the cache area, and processes missing values and outliers when new data is added to construct a new set of monitoring indicator values; the data analysis module performs spatio-temporal feature analysis on the stored set of indicator values, including trend and breakpoint identification of time series and autocorrelation analysis of spatial distribution, and locates abnormal sand fixation sub-areas based on the analysis results; the decision feedback module adjusts the collection frequency of abnormal sensors after detecting abnormal areas, feeds back the adjusted frequency to the data collection module, and at the same time displays the characteristic values of monitoring indicators in abnormal areas, real-time data of abnormal sensors and the record of collection frequency adjustment through a visualization interface, and can also give early warnings and conduct on-site inspections according to the proportion of abnormal sensors to achieve effective monitoring and management of desert sand fixation areas.

[0005] To achieve the above object, the present invention provides the following technical solutions: A desert sand fixation monitoring and management system based on data analysis, comprising a data acquisition module, a data analysis module and a decision feedback module; The data acquisition module is used to collect monitoring data for the implementation area of the sand fixation project. It sends acquisition instructions to the sensors deployed in the implementation area through the Internet of Things, obtains monitoring data, performs integrity checks and preliminary outlier tests on the monitoring data, and then stores it in the buffer area; when new monitoring data is added to the buffer area, new monitoring index characteristic values are obtained through missing value processing, outlier processing and area division, and a new monitoring index value set is constructed and stored in the storage area of the central management platform; The data analysis module is used to perform spatio-temporal feature analysis on the monitoring index value set in the storage area, identify abnormal sand fixation sub-areas. Through time series analysis, it mines the change characteristics of each monitoring index characteristic value in the monitoring index value set over time, identifies the time series change trend, and through spatial distribution analysis, obtains the spatial distribution characteristics of the monitoring index characteristic values, identifies the spatial abnormal trend, and locates the abnormal sand fixation sub-areas based on the time series change trend and the spatial abnormal trend; The decision feedback module is used to adjust the acquisition frequency of the sensors in the abnormal sand fixation sub-areas, send acquisition instructions through Internet of Things technology to obtain the monitoring index characteristic values of the abnormal sand fixation sub-areas, and monitor the change trend of the ecological benefits in the abnormal sand fixation sub-areas.

[0006] Specifically, the specific steps of the spatio-temporal feature analysis include: Set the abnormal analysis interval for each monitoring index characteristic value. Every time an abnormal analysis interval passes, select the monitoring index characteristic values from the monitoring index value set in the storage area to construct an abnormal analysis set of the monitoring index characteristic values; Divide the abnormal analysis set according to the time series to obtain the time series abnormal analysis set of the monitoring index characteristic values of each sand fixation sub-area; For the time series abnormal analysis set after missing value processing, perform time series change trend identification, including trend identification and mutation point identification, and calculate the time series abnormal score of the time series abnormal analysis set; Divide the abnormal analysis set according to the spatial sequence to obtain the spatial abnormal analysis set of the monitoring index characteristic values at each moment; For the spatial abnormal analysis set after missing value processing, perform spatial change trend identification, including autocorrelation analysis and mutation point identification, and calculate the spatial abnormal score of the spatial abnormal analysis set; Configure the spatial abnormal threshold and the time series abnormal threshold. If the spatial abnormal score of the spatial abnormal analysis set is greater than the spatial abnormal threshold, mark the moment where the spatial abnormal analysis set is located as the time series abnormal moment, otherwise do not perform any processing; If the timing anomaly score of the timing anomaly analysis set is greater than the timing anomaly threshold, the fixed sand sub-region where the timing anomaly analysis set is located is marked as a spatial anomaly region; Within the implementation area of the sand fixation project, screen the fixed sand sub-regions that simultaneously have the marks of timing anomaly moments and spatial anomaly regions, and mark them as abnormal fixed sand sub-regions.

[0007] Specifically, the specific steps for identifying the timing change trend include: Set a smoothing time window, perform a moving average on the timing anomaly analysis set, obtain the moving average value of each monitoring index feature value in the timing anomaly analysis set, calculate the moving deviation between each monitoring index feature value and its moving average value, and calculate the standard deviation of the moving deviation; Configure the deviation change threshold. If the standard deviation of the moving deviation of the timing anomaly analysis set is greater than the deviation change threshold, perform mutation point identification on the timing anomaly analysis set; otherwise, do not perform any processing; Specifically, the steps for performing mutation point identification on the timing anomaly analysis set include: Configure the deviation anomaly threshold. If the moving deviation of the monitoring index feature value is greater than the deviation anomaly threshold, mark the monitoring index feature value as a potential mutation point; otherwise, do not perform any operation; Calculate the relative change rate of each potential mutation point based on the relative magnitude of the monitoring index feature value at the potential mutation point with respect to the monitoring index feature values at adjacent moments; Configure the change rate threshold. If the relative change rate of the potential mutation point is greater than the change rate threshold, mark the point as a mutation point, mark the timestamp where the mutation point is located and the timing anomaly analysis set where the mutation point is located; otherwise, do not perform any processing; Combine the standard deviation of the moving deviation of the monitoring index feature values in the timing anomaly analysis set and the number of mutation points to calculate the timing anomaly score of the timing anomaly analysis set.

[0008] Specifically, the specific steps for identifying the spatial change trend include: Perform a global spatial autocorrelation analysis on the spatial anomaly analysis set. Combine the spatial positions of the fixed sand sub-regions to obtain the difference between the monitoring index feature value of each fixed sand sub-region in the spatial anomaly analysis set and its mean value, and calculate the overall spatial autocorrelation score of the monitoring index feature values in the fixed sand region for the spatial anomaly analysis set; Configure the autocorrelation score threshold. If the overall spatial autocorrelation score of the monitoring index feature values in the fixed sand region for the spatial anomaly analysis set is greater than the autocorrelation score threshold, do not perform any processing; otherwise, perform mutation point identification on the spatial anomaly analysis set; Calculate the local spatial autocorrelation coefficient for each sand-fixing area, configure the relevant mutation threshold. If the local spatial autocorrelation coefficient of the sand-fixing area is less than the relevant mutation threshold, mark the sand-fixing area as a mutation area; otherwise, do not perform any processing. Combine the overall spatial autocorrelation score of the monitoring index eigenvalues in the spatial anomaly analysis set , the local spatial autocorrelation coefficient of the sand-fixing area and the number of mutation areas in the spatial anomaly analysis set to calculate the spatial anomaly score of the spatial anomaly analysis set.

[0009] Specifically, the steps for collecting monitoring data include: Set the sensor data collection frequency. Based on the data collection frequency, send collection instructions to the sensors within the implementation area of the sand-fixing project through the Internet of Things. When the sensor receives the collection instruction, measure the monitoring data, and the monitoring data is returned to the central management platform in the form of digital signals or analog signals through the Internet of Things. After the central management platform marks the received monitoring data with sensor tags and timestamp tags, check the integrity of the monitoring data and determine whether there are missing values. If the received monitoring data has missing values, according to the sensor tags, the data collection module resends the collection instruction to obtain substitute monitoring data for filling the missing values. Judge whether the substitute monitoring data is a missing value. If the substitute monitoring data is a missing value, issue a sensor warning; otherwise, do not perform any operation. Conduct a preliminary outlier test on the monitoring data after integrity check. According to the sensor type, set the sensor data range. Based on the sensor tags and sensor data range of the monitoring data, screen the monitoring data outside the sensor data range and mark it as abnormal monitoring data. Classify the monitoring data that has passed the integrity check and preliminary outlier test according to the sensor tags and store it in the cache area of the central management platform.

[0010] Specifically, the monitoring indicators include soil monitoring indicators, meteorological monitoring indicators, vegetation monitoring indicators, and sand-fixing equipment monitoring indicators. Specifically, the steps for obtaining the monitoring index eigenvalues include: When new monitoring data is added to the cache area, select the new monitoring data of the corresponding sensors according to the monitoring index type, construct a new monitoring data set, and obtain the location coordinates of each sensor in the new monitoring data set. Perform missing value processing on the new monitoring data set, screen the missing values in the new monitoring data set, count the number of missing values, and calculate the missing value frequency of the new monitoring data set. Configure the missing frequency threshold. If the missing value frequency of the newly added monitoring data set is greater than the missing frequency threshold, start the sensor fault troubleshooting process and set the newly added monitoring data set to an empty set; otherwise, fill in the missing values of the newly added monitoring data set through spatial interpolation; Perform outlier processing on the newly added monitoring data set, filter out the data points marked as abnormal monitoring data in each newly added monitoring data set, count the number of data points marked as abnormal monitoring data, and calculate the outlier frequency of the newly added monitoring data set; Configure the outlier frequency threshold. If the outlier frequency of the newly added monitoring data set is greater than the outlier frequency threshold, perform cluster analysis on the abnormal monitoring data to locate the abnormal area; otherwise, fill in the abnormal monitoring data of the newly added monitoring data set through spatial interpolation.

[0011] Specifically, the steps for obtaining the monitoring index characteristic values further include: Divide the sand fixation sub-areas in the area where the sand fixation project is implemented. According to the sensor position coordinates in the sand fixation area, divide the newly added monitoring data set after missing value processing and outlier processing to obtain the newly added monitoring index set for each sand fixation sub-area; According to the sensor type, divide the newly added monitoring index set to obtain the newly added monitoring index subset for each type of sensor, and calculate the mean value of the monitoring data in each newly added monitoring index subset as the monitoring index characteristic value of the newly added monitoring index subset in the sand fixation sub-area; Obtain the monitoring index characteristic values of each monitoring index in each sensor type for all sand fixation sub-areas, construct the newly added monitoring index value set for the sand fixation area, mark the time stamp and store it in the storage area of the central management platform.

[0012] Specifically, the steps for filling in the missing values of the newly added monitoring data set include: According to the sensor type, divide the newly added monitoring data set to obtain the newly added monitoring data subset; Obtain the position coordinates of the sensor where the missing value is located in the newly added monitoring data subset , configure the compensation radius, and divide the compensation area of the missing value according to the compensation radius , filter out the monitoring data of non-missing values in the compensation area, and calculate the compensated monitoring data of the missing value according to the inverse distance weighted interpolation.

[0013] Specifically, the steps for performing cluster analysis on the abnormal monitoring data include: Obtain the position coordinates of the sensor where the abnormal monitoring data is located in the newly added monitoring data set, set the number of clusters, and based on the number of clusters, divide the sensor where the abnormal monitoring data is located into multiple cluster clusters through the clustering algorithm; Count the number of abnormal monitoring data in each cluster, and calculate the abnormal concentration of the sensors where the abnormal monitoring data is located in each cluster according to the area of the cluster. Configure a concentration threshold. If the abnormal concentration of a cluster is greater than the concentration threshold, divide the area where the cluster is located into an abnormal area, issue an abnormal warning for the cluster in the abnormal area, and set the abnormal monitoring data in the cluster in the abnormal area to null values; otherwise, fill the abnormal monitoring data of the cluster through spatial interpolation.

[0014] Specifically, the steps for adjusting the acquisition frequency of sensors in the abnormal sand-fixing area include: When an abnormal sand-fixing area is detected, screen the characteristic values of the monitoring indicators at abnormal times in the abnormal sand-fixing area, obtain the sensors where the characteristic values of the monitoring indicators are located, mark them as abnormal sensors, and obtain the acquisition frequency of the abnormal sensors. Configure an abnormal sensor threshold, count the number of abnormal sensors in the abnormal sand-fixing area, calculate the proportion of abnormal sensors. If the proportion of abnormal sensors in the sand-fixing area is greater than the abnormal sensor threshold, issue a warning for the sand-fixing area; otherwise, do nothing. Set a set of adjustment coefficients according to the proportion of abnormal sensors in the abnormal sand-fixing area, and each adjustment coefficient is applied to the proportion of abnormal sensors in different abnormal sand-fixing areas. Based on the adjustment coefficient, adjust the acquisition frequency of the abnormal sensors in the abnormal sand-fixing area according to the current acquisition frequency of the abnormal sensors in the abnormal sand-fixing area.

[0015] The beneficial effects of the present invention: 1. A multi-layer data quality guarantee system is constructed from the data acquisition source. In the data acquisition link, the integrity of the sensor data is checked. Once a missing value is found, the process of re-acquiring replacement data is immediately started to ensure that there is no omission in the data. At the same time, through preliminary outlier tests, abnormal monitoring data outside the sensor data range is screened out to prevent incorrect data from entering the subsequent processing process. In the data processing stage, scientific methods such as spatial interpolation and clustering analysis are used to process the missing values and outliers in the newly added monitoring data set to ensure that the finally stored data is accurate and reliable. The reliability of the data during the operation of the system is enhanced, providing a solid foundation for the stable operation of the system.

[0016] 2. By means of the spatio-temporal feature analysis method, deeply explore the potential information in the monitoring index values. In terms of time series analysis, by setting a smoothing time window, identifying mutation points and other operations, accurately capture the changing trend of the characteristic values of the monitoring index over time, and calculate the time series anomaly score. In spatial distribution analysis, use techniques such as global and local spatial autocorrelation analysis to accurately obtain the spatial distribution characteristics of the characteristic values of the monitoring index, and calculate the spatial anomaly score. Based on these two anomaly scores, the system can accurately locate the abnormal sand-fixing areas, providing a key basis for subsequent decision-making.

[0017] 3. Automatically set the adjustment coefficient according to the proportion of abnormal sensors in the abnormal sand-fixing area, and then intelligently adjust the acquisition frequency of the abnormal sensors. Fully consider the severity and influence range of the abnormality. For areas with more serious abnormalities, increase the sensor acquisition frequency to obtain monitoring data more densely and timely grasp the changing trend of ecological benefits. At the same time, the adjusted acquisition frequency can be fed back to the data acquisition module in real time, realizing a closed-loop intelligent decision-making from abnormal monitoring to data acquisition strategy adjustment, and enhancing the system's decision-making ability to handle complex situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic structural diagram of the desert sand-fixing monitoring and management system based on data analysis of the present invention; Figure 2 is a flowchart of the specific steps for collecting monitoring data of the present invention; Figure 3 is a flowchart of the specific steps for filling in the missing values of the newly added monitoring data set of the present invention; Figure 4 is a flowchart of the specific steps for performing clustering analysis on the abnormal monitoring data of the present invention; Figure 5 is a flowchart of the specific steps for spatio-temporal feature analysis of the present invention; Figure 6 is a flowchart of the specific steps for identifying the time series change trend of the present invention; Figure 7 is a flowchart of the specific steps for identifying the spatial change trend of the present invention; Figure 8 is a flowchart of the specific steps for adjusting the acquisition frequency of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] Please refer to Figure 1 , this embodiment introduces a desert sand-fixing monitoring and management system based on data analysis, including a data acquisition module, a data analysis module and a decision feedback module; The data acquisition module is used to collect monitoring data in the implementation area of the sand fixation project. It sends acquisition instructions to the sensors deployed in the implementation area through the Internet of Things, obtains the monitoring data, performs integrity checks and preliminary outlier tests on the monitoring data, and then stores it in the cache area. When new monitoring data is added to the cache area, the new monitoring index characteristic values are obtained through missing value processing, outlier processing and regional division, and the new monitoring index value set is constructed and stored in the storage area of the central management platform.

[0020] The sensors include: soil humidity sensors, soil nutrient sensors, temperature sensors, humidity sensors, wind speed sensors, wind direction sensors, AI vision sensors and sand barrier displacement sensors. The monitoring data includes: soil humidity data, soil nutrient data, temperature data, humidity data, wind speed data, wind direction data, vegetation coverage rate, vegetation growth rate and sand barrier displacement data. The monitoring indicators include soil monitoring indicators, meteorological monitoring indicators, vegetation monitoring indicators and sand fixation equipment monitoring indicators. The soil monitoring indicators include soil humidity characteristics and soil nutrient characteristics. The meteorological monitoring indicators include meteorological temperature characteristics, meteorological humidity characteristics, meteorological wind speed characteristics and meteorological wind direction characteristics. The vegetation monitoring indicators include vegetation coverage rate characteristics and vegetation growth rate characteristics. The sand fixation equipment monitoring indicators include sand barrier displacement characteristics. Please refer to Figure 2 , preferably, the specific steps of monitoring data acquisition include: Set the sensor data acquisition frequency. Based on the data acquisition frequency, the data acquisition module sends acquisition instructions to the sensors through the Internet of Things. Set the sensor data acquisition frequency according to the characteristics and monitoring requirements of different monitoring indicators. Exemplarily: For the sensors related to meteorological monitoring indicators, since they are greatly affected by weather and time factors and change relatively frequently, the data acquisition frequency can be set to once per minute to capture the rapid changes in meteorological conditions. For the sensors related to soil monitoring indicators, their changes are relatively slow, and it can be set to once per hour or once per day according to the evaporation and infiltration laws of soil moisture and the consumption and replenishment cycles of soil nutrients. For the sand barrier displacement sensor, considering the uncertainty of the sand barrier affected by wind and sand erosion and external forces, the acquisition frequency can be set to once every half hour to timely grasp the stability of the sand barrier. For the sensors related to vegetation monitoring indicators, such as AI vision sensors, to monitor the changes in the growth state of vegetation, set the acquisition frequency according to the growth rate of vegetation, and collect video data at several key time periods to obtain the vegetation coverage rate and vegetation growth rate. When the sensor receives the acquisition instruction, it measures the monitoring data, and the monitoring data returns to the central management platform through the Internet of Things in the form of digital signals or analog signals. After the central management platform marks the received monitoring data, the marks include sensor marks and timestamp marks. It checks the integrity of the monitoring data and determines whether there are missing values. If there are missing values in the received monitoring data, according to the sensor marks, the data acquisition module resends the acquisition instruction to obtain substitute monitoring data for filling the missing values. Determine whether the substitute monitoring data is a missing value. If the substitute monitoring data is a missing value, sensor warning is performed to check whether there is a sensor failure or communication interference, and the missing value is retained; otherwise, no operation is performed. Perform a preliminary outlier test on the monitoring data after integrity check. According to the sensor type, set the sensor data range. According to the sensor marks and sensor data range of the monitoring data, filter out the monitoring data outside the sensor data range and mark it as abnormal monitoring data. Store the monitoring data that has passed the integrity check and preliminary outlier test into the cache area of the central management platform according to the sensor marks.

[0021] Preferably, the specific steps for obtaining the monitoring index characteristic values include: When new monitoring data is added to the cache area, select the new monitoring data of relevant sensors according to the monitoring index type, construct a new monitoring data set, and obtain the location coordinates of each sensor in the new monitoring data set. Exemplarily, for soil monitoring indexes, filter out the monitoring data of soil moisture sensors and soil nutrient sensors; for meteorological monitoring indexes, select the monitoring data of temperature, humidity, wind speed, and wind direction sensors. At the same time, quickly obtain the accurate location coordinates of each sensor from the sensor information library to ensure the close association between the data and the geographical location.

[0022] Perform missing value processing on the new monitoring data set, filter out the missing values in the new monitoring data set, count the number of missing values, and calculate the missing value frequency of the new monitoring data set, that is: ; Where is the missing value frequency of the th new monitoring data set, is the number of missing values in the th new monitoring data set, is the number of monitoring data in the th new monitoring data set; Configure the missing frequency threshold , if the missing value frequency of the new monitoring data set is greater than the missing frequency threshold , if it is indicated that there are large-scale anomalies in the sensor monitoring data in the newly added monitoring dataset, then start the sensor fault troubleshooting process and set the newly added monitoring dataset to an empty set; otherwise, fill in the missing values in the newly added monitoring dataset through spatial interpolation; Please refer to Figure 3 , specifically, the specific steps for filling in the missing values in the newly added monitoring dataset through spatial interpolation include: Divide the newly added monitoring dataset according to the sensor type to obtain the newly added monitoring data subsets , where is the th newly added monitoring data subset of the th newly added monitoring dataset, is the th newly added monitoring data subset of the th newly added monitoring dataset, and is the monitoring data collected by the th sensor in the th newly added monitoring data subset of the th newly added monitoring dataset; taking the newly added soil monitoring dataset as an example, it can be divided into the newly added soil moisture monitoring data subset and the newly added soil nutrient monitoring data subset.

[0023] Obtain the position coordinates of the sensors where the missing values are located in the newly added monitoring data subsets , configure the compensation radius, and divide the compensation area of the missing values according to the compensation radius , screen the monitoring data of non-missing values in the compensation area, and calculate the compensated monitoring data of the missing values according to the inverse distance weighted interpolation, that is: ; ; where is the compensated monitoring data of the missing values in the th newly added monitoring data subset of the th newly added monitoring dataset, is the monitoring data collected by the th sensor in the compensation area where the missing value is located of the position coordinates, is the monitoring data collected by the th sensor in the compensation area where the missing value is located of the weighting coefficient, is the position coordinate and of the distance, is the power of the distance, and the value range is [1, 2].

[0024] Perform outlier processing on the newly added monitoring dataset, screen the data points marked as abnormal monitoring data in each newly added monitoring dataset, and count the number of data points marked as abnormal monitoring data. Calculate the outlier frequency of the newly added monitoring dataset, i.e.: ; where is the outlier frequency of the th newly added monitoring dataset, is the number of abnormal monitoring data in the th newly added monitoring dataset; Configure the outlier frequency threshold . If the outlier frequency of the newly added monitoring dataset is greater than the outlier frequency threshold , perform cluster analysis on the abnormal monitoring data to locate the abnormal area. Otherwise, fill in the abnormal monitoring data of the newly added monitoring dataset through spatial interpolation; Specifically, the specific steps for filling in the abnormal monitoring data of the newly added monitoring dataset through spatial interpolation include: Divide the newly added monitoring dataset according to the sensor type to obtain the newly added monitoring data subset; Obtain the position coordinates of the sensors where the abnormal monitoring data in the newly added monitoring data subset are located, configure the filling radius, divide the filling area of the abnormal monitoring data according to the filling radius, screen the monitoring data of non-abnormal monitoring data in the filling area, and calculate the filled monitoring data of the abnormal monitoring data according to the inverse distance weighted interpolation.

[0025] Please refer to Figure 4 . Specifically, the specific steps for performing cluster analysis on the abnormal monitoring data include: Obtain the position coordinates of the sensors where the abnormal monitoring data are located in the newly added monitoring dataset, set the number of clusters , and divide the sensors where the abnormal monitoring data are located into cluster clusters through the clustering algorithm, and obtain the position coordinates of the cluster centers; Calculate the distance between each sensor where the abnormal monitoring data are located and the position of the cluster center, select the distance of the sensor farthest from the position of the cluster center as the radius to calculate the area of the cluster, i.e.: ; where is the area of the cluster , is the position coordinates of the sensors where the abnormal monitoring data of the cluster are located, is the position coordinates of the center of the cluster , is the position coordinate and distance; Count the number of abnormal monitoring data in each cluster, and calculate the abnormal concentration of the sensor where the abnormal monitoring data is located in each cluster according to the area of the cluster, that is: ; Wherein, is the abnormal concentration in the cluster , is the number of abnormal monitoring data in the cluster ; Configure a concentration threshold. If the abnormal concentration of the cluster is greater than the concentration threshold, it means that the abnormal monitoring data in the cluster is in an aggregated state and there is an aggregated abnormality. Then divide the area where the cluster is located into an abnormal area, issue an abnormal warning for the cluster in the abnormal area, and set the abnormal monitoring data in the cluster in the abnormal area to null values; otherwise, fill in the abnormal monitoring data of the cluster through spatial interpolation; Divide the sand fixation area of the sand fixation control project implementation area to divide the sand fixation sub-areas. According to the sensor position coordinates in the sand fixation area, divide the new monitoring data set after missing value processing and outlier processing to obtain the new monitoring index set for each sand fixation sub-area; According to the sensor type, divide the new monitoring index set to obtain the new monitoring index subset for each type of sensor, and calculate the mean value of the monitoring data in each new monitoring index subset as the monitoring index characteristic value of the new monitoring index subset in the sand fixation sub-area; Obtain the monitoring index characteristic values of each monitoring index in each sensor type for all sand fixation sub-areas, construct the new monitoring index value set of the sand fixation area, mark the time stamp and store it in the storage area of the central management platform. The new monitoring index value set contains the monitoring index characteristic values included in each monitoring index in each sand fixation sub-area for the new monitoring data in the cache area, and mark the time stamp for the new monitoring index value set according to the time stamp of the monitoring data in the new monitoring index set.

[0026] The data analysis module is used to perform spatio-temporal feature analysis on the monitoring index value set in the storage area to identify abnormal sand fixation sub-areas. Through time series analysis, it mines the change characteristics of each monitoring index characteristic value in the monitoring index value set over time, identifies the time series change trend, and through spatial distribution analysis, obtains the spatial distribution characteristics of the monitoring index characteristic values, identifies the spatial abnormal trend, and locates the abnormal sand fixation sub-areas based on the time series change trend and the spatial abnormal trend; Please refer to Figure 5 , preferably, the specific steps of spatio-temporal feature analysis include: Set the abnormal analysis interval for the characteristic values of each monitoring index. Every time an abnormal analysis interval passes, screen the characteristic values of the monitoring index from the monitoring index value set in the storage area, and construct an abnormal analysis set of the characteristic values of the monitoring index , that is: ; Among them, is the characteristic value of the monitoring index at the moment of the th fixed sand area, when, is the abnormal analysis interval, which is used to measure the number of characteristic values of the screened monitoring index, is the total number of fixed sand areas, is the final acquisition moment of the characteristic value of the monitoring index when constructing the abnormal analysis set; according to the characteristics and actual needs of different monitoring indexes, set a suitable abnormal analysis interval for the characteristic value of each monitoring index to determine the acquisition time span of the screened characteristic value of the monitoring index

[0027] Divide the abnormal analysis set according to the time series to obtain the time series abnormal analysis set of the characteristic values of the monitoring index for each fixed sand area. The time series abnormal analysis set for the th fixed sand area is ; perform missing value interpolation filling on the time series abnormal analysis set. The missing value interpolation filling methods include linear interpolation, polynomial interpolation, and statistical feature filling For the time series abnormal analysis set after missing value processing, perform time series change trend recognition, including trend recognition and mutation point recognition, and calculate the time series abnormal score of the time series abnormal analysis set Please refer to Figure 6 , specifically, the specific steps of time series change trend recognition include: Set a smoothing time window, perform moving average on the time series abnormal analysis set, smooth the data fluctuations of the time series abnormal analysis set, obtain the moving average value of each characteristic value of the monitoring index in the time series abnormal analysis set, calculate the moving deviation between each characteristic value of the monitoring index and its moving average value, and calculate the standard deviation of the moving deviation to evaluate the trend stability of the time series abnormal analysis set Configure the deviation change threshold. If the standard deviation of the moving deviation of the time series abnormal analysis set is greater than the deviation change threshold, it indicates that the characteristic values of the monitoring index in the time series abnormal analysis set fluctuate greatly and there is an abnormal trend. Then perform mutation point recognition on the time series abnormal analysis set, otherwise do not perform any processing Perform mutation point recognition on the time series abnormal analysis set, including configuring the abnormal deviation threshold. If the moving deviation of the characteristic value of the monitoring index is greater than the abnormal deviation threshold, then mark the characteristic value of the monitoring index as a potential mutation point, otherwise do not perform any operation Calculate the relative change rate of each potential mutation point based on the relative magnitude of the monitoring index eigenvalue at the potential mutation point with respect to the monitoring index eigenvalues at adjacent moments, i.e.: ; where is the monitoring index eigenvalue at the th moment of the sand-fixing area , the relative change rate, is the maximum value function; Configure the change rate threshold. If the relative change rate of a potential mutation point is greater than the change rate threshold, mark this point as a mutation point, mark the timestamp where the mutation point is located and the abnormal analysis set of the time sequence where the mutation point is located; otherwise, do not perform any processing; Combine the standard deviation of the moving deviation of the monitoring index eigenvalues in the abnormal analysis set of the time sequence and the number of mutation points to calculate the time sequence abnormal score of the abnormal analysis set of the time sequence, i.e.: ; where is the time sequence abnormal score of the abnormal analysis set , is the standard deviation of the moving deviation of the monitoring index eigenvalues of the abnormal analysis set of the time sequence, is the number of mutation points in the abnormal analysis set of the time sequence, , are both non - negative weighting coefficients, and the value range is (0, 1); Divide the abnormal analysis set according to the spatial sequence to obtain the spatial abnormal analysis set of the monitoring index eigenvalues at each moment. The spatial abnormal analysis set at moment is ; Perform spatial interpolation filling on the spatial abnormal analysis set; For the spatial abnormal analysis set after missing value processing, perform spatial change trend identification, including autocorrelation analysis and mutation point identification, and calculate the spatial abnormal score of the spatial abnormal analysis set; Please refer to Figure 7 , specifically, the specific steps of spatial change trend identification include: Perform global spatial autocorrelation analysis on the spatial abnormal analysis set. Combine the spatial positions of the sand - fixing areas to calculate the overall spatial autocorrelation score of the monitoring index eigenvalues in the spatial abnormal analysis set within the sand - fixing areas, i.e.: ; where is the overall spatial autocorrelation score of the monitoring index eigenvalues of the spatial abnormal analysis set , is the mean of the monitoring index eigenvalues of the spatial anomaly analysis set The mean value of the monitoring index eigenvalues is the spatial anomaly analysis set In the th fixed sand area and the th fixed sand area, the non - negative weighting coefficient ranges from (0, 1). is the th fixed sand area at time The monitoring index eigenvalue The value range of , is the th fixed sand area at time The monitoring index eigenvalue The value range of ; Configure the spatial autocorrelation score threshold. If the overall spatial autocorrelation score of the monitoring index eigenvalues in the spatial anomaly analysis set within the fixed sand area is greater than the autocorrelation score threshold, it indicates that the monitoring index eigenvalues show a clustered distribution in space, there is a strong spatial autocorrelation within the entire fixed sand area, and there is no mutation area, so no treatment is performed. Otherwise, identify the mutation points for the spatial anomaly analysis set; For each fixed sand area, calculate its local spatial autocorrelation coefficient. For the th fixed sand area, its local spatial autocorrelation coefficient is: ; Among them, is the local spatial autocorrelation coefficient of the th fixed sand area, is the spatial anomaly analysis set In the th fixed sand area and the th fixed sand area, the non - negative weighting coefficient ranges from (0, 1); Configure the relevant mutation threshold. If the local spatial autocorrelation coefficient of the fixed sand area is less than the relevant mutation threshold, it indicates that there is a large difference in the monitoring index eigenvalues between this fixed sand area and the surrounding fixed sand areas, and it is the area where the spatial mutation point is located. Then mark this fixed sand area as a mutation area, otherwise no treatment is performed; Combined with the overall spatial autocorrelation score of the monitoring index eigenvalues of the spatial anomaly analysis set, the local spatial autocorrelation coefficient of the fixed sand area, and the number of mutation areas in the spatial anomaly analysis set, calculate the spatial anomaly score of the spatial anomaly analysis set: ; Among them, is the spatial anomaly analysis set Spatial anomaly score, is the local spatial autocorrelation coefficient of the th solid sand area, is the number of mutation regions in the spatial anomaly analysis set , , and are all non - negative weighted coefficients, and the value range is (0, 1); Configure the spatial anomaly threshold and the time - series anomaly threshold. If the spatial anomaly score of the spatial anomaly analysis set is greater than the spatial anomaly threshold, mark the moment where the spatial anomaly analysis set is located as the time - series anomaly moment, otherwise do not perform any processing; if the time - series anomaly score of the time - series anomaly analysis set is greater than the time - series anomaly threshold, mark the solid sand area where the time - series anomaly analysis set is located as the spatial anomaly area; In the area where the sand - fixation project is implemented, screen the solid sand areas that simultaneously have the time - series anomaly moment mark and the spatial anomaly area mark, and mark them as abnormal solid sand areas.

[0028] The decision - feedback module is used to adjust the acquisition frequency of sensors in the abnormal solid sand area, send acquisition instructions through the Internet of Things technology to obtain the monitoring index characteristic values of the abnormal solid sand area, and monitor the change trend of the ecological benefits in the abnormal solid sand area; Please refer to Figure 8 , preferably, the specific steps for adjusting the acquisition frequency of sensors in the abnormal solid sand area include: When an abnormal solid sand area is detected, screen the monitoring index characteristic values at abnormal moments in the abnormal solid sand area, obtain the sensors where the monitoring index characteristic values are located, mark them as abnormal sensors, and obtain the acquisition frequency of the abnormal sensors; Configure the abnormal sensor threshold, count the number of abnormal sensors in the abnormal solid sand area, calculate the proportion of abnormal sensors. If the proportion of abnormal sensors in the solid sand area is greater than the abnormal sensor threshold, issue a warning for the solid sand area, indicating that there is an obvious deviation in this solid sand area, and notify the staff to conduct on - site investigation through the warning, otherwise do not perform any operation; Set the adjustment coefficient set according to the proportion of abnormal sensors in the abnormal solid sand area , where , and each adjustment coefficient is applied to the proportion of abnormal sensors in different abnormal solid sand areas, that is: ; Among them, is the adjustment coefficient, is the proportion of abnormal sensors in the abnormal solid sand area, , and are all abnormal sensor proportion thresholds, and , set according to the experimental results; Based on the adjustment coefficient, according to the current acquisition frequency of the abnormal sensors in the abnormal sand-fixing area, adjust the acquisition frequency of the abnormal sensors in the abnormal sand-fixing area, that is: ; Among them, is the adjusted acquisition frequency of the th abnormal sensor in the abnormal sand-fixing area, is the maximum acquisition frequency of the th abnormal sensor in the abnormal sand-fixing area, is the current acquisition frequency of the th abnormal sensor in the abnormal sand-fixing area, is the ceiling function, is the minimum value function; Feed back the adjusted acquisition frequency of the abnormal sensors to the data acquisition module. The data acquisition module sends acquisition instructions based on the adjusted acquisition frequency of the abnormal sensors to obtain the monitoring data of the abnormal sensors, so as to obtain the monitoring index characteristic values; Summarize and display the monitoring index characteristic values of the abnormal sand-fixing area in the form of a chart through the visualization interface, and give the real-time monitoring data of the abnormal sensors and the record information of the adjustment of the acquisition frequency of the abnormal sensors.

[0029] Working principle and its effect: The desert sand-fixing monitoring and management system based on data analysis realizes the efficient monitoring and management of the desert sand-fixing area through the collaborative work of the data acquisition module, the data analysis module and the decision feedback module.

[0030] The data acquisition module sends acquisition instructions to various sensors according to the characteristics of the monitoring indicators, such as meteorological indicators per minute, soil indicators per hour or per day, sand barrier displacement per half hour, and vegetation indicators at regular time intervals according to the growth rate. The sensors transmit the monitoring data to the central management platform. The platform marks, checks the integrity, processes the missing values and abnormal values, and then stores them in the cache area. When there is new data in the cache, a data set is constructed, the missing values and abnormal values are processed, the sand-fixing areas are divided, the monitoring index characteristic values are calculated, and the monitoring index value set is constructed and stored.

[0031] The data analysis module conducts spatio-temporal feature analysis on the stored monitoring index value set. An abnormal analysis set is constructed according to the abnormal analysis interval. After being divided by time series, through missing value processing, trend and mutation point identification, the time series abnormal score is calculated; after being divided by space series, through spatial interpolation and autocorrelation analysis, the spatial abnormal score is calculated. According to the scores and thresholds, the abnormal sand-fixing areas are determined.

[0032] After the decision feedback module detects an abnormal area, it screens the characteristic values of the indicators at the abnormal moment and the corresponding sensors, and decides whether to give an early warning according to the proportion of abnormal sensors. At the same time, it adjusts the acquisition frequency of the abnormal sensors according to the set of adjustment coefficients and feeds it back to the data acquisition module. Finally, it displays the characteristic values of the monitoring indicators in the abnormal area in the form of charts, providing real-time data of the abnormal sensors and records of the adjustment of the acquisition frequency.

[0033] The following effects are achieved: on the one hand, the system can effectively guarantee the data quality, ensure integrity and accuracy from the source of data acquisition, timely discover and process missing values and abnormal values, improve data reliability, and at the same time give early warnings and conduct investigations on sensor failures and large-scale abnormalities in a timely manner to maintain the stable operation of the system. On the other hand, through in-depth spatio-temporal analysis, it can accurately identify abnormal areas and moments, comprehensively evaluate the degree and scope of abnormalities, and provide a scientific basis for sand fixation governance. Finally, the intelligent decision-making ability of the system can dynamically adjust the acquisition frequency of sensors according to abnormal situations to more accurately grasp the changing trend of the ecological benefits in the abnormal area. At the same time, it visualizes the information, which is convenient for the staff to view and make decisions intuitively, greatly improving the efficiency and scientific nature of desert sand fixation monitoring and management, contributing to the implementation and management of desert sand fixation governance projects, and promoting the smooth development of desert governance work.

[0034] The above is only the preferred implementation mode of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for those of ordinary skill in the art, several improvements and refinements made without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A desert sand fixation monitoring and management system based on data analysis, characterized in that, It includes a data acquisition module, a data analysis module, and a decision feedback module; The data acquisition module is used to collect monitoring data for the implementation area of the sand fixation project. It sends acquisition instructions to the sensors deployed in the implementation area through the Internet of Things, obtains the monitoring data, performs integrity checks and preliminary outlier tests on the monitoring data, and then stores it in the cache area. When new monitoring data is added to the cache area, it obtains the characteristic values of the new monitoring indicators through missing value processing, outlier processing, and area division, and constructs a set of new monitoring indicator values and stores them in the storage area of the central management platform; The data analysis module is used to perform spatio-temporal characteristic analysis on the set of monitoring indicator values in the storage area, identify abnormal sand fixation sub-areas. Through time series analysis, it mines the change characteristics of each monitoring indicator characteristic value in the set of monitoring indicator values over time, identifies the time series change trend, and through spatial distribution analysis, obtains the spatial distribution characteristics of the monitoring indicator characteristic values, identifies the spatial abnormal trend. Based on the time series change trend and the spatial abnormal trend, it locates the abnormal sand fixation sub-areas; The decision feedback module is used to adjust the acquisition frequency of the sensors in the abnormal sand fixation sub-areas, send acquisition instructions through the Internet of Things technology to obtain the monitoring indicator characteristic values of the abnormal sand fixation sub-areas, and monitor the change trend of the ecological benefits in the abnormal sand fixation sub-areas.

2. The desert sand fixation monitoring and management system based on data analysis according to claim 1, characterized in that The specific steps of the spatio-temporal characteristic analysis include: Set the abnormal analysis interval for each monitoring indicator characteristic value. Every time an abnormal analysis interval passes, select the monitoring indicator characteristic values from the set of monitoring indicator values in the storage area to construct an abnormal analysis set of the monitoring indicator characteristic values; Divide the abnormal analysis set according to the time series to obtain the time series abnormal analysis set of the monitoring indicator characteristic values of each sand fixation sub-area; For the time series abnormal analysis set after missing value processing, perform time series change trend identification, including trend identification and mutation point identification, and calculate the time series abnormal score of the time series abnormal analysis set; Divide the abnormal analysis set according to the spatial series to obtain the spatial abnormal analysis set of the monitoring indicator characteristic values at each moment; For the spatial abnormal analysis set after missing value processing, perform spatial change trend identification, including autocorrelation analysis and mutation point identification, and calculate the spatial abnormal score of the spatial abnormal analysis set; Configure the spatial abnormal threshold and the time series abnormal threshold. If the spatial abnormal score of the spatial abnormal analysis set is greater than the spatial abnormal threshold, mark the moment where the spatial abnormal analysis set is located as the time series abnormal moment, otherwise do not perform any processing; If the time series abnormal score of the time series abnormal analysis set is greater than the time series abnormal threshold, mark the sand fixation sub-area where the time series abnormal analysis set is located as the spatial abnormal area; In the implementation area of the sand fixation project, select the sand fixation sub-areas that have both the time series abnormal moment mark and the spatial abnormal area mark, and mark them as the abnormal sand fixation sub-areas.

3. The desert sand fixation monitoring and management system based on data analysis according to claim 2, wherein The specific steps of the time series change trend identification include: Set a smoothing time window, perform moving average on the time series abnormal analysis set to obtain the moving average value of each monitoring indicator characteristic value in the time series abnormal analysis set, calculate the moving deviation between each monitoring indicator characteristic value and its moving average value, and calculate the standard deviation of the moving deviation; Configure a deviation change threshold. If the standard deviation of the moving deviation of the time series anomaly analysis set is greater than the deviation change threshold, identify the mutation points in the time series anomaly analysis set; otherwise, do not perform any processing. The steps for identifying the mutation points in the time series anomaly analysis set include: Configure a deviation anomaly threshold. If the moving deviation of the monitoring index feature value is greater than the deviation anomaly threshold, mark the monitoring index feature value as a potential mutation point; otherwise, do not perform any operation. Calculate the relative change rate of each potential mutation point based on the relative magnitude of the monitoring index feature value at the potential mutation point with respect to the monitoring index feature values at adjacent times. Configure a change rate threshold. If the relative change rate of a potential mutation point is greater than the change rate threshold, mark this point as a mutation point, and mark the timestamp where the mutation point is located and the time series anomaly analysis set where the mutation point is located; otherwise, do not perform any processing. Calculate the time series anomaly score of the time series anomaly analysis set by combining the standard deviation of the moving deviation of the monitoring index feature values in the time series anomaly analysis set and the number of mutation points.

4. The desert sand fixation monitoring and management system based on data analysis according to claim 2, characterized in that, The specific steps for identifying the spatial change trend include: Perform a global spatial autocorrelation analysis on the spatial anomaly analysis set, and combine the spatial positions of the fixed sand areas to obtain the difference between the monitoring index feature value of each fixed sand area in the spatial anomaly analysis set and its mean value, and calculate the overall spatial autocorrelation score of the monitoring index feature values of the spatial anomaly analysis set within the fixed sand area. Configure an autocorrelation score threshold. If the overall spatial autocorrelation score of the monitoring index feature values of the spatial anomaly analysis set within the fixed sand area is greater than the autocorrelation score threshold, do not perform any processing; otherwise, identify the mutation points in the spatial anomaly analysis set. Calculate the local spatial autocorrelation coefficient for each fixed sand area, and configure a relevant mutation threshold. If the local spatial autocorrelation coefficient of a fixed sand area is less than the relevant mutation threshold, mark this fixed sand area as a mutation area; otherwise, do not perform any processing. Overall spatial autocorrelation score of the monitoring index eigenvalues combined with the spatial anomaly analysis set Calculate the spatial anomaly score of the spatial anomaly analysis set by using the local spatial autocorrelation coefficient of the sand-fixing area and the number of mutation areas in the spatial anomaly analysis set.

5. The desert sand fixation monitoring and management system based on data analysis according to claim 1, characterized in that The steps for collecting the monitoring data include: Set the sensor data collection frequency, and based on the data collection frequency, send a collection instruction to the sensors within the implementation area of the sand fixation project through the Internet of Things. When the sensor receives the collection instruction, measure the monitoring data, and the monitoring data is returned to the central management platform in the form of digital signals or analog signals through the Internet of Things. After the central management platform performs sensor marking and timestamp marking on the received monitoring data, check the integrity of the monitoring data to determine whether there are missing values. If there are missing values in the received monitoring data, according to the sensor marking, the data collection module resends the collection instruction to obtain substitute monitoring data for filling the missing values. Judge whether the substitute monitoring data is a missing value. If the substitute monitoring data is a missing value, issue a sensor warning; otherwise, do not perform any operation. Perform a preliminary outlier test on the monitoring data after integrity check. According to the sensor type, set the sensor data range, and based on the sensor marking and sensor data range of the monitoring data, filter out the monitoring data outside the sensor data range and mark it as abnormal monitoring data. Classify the monitoring data that has passed the integrity check and preliminary outlier test according to the sensor tags and store it in the cache area of the central management platform.

6. The desert sand fixation monitoring and management system based on data analysis according to claim 1, characterized in that The monitoring indicators include soil monitoring indicators, meteorological monitoring indicators, vegetation monitoring indicators, and sand fixation equipment monitoring indicators. The steps for obtaining the characteristic values of the monitoring indicators are as follows: When new monitoring data is added to the cache area, select the newly added monitoring data of the corresponding sensors according to the monitoring indicator type, construct a new monitoring data set, and obtain the location coordinates of each sensor in the new monitoring data set. Perform missing value processing on the new monitoring data set, filter out the missing values in the new monitoring data set, count the number of missing values, and calculate the missing value frequency of the new monitoring data set. Configure the missing frequency threshold. If the missing value frequency of the new monitoring data set is greater than the missing frequency threshold, start the sensor fault troubleshooting process and set the new monitoring data set to an empty set; otherwise, fill in the missing values in the new monitoring data set through spatial interpolation. Perform outlier processing on the new monitoring data set, filter out the data points marked as abnormal monitoring data in each new monitoring data set, count the number of data points marked as abnormal monitoring data, and calculate the outlier frequency of the new monitoring data set. Configure the outlier frequency threshold. If the outlier frequency of the new monitoring data set is greater than the outlier frequency threshold, perform cluster analysis on the abnormal monitoring data to locate the abnormal area; otherwise, fill in the abnormal monitoring data in the new monitoring data set through spatial interpolation.

7. The desert sand fixation monitoring and management system based on data analysis according to claim 6, characterized in that The steps for obtaining the characteristic values of the monitoring indicators also include: Divide the sand fixation sub-areas in the area where the sand fixation project is implemented. According to the sensor location coordinates in the sand fixation area, divide the new monitoring data set after missing value processing and outlier processing to obtain the new monitoring indicator set for each sand fixation sub-area. According to the sensor type, divide the new monitoring indicator set to obtain the new monitoring indicator subset for each type of sensor, and calculate the mean value of the monitoring data in each new monitoring indicator subset as the characteristic value of the monitoring indicator for the new monitoring indicator subset in the sand fixation sub-area. Obtain the characteristic values of each monitoring indicator in each sensor type for all sand fixation sub-areas, construct a new monitoring indicator value set for the sand fixation area, mark the time stamp, and store it in the storage area of the central management platform.

8. The desert sand fixation monitoring and management system based on data analysis according to claim 6, wherein The steps for filling in the missing values in the new monitoring data set include: According to the sensor type, divide the new monitoring data set to obtain the new monitoring data subset. Obtain the position coordinates of the sensors where the missing values are located in the newly added monitoring data subset , configure the compensation radius, and divide the compensation area of the missing values according to the compensation radius , filter the monitoring data of non-missing values in the compensation area, and calculate the compensated monitoring data of the missing values according to the inverse distance weighted interpolation 9. The desert sand fixation monitoring and management system based on data analysis according to claim 6, characterized in that, The steps for performing cluster analysis on the abnormal monitoring data include: Obtain the location coordinates of the sensor where the abnormal monitoring data is located in the new monitoring data set, set the number of clusters, and based on the number of clusters, divide the sensor where the abnormal monitoring data is located into multiple cluster clusters through the clustering algorithm. Count the number of abnormal monitoring data in each cluster cluster, and calculate the abnormal concentration of the sensor where the abnormal monitoring data is located in each cluster cluster according to the area of the cluster cluster. Configure a concentration threshold. If the abnormal concentration of a clustering cluster is greater than the concentration threshold, the area where the clustering cluster is located is divided into an abnormal area, an abnormal warning is issued for the clustering clusters in the abnormal area, and the abnormal monitoring data within the clustering clusters in the abnormal area is set to null values; otherwise, the abnormal monitoring data of the clustering clusters is filled by spatial interpolation.

10. The desert sand fixation monitoring and management system based on data analysis according to claim 1, characterized in that The steps for adjusting the acquisition frequency of sensors in the abnormal solid sand area include: When an abnormal solid sand area is detected, screen the characteristic values of the monitoring indicators at abnormal times in the abnormal solid sand area, obtain the sensors where the characteristic values of the monitoring indicators are located, mark them as abnormal sensors, and obtain the acquisition frequency of the abnormal sensors. Configure an abnormal sensor threshold, count the number of abnormal sensors in the abnormal solid sand area, calculate the proportion of abnormal sensors, and if the proportion of abnormal sensors in the solid sand area is greater than the abnormal sensor threshold, issue a warning for the solid sand area; otherwise, do nothing. Set a set of adjustment coefficients according to the proportion of abnormal sensors in the abnormal solid sand area, and each adjustment coefficient is applied to the proportion of abnormal sensors in different abnormal solid sand areas. Based on the adjustment coefficient, adjust the acquisition frequency of the abnormal sensors in the abnormal solid sand area according to the current acquisition frequency of the abnormal sensors in the abnormal solid sand area.

Images