A green forest soil intelligent monitoring system and method based on multi-source data analysis

Abstract

This invention discloses an intelligent monitoring system and method for forest soil based on multi-source data analysis, relating to the field of soil monitoring technology. The system includes: collecting soil monitoring data from monitoring points and storing it as historical data; retrieving historical data for time-series feature analysis, extracting the range of peak and trough change rates as a first evaluation index; acquiring spatial location data for spatial feature analysis, obtaining a second evaluation index based on the distribution range of vegetation type and terrain slope; correlating the first and second evaluation indices to calculate the soil quality assessment value for each monitoring area; identifying abnormal areas based on the assessment values ​​and generating risk alerts; and outputting maintenance plans from the intelligent monitoring terminal.

Description

Technical Field

[0001] This invention relates to the field of soil monitoring technology, specifically a smart monitoring system and method for forest soil based on multi-source data analysis. Background Technology

[0002] With the acceleration of urbanization and the increasing demands for ecological and environmental protection, the need for monitoring forest soil is becoming increasingly urgent. However, the current assessment of forest soil quality mainly relies on traditional manual sampling and laboratory analysis methods, which involve collecting soil samples on-site and sending them to specialized laboratories for physicochemical testing. While these methods offer high accuracy, laboratory resources are limited. When dealing with large-scale, multi-site monitoring tasks such as forest areas, the sample processing cycle is long and costly, making it difficult to meet the real-time and large-scale, high-frequency monitoring requirements. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent monitoring system and method for forest soil based on multi-source data analysis, so as to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a smart monitoring method for forest soil based on multi-source data analysis, the smart monitoring method comprising: By setting up soil monitoring points in the target green forest area, soil monitoring data of the target green forest area is collected, and the collected soil monitoring data is stored in the soil monitoring terminal to obtain historical soil monitoring data; wherein, the historical soil monitoring data includes historically stored soil monitoring data and real-time collected soil monitoring data; Historical soil monitoring data recorded by the intelligent soil monitoring terminal is retrieved, and time-series characteristic analysis is performed on the historical soil monitoring data to obtain the first evaluation index. Acquire spatial location data of each soil monitoring point, and perform spatial characteristic analysis on the soil monitoring data based on the spatial location data to obtain the second evaluation index; By performing a correlation analysis on the first and second evaluation indicators, the soil quality evaluation values ​​for each target monitoring area are obtained. Based on the soil quality assessment values, abnormal soil areas within the target green forest are identified, and soil quality risk warnings are generated. The intelligent soil monitoring terminal outputs a corresponding soil maintenance plan based on the risk alert.

[0005] Furthermore, by setting up soil monitoring points in the target forest area, soil monitoring data of the target forest area is collected, and the collected soil monitoring data is stored in the soil monitoring terminal to obtain historical soil monitoring data, including: Obtain a topographic survey map of the target green forest, which includes topographic slope and vegetation type; divide plots with the same topographic slope level and the same vegetation type into the same type of target monitoring area; Corresponding soil monitoring points are deployed in several target monitoring areas, and soil monitoring data of the corresponding target monitoring areas are collected through the monitoring devices at each soil monitoring point. The collected soil monitoring data is converted into a preset standard data format, and the standardized soil monitoring data is bound with the corresponding collection timestamp and spatial coordinates. The bound soil monitoring data is then transmitted to the soil monitoring terminal for continuous storage. As the sampling cycle continues to accumulate, historical soil monitoring data of the target green forest is formed. This invention divides monitoring areas by using topographic slope and vegetation type on topographic survey maps and deploys monitoring points, ensuring the scientific and representative nature of the monitoring point settings and avoiding data deviations caused by random point placement. At the same time, by standardizing the format of the collected data and binding it with timestamps and spatial coordinates before storage, a historical soil monitoring database with spatiotemporal consistency is constructed, providing a standardized, reliable and traceable data foundation for subsequent multi-dimensional feature analysis.

[0006] Furthermore, historical soil monitoring data recorded by the intelligent soil monitoring terminal is retrieved, and time-series characteristic analysis is performed on the historical soil monitoring data to obtain the first evaluation indicators, including: The system retrieves all historical soil monitoring data corresponding to each soil monitoring point from the intelligent soil monitoring terminal, sorts the historical soil monitoring data of a single soil monitoring point according to the order of collection timestamps, and divides the sorted historical soil monitoring data into several time series units according to a fixed time period. For each time series unit, a statistical chart of the change of soil monitoring data within the time series unit is plotted with time as the horizontal axis and the value of soil monitoring data as the vertical axis. The change trajectory of soil monitoring data over time is presented in the statistical chart in the form of a continuous curve. In the statistical chart of changes, identify all local peak points and local valley points in the continuous curve; connect all local peak points sequentially and smoothly to form a first time series curve; connect all local valley points sequentially and smoothly to form a second time series curve; Extract the first and second time series curves corresponding to all time series units at the same soil monitoring point; extract the vertical and horizontal offsets of the first time series curve as a whole; extract the vertical and horizontal offsets of the second time series curve as a whole. According to the sequential order of the timing units, the difference between the vertical offsets of the first timing curves of adjacent timing units is calculated to obtain the rate of change of the vertical offset, which is denoted as the first peak rate of change; the difference between the horizontal offsets of the first timing curves of adjacent timing units is calculated to obtain the rate of change of the horizontal offset, which is denoted as the second peak rate of change; the difference between the vertical offsets of the second timing curves of adjacent timing units is calculated to obtain the rate of change of the vertical offset, which is denoted as the first valley rate of change; the difference between the horizontal offsets of the second timing curves of adjacent timing units is calculated to obtain the rate of change of the horizontal offset, which is denoted as the second valley rate of change. The historical values ​​of the first peak rate of change, the second peak rate of change, the first trough rate of change, and the second trough rate of change were statistically analyzed to extract the concentrated fluctuation range of each type of rate of change, and the concentrated fluctuation intervals of each type of rate of change were obtained, which were denoted as the first peak rate interval, the second peak rate interval, the first trough rate interval, and the second trough rate interval, respectively. The first peak value variation range, the second peak value variation range, the first valley value variation range, and the second valley value variation range are used as the first evaluation indicators; This invention divides historical soil monitoring data into time-series units, plots continuous curves, extracts peak / valley curves that reflect the dynamic changes in soil properties, and further quantifies them into vertical and horizontal offsets and their rates of change. At the same time, by statistically analyzing a large number of historical change rates, a concentrated fluctuation range is obtained as the first evaluation index. This index is not a simple data mean, but represents the dynamic change pattern of soil in a healthy state.

[0007] Furthermore, spatial location data of each soil monitoring point is obtained, and spatial characteristic analysis is performed on the soil monitoring data based on the spatial location data to obtain the second evaluation index, including: For each time series unit, the vegetation type and terrain slope bound to each soil monitoring point are retrieved. The terrain slope corresponding to each vegetation type is sorted according to the slope value. Based on the sorted slope values, the upper and lower bounds of the slope distribution corresponding to the vegetation type are determined, and the slope distribution interval corresponding to the vegetation type is generated. According to the chronological order of the time series units, the slope distribution intervals of the same vegetation type under each time series unit are compared unit by unit. The upper and lower bound offsets of the slope distribution intervals corresponding to the vegetation type between adjacent time series units are calculated respectively. Based on the upper and lower bound offsets, the increase or decrease in the span of the slope distribution interval is calculated. Extract the time interval between adjacent time units and the increase or decrease in the span of the slope distribution range, and calculate the increase or decrease rate of the slope span for adjacent time units corresponding to the vegetation type; For each vegetation type, the rate of increase and decrease of slope span is statistically distributed, and the concentrated fluctuation range of the rate of increase and decrease is extracted to obtain the slope change rate range corresponding to the vegetation type. The range of slope change rates is denoted as the second evaluation index; This invention utilizes spatial location data linked to soil monitoring points to analyze the distribution range and rate of change of topographic slope under different vegetation types. This step dynamically links changes in soil quality with the spatial environment in which the soil grows. The resulting range of slope change rates can effectively reflect the stability changes of soil under specific vegetation types caused by factors such as slope runoff and erosion, providing a reliable basis for identifying soil degradation risks from a spatial perspective.

[0008] Furthermore, a correlation analysis was performed on the first and second assessment indicators to obtain the soil quality assessment values ​​for each target monitoring area, including: Acquire soil monitoring data for the current time series unit and the previous time series unit, and calculate the first peak change rate, second peak change rate, first valley change rate, second valley change rate, and slope span increase / decrease rate corresponding to each soil monitoring point in the current time series unit and the vegetation type to which each monitoring point belongs. The first peak change rate, second peak change rate, first trough change rate, and second trough change rate of each soil monitoring point are compared with the corresponding change intervals in the first evaluation index one by one. The deviation of the soil monitoring point from the change interval is calculated to obtain the temporal characteristic deviation of the soil monitoring point. The slope span increase / decrease rate of each soil monitoring point is compared with the corresponding slope change rate range in the second evaluation index to obtain the spatial characteristic deviation of the vegetation type corresponding to the soil monitoring point. The soil quality assessment value of the target monitoring area corresponding to each soil monitoring point is obtained by weighted summing of the temporal characteristic deviation and spatial characteristic deviation. This invention calculates the temporal and spatial deviations by comparing the real-time change rate of a single monitoring point with the first and second evaluation indicators representing the normal range, and obtains a comprehensive soil quality assessment value through weighted summation. This correlation analysis method considers both the evolution of soil properties in the time dimension and environmental influencing factors in the spatial dimension, making the final assessment results more comprehensive and accurate than single-dimensional analysis, and significantly improving the intelligence level of soil quality assessment.

[0009] Furthermore, based on the soil quality assessment values, abnormal soil areas within the target green space are identified, and soil quality risk alerts are generated, including: Obtain the soil quality assessment value corresponding to each target monitoring area within the target green forest, and mark the target monitoring area whose soil quality assessment value exceeds the quality assessment threshold as a soil abnormality area; Soil anomaly areas are sorted in descending order of soil quality assessment values, and each soil anomaly area is numbered sequentially according to the sorting results. The intelligent soil monitoring terminal collects soil quality data sequentially through soil quality monitoring sensors according to the numbering order of soil anomaly areas, and generates soil quality risk warnings for each soil anomaly area based on the soil quality data. This invention identifies soil anomaly areas from large areas of green forest by setting quality assessment thresholds and sorts and numbers them according to the assessment values. This allows regulators to quickly pinpoint the areas with the most serious problems and guide the intelligent soil monitoring terminal to conduct targeted data review and collection according to priority. This not only greatly improves the efficiency of risk investigation, but also ensures that limited regulatory resources can be invested in the areas with the highest risk first.

[0010] Furthermore, the soil intelligent monitoring terminal outputs a corresponding soil conservation plan based on the risk alert, including: Based on the generated soil quality risk alerts, the soil intelligent monitoring terminal generates corresponding soil maintenance plans and outputs the soil maintenance plans sequentially according to the numbering order of the target monitoring areas. This invention realizes a complete closed loop from risk identification to solution output. The soil intelligent monitoring terminal can automatically match and generate corresponding soil maintenance solutions based on specific risk prompts and output them in priority order. This process eliminates the problems of long sample processing cycle and high cost when facing large-area green forest and multi-point monitoring tasks in traditional methods, and significantly improves the response speed and decision quality of supervision.

[0011] Furthermore, in order to better implement the above method, a smart monitoring system for forest soil based on multi-source data analysis is also provided. The smart monitoring system includes: a data acquisition module, a time series feature analysis module, a spatial feature analysis module, a feature correlation analysis module, a risk identification module, and a maintenance plan output module. The data acquisition module is used to collect soil monitoring data of the target green forest by setting up soil monitoring points in the target green forest, and store the collected soil monitoring data in the soil monitoring terminal to obtain historical soil monitoring data. The time-series feature analysis module is used to retrieve historical soil monitoring data recorded by the soil intelligent monitoring terminal, perform time-series feature analysis on the historical soil monitoring data, and obtain the first evaluation index. The spatial feature analysis module is used to acquire spatial location data of each soil monitoring point, and to perform spatial feature analysis on the soil monitoring data based on the spatial location data to obtain the second evaluation index. The feature correlation analysis module is used to perform correlation analysis on the first evaluation index and the second evaluation index to obtain the soil quality evaluation value of each target monitoring area. The risk identification module is used to identify abnormal soil areas within the target green forest based on the soil quality assessment value and generate soil quality risk warnings. The soil maintenance plan output module is used by the soil intelligent monitoring terminal to output the corresponding soil maintenance plan based on the risk warning.

[0012] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention integrates temporal and spatial feature analysis to comprehensively assess soil quality from both temporal and spatial dimensions, significantly improving the accuracy and reliability of soil anomaly identification.

[0013] 2. This invention utilizes an intelligent monitoring terminal to automatically collect and store historical data, enabling real-time dynamic monitoring of soil quality without the need for frequent manual sampling, thus significantly reducing monitoring costs and improving monitoring efficiency.

[0014] 3. This invention automatically identifies abnormal areas based on soil quality assessment values ​​and generates targeted maintenance plans, achieving precise and intelligent management of forest soil, which is conducive to taking timely maintenance measures and protecting the ecological environment. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the process flow of a smart monitoring system and method for green forest soil based on multi-source data analysis according to the present invention; Figure 2 This is a schematic diagram illustrating an application scenario of the intelligent monitoring system and method for green forest soil based on multi-source data analysis according to the present invention. Detailed Implementation

[0016] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0017] Example 1: As Figure 1 As shown, this invention provides a technical solution: an intelligent monitoring method for forest soil based on multi-source data analysis. This intelligent monitoring method includes: By setting up soil monitoring points in the target green forest area, soil monitoring data of the target green forest area is collected, and the collected soil monitoring data is stored in the soil monitoring terminal to obtain historical soil monitoring data; wherein, the historical soil monitoring data includes historically stored soil monitoring data and real-time collected soil monitoring data; Historical soil monitoring data recorded by the intelligent soil monitoring terminal is retrieved, and time-series characteristic analysis is performed on the historical soil monitoring data to obtain the first evaluation index. Acquire spatial location data of each soil monitoring point, and perform spatial characteristic analysis on the soil monitoring data based on the spatial location data to obtain the second evaluation index; By performing a correlation analysis on the first and second evaluation indicators, the soil quality evaluation values ​​for each target monitoring area are obtained. Based on the soil quality assessment values, abnormal soil areas within the target green forest are identified, and soil quality risk warnings are generated. The intelligent soil monitoring terminal outputs a corresponding soil maintenance plan based on the risk alert; Specifically, soil monitoring data is collected from soil monitoring points set up in the target forest area, and the collected soil monitoring data is stored in a soil monitoring terminal to obtain historical soil monitoring data, including: Obtain a topographic survey map of the target green forest, which includes topographic slope and vegetation type; divide plots with the same topographic slope level and the same vegetation type into the same type of target monitoring area; Corresponding soil monitoring points are deployed in several target monitoring areas, and soil monitoring data of the corresponding target monitoring areas are collected through the monitoring devices at each soil monitoring point. The collected soil monitoring data is converted into a preset standard data format, and the standardized soil monitoring data is bound with the corresponding collection timestamp and spatial coordinates. The bound soil monitoring data is then transmitted to the soil monitoring terminal for continuous storage. As the sampling cycle continues to accumulate, historical soil monitoring data of the target green forest is formed. In an embodiment of the present invention, a 1:1000 topographic survey map of a suburban park green area is obtained, and plots with a slope of 0° to 5° and planted with camphor trees are designated as the same monitoring area. In each area, a soil multi-parameter sensor is deployed to monitor pH, humidity, and electrical conductivity. Data is collected every 30 minutes, and the collected data is uniformly converted into JSON format and uploaded to the monitoring terminal with timestamps and GPS coordinates. Historical data is formed by continuous collection for 3 months. Specifically, historical soil monitoring data recorded by the intelligent soil monitoring terminal is retrieved, and time-series characteristic analysis is performed on the historical soil monitoring data to obtain the first evaluation index, which includes: The system retrieves all historical soil monitoring data corresponding to each soil monitoring point from the intelligent soil monitoring terminal, sorts the historical soil monitoring data of a single soil monitoring point according to the order of collection timestamps, and divides the sorted historical soil monitoring data into several time series units according to a fixed time period. For each time series unit, a statistical chart of the change of soil monitoring data within the time series unit is plotted with time as the horizontal axis and the value of soil monitoring data as the vertical axis. The change trajectory of soil monitoring data over time is presented in the statistical chart in the form of a continuous curve. In the statistical chart of changes, identify all local peak points and local valley points in the continuous curve; connect all local peak points sequentially and smoothly to form a first time series curve; connect all local valley points sequentially and smoothly to form a second time series curve; Extract the first and second time series curves corresponding to all time series units at the same soil monitoring point; extract the vertical and horizontal offsets of the first time series curve as a whole; extract the vertical and horizontal offsets of the second time series curve as a whole. According to the sequential order of the timing units, the difference between the vertical offsets of the first timing curves of adjacent timing units is calculated to obtain the rate of change of the vertical offset, which is denoted as the first peak rate of change; the difference between the horizontal offsets of the first timing curves of adjacent timing units is calculated to obtain the rate of change of the horizontal offset, which is denoted as the second peak rate of change; the difference between the vertical offsets of the second timing curves of adjacent timing units is calculated to obtain the rate of change of the vertical offset, which is denoted as the first valley rate of change; the difference between the horizontal offsets of the second timing curves of adjacent timing units is calculated to obtain the rate of change of the horizontal offset, which is denoted as the second valley rate of change. The historical values ​​of the first peak rate of change, the second peak rate of change, the first trough rate of change, and the second trough rate of change were statistically analyzed to extract the concentrated fluctuation range of each type of rate of change, and the concentrated fluctuation intervals of each type of rate of change were obtained, which were denoted as the first peak rate interval, the second peak rate interval, the first trough rate interval, and the second trough rate interval, respectively. The first peak value variation range, the second peak value variation range, the first valley value variation range, and the second valley value variation range are used as the first evaluation indicators; In an embodiment of the present invention, a 7-day time series unit is used to divide the 3-month data of a certain monitoring point into 12 units. The humidity change curve in each unit is plotted, the peak value and the valley value are identified, and they are connected to form upper and lower envelopes respectively. The vertical offset of the envelopes of adjacent units is calculated, such as humidity change of 0.2% to 0.5% / day, and the horizontal offset is calculated, such as peak time shifted back by 1 to 2 hours. The first peak change range is statistically obtained as [0.1, 0.6] / day, which is used as the first evaluation index. Specifically, the spatial location data of each soil monitoring point is acquired, and spatial characteristic analysis is performed on the soil monitoring data based on the spatial location data to obtain the second evaluation index, including: For each time series unit, the vegetation type and terrain slope bound to each soil monitoring point are retrieved. The terrain slope corresponding to each vegetation type is sorted according to the slope value. Based on the sorted slope values, the upper and lower bounds of the slope distribution corresponding to the vegetation type are determined, and the slope distribution interval corresponding to the vegetation type is generated. According to the chronological order of the time series units, the slope distribution intervals of the same vegetation type under each time series unit are compared unit by unit. The upper and lower bound offsets of the slope distribution intervals corresponding to the vegetation type between adjacent time series units are calculated respectively. Based on the upper and lower bound offsets, the increase or decrease in the span of the slope distribution interval is calculated. Extract the time interval between adjacent time units and the increase or decrease in the span of the slope distribution range, and calculate the increase or decrease rate of the slope span for adjacent time units corresponding to the vegetation type; For each vegetation type, the rate of increase and decrease of slope span is statistically distributed, and the concentrated fluctuation range of the rate of increase and decrease is extracted to obtain the slope change rate range corresponding to the vegetation type. The range of slope change rates is denoted as the second evaluation index; In an embodiment of the present invention, for the same vegetation type, such as Masson pine, the slope values ​​of each monitoring point are retrieved and sorted by time series units to obtain the slope distribution range, such as 10° to 25°; by comparing adjacent units, it is found that the upper boundary offset is +2° and the lower boundary offset is -1°, so the span increase or decrease is +3°, the time interval is 7 days, and the slope span increase or decrease rate is calculated to be 0.43° / day; the slope change rate range of this vegetation type is obtained by statistically analyzing all units as [0.2, 0.8], which is used as the second evaluation index; The soil quality assessment values ​​for each target monitoring area are obtained by performing a correlation analysis between the first and second assessment indicators: Acquire soil monitoring data for the current time series unit and the previous time series unit, and calculate the first peak change rate, second peak change rate, first valley change rate, second valley change rate, and slope span increase / decrease rate corresponding to each soil monitoring point in the current time series unit and the vegetation type to which each monitoring point belongs. The first peak change rate, second peak change rate, first trough change rate, and second trough change rate of each soil monitoring point are compared with the corresponding change intervals in the first evaluation index one by one. The deviation of the soil monitoring point from the change interval is calculated to obtain the temporal characteristic deviation of the soil monitoring point. The slope span increase / decrease rate of each soil monitoring point is compared with the corresponding slope change rate range in the second evaluation index to obtain the spatial characteristic deviation of the vegetation type corresponding to the soil monitoring point. The soil quality assessment value of the target monitoring area corresponding to each soil monitoring point is obtained by weighted summing of the temporal characteristic deviation and spatial characteristic deviation. In an embodiment of the present invention, the current 7-day time series unit is taken, and the first peak change rate of a certain monitoring point is calculated to be 0.7 / day, which exceeds the upper limit of the corresponding interval by 0.6, with an excess magnitude of 0.1; the slope span increase / decrease rate is 0.9 / day, which exceeds the upper limit of the interval by 0.8, with an excess magnitude of 0.1; the time series weight is set to 0.6 and the spatial weight to 0.4, and the weighted sum is used to obtain the soil quality assessment value of 0.1×0.6+0.1×0.4=0.1; Specifically, identifying soil anomaly areas within the target green space based on the soil quality assessment values ​​and generating soil quality risk alerts includes: Obtain the soil quality assessment value corresponding to each target monitoring area within the target green forest, and mark the target monitoring area whose soil quality assessment value exceeds the quality assessment threshold as a soil abnormality area; Soil anomaly areas are sorted in descending order of soil quality assessment values, and each soil anomaly area is numbered sequentially according to the sorting results. The intelligent soil monitoring terminal collects soil quality data sequentially through soil quality monitoring sensors according to the numbering order of soil anomaly areas, and generates soil quality risk warnings for each soil anomaly area based on the soil quality data. In an embodiment of the present invention, a quality assessment threshold of 0.15 is set, and all areas with assessment values ​​exceeding 0.15 are marked as abnormal and numbered in descending order of assessment values, such as 001, 002, etc. The smart terminal sequentially retrieves the pH and heavy metal sensor data of area 001. If the pH is lower than 5.5 and the lead content exceeds the standard, a risk warning for acidification and heavy metal pollution risk is generated and the priority is marked. The soil intelligent monitoring terminal outputs a corresponding soil conservation plan based on the risk alert, including: Based on the generated soil quality risk alerts, the soil intelligent monitoring terminal generates corresponding soil maintenance plans and outputs the soil maintenance plans sequentially according to the numbering order of the target monitoring areas. In an embodiment of the present invention, in response to the risk warnings of acidification and heavy metal pollution, the system matches the maintenance knowledge base with the risk warning information to generate a plan for applying lime to adjust the pH to 6.0-6.5 and applying an organic chelating agent to fix heavy metals. At the same time, based on the area of ​​001, such as 500㎡, the system calculates the amount of materials to be used and pushes the plan text and operation charts to the mobile terminal of the management personnel in numerical order. Example 2: Figure 2 As shown, in order to better implement the above method, a smart monitoring system for forest soil based on multi-source data analysis is also provided. The smart monitoring system includes: a data acquisition module, a time series feature analysis module, a spatial feature analysis module, a feature correlation analysis module, a risk identification module, and a maintenance plan output module. The data acquisition module is used to collect soil monitoring data of the target green forest by setting up soil monitoring points in the target green forest, and store the collected soil monitoring data in the soil monitoring terminal to obtain historical soil monitoring data. The time-series feature analysis module is used to retrieve historical soil monitoring data recorded by the soil intelligent monitoring terminal, perform time-series feature analysis on the historical soil monitoring data, and obtain the first evaluation index. The spatial feature analysis module is used to acquire spatial location data of each soil monitoring point, and to perform spatial feature analysis on the soil monitoring data based on the spatial location data to obtain the second evaluation index. The feature correlation analysis module is used to perform correlation analysis on the first evaluation index and the second evaluation index to obtain the soil quality evaluation value of each target monitoring area. The risk identification module is used to identify abnormal soil areas within the target green forest based on the soil quality assessment value and generate soil quality risk warnings. The soil maintenance plan output module is used by the soil intelligent monitoring terminal to output the corresponding soil maintenance plan based on the risk warning.

[0018] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent monitoring of forest soil based on multi-source data analysis, characterized in that, The intelligent supervision method includes: By setting up soil monitoring points in the target green forest area, soil monitoring data of the target green forest area is collected, and the collected soil monitoring data is stored in the soil monitoring terminal to obtain historical soil monitoring data; wherein, the historical soil monitoring data includes historically stored soil monitoring data and real-time collected soil monitoring data; Historical soil monitoring data recorded by the intelligent soil monitoring terminal is retrieved, and time-series characteristic analysis is performed on the historical soil monitoring data to obtain the first evaluation index. Acquire spatial location data of each soil monitoring point, and perform spatial characteristic analysis on the soil monitoring data based on the spatial location data to obtain the second evaluation index; By performing a correlation analysis on the first and second evaluation indicators, the soil quality evaluation values ​​for each target monitoring area are obtained. Based on the soil quality assessment values, abnormal soil areas within the target green forest are identified, and soil quality risk warnings are generated. The intelligent soil monitoring terminal outputs a corresponding soil maintenance plan based on the risk alert.

2. The intelligent monitoring method for forest soil based on multi-source data analysis according to claim 1, characterized in that, Soil monitoring data is collected from soil monitoring points deployed in the target forest area. The collected soil monitoring data is stored in a soil monitoring terminal, resulting in historical soil monitoring data, including: Obtain a topographic survey map of the target green forest, which includes topographic slope and vegetation type; divide plots with the same topographic slope level and the same vegetation type into the same type of target monitoring area; Corresponding soil monitoring points are deployed in several target monitoring areas, and soil monitoring data of the corresponding target monitoring areas are collected through the monitoring devices at each soil monitoring point. The collected soil monitoring data is converted into a preset standard data format. The standardized soil monitoring data is then bound with the corresponding collection timestamp and spatial coordinates. The bound soil monitoring data is then transmitted to the soil monitoring terminal for continuous storage. As the sampling cycle continues, historical soil monitoring data of the target green forest is formed.

3. The intelligent monitoring method for forest soil based on multi-source data analysis according to claim 1, characterized in that, Historical soil monitoring data recorded by the intelligent soil monitoring terminal is retrieved, and time-series characteristic analysis is performed on the historical soil monitoring data to obtain the first evaluation index, which includes: The system retrieves all historical soil monitoring data corresponding to each soil monitoring point from the intelligent soil monitoring terminal, sorts the historical soil monitoring data of a single soil monitoring point according to the order of collection timestamps, and divides the sorted historical soil monitoring data into several time series units according to a fixed time period. For each time series unit, a statistical chart of the change of soil monitoring data within the time series unit is plotted with time as the horizontal axis and the value of soil monitoring data as the vertical axis. The change trajectory of soil monitoring data over time is presented in the statistical chart in the form of a continuous curve. In the statistical chart of changes, identify all local peak points and local valley points in the continuous curve; connect all local peak points sequentially and smoothly to form a first time series curve; connect all local valley points sequentially and smoothly to form a second time series curve; Extract the first and second time series curves corresponding to all time series units at the same soil monitoring point; extract the vertical and horizontal offsets of the first time series curve as a whole; extract the vertical and horizontal offsets of the second time series curve as a whole. According to the sequential order of the timing units, the difference between the vertical offsets of the first timing curves of adjacent timing units is calculated to obtain the rate of change of the vertical offset, which is denoted as the first peak rate of change; the difference between the horizontal offsets of the first timing curves of adjacent timing units is calculated to obtain the rate of change of the horizontal offset, which is denoted as the second peak rate of change; the difference between the vertical offsets of the second timing curves of adjacent timing units is calculated to obtain the rate of change of the vertical offset, which is denoted as the first valley rate of change; the difference between the horizontal offsets of the second timing curves of adjacent timing units is calculated to obtain the rate of change of the horizontal offset, which is denoted as the second valley rate of change. The historical values ​​of the first peak rate of change, the second peak rate of change, the first trough rate of change, and the second trough rate of change were statistically analyzed to extract the concentrated fluctuation range of each type of rate of change, and the concentrated fluctuation intervals of each type of rate of change were obtained, which were denoted as the first peak rate interval, the second peak rate interval, the first trough rate interval, and the second trough rate interval, respectively. The first peak value variation range, the second peak value variation range, the first trough value variation range, and the second trough value variation range are used as the first evaluation indicators.

4. The intelligent monitoring method for forest soil based on multi-source data analysis according to claim 1, characterized in that, Spatial location data of each soil monitoring point are obtained. Based on the spatial location data, spatial characteristic analysis is performed on the soil monitoring data to obtain the second evaluation index, including: For each time series unit, the vegetation type and terrain slope bound to each soil monitoring point are retrieved. The terrain slope corresponding to each vegetation type is sorted according to the slope value. Based on the sorted slope values, the upper and lower bounds of the slope distribution corresponding to the vegetation type are determined, and the slope distribution interval corresponding to the vegetation type is generated. According to the chronological order of the time series units, the slope distribution intervals of the same vegetation type under each time series unit are compared unit by unit. The upper and lower bound offsets of the slope distribution intervals corresponding to the vegetation type between adjacent time series units are calculated respectively. Based on the upper and lower bound offsets, the increase or decrease in the span of the slope distribution interval is calculated. Extract the time interval between adjacent time units and the increase or decrease in the span of the slope distribution range, and calculate the increase or decrease rate of the slope span for adjacent time units corresponding to the vegetation type; For each vegetation type, the rate of increase and decrease of slope span is statistically distributed, and the concentrated fluctuation range of the rate of increase and decrease is extracted to obtain the slope change rate range corresponding to the vegetation type. The range of slope change rate is denoted as the second evaluation index.

5. The intelligent monitoring method for forest soil based on multi-source data analysis according to claim 1, characterized in that, By performing a correlation analysis on the first and second evaluation indicators, the soil quality evaluation values ​​for each target monitoring area are obtained as follows: Acquire soil monitoring data for the current time series unit and the previous time series unit, and calculate the first peak change rate, second peak change rate, first valley change rate, second valley change rate, and slope span increase / decrease rate corresponding to each soil monitoring point in the current time series unit and the vegetation type to which each monitoring point belongs. The first peak change rate, second peak change rate, first trough change rate, and second trough change rate of each soil monitoring point are compared with the corresponding change intervals in the first evaluation index one by one. The deviation of the soil monitoring point from the change interval is calculated to obtain the temporal characteristic deviation of the soil monitoring point. The slope span increase / decrease rate of each soil monitoring point is compared with the corresponding slope change rate range in the second evaluation index to obtain the spatial characteristic deviation of the vegetation type corresponding to the soil monitoring point. The soil quality assessment value of the target monitoring area corresponding to each soil monitoring point is obtained by weighted summing of the temporal and spatial characteristic deviations.

6. The intelligent monitoring method for forest soil based on multi-source data analysis according to claim 1, characterized in that... Based on the soil quality assessment values, abnormal soil areas within the target green forest are identified, and soil quality risk alerts are generated, including: Obtain the soil quality assessment value corresponding to each target monitoring area within the target green forest, and mark the target monitoring area whose soil quality assessment value exceeds the quality assessment threshold as a soil abnormality area; Soil anomaly areas are sorted in descending order of soil quality assessment values, and each soil anomaly area is numbered sequentially according to the sorting results. The intelligent soil monitoring terminal collects soil quality data sequentially through soil quality monitoring sensors according to the numbering order of soil anomaly areas, and generates soil quality risk warnings for each soil anomaly area based on the soil quality data.

7. The intelligent monitoring method for forest soil based on multi-source data analysis according to claim 1, characterized in that, The intelligent soil monitoring terminal outputs corresponding soil maintenance plans based on the risk alerts, including: Based on the generated soil quality risk alerts, the soil intelligent monitoring terminal generates corresponding soil maintenance plans and outputs the soil maintenance plans sequentially according to the numbering order of the target monitoring areas.

8. A smart monitoring system for forest soil based on multi-source data analysis, used to execute the smart monitoring method for forest soil based on multi-source data analysis as described in any one of claims 1-7, characterized in that, The intelligent monitoring system includes: a data acquisition module, a time-series feature analysis module, a spatial feature analysis module, a feature correlation analysis module, a risk identification module, and a maintenance plan output module; The data acquisition module is used to collect soil monitoring data of the target green forest by setting up soil monitoring points in the target green forest, and store the collected soil monitoring data in the soil monitoring terminal to obtain historical soil monitoring data. The time-series feature analysis module is used to retrieve historical soil monitoring data recorded by the soil intelligent monitoring terminal, perform time-series feature analysis on the historical soil monitoring data, and obtain the first evaluation index. The spatial feature analysis module is used to acquire the spatial location data of each soil monitoring point, and to perform spatial feature analysis on the soil monitoring data based on the spatial location data to obtain the second evaluation index. The feature correlation analysis module is used to perform correlation analysis on the first evaluation index and the second evaluation index to obtain the soil quality evaluation value of each target monitoring area. The risk identification module is used to identify abnormal soil areas within the target green forest based on the soil quality assessment value and generate soil quality risk warnings. The maintenance plan output module is used by the soil intelligent monitoring terminal to output the corresponding soil maintenance plan based on the risk warning.

Images