Soil erosion risk early warning method and device based on dust data
By using gridded processing of dust data and neural network algorithms, the problems of accuracy in calculating and dynamic monitoring of soil erosion were solved, enabling efficient early warning of soil erosion risks and providing targeted risk identification and control measures.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN QINGYAN YINGSHI TECHNOLOGY CO LTD
- Filing Date
- 2026-01-19
- Publication Date
- 2026-06-05
AI Technical Summary
Existing methods for calculating soil erosion do not adequately consider spatial differences and the combined effects of multiple factors, resulting in insufficient accuracy and reliability of the calculation results. Furthermore, they lack dynamic monitoring capabilities, making it difficult to identify high-risk areas in a timely manner.
A dust data-based approach was adopted to grid the area to be analyzed, obtain NDVI data, soil moisture data, and slope factors, eliminate the influence of wind direction, and use a neural network algorithm combined with net dust data to calculate soil erosion intensity and soil loss. The model parameters were optimized through historical data to achieve dynamic monitoring and risk warning.
It significantly reduces calculation errors, enables hourly dynamic monitoring of soil erosion status, and can identify high-risk grids accounting for 5%-10%, providing targeted targets for soil and water conservation measures and improving the accuracy and timeliness of risk warnings.
Smart Images
Figure CN122155372A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of soil and water loss risk early warning technology, and in particular to a method and device for soil and water loss risk early warning based on dust data. Background Technology
[0002] Soil erosion refers to the phenomenon of soil loss caused by the deposition or siltation of soil and water materials from rivers, lakes, ditches, the surface, or soil, as well as changes in land slope. Currently, soil erosion is calculated using a formula developed and refined by geologists and agricultural scientists, which, combined with practical considerations, is used to estimate the amount of soil erosion.
[0003] Soil erosion is a widespread environmental problem worldwide, severely impacting the sustainable development of farmland and ecosystems. Accurate monitoring and scientific assessment of soil erosion are crucial for developing effective soil and water conservation measures and management decisions. Traditional soil erosion assessment methods typically consider only land use type and slope, neglecting spatial variability and the combined effects of multiple factors, resulting in low accuracy and reliability in assessing soil erosion levels. Recent methods employing a multi-factor spatial-ground approach to quantify soil erosion levels involve acquiring multispectral remote sensing images of the monitored area, processing the image data to obtain land use classification results, collecting precipitation data from various stations within the monitored area, and collecting standard plot observation data to obtain a ground dataset. Then, based on the land analysis results and the ground dataset, soil erosion modulus, soil erosion intensity, and erosion area are calculated, ultimately yielding a quantitative result of the soil erosion level in the monitored area.
[0004] Calculating soil erosion can help us accurately estimate the amount of soil loss, thus providing a valid reference value for soil and water conservation and enabling the implementation of effective prevention and control measures. First, potential soil erosion risks should be assessed, and effective soil and water conservation measures should be developed. Second, soil erosion should be monitored regularly to promptly identify problems and take effective countermeasures. Finally, the formula for calculating soil erosion should be reviewed and updated regularly to ensure accurate estimations.
[0005] There are generally two formulas for calculating soil erosion: 1. Soil erosion calculation formula Q=KSLA·C·P, where Q represents soil erosion volume, KSLA represents the soil erosion rate per square kilometer per hour, C represents the soil moisture correction coefficient, and P represents the land cover per square kilometer. 2. Soil erosion calculation formula: Q=A·I·C·L, where Q represents soil erosion volume, A represents the land area per square kilometer, I represents the land slope coefficient, C represents the soil moisture correction coefficient, and L represents the land cover per square kilometer.
[0006] Existing methods do not adequately consider spatial differences and the combined influence of multiple factors, resulting in insufficient accuracy and reliability of the calculation results in assessing the degree of soil erosion. The general method for quantifying the degree of soil erosion based on multiple air-ground factors considers various air and ground methods, but only considers precipitation data and standard plot observation data for ground data. Precipitation data and plot observation data reflect the soil erosion situation from a side perspective, which can lead to a large deviation between the calculated assessment results and the actual situation. Summary of the Invention
[0007] To address the aforementioned technical problems, embodiments of the present invention provide a method for early warning of soil erosion risk based on dust data, comprising: The region to be analyzed is gridded, and the resulting grid is filtered to obtain the effective grid region; Obtain NDVI data and soil moisture data for the effective grid area; Based on the terrain location of each effective grid region, determine the slope length factor and slope factor of each effective grid region; Determine the net dust data within the area to be analyzed, excluding the influence of wind direction; The dust generation value for each effective grid area is determined based on the NDVI data, soil moisture data, and net dust data. The predicted value of soil erosion intensity is determined by using neural network algorithms to calculate the NDVI data, soil moisture data, slope length factor, slope gradient factor, and dust generation value. The soil erosion intensity prediction value is used to determine the soil loss value for each effective grid area; Based on the current soil erosion value and historical soil erosion data, a soil erosion risk grid is determined, and risk warnings are issued for the soil erosion risk grid.
[0008] In one embodiment, obtaining the NDVI data and soil moisture data of the effective grid area includes: NDVI data and soil moisture data for the area to be analyzed are obtained based on satellite remote sensing data and ground moisture data for the area to be analyzed. The NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area.
[0009] In one embodiment, the NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area, including: Using the Kriging interpolation algorithm, with the center point of each effective grid as the interpolation target, the NDVI data of each effective grid region is calculated by fitting a semi-variogram function based on the NDVI pixels within a specified area of the center point. The inverse distance weighted interpolation algorithm is used to process the obtained ground moisture data in the area to be analyzed, so as to obtain the soil moisture data of each effective grid area.
[0010] In one embodiment, determining the slope factor of each effective grid region based on its terrain location includes: Obtain digital elevation data of the terrain location of each of the effective grid areas; The slope of each effective grid area is calculated using the maximum gradient method in conjunction with the digital elevation data. The slope is converted based on the USLE standard to obtain the slope factor corresponding to each effective grid area.
[0011] In one embodiment, determining the slope length factor for each effective grid region based on its terrain location includes: Obtain digital elevation data of the terrain location of each of the effective grid areas; The D8 algorithm is used to process the digital elevation data to determine the direction of water flow; The pixel slope length is obtained by summing the length value of each pixel in the direction of water flow within each effective grid area; The average slope length of each pixel in the same effective grid region is calculated, and the slope length factor of the effective grid region is determined based on the average calculation result.
[0012] In one embodiment, determining the net dust data within the area to be analyzed after removing the influence of wind direction includes: Dust monitoring data were collected from the area to be analyzed by different dust monitoring stations; Determine the dust monitoring data around each effective grid area and the upwind station data during the monitoring period; The net dust data is determined based on the difference between the dust monitoring data and the data from the upwind station.
[0013] In one embodiment, determining the dust emission value for each effective grid area based on the NDVI data, soil moisture data, and net dust data includes: Based on the NDVI data, soil moisture data, and net dust data, the inhibitory effect of vegetation and soil moisture on dust is determined, and the dust generation amount is corrected by combining the inhibitory effect to obtain the dust generation amount value.
[0014] In one embodiment, the method further includes: An initial neural network model is constructed, comprising an input layer with at least five neurons, a hidden layer with at least two layers, and an output layer with at least one neuron. The hidden layer has at least twelve neurons, and the five neurons of the input layer represent NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value, respectively. The initial neural network model is trained and optimized based on historical data to obtain a target neural network model for generating the predicted value of soil erosion intensity. The historical data includes NDVI data, soil moisture data, slope length factor, slope factor, dust generation value, and measured value of soil erosion intensity during the historical period. The process of using a neural network algorithm to calculate the predicted value of soil erosion intensity based on the NDVI data, soil moisture data, slope length factor, slope gradient factor, and dust emission value includes: The target neural network model is used to calculate the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value to obtain the predicted value of soil erosion intensity.
[0015] In one embodiment, determining the soil erosion amount for each effective grid area by combining the predicted soil erosion intensity includes: The soil erosion intensity prediction, grid area, and time period are multiplied to calculate the grid soil loss. The process of determining the soil erosion risk grid based on current soil erosion values and historical soil erosion data includes: The current value of soil erosion is compared with a preset first threshold to obtain a first comparison result; The rate of change of soil erosion is determined based on the current value of soil erosion and historical soil erosion data. The soil erosion change rate is compared with a preset second threshold to obtain a second comparison result; The soil and water loss risk grid is determined based on the first comparison result and / or the second comparison result.
[0016] Another embodiment of the present invention also provides a soil erosion risk early warning device based on dust data, comprising: The first processing module is used to perform gridding on the region to be analyzed and to filter the resulting grid to obtain the effective grid region. The acquisition module is used to acquire NDVI data and soil moisture data of the effective grid area; The first determining module is used to determine the slope length factor and slope factor of each effective grid area based on the terrain location of each effective grid area; The second determining module is used to determine the net dust data of the area to be analyzed after removing the influence of wind direction. The third determining module is used to determine the dust generation value for each of the effective grid areas based on the NDVI data, soil moisture data, and net dust data. The calculation module is used to calculate the predicted value of soil erosion intensity by using a neural network algorithm on the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value. The fourth determining module is used to determine the soil and water loss value for each effective grid area by combining the predicted soil erosion intensity value; The early warning module is used to determine the soil erosion risk grid based on the current soil erosion value and historical soil erosion data, and to provide risk warnings for the soil erosion risk grid.
[0017] Based on the content disclosed in the above embodiments, it can be seen that the method provided by the embodiments of the present invention includes reducing the calculation error of soil erosion within the effective grid from more than 30% in the existing methods to less than 15%; moreover, by relying on hourly updated dust data, it realizes hourly dynamic monitoring of soil erosion status, replacing the traditional monthly / quarterly lagging assessment; in addition, it can identify 5%-10% of the area as "high-risk grids", providing "targets" for soil and water conservation measures.
[0018] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.
[0019] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0021] Figure 1 This is a flowchart illustrating the soil erosion risk early warning method based on dust data in an embodiment of the present invention.
[0022] Figure 2 This is a flowchart illustrating a method for early warning of soil erosion risk based on dust data, according to another embodiment of the present invention.
[0023] Figure 3 This is a flowchart illustrating a method for early warning of soil erosion risk based on dust data in another embodiment of the present invention.
[0024] Figure 4 This is a structural block diagram of the soil and water loss risk early warning device based on dust data in an embodiment of the present invention. Detailed Implementation
[0025] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but these are not intended to limit the scope of the invention.
[0026] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the following description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope of this disclosure will be apparent to those skilled in the art.
[0027] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.
[0028] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.
[0029] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention, which have the features described in the claims and are therefore all within the scope of protection defined herein.
[0030] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.
[0031] Specific embodiments of the present disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure and can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the present disclosure. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely to serve as the basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of substantially any suitable detailed structures.
[0032] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.
[0033] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0034] like Figure 1 As shown, this embodiment of the invention provides a method for early warning of soil erosion risk based on dust data, including: S1: The region to be analyzed is gridded, and the resulting grid is filtered to obtain the effective grid region; S2: Obtain NDVI data and soil moisture data for the effective grid area; S3: Based on the terrain location of each effective grid region, determine the slope length factor and slope factor of each effective grid region; S4: Determine the net dust data within the area to be analyzed after removing the influence of wind direction; S5: Determine the dust generation value for each effective grid area based on the NDVI data, soil moisture data, and net dust data; S6: Calculate the predicted value of soil erosion intensity using the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value using a neural network algorithm; S7: Determine the soil and water loss value for each effective grid area based on the predicted soil erosion intensity value; S8: Determine the soil erosion risk grid based on the current soil erosion value and historical soil erosion data, and issue risk warnings for the soil erosion risk grid.
[0035] Based on the above, this embodiment collects "dust monitoring data," "satellite NDVI data," and "ground soil moisture data," and integrates these data types. It also constructs effective analysis units using a combination of gridding and water area removal. Next, using "net dust volume" as the core variable, it establishes a dust volume-erosion intensity correlation based on vegetation cover and soil moisture, replacing the traditional indirect "precipitation-erosion" relationship. A neural network algorithm is introduced to dynamically optimize model parameters using historical data, enabling the rapid and effective determination of soil erosion values. Finally, based on the dual standards of "grid-based dynamic change rate of soil erosion" and "absolute erosion threshold," key risk areas are identified, replacing the traditional static method of "classifying risk solely by absolute amount," thus achieving accurate risk warnings.
[0036] Based on the content disclosed in the above embodiments, it can be seen that the method provided in this embodiment can reduce the calculation error of soil erosion within the effective grid from more than 30% in the existing methods to less than 15%; moreover, by relying on hourly updated dust data, it realizes hourly dynamic monitoring of soil erosion status, replacing the traditional monthly / quarterly lagging assessment; in addition, it can identify 5%-10% of the area as "high-risk grids", providing "targets" for soil and water conservation measures.
[0037] Furthermore, in one embodiment, the region to be analyzed is gridded, and the resulting grid is filtered to obtain an effective grid region, including obtaining the latitude and longitude range of the analysis region and drawing the grid at a resolution such as 3.3 km.
[0038] Calculate the number of horizontal grids (3km ≈ 0.027° longitude), number of vertical grids , co-generated An initial grid; Import contemporaneous Sentinel-2 satellite imagery (10m resolution), calculate the NDWI value of each initial grid, and when the percentage of pixels with NDWI ≥ 0.3 within a grid is ≥ 50%, it is identified as a "water area grid" and removed, and finally "effective analysis grids" are retained.
[0039] Furthermore, such as Figure 2 As shown, obtaining the NDVI data and soil moisture data of the effective grid area includes: S201: Based on satellite remote sensing data and ground moisture data for the area to be analyzed, obtain the corresponding NDVI data and soil moisture data for the area to be analyzed; S202: The NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area.
[0040] Specifically, the NDVI data and soil moisture data of the area to be analyzed are processed using an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area, including: S203: Using the Kriging interpolation algorithm, with the center point of each effective grid as the interpolation target, a semi-variogram function is fitted based on the NDVI pixels within a specified area of the center point to calculate the NDVI data of each effective grid region. S204: The inverse distance weighted interpolation algorithm is used to process the obtained ground moisture data in the area to be analyzed to obtain soil moisture data for each effective grid area.
[0041] For example, the processing of NDVI data includes: Data source: Landsat-8 satellite imagery (30m resolution, updated every 16 days), NDVI value calculated. ; Interpolation method: Kriging interpolation is used, with the grid center point as the interpolation target. Combined with the surrounding NDVI pixels within a range of, but not limited to, 5km (sample size ≥ 20), a semi-variogram function (spherical model) is fitted to obtain the NDVI of each effective grid. i,j ; The processing of soil moisture data includes: Data source: Soil moisture data is obtained from ground moisture monitoring stations within the region; Interpolation method: Inverse distance weighted interpolation (IDW) is used, where the weights are inversely proportional to the square of the distance, to obtain soil moisture data for each effective grid. (unit:%).
[0042] In another embodiment, determining the slope factor of each effective grid region based on its terrain location includes: S301: Obtain digital elevation data of the terrain location of each of the effective grid areas; S302: The slope of each effective grid area is calculated using the maximum gradient method in conjunction with the digital elevation data; S303: Based on the USLE standard, the slope is converted to obtain the slope factor corresponding to each of the effective grid areas.
[0043] Specifically, digital elevation data can be obtained using ASTER GDEM, with a resolution of 30m. Then, the slope of each DEM pixel is calculated using the "maximum gradient method". :
[0044] in, This represents the maximum elevation difference between a pixel and its eight adjacent pixels. Next, convert the slope to a slope factor according to the USLE standard. : .
[0045] Furthermore, based on the terrain location of each effective grid region, the slope length factor of each effective grid region is determined, including: S304: Obtain digital elevation data of the terrain location of each of the effective grid areas; S305: The D8 algorithm is used to process the digital elevation data to determine the direction of water flow; S306: For each pixel within the effective grid area, sum the length value of the pixel in the direction of water flow to obtain the pixel slope length; S307: Calculate the average slope length of the pixels corresponding to the same effective grid region, and determine the slope length factor of the effective grid region based on the average calculation result.
[0046] In this embodiment, digital elevation data is obtained using the same method described above. Then, the D8 algorithm is used to calculate the digital elevation data to determine the water flow direction. The length of each pixel along the water flow direction within the same effective grid area is then accumulated to obtain the pixel slope length. Finally, the average value of all pixel slope lengths within the effective grid area is taken. L avg Then convert it into a slope length factor: (22.13mwei USLE standard slope length).
[0047] like Figure 3 As shown, determining the net dust data within the area to be analyzed after removing the influence of wind direction includes: S401: Collect dust monitoring data of the area to be analyzed through different dust monitoring stations; S402: Determine the dust monitoring data around each effective grid area and the upwind station data during the monitoring period; S403: Determine the net dust data based on the difference between the dust monitoring data and the upwind station data.
[0048] For example, in this embodiment, to obtain net dust data by eliminating external dust interference, the formula used is: ,in, t For the monitoring period, Data for dust monitoring stations surrounding the grid. Data for the upwind station.
[0049] Furthermore, determining the dust emission value for each effective grid area based on the NDVI data, soil moisture data, and net dust data includes: S501: Based on the NDVI data, soil moisture data, and net dust data, determine the inhibitory effect of vegetation and soil moisture on dust, and combine the inhibitory effect to perform a dust generation correction calculation on the net dust data to obtain the dust generation value.
[0050] In this embodiment, the dust generation rate is calculated by considering the dust-suppressing effects of vegetation and soil moisture, along with the following formula:
[0051] in, , This is the value of bare land. This represents the total vegetation coverage value.
[0052] 35% is the soil saturation moisture content, suitable for red soil in South China. , is the regional calibration coefficient, calculated from the measured values of PM2.5 in the region during the historical period. 10 Data inversion yielded the results.
[0053] In another embodiment, the method further includes: S9: Construct an initial neural network model, which includes an input layer with at least five neurons, a hidden layer with at least two layers, and an output layer with at least one neuron. The hidden layer has at least twelve neurons, and the five neurons of the input layer represent NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value, respectively. S10: The initial neural network model is trained and optimized based on historical data to obtain a target neural network model for generating the predicted value of soil erosion intensity. The historical data includes NDVI data, soil moisture data, slope length factor, slope factor, dust generation value and measured value of soil erosion intensity during the historical period. The process of using a neural network algorithm to calculate the predicted value of soil erosion intensity based on the NDVI data, soil moisture data, slope length factor, slope gradient factor, and dust emission value includes: S601: The target neural network model is used to calculate the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value to obtain the predicted value of soil erosion intensity.
[0054] For example, the neural network algorithm described in this embodiment is actually using a neural network model to calculate soil erosion intensity. The model in this embodiment is obtained based on the following method: (1) Neural network model construction: Input layer: 5 neurons All parameters are normalized to [0,1]. Hidden layers: 2 layers (12 neurons per layer), activation function is ; Output layer: 1 neuron (soil erosion intensity) (Unit: t / (km²·a)), the activation function is a linear function.
[0055] (2) Model training and optimization: Training set: Historical data from the past n years in the region (assuming it contains 1200 sets of "input parameters - measured erosion intensity" samples, with measured values obtained by the runoff plot weighing method); Optimization logic: based on mean squared error (MSE) Using as the objective function, the Adam optimizer (learning rate 0.001, 500 iterations) is employed until the validation set MSE is less than 0.05; (3) Erosion intensity output: The grid parameters obtained in the previous steps, i.e. the parameters represented by the five neurons mentioned above, are input into the trained model to obtain the soil erosion intensity of each effective grid area output by the model. .
[0056] After calculating the soil erosion intensity, the soil and water loss value for each effective grid area can be determined by combining the predicted soil erosion intensity value, including: S701: The soil erosion intensity prediction value, grid area and time period are combined to calculate the grid soil loss amount; The process of determining the soil erosion risk grid based on current soil erosion values and historical soil erosion data includes: S801: Compare the current value of soil erosion with a preset first threshold to obtain a first comparison result; S802: Determine the rate of change of soil erosion based on the current value of soil erosion and historical soil erosion data; S803: Compare the soil erosion change rate with a preset second threshold to obtain a second comparison result; S804: Determine the soil and water loss risk grid based on the first comparison result and / or the second comparison result.
[0057] In this embodiment, the calculation of grid soil erosion is obtained by combining the grid area (e.g., 9 km²) and the calculation period (e.g., 1 year) using a formula: (Unit: t); Next, we can compare the grid soil erosion data from the past two years, such as 2023 and 2024, and calculate the rate of change:
[0058] In this embodiment, a first threshold of 800t and a second threshold of 30% are set. The risk grid determination includes: High-risk grid: (90th percentile of the region) or ; Medium-risk grid: or .
[0059] Based on the above judgment, when it is determined that an early warning needs to be issued, such as for medium-risk grids or high-risk grids, the system can choose to generate an "analysis area risk heat map" to mark the latitude and longitude boundaries of high / medium-risk grids (e.g., 5 high-risk grids were identified in the region in 2024, concentrated in the exposed slope area of a certain street), providing precise guidance for governance measures.
[0060] like Figure 4 As shown, another embodiment of the present invention also provides a soil erosion risk early warning device based on dust data, comprising: The first processing module is used to perform gridding on the region to be analyzed and to filter the resulting grid to obtain the effective grid region. The acquisition module is used to acquire NDVI data and soil moisture data of the effective grid area; The first determining module is used to determine the slope length factor and slope factor of each effective grid area based on the terrain location of each effective grid area; The second determining module is used to determine the net dust data of the area to be analyzed after removing the influence of wind direction. The third determining module is used to determine the dust generation value for each of the effective grid areas based on the NDVI data, soil moisture data, and net dust data. The calculation module is used to calculate the predicted value of soil erosion intensity by using a neural network algorithm on the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value. The fourth determining module is used to determine the soil and water loss value for each effective grid area by combining the predicted soil erosion intensity value; The early warning module is used to determine the soil erosion risk grid based on the current soil erosion value and historical soil erosion data, and to provide risk warnings for the soil erosion risk grid.
[0061] In one embodiment, obtaining the NDVI data and soil moisture data of the effective grid area includes: NDVI data and soil moisture data for the area to be analyzed are obtained based on satellite remote sensing data and ground moisture data for the area to be analyzed. The NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area.
[0062] In one embodiment, the NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area, including: Using the Kriging interpolation algorithm, with the center point of each effective grid as the interpolation target, the NDVI data of each effective grid region is calculated by fitting a semi-variogram function based on the NDVI pixels within a specified area of the center point. The inverse distance weighted interpolation algorithm is used to process the obtained ground moisture data in the area to be analyzed, so as to obtain the soil moisture data of each effective grid area.
[0063] In one embodiment, determining the slope factor of each effective grid region based on its terrain location includes: Obtain digital elevation data of the terrain location of each of the effective grid areas; The slope of each effective grid area is calculated using the maximum gradient method in conjunction with the digital elevation data. The slope is converted based on the USLE standard to obtain the slope factor corresponding to each effective grid area.
[0064] In one embodiment, determining the slope length factor for each effective grid region based on its terrain location includes: Obtain digital elevation data of the terrain location of each of the effective grid areas; The D8 algorithm is used to process the digital elevation data to determine the direction of water flow; The pixel slope length is obtained by summing the length value of each pixel in the direction of water flow within each effective grid area; The average slope length of each pixel in the same effective grid region is calculated, and the slope length factor of the effective grid region is determined based on the average calculation result.
[0065] In one embodiment, determining the net dust data within the area to be analyzed after removing the influence of wind direction includes: Dust monitoring data were collected from the area to be analyzed by different dust monitoring stations; Determine the dust monitoring data around each effective grid area and the upwind station data during the monitoring period; The net dust data is determined based on the difference between the dust monitoring data and the data from the upwind station.
[0066] In one embodiment, determining the dust emission value for each effective grid area based on the NDVI data, soil moisture data, and net dust data includes: Based on the NDVI data, soil moisture data, and net dust data, the inhibitory effect of vegetation and soil moisture on dust is determined, and the dust generation amount is corrected by combining the inhibitory effect to obtain the dust generation amount value.
[0067] In one embodiment, the device further includes: A construction module is used to construct an initial neural network model, which includes an input layer with at least five neurons, at least two hidden layers, and an output layer with at least one neuron. The hidden layer has at least twelve neurons, and the five neurons of the input layer represent NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value, respectively. The training module is used to train and optimize the initial neural network model based on historical data to obtain a target neural network model for generating the predicted value of soil erosion intensity. The historical data includes NDVI data, soil moisture data, slope length factor, slope factor, dust generation value and measured value of soil erosion intensity during the historical period. The process of using a neural network algorithm to calculate the predicted value of soil erosion intensity based on the NDVI data, soil moisture data, slope length factor, slope gradient factor, and dust emission value includes: The target neural network model is used to calculate the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value to obtain the predicted value of soil erosion intensity.
[0068] In one embodiment, determining the soil erosion amount for each effective grid area by combining the predicted soil erosion intensity includes: The soil erosion intensity prediction, grid area, and time period are multiplied to calculate the grid soil loss. The process of determining the soil erosion risk grid based on current soil erosion values and historical soil erosion data includes: The current value of soil erosion is compared with a preset first threshold to obtain a first comparison result; The rate of change of soil erosion is determined based on the current value of soil erosion and historical soil erosion data. The soil erosion change rate is compared with a preset second threshold to obtain a second comparison result; The soil and water loss risk grid is determined based on the first comparison result and / or the second comparison result.
[0069] Another embodiment of the present invention also provides an electronic device, comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the soil and water loss risk early warning method based on dust data as described above.
[0070] Furthermore, one embodiment of the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the soil erosion risk early warning method based on dust data as described above. It should be understood that the various solutions in this embodiment have the corresponding technical effects in the above-described method embodiments, and will not be repeated here.
[0071] Furthermore, embodiments of the present invention also provide a computer program product, which is tangibly stored on a computer-readable medium and includes computer-readable instructions, which, when executed, cause at least one processor to perform a soil erosion risk early warning method based on dust data, such as the embodiment described above.
[0072] It should be noted that the computer storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access storage medium (RAM), a read-only storage medium (ROM), an erasable programmable read-only storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only storage medium (CD-ROM), an optical storage medium, a magnetic storage medium, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program configured for use by or in connection with an instruction execution system, system, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, antenna, optical fiber, RF, etc., or any suitable combination thereof.
[0073] Furthermore, those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.
[0074] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.
[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0076] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.
Claims
1. A method for early warning of soil erosion risk based on dust data, characterized in that, include: The region to be analyzed is gridded, and the resulting grid is filtered to obtain the effective grid region; Obtain NDVI data and soil moisture data for the effective grid area; Based on the terrain location of each effective grid region, determine the slope length factor and slope factor of each effective grid region; Determine the net dust data within the area to be analyzed, excluding the influence of wind direction; The dust generation value for each effective grid area is determined based on the NDVI data, soil moisture data, and net dust data. The predicted value of soil erosion intensity is determined by using neural network algorithms to calculate the NDVI data, soil moisture data, slope length factor, slope gradient factor, and dust generation value. The soil erosion intensity prediction value is used to determine the soil loss value for each effective grid area; Based on the current soil erosion value and historical soil erosion data, a soil erosion risk grid is determined, and risk warnings are issued for the soil erosion risk grid.
2. The method for early warning of soil erosion risk based on dust data according to claim 1, characterized in that, The process of obtaining NDVI data and soil moisture data for the effective grid area includes: NDVI data and soil moisture data for the area to be analyzed are obtained based on satellite remote sensing data and ground moisture data for the area to be analyzed. The NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area.
3. The method for early warning of soil erosion risk based on dust data according to claim 2, characterized in that, The NDVI data and soil moisture data of the area to be analyzed are processed by an interpolation algorithm to obtain the NDVI data and soil moisture data corresponding to the effective grid area, including: Using the Kriging interpolation algorithm, with the center point of each effective grid as the interpolation target, the NDVI data of each effective grid region is calculated by fitting a semi-variogram function based on the NDVI pixels within a specified area of the center point. The inverse distance weighted interpolation algorithm is used to process the obtained ground moisture data in the area to be analyzed, so as to obtain the soil moisture data of each effective grid area.
4. The method for early warning of soil erosion risk based on dust data according to claim 1, characterized in that, The step of determining the slope factor of each effective grid region based on its terrain location includes: Obtain digital elevation data of the terrain location of each of the effective grid areas; The slope of each effective grid area is calculated using the maximum gradient method in conjunction with the digital elevation data. The slope is converted based on the USLE standard to obtain the slope factor corresponding to each effective grid area.
5. The method for early warning of soil erosion risk based on dust data according to claim 1, characterized in that, Based on the terrain location of each effective grid region, the slope length factor of each effective grid region is determined, including: Obtain digital elevation data of the terrain location of each of the effective grid areas; The D8 algorithm is used to process the digital elevation data to determine the direction of water flow; The pixel slope length is obtained by summing the length value of each pixel in the direction of water flow within each effective grid area; The average slope length of each pixel in the same effective grid region is calculated, and the slope length factor of the effective grid region is determined based on the average calculation result.
6. The method for early warning of soil erosion risk based on dust data according to claim 1, characterized in that, The determination of net dust data within the area to be analyzed, excluding the influence of wind direction, includes: Dust monitoring data were collected from the area to be analyzed by different dust monitoring stations; Determine the dust monitoring data around each effective grid area and the upwind station data during the monitoring period; The net dust data is determined based on the difference between the dust monitoring data and the data from the upwind station.
7. The method for early warning of soil erosion risk based on dust data according to claim 6, characterized in that, The determination of the dust emission value for each effective grid area based on the NDVI data, soil moisture data, and net dust data includes: Based on the NDVI data, soil moisture data, and net dust data, the inhibitory effect of vegetation and soil moisture on dust is determined, and the dust generation amount is corrected by combining the inhibitory effect to obtain the dust generation amount value.
8. The method for early warning of soil erosion risk based on dust data according to claim 1, characterized in that, The method further includes: An initial neural network model is constructed, comprising an input layer with at least five neurons, a hidden layer with at least two layers, and an output layer with at least one neuron. The hidden layer has at least twelve neurons, and the five neurons of the input layer represent NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value, respectively. The initial neural network model is trained and optimized based on historical data to obtain a target neural network model for generating the predicted value of soil erosion intensity. The historical data includes NDVI data, soil moisture data, slope length factor, slope factor, dust generation value, and measured value of soil erosion intensity during the historical period. The process of using a neural network algorithm to calculate the predicted value of soil erosion intensity based on the NDVI data, soil moisture data, slope length factor, slope gradient factor, and dust emission value includes: The target neural network model is used to calculate the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value to obtain the predicted value of soil erosion intensity.
9. The method for early warning of soil erosion risk based on dust data according to claim 1, characterized in that, The determination of soil erosion amount for each effective grid area based on the predicted soil erosion intensity includes: The soil erosion intensity prediction, grid area, and time period are multiplied to calculate the grid soil loss. The process of determining the soil erosion risk grid based on current soil erosion values and historical soil erosion data includes: The current value of soil erosion is compared with a preset first threshold to obtain a first comparison result; The rate of change of soil erosion is determined based on the current value of soil erosion and historical soil erosion data. The soil erosion change rate is compared with a preset second threshold to obtain a second comparison result; The soil and water loss risk grid is determined based on the first comparison result and / or the second comparison result.
10. A soil erosion risk early warning device based on dust data, characterized in that, include: The first processing module is used to perform gridding on the region to be analyzed and to filter the resulting grid to obtain the effective grid region. The acquisition module is used to acquire NDVI data and soil moisture data of the effective grid area; The first determining module is used to determine the slope length factor and slope factor of each effective grid area based on the terrain location of each effective grid area; The second determining module is used to determine the net dust data of the area to be analyzed after removing the influence of wind direction. The third determining module is used to determine the dust generation value for each of the effective grid areas based on the NDVI data, soil moisture data, and net dust data. The calculation module is used to calculate the predicted value of soil erosion intensity by using a neural network algorithm on the NDVI data, soil moisture data, slope length factor, slope factor, and dust generation value. The fourth determining module is used to determine the soil and water loss value for each effective grid area by combining the predicted soil erosion intensity value; The early warning module is used to determine the soil erosion risk grid based on the current soil erosion value and historical soil erosion data, and to provide risk warnings for the soil erosion risk grid.