Water and soil loss telemetry data analysis method and system based on deep learning

Abstract

The invention discloses a water and soil loss telemetry data analysis method and system based on deep learning, and relates to the technical field of data analysis, and the method comprises the steps: extracting soil loss data, surface runoff data and topographic data; fusing the soil loss data, the surface runoff data and the topographic data, and obtaining water and soil loss risk index data and soil erosion rate data through a feature extraction technology; calculating weight values of the water and soil loss risk index data and the soil erosion rate data by using a feature evaluation technology; and based on the water and soil loss risk index data, the soil erosion rate data and the weight value, constructing a water and soil loss prediction model by using a deep learning framework and a space-time analysis algorithm. According to the invention, through telemetry data collection and feature extraction, key water and soil loss information can be rapidly obtained, the data processing flow is simplified, and the accuracy and reliability of data are ensured.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a soil and water loss telemetry data analysis method and system based on deep learning. Background Art

[0002] Soil erosion is a complex environmental problem. It refers to the erosion of surface soil and rock under the action of natural external forces such as water flow, wind, gravity and freeze-thaw cycles, accompanied by material migration and deposition. This process not only includes multiple erosion mechanisms, but also leads to a significant decrease in land productivity. Therefore, accurate and efficient monitoring and analysis of soil erosion is crucial to solving this problem.

[0003] In recent years, with the development of remote sensing technology, it has become an important means to monitor soil erosion in large areas using image data collected by platforms such as satellites or drones. These remote sensing technologies can provide real-time and continuous data coverage. However, the traditional method of remote sensing data analysis, which relies on manual interpretation and basic statistical methods, has limitations in deep mining of data information and is inefficient. To address these problems, deep learning-based methods have been introduced into the analysis of remote sensing data of soil erosion. This method automatically extracts important features from images through deep learning algorithms, thereby achieving more accurate identification and quantitative evaluation.

[0004] Despite this, soil and water loss monitoring equipment is currently mainly concentrated in key ecological areas and large watersheds, while the coverage of the monitoring network is still insufficient for urban fringe areas, small watersheds and remote areas. This uneven distribution of data collection has led to an incomplete understanding of the soil and water loss situation in these specific areas, which in turn limits the ability to formulate effective governance measures for these areas. In addition, due to technical limitations, some monitoring equipment may have false alarms or omissions, which not only affects the authenticity of the data, but may also mislead the subsequent soil and water conservation strategy planning, and ultimately affect the accuracy of the prediction model and analysis results.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In response to the problems in the related technology, the present invention proposes a soil and water loss telemetry data analysis method and system based on deep learning to overcome the above-mentioned technical problems existing in the existing related technology.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] According to one aspect of the present invention, a method for analyzing soil and water loss telemetry data based on deep learning is provided, the method comprising the following steps:

[0009] S1. Collect telemetry data of soil erosion monitoring areas, and extract soil loss data, surface runoff data and terrain data based on the telemetry data;

[0010] S2, integrating soil loss data, surface runoff data and terrain data, and obtaining soil and water loss risk index data and soil erosion rate data through feature extraction technology;

[0011] S3. Calculate the weight values ​​of soil and water loss risk index data and soil erosion rate data using feature evaluation technology;

[0012] S4. Based on the soil and water loss risk index data, soil erosion rate data and weight values, a soil and water loss prediction model is constructed using a deep learning framework and spatiotemporal analysis algorithm;

[0013] S5. Use the soil and water loss prediction model to predict the soil and water loss situation, and formulate soil and water loss prevention and control measures based on the prediction results.

[0014] Furthermore, collecting telemetry data of the soil erosion monitoring area and extracting soil loss data, surface runoff data and terrain data based on the telemetry data includes the following steps:

[0015] S11. Obtain remote sensing data of soil erosion monitoring areas through satellite remote sensing platforms;

[0016] S12. Use geographic reference points and geometric registration technology of the geographic information system to perform geographic correction on the telemetry data, and use atmospheric correction software to process the geographically corrected telemetry data;

[0017] S13. Based on the processed telemetry data, compare the changes in vegetation coverage and bare surface area in different time series, and obtain soil loss data in the monitoring area through the differential vegetation index algorithm;

[0018] S14, extracting water body information from the processed telemetry data, monitoring the change in the surface water area, and combining rainfall data with the hydrological model to obtain surface runoff data in the monitoring area;

[0019] S15. Use remote sensing technology to generate digital elevation model data, and combine it with terrain analysis algorithms to calculate and extract terrain data of the monitored area.

[0020] Furthermore, the telemetry data is geographically corrected using the geographic reference points and geometric registration technology of the geographic information system, and the atmospheric correction software is used to process the geographically corrected telemetry data, including the following steps:

[0021] S121, importing the acquired telemetry data into a geographic information system, and selecting map projection and coordinates according to the geographic features of the monitoring area;

[0022] S122, identifying and marking ground control points with known coordinates as geographic reference points in the geographic information system, and selecting pixel locations corresponding to the geographic reference points in the telemetry data to establish control point pairs;

[0023] S123, performing affine transformation based on the control point pairs, geo-correcting the telemetry data, and resampling the geo-corrected telemetry data;

[0024] S124, using atmospheric correction software to perform radiation calibration on the resampled remote sensing data, and converting the value of each band in the remote sensing data into an atmospheric radiation brightness value;

[0025] S125. Use atmospheric correction software to process the radiation brightness value and restore the radiation brightness value to the surface reflectance value.

[0026] Furthermore, based on the processed telemetry data, the changes in vegetation coverage and bare surface area in different time series are compared, and the soil loss data of the monitoring area is obtained by using the differential vegetation index algorithm, including the following steps:

[0027] S131, based on the processed telemetry data, using the normalized vegetation index formula to calculate the telemetry data of each period;

[0028] S132, setting a threshold value according to the calculated normalized vegetation index, distinguishing the vegetation-covered area from the bare surface area by the threshold value, and vectorizing the vegetation-covered area and the bare surface area into a surface layer;

[0029] S133, in the geographic information system, overlaying the vegetation coverage layer and the bare surface layer of different periods, identifying the change area, and counting the change amount of the vegetation coverage area and the bare surface area in each period;

[0030] S134. Analyze the changing trends of vegetation cover and bare surface area based on the statistical changes;

[0031] S135, selecting one of the telemetry data of different periods as the baseline data, and calculating the differential vegetation index between the baseline data and the telemetry data of each period using a differential vegetation index algorithm;

[0032] S136. Using the pre-built soil and water loss assessment model and the differential vegetation index, estimate the soil loss data in the monitoring area;

[0033] S137. Integrate the estimated soil loss data and change trends to obtain the soil loss data of the monitoring area at different periods.

[0034] Furthermore, the normalized vegetation index formula is:

[0035]

[0036] Where, NDVI represents the normalized difference vegetation index;

[0037] NIR represents the reflectivity in the near infrared band;

[0038] RED represents the reflectivity of the red light band.

[0039] Furthermore, integrating soil loss data, surface runoff data and terrain data, and obtaining soil and water loss risk index data and soil erosion rate data through feature extraction technology includes the following steps:

[0040] S21. Using principal component analysis, soil loss data, surface runoff data and terrain data are integrated into the data set;

[0041] S22. Extracting characteristics of soil and water loss from the data set, the characteristics of soil and water loss include average soil loss in different time periods, average surface runoff, and volatility of soil loss;

[0042] S23. Calculate the soil and water loss risk index data based on the average soil loss and average surface runoff in different time periods and combined with terrain data;

[0043] S24. Calculate soil erosion rate data based on the volatility of soil loss in different time periods and combined with terrain data.

[0044] Furthermore, calculating the weight values ​​of the soil and water loss risk index data and the soil erosion rate data using the feature evaluation technology includes the following steps:

[0045] S31, extracting characteristic data from the soil and water loss risk index data and the soil erosion rate data, and combining the extracted characteristic data into a characteristic matrix;

[0046] S32. According to the analysis requirements, define the soil and water loss risk index and soil erosion rate as target variables, and use statistical algorithms to calculate the correlation between each feature and the target variable to obtain the feature correlation coefficient;

[0047] S33, normalizing the feature correlation coefficient to a preset interval, and assigning a corresponding weight value to each feature according to the normalized feature correlation coefficient score.

[0048] Furthermore, based on the soil erosion risk index data, soil erosion rate data and weight values, a soil erosion prediction model is constructed using a deep learning framework and spatiotemporal analysis algorithm, including the following steps:

[0049] S41. Use a deep learning framework to perform time series analysis on the soil and water loss risk index data and the soil erosion rate data to detect whether there is periodic data in the data. If there is periodic data, use a time series decomposition algorithm to remove the periodic data. If there is no periodic data, continue to analyze the periodic changes in the data.

[0050] S42, based on the soil and water loss risk index data and soil erosion rate data after removing the periodic data, the beam forming technology in the spatiotemporal analysis algorithm is used to extract the amplitude and phase information of each frequency component as a feature vector;

[0051] S43, according to the acquired characteristic vector, the significance of each frequency component is evaluated by statistical test, and screening is performed based on the evaluation result to construct a periodicity prediction model;

[0052] S44, taking the remaining data after removing the periodic data as random fluctuation data, and constructing a fluctuation prediction model using a deep learning framework;

[0053] S45, integrating and superimposing the periodic prediction model, the fluctuation prediction model and the weight value to obtain a soil and water loss prediction model.

[0054] Furthermore, the formula of soil erosion prediction model is:

[0055]

[0056] In the formula, It represents the predicted value of soil erosion;

[0057] y1 represents the predicted value of the periodic forecast model;

[0058] ω1 represents the weight value of the periodic prediction model;

[0059] y2 represents the predicted value of the volatility prediction model;

[0060] ω2 represents the weight value of the volatility prediction model.

[0061] According to another aspect of the present invention, there is also provided a soil and water loss telemetry data analysis system based on deep learning, the system comprising a data collection and extraction module, a data fusion and feature extraction module, a feature evaluation and weight calculation module, a model building module and a prediction and prevention strategy formulation module;

[0062] The data collection and extraction module is used to collect telemetry data of the soil erosion monitoring area and extract soil loss data, surface runoff data and terrain data based on the telemetry data;

[0063] Data fusion and feature extraction module, used to fuse soil loss data, surface runoff data and terrain data, and obtain soil and water loss risk index data and soil erosion rate data through feature extraction technology;

[0064] The feature evaluation and weight calculation module is used to calculate the weight values ​​of soil and water loss risk index data and soil erosion rate data using feature evaluation technology;

[0065] Model building module, which is used to build a soil and water loss prediction model based on soil and water loss risk index data, soil erosion rate data and weight values ​​using a deep learning framework and spatiotemporal analysis algorithm;

[0066] The prediction and prevention strategy formulation module is used to predict the soil and water loss situation using the soil and water loss prediction model, and formulate soil and water loss prevention and control measures based on the prediction results.

[0067] The beneficial effects of the present invention are:

[0068] 1. The present invention can quickly obtain key soil and water loss information through telemetry data collection and feature extraction, which not only simplifies the data processing process, but also ensures the accuracy and reliability of the data, laying a solid foundation for subsequent analysis and prediction.

[0069] 2. By constructing a soil and water loss prediction model, the present invention not only has powerful learning and generalization capabilities, but also can fully consider the changing factors in time and space, thereby realizing accurate prediction of soil and water loss conditions, providing strong technical support for the formulation of targeted prevention and control measures, and helping to more effectively deal with the problem of soil and water loss.

[0070] 3. The present invention formulates soil and water loss prevention and control measures based on the prediction results, and can accurately implement measures according to the characteristics of soil and water loss in different regions and different time periods. It can not only effectively curb the deteriorating trend of soil and water loss, but also promote the protection and restoration of the ecological environment and achieve sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0072] Figure 1 is a flow chart of a soil and water loss telemetry data analysis method based on deep learning according to an embodiment of the present invention;

[0073] Figure 2It is a principle block diagram of a soil and water loss telemetry data analysis system based on deep learning according to an embodiment of the present invention.

[0074] In the figure:

[0075] 1. Data collection and extraction module; 2. Data fusion and feature extraction module; 3. Feature evaluation and weight calculation module; 4. Model building module; 5. Prediction and prevention strategy formulation module. DETAILED DESCRIPTION

[0076] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0077] According to an embodiment of the present invention, a method and system for analyzing soil and water loss telemetry data based on deep learning are provided.

[0078] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the soil and water loss telemetry data analysis method based on deep learning in an embodiment of the present invention, the method includes the following steps:

[0079] S1. Collect telemetry data of soil erosion monitoring areas, and extract soil loss data, surface runoff data and terrain data based on the telemetry data.

[0080] Specifically, collecting telemetry data of the soil erosion monitoring area and extracting soil loss data, surface runoff data and terrain data based on the telemetry data includes the following steps:

[0081] S11. Obtain remote sensing data of soil erosion monitoring areas through satellite remote sensing platforms.

[0082] It should be noted that telemetry data includes remote sensing images, surface reflectivity, vegetation index and terrain data.

[0083] S12. Use the geographic reference points and geometric registration technology of the geographic information system to geo-correct the telemetry data, and use atmospheric correction software to process the geo-corrected telemetry data.

[0084] Specifically, using the geographic reference point and geometric registration technology of the geographic information system to perform geographic correction on the telemetry data, and applying the atmospheric correction software to process the geographically corrected telemetry data includes the following steps:

[0085] S121, importing the acquired telemetry data into a geographic information system, and selecting map projection and coordinates according to the geographic features of the monitoring area;

[0086] S122, identifying and marking ground control points with known coordinates as geographic reference points in the geographic information system, and selecting pixel locations corresponding to the geographic reference points in the telemetry data to establish control point pairs;

[0087] S123, performing affine transformation based on the control point pairs, geo-correcting the telemetry data, and resampling the geo-corrected telemetry data;

[0088] S124, using atmospheric correction software to perform radiation calibration on the resampled remote sensing data, and converting the value of each band in the remote sensing data into an atmospheric radiation brightness value;

[0089] S125. Use atmospheric correction software to process the radiation brightness value and restore the radiation brightness value to the surface reflectance value.

[0090] S13. Based on the processed telemetry data, compare the changes in vegetation coverage and bare surface area in different time series, and obtain soil loss data in the monitoring area through the differential vegetation index algorithm.

[0091] Specifically, based on the processed telemetry data, the changes in vegetation coverage and bare surface area in different time series are compared, and the soil loss data of the monitoring area is obtained by using the differential vegetation index algorithm, including the following steps:

[0092] S131. Based on the processed telemetry data, the telemetry data of each period is calculated using the normalized vegetation index formula.

[0093] Specifically, the normalized vegetation index formula is:

[0094]

[0095] Where, NDVI represents the normalized difference vegetation index;

[0096] NIR represents the reflectivity in the near infrared band;

[0097] RED represents the reflectivity of the red light band.

[0098] It should be noted that the NDVI value range is usually from -1 to +1, but in most cases, the value will be between 0 and 1; positive values ​​indicate vegetation cover, and the closer the value is to +1, the more lush the vegetation; negative values ​​may indicate water bodies or clouds, etc.; values ​​close to 0 may represent bare soil or other non-vegetated surfaces.

[0099] S132. A threshold is set according to the calculated normalized vegetation index, and the vegetation-covered area and the bare surface area are distinguished by the threshold, and the vegetation-covered area and the bare surface area are vectorized into a surface layer.

[0100] S133. In the geographic information system, the vegetation coverage layer and the bare surface layer of different periods are superimposed to identify the changed areas, and the changes in the vegetation coverage area and the bare surface area in each period are counted.

[0101] S134. Analyze the changing trends of vegetation coverage and bare surface area based on the statistical changes.

[0102] S135. Select one of the telemetry data from different periods as the baseline data, and use the differential vegetation index algorithm to calculate the differential vegetation index between the baseline data and the telemetry data of each period.

[0103] S136. Use the pre-built soil and water loss assessment model in combination with the differential vegetation index to estimate the soil loss data in the monitoring area.

[0104] It should be noted that the formula of the soil and water loss assessment model is: A=R*K*LS*C*P; where A represents the average annual soil loss (unit: tons / hectare·year); R represents the rainfall erosivity factor, which reflects the rainfall intensity and the energy of raindrops hitting the ground; K represents the soil erodibility factor, which is determined based on soil type and texture; LS represents the slope length and slope factor, which describes the influence of terrain characteristics on erosion; C represents the crop management factor, which reflects the influence of vegetation coverage on the erosion process; P represents the soil and water conservation measures factor, which takes into account the control effect of human activities such as terraces and vegetation belts on erosion.

[0105] Combining the results of the differential vegetation index with other relevant geographic information data, the C factor can be adjusted to more accurately estimate soil loss; for example, in areas where vegetation cover increases, the C factor may decrease, thereby reducing the predicted amount of soil loss.

[0106] S137. Integrate the estimated soil loss data and change trends to obtain the soil loss data of the monitoring area at different periods.

[0107] S14. Extract water body information from the processed telemetry data, monitor the change in surface water area, and obtain surface runoff data in the monitoring area by combining rainfall data with a hydrological model.

[0108] It should be noted that a hydrological model refers to a model that simulates hydrological processes using mathematical or physical methods. It can simulate and predict the formation and change of surface runoff based on input hydrological data (such as rainfall, topography, vegetation cover, etc.); in soil erosion monitoring, hydrological models are mainly used to calculate surface runoff, thereby assessing the risk and extent of soil erosion.

[0109] S15. Use remote sensing technology to generate digital elevation model data, and combine it with terrain analysis algorithms to calculate and extract terrain data of the monitored area.

[0110] It should be noted that the digital elevation model is a kind of spatial geographic information data, which realizes the digital simulation of the ground terrain through limited terrain elevation data, that is, the digital expression of the terrain surface morphology; it is the core data system for terrain analysis in the geographic information system (GIS), and can provide quantitative analysis of terrain features, such as slope, slope direction, terrain curvature, etc. In addition, terrain data includes terrain type, terrain undulation, terrain texture, etc.

[0111] S2. Integrate soil loss data, surface runoff data and terrain data, and obtain soil and water loss risk index data and soil erosion rate data through feature extraction technology.

[0112] Specifically, integrating soil loss data, surface runoff data and terrain data, and obtaining soil and water loss risk index data and soil erosion rate data through feature extraction technology includes the following steps:

[0113] S21. Using principal component analysis, soil loss data, surface runoff data and terrain data are integrated into the data set;

[0114] S22. Extracting characteristics of soil and water loss from the data set, the characteristics of soil and water loss include average soil loss in different time periods, average surface runoff, and volatility of soil loss;

[0115] S23. Calculate the soil and water loss risk index data based on the average soil loss and average surface runoff in different time periods and combined with terrain data;

[0116] S24. Calculate soil erosion rate data based on the volatility of soil loss in different time periods and combined with terrain data.

[0117] S3. Calculate the weight values ​​of soil and water loss risk index data and soil erosion rate data using feature evaluation technology.

[0118] Specifically, the calculation of the weight values ​​of soil and water loss risk index data and soil erosion rate data using feature evaluation technology includes the following steps:

[0119] S31, extracting characteristic data from the soil and water loss risk index data and the soil erosion rate data, and combining the extracted characteristic data into a characteristic matrix;

[0120] S32. According to the analysis requirements, define the soil and water loss risk index and soil erosion rate as target variables, and use statistical algorithms to calculate the correlation between each feature and the target variable to obtain the feature correlation coefficient;

[0121] S33, normalizing the feature correlation coefficient to a preset interval, and assigning a corresponding weight value to each feature according to the normalized feature correlation coefficient score.

[0122] S4. Based on the soil and water loss risk index data, soil erosion rate data and weight values, a soil and water loss prediction model is constructed using the deep learning framework and spatiotemporal analysis algorithm.

[0123] Specifically, based on the soil and water loss risk index data, soil erosion rate data and weight values, the deep learning framework and spatiotemporal analysis algorithm are used to build a soil and water loss prediction model, which includes the following steps:

[0124] S41. Use the deep learning framework to perform time series analysis on the soil and water loss risk index data and soil erosion rate data to detect whether there is periodic data in the data. If there is periodic data, use the time series decomposition algorithm to remove the periodic data. If there is no periodic data, continue to analyze the periodic changes in the data.

[0125] S42. Based on the soil and water loss risk index data and soil erosion rate data after removing the periodic data, the beam forming technology in the spatiotemporal analysis algorithm is used to extract the amplitude and phase information of each frequency component as a feature vector.

[0126] S43. According to the acquired characteristic vector, the significance of each frequency component is evaluated through statistical testing, and screening is performed based on the evaluation results to construct a periodicity prediction model.

[0127] It should be noted that the periodic forecasting model is built on the basis of the time series forecasting model. The formula of the periodic forecasting model is:

[0128]

[0129] Where y represents the periodic prediction result; m represents the number of frequency components considered; i represents a natural number; ω i Represents the frequency component f i The weight of A(f i ) represents the frequency component f i The amplitude of f i represents the frequency component; t represents the time point; P(f i) represents the frequency component f i phase.

[0130] S44. The remaining data after removing the periodic data is used as random fluctuation data, and a fluctuation prediction model is constructed using a deep learning framework.

[0131] It should be noted that the fluctuation prediction model is built on the basis of the recurrent neural network model. The formula of the fluctuation prediction model is:

[0132]

[0133] In the formula, h t represents the hidden state, the hidden layer output at time t; LSTM represents the recurrent neural network model; v t-1 represents the feature vector at the previous time t-1; h t-1 Represents the hidden state at the previous moment t-1; represents the predicted output at time t; W represents the weight matrix; b represents the bias vector.

[0134] S45, integrating and superimposing the periodic prediction model, the fluctuation prediction model and the weight value to obtain a soil and water loss prediction model.

[0135] Specifically, the formula of soil and water loss prediction model is:

[0136]

[0137] In the formula, It represents the predicted value of soil erosion;

[0138] y1 represents the predicted value of the periodic forecast model;

[0139] ω1 represents the weight value of the periodic prediction model;

[0140] y2 represents the predicted value of the volatility prediction model;

[0141] ω2 represents the weight value of the volatility prediction model.

[0142] S5. Use the soil and water loss prediction model to predict the soil and water loss situation, and formulate soil and water loss prevention and control measures based on the prediction results.

[0143] It should be noted that the soil and water loss prediction model is used to predict the soil and water loss situation, and the soil and water loss prevention and control measures are formulated according to the prediction results, including:

[0144] Step 1: Analysis of model prediction results:

[0145] Use the soil and water loss prediction model to predict the target area and obtain the prediction results, including the soil and water loss risk level distribution map, soil erosion rate prediction value, etc.; analyze the prediction results to identify high-risk areas and low-risk areas, as well as hot spots with high soil erosion rates.

[0146] Step 2: Preliminary planning of prevention and control measures:

[0147] Based on the prediction results, preliminary prevention and control measures are planned, including engineering measures (such as building terraces, silt dams, and gullies), biological measures (such as afforestation and grass planting), and agricultural farming measures (such as changing farming methods, crop rotation and fallow). The priority of prevention and control measures is determined, and high-risk areas and hot spots with high soil erosion rates should be given priority.

[0148] Step 3: Detailed design of prevention and control measures:

[0149] Carry out detailed design of the prevention and control measures in the preliminary plan, including the implementation location, implementation methods, required materials, budget estimates, etc. of specific measures; consider natural conditions such as topography, climate, soil, as well as local socio-economic conditions to ensure the scientific nature and feasibility of the prevention and control measures.

[0150] Step 4: Implementation and supervision of prevention and control measures:

[0151] Implement the prevention and control measures plan in detail to ensure that all measures are completed on time, with good quality and in quantity; establish a supervision mechanism to supervise and inspect the implementation process of prevention and control measures to ensure their effective implementation.

[0152] Step 5: Effect evaluation and feedback adjustment:

[0153] After the prevention and control measures have been implemented for a period of time, an evaluation is conducted on their effectiveness, including changes in soil and water loss conditions, the degree of reduction in soil erosion rate, etc. Based on the evaluation results, feedback adjustments are made to the prevention and control measures to optimize the prevention and control measures and improve the effectiveness of the prevention and control measures.

[0154] Step 6: Continuous monitoring and dynamic management:

[0155] Establish a continuous monitoring mechanism to regularly monitor and evaluate soil and water erosion conditions and promptly identify new problems and changes; dynamically adjust prevention and control measures based on monitoring results to ensure the continuity and effectiveness of soil and water erosion prevention and control work.

[0156] like Figure 2 As shown, according to another embodiment of the present invention, a soil and water loss telemetry data analysis system based on deep learning is also provided, the system includes a data collection and extraction module 1, a data fusion and feature extraction module 2, a feature evaluation and weight calculation module 3, a model building module 4 and a prediction and prevention strategy formulation module 5;

[0157] Data collection and extraction module 1, used to collect telemetry data of the soil erosion monitoring area, and extract soil loss data, surface runoff data and terrain data based on the telemetry data;

[0158] Data fusion and feature extraction module 2, used to fuse soil loss data, surface runoff data and terrain data, and obtain soil and water loss risk index data and soil erosion rate data through feature extraction technology;

[0159] The feature evaluation and weight calculation module 3 is used to calculate the weight values ​​of the soil and water loss risk index data and the soil erosion rate data using the feature evaluation technology;

[0160] Model building module 4, used to build a soil and water loss prediction model based on soil and water loss risk index data, soil erosion rate data and weight value using a deep learning framework and spatiotemporal analysis algorithm;

[0161] The prediction and prevention strategy formulation module 5 is used to predict the soil and water loss situation using the soil and water loss prediction model, and formulate soil and water loss prevention and control measures based on the prediction results.

[0162] In summary, with the help of the above technical solution of the present invention, through telemetry data collection and feature extraction, key soil and water loss information can be quickly obtained, which not only simplifies the data processing process, but also ensures the accuracy and reliability of the data, laying a solid foundation for subsequent analysis and prediction. By constructing a soil and water loss prediction model, it not only has powerful learning and generalization capabilities, but also can fully consider the changing factors in time and space, so as to achieve accurate prediction of soil and water loss conditions, provide strong technical support for the formulation of targeted prevention and control measures, and help to more effectively deal with soil and water loss problems. Through the soil and water loss prevention and control measures formulated according to the prediction results, it is possible to accurately implement policies based on the characteristics of soil and water loss in different regions and different time periods, which can not only effectively curb the deterioration trend of soil and water loss, but also promote the protection and restoration of the ecological environment and achieve sustainable development.

[0163] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A soil and water loss telemetry data analysis method based on deep learning, characterized in that: The method comprises the following steps: S1. Collect telemetry data of soil erosion monitoring areas, and extract soil loss data, surface runoff data and terrain data based on the telemetry data; S2, integrating soil loss data, surface runoff data and terrain data, and obtaining soil and water loss risk index data and soil erosion rate data through feature extraction technology; S3. Calculate the weight values ​​of soil and water loss risk index data and soil erosion rate data using feature evaluation technology; S4. Based on the soil and water loss risk index data, soil erosion rate data and weight values, a soil and water loss prediction model is constructed using a deep learning framework and spatiotemporal analysis algorithm; S5. Use the soil and water loss prediction model to predict the soil and water loss situation, and formulate soil and water loss prevention and control measures based on the prediction results.

2. According to the method for analyzing soil and water loss telemetry data based on deep learning in claim 1, it is characterized in that: The collecting of telemetry data of the soil erosion monitoring area and extracting soil loss data, surface runoff data and terrain data based on the telemetry data comprises the following steps: S11. Obtain remote sensing data of soil erosion monitoring areas through satellite remote sensing platforms; S12. Use geographic reference points and geometric registration technology of the geographic information system to perform geographic correction on the telemetry data, and use atmospheric correction software to process the geographically corrected telemetry data; S13. Based on the processed telemetry data, compare the changes in vegetation coverage and bare surface area in different time series, and obtain soil loss data in the monitoring area through the differential vegetation index algorithm; S14, extracting water body information from the processed telemetry data, monitoring the change in the surface water area, and combining rainfall data with the hydrological model to obtain surface runoff data in the monitoring area; S15. Use remote sensing technology to generate digital elevation model data, and combine it with terrain analysis algorithms to calculate and extract terrain data of the monitored area.

3. According to the method for analyzing soil and water loss telemetry data based on deep learning in claim 2, it is characterized in that: The method of using the geographic reference points and geometric registration technology of the geographic information system to perform geographic correction on the telemetry data, and applying the atmospheric correction software to process the geographically corrected telemetry data includes the following steps: S121, importing the acquired telemetry data into a geographic information system, and selecting map projection and coordinates according to the geographic features of the monitoring area; S122, identifying and marking ground control points with known coordinates as geographic reference points in the geographic information system, and selecting pixel locations corresponding to the geographic reference points in the telemetry data to establish control point pairs; S123, performing affine transformation based on the control point pairs, geo-correcting the telemetry data, and resampling the geo-corrected telemetry data; S124, using atmospheric correction software to perform radiation calibration on the resampled remote sensing data, and converting the value of each band in the remote sensing data into an atmospheric radiation brightness value; S125. Use atmospheric correction software to process the radiation brightness value and restore the radiation brightness value to the surface reflectance value.

4. The method for analyzing soil and water loss telemetry data based on deep learning according to claim 2 is characterized in that: The method of comparing the vegetation coverage and bare surface area changes of different time series based on the processed telemetry data and obtaining the soil loss data of the monitoring area by using the differential vegetation index algorithm includes the following steps: S131, based on the processed telemetry data, using the normalized vegetation index formula to calculate the telemetry data of each period; S132, setting a threshold value according to the calculated normalized vegetation index, distinguishing the vegetation-covered area from the bare surface area by the threshold value, and vectorizing the vegetation-covered area and the bare surface area into a surface layer; S133, in the geographic information system, overlaying the vegetation coverage layer and the bare surface layer of different periods, identifying the change area, and counting the change amount of the vegetation coverage area and the bare surface area in each period; S134. Analyze the changing trends of vegetation cover and bare surface area based on the statistical changes; S135, selecting one of the telemetry data of different periods as the baseline data, and calculating the differential vegetation index between the baseline data and the telemetry data of each period using a differential vegetation index algorithm; S136. Using the pre-built soil and water loss assessment model and the differential vegetation index, estimate the soil loss data in the monitoring area; S137. Integrate the estimated soil loss data and change trends to obtain the soil loss data of the monitoring area at different periods.

5. The method for analyzing soil and water loss telemetry data based on deep learning according to claim 4 is characterized in that: The normalized vegetation index formula is: Where, NDVI represents the normalized difference vegetation index; NIR represents the reflectivity in the near infrared band; RED represents the reflectivity of the red light band.

6. The method for analyzing soil and water loss telemetry data based on deep learning according to claim 1, characterized in that: The method of fusing soil loss data, surface runoff data and terrain data, and obtaining soil and water loss risk index data and soil erosion rate data by feature extraction technology comprises the following steps: S21. Using principal component analysis, soil loss data, surface runoff data and terrain data are integrated into the data set; S22, extracting characteristics of soil erosion from the data set, wherein the characteristics of soil erosion include average soil loss, average surface runoff, and volatility of soil loss in different time periods; S23. Calculate the soil and water loss risk index data based on the average soil loss and average surface runoff in different time periods and combined with terrain data; S24. Calculate soil erosion rate data based on the volatility of soil loss in different time periods and combined with terrain data.

7. The method for analyzing soil and water loss telemetry data based on deep learning according to claim 1, characterized in that: The method of calculating the weight values ​​of soil and water loss risk index data and soil erosion rate data by using the feature evaluation technology comprises the following steps: S31, extracting characteristic data from the soil and water loss risk index data and the soil erosion rate data, and combining the extracted characteristic data into a characteristic matrix; S32. According to the analysis requirements, define the soil and water loss risk index and soil erosion rate as target variables, and use statistical algorithms to calculate the correlation between each feature and the target variable to obtain the feature correlation coefficient; S33, normalizing the feature correlation coefficient to a preset interval, and assigning a corresponding weight value to each feature according to the normalized feature correlation coefficient score.

8. The method for analyzing soil and water loss telemetry data based on deep learning according to claim 1, characterized in that: The method of constructing a soil and water loss prediction model based on soil and water loss risk index data, soil erosion rate data and weight values ​​using a deep learning framework and a spatiotemporal analysis algorithm includes the following steps: S41. Use a deep learning framework to perform time series analysis on the soil and water loss risk index data and the soil erosion rate data to detect whether there is periodic data in the data. If there is periodic data, use a time series decomposition algorithm to remove the periodic data. If there is no periodic data, continue to analyze the periodic changes in the data. S42, based on the soil and water loss risk index data and soil erosion rate data after removing the periodic data, the beam forming technology in the spatiotemporal analysis algorithm is used to extract the amplitude and phase information of each frequency component as a feature vector; S43, according to the acquired characteristic vector, the significance of each frequency component is evaluated by statistical test, and screening is performed based on the evaluation result to construct a periodicity prediction model; S44, taking the remaining data after removing the periodic data as random fluctuation data, and constructing a fluctuation prediction model using a deep learning framework; S45, integrating and superimposing the periodic prediction model, the fluctuation prediction model and the weight value to obtain a soil and water loss prediction model.

9. The method for analyzing soil and water loss telemetry data based on deep learning according to claim 8, characterized in that: The formula of the soil and water loss prediction model is: In the formula, It represents the predicted value of soil erosion; y1 represents the predicted value of the periodic forecast model; ω1 represents the weight value of the periodic prediction model; y2 represents the predicted value of the volatility prediction model; ω2 represents the weight value of the volatility prediction model.

10. A soil and water loss telemetry data analysis system based on deep learning, used to implement the soil and water loss telemetry data analysis method based on deep learning according to any one of claims 1 to 9, characterized in that: The system includes a data collection and extraction module, a data fusion and feature extraction module, a feature evaluation and weight calculation module, a model building module, and a prediction and prevention strategy formulation module; The data collection and extraction module is used to collect telemetry data of the soil erosion monitoring area, and extract soil loss data, surface runoff data and terrain data based on the telemetry data; The data fusion and feature extraction module is used to fuse soil loss data, surface runoff data and terrain data, and obtain soil and water loss risk index data and soil erosion rate data through feature extraction technology; The feature evaluation and weight calculation module is used to calculate the weight values ​​of soil and water loss risk index data and soil erosion rate data using feature evaluation technology; The model building module is used to build a soil and water loss prediction model based on soil and water loss risk index data, soil erosion rate data and weight values ​​using a deep learning framework and a spatiotemporal analysis algorithm; The prediction and prevention strategy formulation module is used to predict the soil and water loss situation using the soil and water loss prediction model, and formulate soil and water loss prevention and control measures based on the prediction results.

Images