A method and system for evaluating vegetation restoration on bedding rock slopes

Abstract

The present invention relates to the technical field of ecological restoration assessment, and discloses a method and system for assessing vegetation restoration on bedding rock slopes. The method comprises: collecting vegetation information of the slope to be assessed to determine a restoration assessment value; collecting humidity data at several locations within a preset time period to establish a time-humidity data chain, and constructing a humidity data set and a representative data chain; comparing with a historical humidity data set to determine predicted humidity data; comparing the predicted humidity data with a humidity threshold, and judging whether to adjust the restoration assessment value based on the comparison result; when it is determined that the restoration assessment value is to be adjusted, determining a slope risk coefficient based on the predicted humidity data, and adjusting the restoration assessment value based on the slope risk coefficient. Compared with traditional static assessment methods, the present application can perceive environmental changes in real time, give early warning of the risk of reduced slope stability, avoid hidden dangers caused by overestimation of the restoration effect, and improve the safety and accuracy of slope management.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological restoration assessment, and in particular to a method and system for assessing vegetation restoration on bedding rock slopes. Background Art

[0002] Bedding rock slopes are widely distributed in mountainous areas and in infrastructure construction areas. Because their structural surfaces align with the slope surface, they are highly susceptible to bedding slippage under external loads, precipitation, and weathering, compromising slope stability. To mitigate the risk of slope landslides, vegetation restoration has become a common and sustainable engineering measure. Vegetation not only improves the slope microenvironment and reduces surface erosion, but also enhances the shear strength of the rock mass through root reinforcement, improving slope stability. Therefore, assessment methods for vegetation restoration of bedding rock slopes are of significant engineering significance.

[0003] Traditional vegetation restoration assessment methods primarily rely on plant coverage and root distribution. They typically monitor slope vegetation status using drone remote sensing, ground surveys, or remote sensing image analysis, and calculate restoration effectiveness based on empirical models. However, they fail to fully consider the long-term impact of humidity on slope stability. Changes in precipitation and soil moisture can reduce the shear strength of structural surfaces, thereby affecting slope safety. Currently, it is not possible to adjust restoration assessment values ​​based on humidity trends. For example, if future increases in humidity are predicted to reduce the slope's safety factor, traditional methods cannot promptly correct the restoration assessment value, potentially overestimating the restoration effect and increasing the risk of slope instability.

[0004] Therefore, it is necessary to design a method for evaluating vegetation restoration on bedding rock slopes to solve the problems existing in current technology. Summary of the Invention

[0005] In view of this, the present invention proposes a method for evaluating vegetation restoration on bedding rock slopes, aiming to solve the problem of the current lack of dynamic evaluation of humidity impact, resulting in low reliability of vegetation restoration evaluation results.

[0006] In one aspect, the present invention provides a method for evaluating vegetation restoration of bedding rock slopes, comprising:

[0007] Collect vegetation information of the slope to be assessed, including green plant area and average root depth, and preliminarily determine a restoration assessment value based on the vegetation information;

[0008] Collecting humidity data at a plurality of locations within a preset time period on the slope to be evaluated using humidity sensors, establishing the data from each humidity sensor as a time-humidity data chain, constructing all the time-humidity data chains into a humidity dataset, and determining representative humidity data at each moment of the slope to be evaluated based on a Gaussian mixture distribution and constructing a representative data chain;

[0009] Comparing the representative data chain with a historical humidity data set, and determining predicted humidity data based on the comparison result, the historical humidity data set including a plurality of historical representative data chains and a plurality of historical verification humidity data, and each of the historical representative data chains corresponds to a piece of historical verification humidity data;

[0010] The predicted humidity data is compared with the humidity threshold, and whether the repair assessment value is to be adjusted is determined based on the comparison result. When it is determined that the repair assessment value is to be adjusted, the slope risk coefficient is determined based on the predicted humidity data, and the repair assessment value is adjusted based on the slope risk coefficient.

[0011] Furthermore, the preliminary determination of the restoration assessment value based on the vegetation information includes:

[0012] ;

[0013] Where S represents the restoration assessment value, As represents the green plant area, Az represents the total slope area, ds represents the average root depth, dz represents the critical rooting depth, τs represents the measured root shear strength, and τz represents the reference root shear strength.

[0014] Furthermore, when determining the representative moisture data of the slope to be evaluated at each moment based on the Gaussian mixture distribution and constructing a representative data chain, the method includes:

[0015] The kernel density function expression is:

[0016]

[0017] Where n represents the total number of humidity data collected at the same time, h represents the smoothing bandwidth, represents the humidity data of the ith time point collected at the same time, and x represents the value of a certain frequency point to be estimated;

[0018] The humidity data corresponding to the highest frequency of kernel density is taken as the representative data at that moment;

[0019] The representative data at each moment are combined to form the representative data chain.

[0020] Furthermore, the representative data chain is compared with the historical humidity data set, and the predicted humidity data is determined according to the comparison result, including:

[0021] When there is data in the historical humidity data set whose similarity to the representative data chain is greater than a similarity threshold, the historical verified humidity value of the historical representative data chain corresponding to the maximum similarity is used as the predicted humidity data;

[0022] When the similarity between all historical representative data chains in the historical humidity data set and the representative data chain is less than or equal to a similarity threshold, an LSTM model is trained based on the historical humidity data set, and the predicted humidity data is determined according to the LSTM model.

[0023] Furthermore, when determining the predicted humidity data according to the LSTM model, the method includes:

[0024] Each humidity data in the representative data chain is divided into windows according to the time series as input data, the output result of the LSTM model is obtained, and the output result is used as the predicted humidity data.

[0025] Furthermore, when determining whether to adjust the repair assessment value based on the comparison result, it includes:

[0026] The predicted humidity data is compared with a humidity threshold. When the predicted humidity data is greater than the humidity threshold, it is determined that the repair evaluation value is adjusted; when the predicted humidity data is less than or equal to the humidity threshold, it is determined that the repair evaluation value is not adjusted.

[0027] Furthermore, when determining the slope risk coefficient based on the predicted humidity data, the method includes:

[0028] obtaining a humidity difference value based on the predicted humidity data and the humidity threshold, the humidity difference value being the difference between the predicted humidity data and the humidity threshold value, comparing the humidity difference value with a first preset difference value and a second preset difference value, respectively, and determining the cohesion force based on the comparison results; the first preset difference value being less than the second preset difference value;

[0029] When the humidity difference is less than or equal to the first preset difference, the cohesion is determined to be the first preset cohesion; when the humidity difference is greater than the first preset difference and less than the second preset difference, the cohesion is determined to be the second preset cohesion; when the humidity difference is greater than the second preset difference, the cohesion is determined to be the third preset cohesion; the first preset cohesion is greater than the second preset cohesion, the second preset cohesion is greater than the third preset cohesion, and the third preset cohesion is greater than or equal to 0.

[0030] Furthermore, when determining the slope risk coefficient based on the predicted humidity data, the method further includes:

[0031]

[0032] Where F is the slope risk coefficient, n is the cohesion, the height of the slope is H, the slope angle is α, the inclination angle of the structural surface is θ, γ is the weight of the rock mass, and φ is the internal friction angle.

[0033] Furthermore, when adjusting the restoration assessment value according to the slope risk coefficient, it includes:

[0034] Comparing the slope risk coefficient with a minimum slope risk coefficient, where the minimum slope risk coefficient is 1, and determining an adjustment coefficient based on the comparison result to adjust the restoration assessment value;

[0035] The adjustment coefficient is proportional to the slope risk coefficient, and the adjustment coefficient has a value range of (0, 1). The adjusted restoration assessment value is the product of the restoration assessment value and the adjustment coefficient.

[0036] Compared with the existing technology, the beneficial effect of the present invention is that it realizes the dynamic evaluation of the vegetation restoration effect of the bedding rock slope through vegetation information collection, humidity dynamic monitoring, data link modeling and risk assessment adjustment analysis. Slope vegetation information is obtained by drone remote sensing or ground measurement, including green plant coverage area and average root depth to calculate the restoration assessment value. Humidity sensors are used to collect humidity data at multiple locations on the slope for a long time, and stored in the form of a time-humidity data link to construct a comprehensive humidity data set, avoiding the problem of insufficient accuracy caused by the dispersion of data points in traditional methods. A Gaussian mixture distribution model is used to perform statistical analysis on the humidity data, extract the most representative humidity data, and reduce the impact of single-point data fluctuations on the evaluation results. By comparing the current representative data link with the historical humidity data set, the humidity change trend in the future period is predicted, making the evaluation method forward-looking. When the predicted humidity data exceeds the safety threshold, the slope risk coefficient is further calculated. Combined with the slope stability theory, the restoration assessment value is dynamically adjusted according to the impact of humidity on the shear strength of the slope to ensure the reliability of the evaluation results. Compared with traditional static assessment methods, it can perceive environmental changes in real time, warn of the risk of reduced slope stability in advance, avoid hidden dangers caused by overestimation of repair effects, and improve the safety and accuracy of slope management.

[0037] On the other hand, the present application also provides a system for evaluating vegetation restoration on bedding rock slopes, which is applied to the above-mentioned method for evaluating vegetation restoration on bedding rock slopes, including:

[0038] a collection unit configured to collect vegetation information of the slope to be assessed, the vegetation information including green plant area and average root depth, and preliminarily determine a restoration assessment value based on the vegetation information;

[0039] a processing unit configured to collect humidity data at a plurality of locations within a preset time period of the slope to be evaluated based on a humidity sensor, establish the data of each humidity sensor into a time-humidity data chain, construct all the time-humidity data chains into a humidity data set, determine representative humidity data of the slope to be evaluated at each moment based on a Gaussian mixture distribution, and construct the representative data chain;

[0040] a judgment unit configured to compare the representative data chain with a historical humidity data set, and determine predicted humidity data according to a comparison result, wherein the historical humidity data set includes a plurality of historical representative data chains and a plurality of historical verification humidity data, and each of the historical representative data chains corresponds to a piece of historical verification humidity data;

[0041] An adjustment unit is configured to compare the predicted humidity data with a humidity threshold, determine whether to adjust the repair assessment value based on the comparison result, and when it is determined that the repair assessment value is to be adjusted, determine a slope risk coefficient based on the predicted humidity data, and adjust the repair assessment value based on the slope risk coefficient.

[0042] It is understandable that the above-mentioned method and system for evaluating vegetation restoration on bedding rock slopes have the same beneficial effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0044] Figure 1 A flow chart of a method for evaluating vegetation restoration of bedding rock slopes provided in an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of parameters for slope risk coefficient in a method for assessing vegetation restoration of bedding rock slopes provided in an embodiment of the present invention;

[0046] Figure 3 This is a functional block diagram of a system for evaluating vegetation restoration on bedding rock slopes provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0048] In some embodiments of the present application, see Figure 1-2As shown, a method for evaluating vegetation restoration of bedding rock slopes includes:

[0049] S100: Collect vegetation information of the slope to be assessed, including the green plant area and average root depth, and preliminarily determine the restoration assessment value based on the vegetation information.

[0050] S200: Collect humidity data at several locations within a preset time period on the slope to be evaluated based on humidity sensors, establish the data of each humidity sensor as a time-humidity data chain, construct all time-humidity data chains into a humidity data set, determine representative humidity data at each moment of the slope to be evaluated based on Gaussian mixture distribution, and construct a representative data chain.

[0051] S300: Compare the representative data chain with the historical humidity data set, and determine the predicted humidity data according to the comparison result. The historical humidity data set includes several historical representative data chains and several historical verification humidity data, and each historical representative data chain corresponds to one historical verification humidity data.

[0052] S400: Compare the predicted humidity data with the humidity threshold, and determine whether to adjust the repair assessment value based on the comparison result. When it is determined that the repair assessment value is to be adjusted, determine the slope risk coefficient based on the predicted humidity data, and adjust the repair assessment value based on the slope risk coefficient.

[0053] Specifically, S100 uses drone remote sensing, ground-based measurements, or remote sensing imagery to collect slope vegetation information, including green plant cover (used to measure the degree of vegetation restoration) and average root depth (used to assess the reinforcement effect of vegetation on the geotechnical surface). Based on this data, a preliminary restoration assessment value is determined. S200, considering the direct impact of soil moisture on slope stability, employs multiple humidity sensors deployed across different areas of the slope to collect humidity data over time and construct a time-humidity data chain. Traditional humidity monitoring methods typically use simple averages or single-point measurements, which cannot accurately reflect the temporal and spatial variations in slope humidity. A Gaussian mixture distribution model is used to statistically model the collected humidity data, removing outliers and extracting the most representative humidity data to form a representative data chain. To further enhance the scientific nature of the assessment, S300 introduces a historical humidity dataset, which includes several historical representative data chains (i.e., humidity trends over different historical periods) and historical validation humidity data (historical humidity predictions verified by actual observations). By comparing the current representative data chain with historical data and employing pattern recognition or time series analysis methods, the humidity trend over the next period of time is predicted to generate predicted humidity data. To ensure that the repair assessment value reflects the actual slope repair situation, S400 compares the predicted humidity data with a set humidity threshold. When the predicted humidity exceeds the threshold, the shear strength of the slope decreases, thereby affecting stability. A slope risk factor is introduced to quantify the impact of humidity changes on slope stability. Based on changes in the risk factor, the initially determined repair assessment value is adjusted to obtain a final repair assessment value that better reflects the actual stability.

[0054] It is understandable that by integrating vegetation information collection, humidity data chain modeling, historical comparison and prediction, and risk adjustment, an optimization of vegetation restoration assessment based on dynamic humidity changes has been achieved. Compared with traditional static assessment methods that rely solely on green plant coverage and root depth, this method can perceive humidity changes in real time, predict potential risks in advance, and dynamically adjust restoration assessment values, thereby improving the accuracy and reliability of the assessment. The use of a Gaussian mixture distribution to extract humidity representative data effectively avoids the calculation errors caused by traditional methods due to excessive humidity fluctuations or high data discreteness. At the same time, through historical data comparison and slope risk factor correction, it ensures that the final assessment results can accurately reflect the long-term stability of the slope and the effectiveness of vegetation restoration.

[0055] In some embodiments of the present application, when preliminarily determining the restoration assessment value based on vegetation information, the process includes:

[0056] ;

[0057] Where S represents the restoration assessment value, As represents the green plant area, Az represents the total slope area, ds represents the average root depth, dz represents the critical rooting depth, τs represents the measured root shear strength, and τz represents the reference root shear strength.

[0058] It is understandable that the measured average rooting depth can be determined through sampling analysis or radar detection. The critical rooting depth is the depth at which plant roots have a significant effect on slope stability, and an empirical value can be set based on soil type and vegetation type. The measured root shear strength can be determined through in-situ shear tests. The reference root shear strength usually selects the root shear strength of the dominant vegetation in the area as the standard value. Compared with the evaluation method based solely on visual remote sensing data, it not only takes into account the surface distribution of vegetation (green plant area), but also quantifies the depth influence of vegetation roots and their shear performance, ensuring that the evaluation value can truly reflect the contribution of vegetation to slope stability.

[0059] In some embodiments of the present application, when determining representative moisture data of the slope to be evaluated at each moment based on the Gaussian mixture distribution and constructing a representative data chain, the process includes:

[0060] The kernel density function expression is:

[0061]

[0062] Where n represents the total number of humidity data collected at the same time, h represents the smoothing bandwidth, represents the i-th humidity data collected at the same time, and x represents the value of a certain frequency point to be estimated.

[0063] The humidity data corresponding to the highest frequency of kernel density is taken as the representative data at that moment.

[0064] The representative data at each moment are combined to form a representative data chain.

[0065] Specifically, the smoothing bandwidth is calculated by the following formula:

[0066]

[0067] Where h is the smoothing bandwidth, β1 is the data skewness, β2 is the data kurtosis, and k is the correction coefficient.

[0068] The data skewness is calculated by the following formula:

[0069]

[0070] The data kurtosis is calculated by the following formula:

[0071] ;

[0072] in, represents the mean of the humidity data collected at the same time, and σ represents the standard deviation of the humidity data collected at the same time.

[0073] It is understandable that by combining a Gaussian mixture distribution with kernel density estimation, the most representative humidity values ​​are extracted from data from multiple humidity sensors, avoiding the distortion that can result from traditional mean calculation methods. Furthermore, an adaptive bandwidth calculation method dynamically adjusts the smoothing bandwidth based on data skewness and kurtosis, improving the accuracy of the kernel density estimate and making the representative humidity data more consistent with the actual slope conditions. This solution constructs a representative humidity data chain over a time series, providing high-quality data input for subsequent humidity trend prediction and dynamic adjustment of restoration assessment values, making assessments more accurate and further enhancing the reliability and stability of slope vegetation restoration results.

[0074] In some embodiments of the present application, comparing a representative data chain with a historical humidity dataset and determining predicted humidity data based on the comparison results includes: when data in the historical humidity dataset has a similarity with the representative data chain greater than a similarity threshold, using the historical verified humidity value of the historical representative data chain corresponding to the maximum similarity as the predicted humidity data. When the similarity between all historical representative data chains in the historical humidity dataset and the representative data chain is less than or equal to the similarity threshold, training an LSTM model based on the historical humidity dataset and determining predicted humidity data based on the LSTM model.

[0075] In some embodiments of the present application, when determining predicted humidity data based on the LSTM model, it includes: dividing each humidity data in the representative data chain into windows according to the time series as input data, obtaining the output result of the LSTM model, and using the output result as the predicted humidity data.

[0076] Specifically, the forget gate of the pre-built LSTM model:

[0077] .

[0078] Input Gate:

[0079] .

[0080] .

[0081] Cell status update:

[0082] .

[0083] Output Gate:

[0084] .

[0085] .

[0086] in, represents the output of the forget gate, Represents the weight matrix of the forget gate, with a value range of [-1, 1], Indicates the hidden state at the previous moment, Represents input data, represents the bias term of the forget gate, σ is the sigmoid function, represents the input gate output, Indicates the candidate cell state, with a value range of (-1, 1). Represents the weight matrix of the input gate, with a value range of [-1, 1], The weight matrix representing the candidate cell state has a value range of [-1, 1]. 、 represent the bias terms of the input gate and candidate cell state, respectively, Indicates the cell state at the current moment, Indicates the cell state at the previous moment, represents the output gate output, Represents the predicted data, Represents the weight matrix of the output gate, with a value range of [-1, 1], Represents the bias term of the output gate.

[0087] It's understandable that the humidity prediction method, constructed by combining similarity matching with LSTM deep learning, prioritizes historical humidity data for matching, ensuring high reliability and computational efficiency of prediction results. When historical data is insufficient, the LSTM model is used for time series prediction, resulting in strong generalization capabilities and adaptability to complex slope environmental changes. Furthermore, the LSTM architecture, which employs a forget gate, input gate, cell state update, and output gate, addresses the long-term dependency of humidity time series data, making predictions more stable and enhancing the scientific nature and accuracy of slope restoration assessments.

[0088] In some embodiments of the present application, determining whether to adjust the repair evaluation value based on the comparison result includes comparing the predicted humidity data with a humidity threshold, and determining to adjust the repair evaluation value when the predicted humidity data is greater than the humidity threshold, and determining not to adjust the repair evaluation value when the predicted humidity data is less than or equal to the humidity threshold.

[0089] In some embodiments of the present application, determining a slope risk factor based on predicted humidity data includes: obtaining a humidity difference value based on the predicted humidity data and a humidity threshold, the humidity difference value being the difference between the predicted humidity data and the humidity threshold value; comparing the humidity difference value with a first preset difference value and a second preset difference value, respectively; and determining cohesion based on the comparison results. The first preset difference value is smaller than the second preset difference value.

[0090] Specifically, when the humidity difference is less than or equal to a first preset difference, the cohesion is determined to be the first preset cohesion. When the humidity difference is greater than the first preset difference and less than a second preset difference, the cohesion is determined to be the second preset cohesion. When the humidity difference is greater than the second preset difference, the cohesion is determined to be the third preset cohesion. The first preset cohesion is greater than the second preset cohesion, the second preset cohesion is greater than the third preset cohesion, and the third preset cohesion is greater than or equal to 0.

[0091] In some embodiments of the present application, when determining the slope risk coefficient based on the predicted humidity data, the method further includes:

[0092]

[0093] Where F is the slope risk coefficient, n is the cohesion, the height of the slope is H, the slope angle is α, the inclination angle of the structural surface is θ, γ is the weight of the rock mass, and φ is the internal friction angle.

[0094] Specifically, ACE in the figure represents the structural surface. When the entire slope structural surface slides, the cohesion is 0, and the internal friction angle is equal to the inclination angle of the structural surface. Therefore, the minimum slope risk coefficient is 1.

[0095] In some embodiments of the present application, adjusting the restoration assessment value based on the slope risk coefficient includes comparing the slope risk coefficient with a minimum slope risk coefficient, where the minimum slope risk coefficient is 1, and determining an adjustment coefficient based on the comparison result to adjust the restoration assessment value. The adjustment coefficient is proportional to the slope risk coefficient and has a value range of (0, 1). The adjusted restoration assessment value is the product of the restoration assessment value and the adjustment coefficient.

[0096] Comparing predicted humidity data with threshold values ​​ensures that adjustments to restoration assessments are based on real-time environmental data, improving assessment accuracy. Adjusting cohesion based on humidity changes, and further calculating the slope risk factor, allows assessments to better reflect actual conditions. Dynamically adjusting restoration assessments based on the slope risk factor allows the assessment system to adapt to slope stability under varying humidity conditions, enhancing the reliability of slope vegetation restoration. Controlling restoration assessments through adjustment factors helps strengthen restoration efforts in high-risk areas and improve overall restoration effectiveness.

[0097] In the above embodiment, a dynamic evaluation of the vegetation restoration effect of the bedding rock slope is achieved through vegetation information collection, humidity dynamic monitoring, data link modeling and risk assessment adjustment analysis. Slope vegetation information is obtained by drone remote sensing or ground measurement, including green plant coverage area and average root depth to calculate the restoration assessment value. Humidity sensors are used to collect humidity data at multiple locations on the slope for a long time, and stored in a time-humidity data link to construct a comprehensive humidity data set, avoiding the problem of insufficient accuracy caused by the dispersion of data points in traditional methods. A Gaussian mixture distribution model is used to perform statistical analysis on the humidity data, extract the most representative humidity data, and reduce the impact of single-point data fluctuations on the assessment results. By comparing the current representative data link with the historical humidity data set, the humidity change trend in the future is predicted, making the assessment method forward-looking. When the predicted humidity data exceeds the safety threshold, the slope risk coefficient is further calculated. Combined with the slope stability theory, the restoration assessment value is dynamically adjusted according to the impact of humidity on the shear strength of the slope to ensure the reliability of the assessment results. Compared with traditional static assessment methods, it can perceive environmental changes in real time, warn of the risk of reduced slope stability in advance, avoid hidden dangers caused by overestimation of repair effects, and improve the safety and accuracy of slope management.

[0098] In another preferred embodiment based on the above embodiment, refer to Figure 3 As shown, this embodiment provides a system for evaluating vegetation restoration of bedding rock slopes, which is used to apply the above-mentioned method for evaluating vegetation restoration of bedding rock slopes, including:

[0099] The collection unit is configured to collect vegetation information of the slope to be evaluated, the vegetation information including the green plant area and the average root depth, and preliminarily determine the restoration assessment value based on the vegetation information.

[0100] The processing unit is configured to collect humidity data at several locations within a preset time period on the slope to be evaluated based on humidity sensors, establish the data of each humidity sensor as a time-humidity data chain, construct all time-humidity data chains into a humidity data set, determine representative humidity data of the slope to be evaluated at each moment based on a Gaussian mixture distribution, and construct a representative data chain.

[0101] The judgment unit is configured to compare the representative data chain with the historical humidity data set, and determine the predicted humidity data according to the comparison result, the historical humidity data set includes several historical representative data chains and several historical verification humidity data, and each historical representative data chain corresponds to a historical verification humidity data.

[0102] The adjustment unit is configured to compare the predicted humidity data with the humidity threshold, and determine whether to adjust the repair assessment value based on the comparison result. When it is determined that the repair assessment value is to be adjusted, the slope risk coefficient is determined based on the predicted humidity data, and the repair assessment value is adjusted based on the slope risk coefficient.

[0103] As can be seen, a dynamic assessment of the effectiveness of vegetation restoration on bedding rock slopes has been achieved through vegetation information collection, dynamic humidity monitoring, data link modeling, and risk assessment and adjustment analysis. Slope vegetation information, including plant cover area and average root depth, is acquired using drone remote sensing or ground-based measurements to calculate restoration assessment values. Humidity sensors collect humidity data at multiple locations along the slope over a long period of time and store it via a time-humidity data link. This constructs a comprehensive humidity dataset, avoiding the inaccuracy inherent in traditional methods due to scattered data points. A Gaussian mixture distribution model is used to statistically analyze humidity data, extracting the most representative humidity data and minimizing the impact of single-point data fluctuations on assessment results. By comparing the current representative data link with historical humidity datasets, future humidity trends are predicted, making the assessment method forward-looking. If the predicted humidity data exceeds a safety threshold, a slope risk factor is further calculated. In combination with slope stability theory, the restoration assessment value is dynamically adjusted based on the impact of humidity on slope shear strength to ensure the reliability of the assessment results. Compared with traditional static assessment methods, it can perceive environmental changes in real time, warn of the risk of reduced slope stability in advance, avoid hidden dangers caused by overestimation of repair effects, and improve the safety and accuracy of slope management.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating vegetation restoration of bedding rock slopes, characterized in that: include: Collect vegetation information of the slope to be assessed, including green plant area and average root depth, and preliminarily determine a restoration assessment value based on the vegetation information; Collecting humidity data at a plurality of locations within a preset time period on the slope to be evaluated using humidity sensors, establishing the data from each humidity sensor as a time-humidity data chain, constructing all the time-humidity data chains into a humidity dataset, and determining representative humidity data at each moment of the slope to be evaluated based on a Gaussian mixture distribution and constructing a representative data chain; Comparing the representative data chain with a historical humidity data set, and determining predicted humidity data based on the comparison result, the historical humidity data set including a plurality of historical representative data chains and a plurality of historical verification humidity data, and each of the historical representative data chains corresponds to a piece of historical verification humidity data; comparing the predicted humidity data with a humidity threshold, determining whether to adjust the restoration assessment value based on the comparison result, and when it is determined that the restoration assessment value is to be adjusted, determining a slope risk coefficient based on the predicted humidity data, and adjusting the restoration assessment value based on the slope risk coefficient; The preliminary determination of the restoration assessment value based on the vegetation information includes: Where S represents the restoration assessment value, As represents the green plant area, Az represents the total slope area, ds represents the average root depth, dz represents the critical rooting depth, τs represents the measured root shear strength, and τz represents the reference root shear strength; When determining representative moisture data of the slope to be evaluated at each moment based on Gaussian mixture distribution and constructing a representative data chain, the method includes: The kernel density function expression is: Where n represents the total number of humidity data collected at the same time, h represents the smoothing bandwidth, represents the humidity data collected at the same time, and x represents the value of a certain frequency point to be estimated; The humidity data corresponding to the highest frequency of kernel density is taken as the representative data at that moment; Combining the representative data at each moment to form the representative data chain; Comparing the representative data chain with the historical humidity data set and determining the predicted humidity data based on the comparison result includes: When there is data in the historical humidity data set whose similarity to the representative data chain is greater than a similarity threshold, the historical verified humidity value of the historical representative data chain corresponding to the maximum similarity is used as the predicted humidity data; When the similarity between all historical representative data chains in the historical humidity data set and the representative data chain is less than or equal to a similarity threshold, training an LSTM model based on the historical humidity data set, and determining the predicted humidity data according to the LSTM model; Determining the predicted humidity data according to the LSTM model includes: Divide each humidity data in the representative data chain into windows according to the time series as input data, obtain the output result of the LSTM model, and use the output result as the predicted humidity data; When determining whether to adjust the restoration assessment value based on the comparison result, it includes: The predicted humidity data is compared with a humidity threshold. When the predicted humidity data is greater than the humidity threshold, it is determined that the repair evaluation value is adjusted; when the predicted humidity data is less than or equal to the humidity threshold, it is determined that the repair evaluation value is not adjusted.

2. The method for evaluating vegetation restoration of bedding rock slopes according to claim 1, characterized in that: When determining the slope risk factor based on the predicted humidity data, the following steps are included: obtaining a humidity difference value based on the predicted humidity data and the humidity threshold, the humidity difference value being the difference between the predicted humidity data and the humidity threshold value, comparing the humidity difference value with a first preset difference value and a second preset difference value, respectively, and determining the cohesion force based on the comparison results; the first preset difference value being less than the second preset difference value; When the humidity difference is less than or equal to the first preset difference, the cohesion is determined to be the first preset cohesion; when the humidity difference is greater than the first preset difference and less than the second preset difference, the cohesion is determined to be the second preset cohesion; when the humidity difference is greater than the second preset difference, the cohesion is determined to be the third preset cohesion; the first preset cohesion is greater than the second preset cohesion, the second preset cohesion is greater than the third preset cohesion, and the third preset cohesion is greater than or equal to 0.

3. The method for evaluating vegetation restoration of bedding rock slopes according to claim 2, characterized in that: When determining the slope risk coefficient based on the predicted humidity data, the following steps are also included: Where F is the slope risk coefficient, n is the cohesion, the height of the slope is H, the slope angle is α, the inclination angle of the structural surface is θ, γ is the weight of the rock mass, and φ is the internal friction angle.

4. The method for evaluating vegetation restoration of bedding rock slopes according to claim 3, characterized in that: Adjusting the restoration assessment value according to the slope risk coefficient includes: Comparing the slope risk coefficient with a minimum slope risk coefficient, where the minimum slope risk coefficient is 1, and determining an adjustment coefficient based on the comparison result to adjust the restoration assessment value; The adjustment coefficient is proportional to the slope risk coefficient, and the adjustment coefficient has a value range of (0, 1). The adjusted restoration assessment value is the product of the restoration assessment value and the adjustment coefficient.

5. A system for evaluating vegetation restoration of bedding rock slopes, for applying the method for evaluating vegetation restoration of bedding rock slopes according to any one of claims 1 to 4, characterized in that: include: a collection unit configured to collect vegetation information of the slope to be assessed, the vegetation information including green plant area and average root depth, and preliminarily determine a restoration assessment value based on the vegetation information; a processing unit configured to collect humidity data at a plurality of locations within a preset time period of the slope to be evaluated based on a humidity sensor, establish the data of each humidity sensor into a time-humidity data chain, construct all the time-humidity data chains into a humidity data set, determine representative humidity data of the slope to be evaluated at each moment based on a Gaussian mixture distribution, and construct the representative data chain; a judgment unit configured to compare the representative data chain with a historical humidity data set, and determine predicted humidity data according to a comparison result, wherein the historical humidity data set includes a plurality of historical representative data chains and a plurality of historical verification humidity data, and each of the historical representative data chains corresponds to a piece of historical verification humidity data; An adjustment unit is configured to compare the predicted humidity data with a humidity threshold, determine whether to adjust the repair assessment value based on the comparison result, and when it is determined that the repair assessment value is to be adjusted, determine a slope risk coefficient based on the predicted humidity data, and adjust the repair assessment value based on the slope risk coefficient.

Images