Slope stability probability prediction method and system and slope stability probability regression model construction system

Abstract

The present invention discloses a slope stability probability prediction method, system and slope stability probability regression model construction system. The method comprises: first, collecting multiple slope monitoring data as samples to construct a data set. Then, combining the LightGBM model and the GAMLSS model to construct a probability regression model, training the probability regression model through the data set, and integrating the optimization algorithm to optimize the hyperparameters of the probability regression model to obtain the optimal probability regression model parameters. The constructed probability regression model combines the LightGBM model and the GAMLSS model to construct a probability regression model, which accurately quantifies the arbitrary uncertainty covered in the slope stability while ensuring the accuracy of slope stability prediction, thereby improving the accuracy of slope stability evaluation. By adopting the optimization algorithm to optimize the parameters of the probability regression model, the prediction accuracy and reliability of the probability regression model are further improved, and the accuracy of slope stability evaluation is improved, so as to provide rich decision-making information for slope prevention and control design and risk management.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing systems or methods specifically suitable for prediction purposes, and in particular to a slope stability probability prediction method and system and a slope stability probability regression model construction system. Background Art

[0002] Slope stability issues are a common problem in sectors such as mining, water conservancy, construction, and transportation. Determining slope stability is fundamental to engineering risk management and preventive design. Therefore, in-depth research on slope stability evaluation and prediction methods is crucial. Currently, slope stability evaluation methods include engineering geological analogy, limit equilibrium methods, numerical methods, and methods based on statistical theory or machine learning.

[0003] Among them, methods based on statistical principles or machine learning are widely favored in slope stability assessment and landslide prediction because they have strong capabilities in handling complex nonlinear problems and fully consider the impact of different factors on slope stability. Examples include grey system theory, fuzzy hierarchical discriminant method, BP neural network, support vector machine (SVM), decision tree, Adaboost algorithm, XGBoost algorithm, random forest RF algorithm, and deep learning.

[0004] Slope systems are highly complex, nonlinear systems influenced by numerous internal and external factors, including rainfall, earthquakes, human activity, lithology, geological structure, and hydrological conditions. This results in strong randomness and uncertainty in slope stability. While machine learning methods have achieved promising results in slope stability assessment and prediction, they cannot accurately reflect and quantify the inherent randomness in slope stability assessment, leading to inaccurate estimates of the slope's true stability. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention proposes a slope stability probabilistic prediction method and system, as well as a slope stability probabilistic regression model construction system. These methods can accurately quantify the arbitrary uncertainty in slope stability while ensuring the accuracy of slope stability prediction. The specific technical solution is as follows:

[0006] In a first aspect, a method for constructing a slope stability probabilistic regression model is provided. In a first possible implementation of the first aspect, the method includes:

[0007] Obtain multiple slope monitoring data to build a data set;

[0008] The probabilistic regression model constructed by combining the LightGBM model and the GAMLSS model is trained using the data set, and the model parameters of the probabilistic regression model are optimized using an optimization algorithm.

[0009] In combination with the first possible implementation of the first aspect, in a second possible implementation of the first aspect, acquiring multiple slope monitoring data to construct a data set includes:

[0010] The acquired slope monitoring data is normalized.

[0011] In combination with the first implementable manner of the first aspect, in a third implementable manner of the first aspect, the log-likelihood / loss function used in the constructed probabilistic regression model is:

[0012] ;

[0013] in, is the number of iterations, and are the first-order derivative and second-order derivative of the loss function, respectively. For the LightGBM model, is the leaf node weight, is the penalty item, is the total number of leaf nodes, is the target number, is the regularization parameter.

[0014] In combination with the first implementable manner of the first aspect, in a fourth implementable manner of the first aspect, the constructed probability regression model adopts a mixed distribution to describe the slope stability coefficient.

[0015] In combination with the first implementable manner of the first aspect, in a fifth implementable manner of the first aspect, a PSO algorithm is used to perform hyperparameter optimization on the probabilistic regression model.

[0016] In a second aspect, a slope stability probabilistic prediction method is provided, which is characterized by comprising:

[0017] Adopting the slope stability probabilistic regression model construction method as described in any one of the first to fifth possible implementations of the first aspect to construct a probabilistic regression model;

[0018] Slope monitoring data of a slope to be predicted is acquired, and the slope stability probability of the slope to be predicted is predicted using a probabilistic regression model.

[0019] In conjunction with the first implementable manner of the second aspect, in a second implementable manner of the second aspect, predicting the slope stability probability of the slope to be predicted includes:

[0020] The slope monitoring data of the slope to be predicted is normalized.

[0021] In combination with the first possible implementation of the second aspect, a third possible implementation of the second aspect further includes:

[0022] The SHAP method was used to perform interpretability analysis on the slope stability probability to quantify the contribution of different factors to slope stability.

[0023] In a third aspect, a slope stability probabilistic regression model construction system is provided, including:

[0024] A data set construction module is configured to acquire multiple slope monitoring data to construct a data set;

[0025] The prediction model construction module is configured to train the probability regression model constructed by combining the LightGBM model and the GAMLSS model through the data set, and optimize the model parameters of the probability regression model using an optimization algorithm.

[0026] In a fourth aspect, a slope stability probability prediction system is provided, comprising:

[0027] A model building module is configured to construct a probabilistic regression model using the slope stability probabilistic regression model building method described in any one of the first to fifth possible implementations of the first aspect;

[0028] The probability prediction module is configured to obtain slope monitoring data of the slope to be predicted and predict the slope stability probability of the slope to be predicted through a probability regression model.

[0029] Beneficial Effects: The present invention employs a probabilistic slope stability prediction method, system, and system for constructing a probabilistic slope stability regression model. By integrating the LightGBM model with the GAMLSS model, the probabilistic regression model accurately quantifies the arbitrary uncertainty involved in slope stability while ensuring the accuracy of slope stability prediction. By optimizing the parameters of the probabilistic regression model using an optimization algorithm, the prediction accuracy and reliability of the probabilistic regression model can be further improved, thereby constructing a reliable slope stability prediction model and improving the accuracy of slope stability evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the specific embodiments of the present invention, the following briefly introduces the drawings required for use in the specific embodiments. In all the drawings, each element or part is not necessarily drawn according to the actual scale.

[0031] Figure 1 A flowchart of a method for constructing a slope stability probabilistic regression model provided by one embodiment of the present invention;

[0032] Figure 2 A flowchart of a slope stability probability prediction method provided by one embodiment of the present invention;

[0033] Figure 3 A system block diagram of a slope stability probabilistic regression model construction system provided by one embodiment of the present invention;

[0034] Figure 4 A system block diagram of a slope stability probability prediction system provided by one embodiment of the present invention;

[0035] Figure 5 An optimal estimation diagram of a mixed distribution of safety factors of a slope provided by an embodiment of the present invention;

[0036] Figure 6 This is a schematic diagram of the results of stability prediction using the prediction method provided by the present invention;

[0037] Figure 7 for Figure 6 Probability prediction results for cases 74, 76, 79, and 81;

[0038] Figure 8 The importance ranking diagram of factors affecting slope stability;

[0039] Figure 9 A SHAP dependency graph of the slope angle calculated based on the prediction result obtained by the prediction method provided by the present invention;

[0040] Figure 10 The SHAP dependency graph of the slope height is obtained by calculating the prediction results based on the prediction method provided by the present invention. DETAILED DESCRIPTION

[0041] The following embodiments of the technical solution of the present invention will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention and are therefore only examples and are not intended to limit the scope of protection of the present invention.

[0042] like Figure 1 The flowchart of the slope stability probabilistic regression model construction method shown in FIG. 1 includes:

[0043] Step 1: Acquire multiple slope monitoring data to build a data set;

[0044] Step 2: The probability regression model constructed by combining the LightGBM model and the GAMLSS model is trained using the data set, and the model parameters of the probability regression model are optimized using an optimization algorithm.

[0045] Specifically, a dataset can be constructed by first collecting multiple different slope monitoring data samples. Then, a probabilistic regression model can be constructed by combining the LightGBM and GAMLSS models. The optimal distribution of the target variable, the slope stability coefficient, can be determined. The probabilistic regression model can then be trained using the constructed dataset to obtain a trained probabilistic regression model. During the training process, an optimization algorithm can be incorporated to optimize the hyperparameters of the probabilistic regression model to obtain the optimal probabilistic regression model parameters.

[0046] The probabilistic regression model constructed by combining the LightGBM model and the GAMLSS model can accurately quantify the arbitrary uncertainty in slope stability while ensuring the accuracy of slope stability prediction, thereby improving the accuracy of slope stability assessment. Furthermore, by using an optimization algorithm to optimize the parameters of the probabilistic regression model, the prediction accuracy and reliability of the probabilistic regression model can be further improved, thereby enhancing the accuracy of slope stability assessment and providing rich decision-making information for slope prevention and control design and risk management.

[0047] In this embodiment, optionally, multiple sets of slope monitoring data are acquired to construct a data set, including:

[0048] The acquired slope monitoring data is normalized.

[0049] Specifically, the collected slope monitoring data includes factors that affect slope stability, such as bulk density, cohesion, internal friction angle, slope angle, slope height, and pore pressure ratio. The data values ​​corresponding to each factor in the acquired slope monitoring data can be normalized. The specific calculation formula is as follows:

[0050] ;

[0051] in, 、 are the values ​​before and after factor normalization, 、 are the maximum and minimum values ​​corresponding to the factors in the slope monitoring data, respectively.

[0052] Specifically, the probabilistic regression model combines the LightGBM model and the GAMLSS model. It models the distribution of the target variable to address the uncertainty of objective things and achieve the purpose of probabilistic regression or probabilistic prediction. When building a probabilistic regression model, it is necessary to select an appropriate log-likelihood / loss function and determine the optimal distribution of the target variable.

[0053] In this embodiment, the log-likelihood / loss function used in the constructed probabilistic regression model is optionally:

[0054] ;

[0055] in, is the number of iterations, and are the first-order derivative and second-order derivative of the loss function, respectively. For the LightGBM model, is the leaf node weight, is the penalty item, is the total number of leaf nodes, is the target number, is the regularization parameter.

[0056] The GAMLSS model is used to model the distribution of the target variable. The specific expression is as follows:

[0057] ;

[0058] in, is the target variable The distribution of is a distribution parameter, and each distribution parameter is modeled by an additive model, such as a linear model, spline regression, etc. In this embodiment, the LightGBM model is used to replace the additive model in the GAMLSS model, and the gradient boosting tree of the LightGBM model is used to fit each parameter, that is, the known function between the distribution parameter and the predictor. is a known function between the distribution parameter and the predictor. The specific expression is as follows:

[0059] .

[0060] in, is the predictor, namely the LightGBM model.

[0061] It can be seen that it is extremely important to determine the appropriate distribution type of the target variable.

[0062] In this embodiment, optionally, the constructed probabilistic regression model adopts a mixed distribution to describe the slope stability coefficient.

[0063] Specifically, the mixed distribution can be used to describe the slope stability coefficient, and the specific expression is as follows:

[0064] ;

[0065] in, is the mixed distribution of observations, is the mth sub-distribution, each sub-distribution has its own parameters and weights , The mixed distribution is composed of multiple different sub-distributions, which can be simple distribution types such as Normal distribution or StudentT distribution. Based on the stability coefficient in the training set, the mixed distribution and parameters of the stability coefficient of the present invention are finally determined as follows: Figure 5 shown.

[0066] In this way, the constructed probabilistic regression model can accurately quantify the inherent uncertainty contained in slope stability, thereby providing rich decision-making information for slope prevention and control design and risk management.

[0067] In this embodiment, optionally, a PSO algorithm is used to perform hyperparameter optimization on the probabilistic regression model.

[0068] Specifically, the particle swarm algorithm can be used to optimize the parameters of the probabilistic regression model. Specifically, first, the parameters of the particle swarm algorithm can be initialized according to the constructed probabilistic regression model, including: eta, max_depth, min_gain_to_split, min_sum_hessian_in_leaf, subsample, feature_fraction and boosting. The initialization parameter value ranges are [1e-5, 1], [1, 200], [1e-8, 20], [1e-8, 500], [0.2, 1], [0.2, 1] and [categorical, gbdt]. Then, the population size, position range and speed range are determined, as well as the position of the initialized particles. and speed , set the maximum number of iterations and initialize the learning factor and After that, iterative training is carried out to update the optimal solution vector of a single particle and the global optimal solution vector of the particle swarm by comparing the fitness value, so as to obtain the optimal probability regression model parameters. The specific calculation formula is as follows:

[0069] ;

[0070] ;

[0071] ;

[0072] in, is the fitness function, is the number of training samples, is the particle velocity, is the particle position, 、 is a random number between 0 and 1. is the true value of the sample, is the predicted value of the probabilistic regression model, is the parameter to be optimized, is the individual extreme value.

[0073] It should be understood that this embodiment is only illustrated by the particle swarm algorithm, but the present invention is not limited thereto. Other optimization algorithms may also be used to optimize the parameters of the probabilistic regression model, such as the Bayesian optimization algorithm, the genetic optimization algorithm, etc.

[0074] In order to verify the prediction effect of the probability regression model constructed by the present invention, the stability coefficients of multiple slopes were predicted using the constructed probability regression model. The prediction results are as follows: Figure 6 、 Figure 7 As shown, the predicted probability density distributions for Cases 74, 76, 79, and 81 all approximate Gaussian distributions, with the true slope stability coefficients falling between the 0.05 and 0.95 quantiles of the predicted distributions and around the uniform distribution and predicted mean. This demonstrates that the probabilistic regression model constructed using the method of the present invention can produce high-quality probabilistic predictions, accurately quantifying the inherent uncertainty and randomness in slope stability, and providing rich decision-making information for slope prevention and control design and risk management.

[0075] like Figure 2 The flowchart of the slope stability probabilistic prediction method is shown in FIG. 1 , and the prediction method includes:

[0076] Step S1: constructing a probabilistic regression model using the above-mentioned slope stability probabilistic regression model construction method;

[0077] Step S2: Obtain slope monitoring data of the slope to be predicted, and predict the slope stability probability of the slope to be predicted using a probabilistic regression model.

[0078] Specifically, first, a probabilistic regression model for predicting slope stability coefficients can be constructed using the above-mentioned construction method. Then, slope monitoring data of the slope to be predicted can be obtained, and the slope stability probability can be predicted using the constructed probabilistic regression model.

[0079] In this embodiment, optionally, predicting the slope stability probability of the slope to be predicted includes: performing normalization processing on the slope monitoring data of the slope to be predicted.

[0080] In this embodiment, optionally, the following is further included:

[0081] The SHAP method was used to perform interpretability analysis on the slope stability probability to quantify the contribution of different factors to slope stability.

[0082] Specifically, after obtaining the stability probability of the slope to be predicted through the probabilistic regression model, the SHAP method can be used to perform an interpretable analysis of the stability probability. The calculated SHAP value quantifies the contribution of different factors to slope stability, thereby providing richer decision-making information for slope safety construction and risk management. The specific calculation formula of the SHAP value is as follows:

[0083] ;

[0084] in, is the initial expected value, is the number of input features, is the SHAP value of the feature, Indicates whether the corresponding feature can be observed. The specific calculation formula of the feature's SHAP value is as follows:

[0085] ;

[0086] in, is the set of all features in the training set, for A subset of 、 Based on S and The calculated sample mean, To include and does not include The difference of .

[0087] In this example, the SHAP method can be used to calculate the contribution of slope angle, slope height, bulk density, cohesion, internal friction angle and pore pressure ratio to the slope stability coefficient, and the results are shown in the order of feature importance. Figure 8 As shown, it can be seen that the slope angle and slope height have the greatest influence on slope stability, followed by cohesion, while the bulk density, internal friction angle and pore pressure ratio have the worst influence on slope stability, especially the pore pressure ratio, whose contribution to the model output is 0, which is consistent with the actual physical laws followed by the slope, proving the accuracy and effectiveness of the present invention.

[0088] In order to analyze the detailed contribution of different input features to the model prediction results, the SHAP method is used to calculate the single factor dependency graph, such as Figure 9 、 Figure 10 As shown in the figure, it can be seen that as the slope angle and slope height increase, the SHAP value gradually decreases, indicating that the greater the slope gradient and height, the lower the slope stability. This is consistent with the actual physical laws followed by the slope, further proving the accuracy and effectiveness of the present invention.

[0089] like Figure 3 The system block diagram of the slope stability probabilistic regression model construction system shown in FIG. 1 includes:

[0090] A data set construction module is configured to acquire multiple slope monitoring data to construct a data set;

[0091] The prediction model construction module is configured to train the probability regression model constructed by combining the LightGBM model and the GAMLSS model through the data set, and optimize the model parameters of the probability regression model using an optimization algorithm.

[0092] Specifically, the construction system includes a dataset construction module and a prediction model construction module. The dataset construction module can collect multiple different slope monitoring data as samples to construct a dataset. The prediction model construction module can combine the LightGBM model and the GAMLSS model to construct a probabilistic regression model, determine the optimal distribution of the target variable, namely the slope stability coefficient, and train the probabilistic regression model using the constructed dataset to obtain a trained probabilistic regression model. During the training process, an optimization algorithm can be incorporated to optimize the hyperparameters of the probabilistic regression model to obtain the optimal probabilistic regression model parameters.

[0093] The probabilistic regression model constructed by combining the LightGBM model and the GAMLSS model can accurately quantify the arbitrary uncertainty in slope stability while ensuring the accuracy of slope stability prediction, thereby improving the accuracy of slope stability assessment. Furthermore, by using an optimization algorithm to optimize the parameters of the probabilistic regression model, the prediction accuracy and reliability of the probabilistic regression model can be further improved, thereby enhancing the accuracy of slope stability assessment and providing rich decision-making information for slope prevention and control design and risk management.

[0094] like Figure 4 The system block diagram of the slope stability probability prediction system shown in FIG. 1 includes:

[0095] A model building module is configured to use the above-mentioned slope stability probability regression model building method to build a probability regression model;

[0096] The probability prediction module is configured to obtain slope monitoring data of the slope to be predicted and predict the slope stability probability of the slope to be predicted through a probability regression model.

[0097] Specifically, the prediction system includes a model building module and a probabilistic prediction module. The model building module uses the aforementioned construction method to construct a probabilistic regression model for predicting slope stability. The probabilistic prediction module obtains slope monitoring data for the slope to be predicted and uses the constructed probabilistic regression model to predict the slope's stability probability.

[0098] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. A slope stability probability prediction method, characterized in that: include: Acquire multiple slope monitoring data sets to build a data set. The slope monitoring data includes bulk density, cohesion, internal friction angle, slope angle, slope height, and pore pressure ratio. The probabilistic regression model constructed by combining the LightGBM model and the GAMLSS model is trained using the data set, and the model parameters of the probabilistic regression model are optimized using an optimization algorithm; The GAMLSS model is used to model the distribution of the target variable. The specific expression is as follows: ； in, is the target variable The distribution of For distribution parameters, each distribution parameter is modeled by an additive model, and the LightGBM model is used to replace the additive model in the GAMLSS model. The gradient boosting tree of the LightGBM model is used to fit the known function between each distribution parameter and the predictor , the specific expression is as follows: ； It is the LightGBM model; The constructed probabilistic regression model uses a mixed distribution to describe the slope stability coefficient. The specific expression is as follows: ； in, is the mixed distribution of observations, is the mth sub-distribution, each sub-distribution has its own parameters and weights , ; Obtaining slope monitoring data of a slope to be predicted, and predicting the slope stability probability of the slope to be predicted using a probabilistic regression model; The SHAP method was used to perform interpretability analysis on the slope stability probability to quantify the contribution of different factors to slope stability.

2. The slope stability probability prediction method according to claim 1, characterized in that: Acquire multiple slope monitoring data sets to build a data set, including: The acquired slope monitoring data is normalized.

3. The slope stability probability prediction method according to claim 1, characterized in that: The log-likelihood / loss function used in the constructed probabilistic regression model is: ； in, is the number of iterations, and are the first-order derivative and second-order derivative of the loss function, respectively. For the LightGBM model, is the leaf node weight, is the penalty item, is the total number of leaf nodes, is the target number, is the regularization parameter.

4. The slope stability probability prediction method according to claim 1, characterized in that: The PSO algorithm is used to optimize the hyperparameters of the probabilistic regression model.

5. The slope stability probability prediction method according to claim 1, characterized in that: Predicting the slope stability probability of the slope to be predicted includes: The slope monitoring data of the slope to be predicted is normalized.

6. A slope stability probabilistic regression model construction system, characterized by: include: A data set construction module is configured to acquire multiple slope monitoring data to construct a data set, wherein the slope monitoring data includes bulk density, cohesion, internal friction angle, slope angle, slope height, and pore pressure ratio; A prediction model construction module is configured to train a probabilistic regression model constructed by combining the LightGBM model and the GAMLSS model using the data set, and optimize the model parameters of the probabilistic regression model using an optimization algorithm; The GAMLSS model is used to model the distribution of the target variable. The specific expression is as follows: ； in, is the target variable The distribution of For distribution parameters, each distribution parameter is modeled by an additive model, and the LightGBM model is used to replace the additive model in the GAMLSS model. The gradient boosting tree of the LightGBM model is used to fit the known function between each distribution parameter and the predictor , the specific expression is as follows: ； It is the LightGBM model; The constructed probabilistic regression model uses a mixed distribution to describe the slope stability coefficient. The specific expression is as follows: ； in, is the mixed distribution of observations, is the mth sub-distribution, each sub-distribution has its own parameters and weights , .

7. A slope stability probability prediction system, characterized in that: include: A model building module configured to use the slope stability probability prediction method according to any one of claims 1 to 4 to build a probability regression model; The probability prediction module is configured to obtain slope monitoring data of the slope to be predicted and predict the slope stability probability of the slope to be predicted through a probability regression model.

Images