Landslide surge height prediction method and system based on sparrow optimization random forest model

Abstract

The invention relates to the technical field of data driving and landslide surge disaster prevention and control, and discloses a landslide surge height prediction method and system based on a sparrow optimization random forest model.The method comprises the steps that for a target landslide area, a corresponding landslide surge physical model is built, and test groups with different landslide volumes and water depths are set for testing; a corresponding test data set is obtained, and equal-proportion scaling is carried out according to Froude similarity criteria; the method comprises the following steps: preprocessing test data to obtain a corresponding data set, and dividing the preprocessed data set into a training set and a test set; building a sparrow optimized random forest model, setting input values of various parameters, enabling the training set to train the sparrow optimized random forest model, and predicting the maximum height of the landslide surge by using the label data set and the trained sparrow optimized random forest model. The system comprises a data acquisition module, a data division module and a landslide surge prediction module. According to the method, the maximum height of the landslide surge can be accurately predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of data-driven and landslide surge disaster prevention and control, and in particular to a landslide surge height prediction method and system based on a sparrow-optimized random forest model. Background Art

[0002] Landslide surge research has always been the focus of landslide surge disaster chain research. For the landslide surge safety of major projects, studying the mechanism and law of landslide surge is helpful to assess the risk of geological disasters, take effective preventive measures, and ensure the safety of the project. For mountain rivers, the landslide body produced by landslide accidents may cause serious landslide surge disasters, posing a major threat to reservoir bank slopes, hydraulic structures, etc. Therefore, the landslide surge disaster caused by landslides cannot be ignored. How to correctly predict the maximum height of landslide surges and carry out targeted prevention and control has important scientific significance and engineering value. In recent years, more and more studies have applied machine learning methods to the field of landslide research. Compared with existing research methods, machine learning methods not only consider multiple factors affecting landslides, but also improve the accuracy of research results. Machine learning methods can quickly process a large amount of data in a short period of time, and comprehensively consider the relationship between various characteristic factors, reducing the complexity of research.

[0003] There are several existing methods for predicting landslide surge height, and each method has certain defects: the energy method only considers the starting and ending positions of the landslide body during the calculation process, ignoring the trajectory changes and the morphological changes of the landslide body; the Pan Jiazheng method considers the influence of the landslide body morphology and water, but can only calculate a certain moment and cannot reflect the entire process of the landslide; the method recommended by the American Society of Civil Engineering considers the influence of the landslide shape, but it has too many assumptions and it is difficult to obtain accurate results; the Scheidegger method establishes a relationship between the friction coefficient and the landslide volume, but it is only applicable to debris materials. The method of using the sparrow optimized random forest model to predict the maximum landslide surge height not only considers the multiple factors that affect the landslide, but also comprehensively considers the relationship between each characteristic factor, reduces the complexity of the research, and improves the accuracy of the research results.

[0004] Prior art 1, Chinese patent, application number 202311133111.5 discloses a method for predicting the probability of exceeding the maximum height of a landslide-surge, including: constructing candidate models in dimensionless form, counting the model test data of each experimental design, establishing each experimental database, performing Bayesian processing on the candidate models according to each experimental database, generating the Bayesian factor of each candidate model, determining the candidate model with the largest Bayesian factor as the maximum height prediction model, updating the maximum height prediction model through Bayesian, determining the parameter probability distribution, and predicting the probability of exceeding the maximum height of the landslide-surge in the target reservoir area according to the parameter probability distribution. Although each candidate model is processed by Bayesian, the maximum height prediction model is determined, the parameter probability distribution is determined, and the uncertainty of the experimental design is quantified, thereby predicting the probability of exceeding the maximum height of the landslide-surge in the target reservoir area. However, only the starting position and the ending position of the landslide body are considered, and the trajectory changes and the morphological changes of the landslide body are ignored, resulting in reduced prediction accuracy;

[0005] Prior art 2, Chinese patent, application number 201910437509.5 discloses a model test device for studying the energy dissipation effect of landslide surge and wave height prediction, including a landslide body model, a sliding device, a test flume, a bank slope rough wall and slope shape device and a wave height test device, the sliding device and the bank slope rough wall and slope shape device are arranged on the wall surface in the test flume, the landslide body model is placed on the sliding device, and the wave height test device is installed on the top of the test flume or placed on the side of the test flume through a mobile frame. A test method for a model test device for studying the energy dissipation effect of landslide surge and wave height prediction is also disclosed, which can simulate the surge changes caused by the sliding process of different landslide bodies through the test device, and the influence of the bank slope shape and bank slope roughness on the surge propagation process. Although it is possible to analyze and predict the propagation law and attenuation trend of landslide surge waves caused by different bank slope shapes and bank slope roughness, and establish a prediction model for the distribution of landslide surge wave height along the way. However, it can only calculate a certain moment and cannot reflect the entire process of the landslide.

[0006] Prior art three, Chinese patent, application number 202410014296.6 discloses a method for judging the type of surge waves induced by landslides in waters and predicting wave heights, including establishing a dynamic model of slope instability, obtaining the landslide velocity u(t) and landslide displacement s(t) processes, calculating dimensionless parameters Fr and Sz, distinguishing the type of surge waves, and calling the oscillation wave / single wave formula to calculate the wave height m of the corresponding wave type. Although the landslide surge waves are classified and distinguished, and a wave height prediction method is proposed for different surge waves, it provides reliable technical support for the determination of relevant disaster prevention and mitigation measures and the formulation of emergency plans. However, there are too many assumptions, and it is difficult to obtain accurate results.

[0007] At present, the existing technologies 1, 2 and 3 only consider the starting position and the ending position of the landslide body in the calculation process, ignore the trajectory change and the morphological change of the landslide body, can only calculate a certain moment, cannot reflect the whole process of the landslide, assume too many conditions, and it is difficult to obtain accurate results. Therefore, the present invention provides a method and system for predicting the height of landslide surge based on the sparrow optimized random forest model. The method for predicting the maximum height of landslide surge using the sparrow optimized random forest model not only considers the multiple factors affecting the landslide, but also comprehensively considers the relationship between each characteristic factor, reduces the complexity of the research, and improves the accuracy of the research results. Summary of the invention

[0008] The main purpose of the present invention is to provide a method and system for predicting landslide surge height based on the sparrow optimized random forest model, so as to solve the problem that the prior art only considers the starting position and the ending position of the landslide body, ignores the trajectory change and the morphological change of the landslide body, can only calculate a certain moment, cannot reflect the entire process of the landslide, assumes too many conditions, and it is difficult to obtain accurate results.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A landslide surge height prediction method based on a sparrow-optimized random forest model, the landslide surge height prediction method based on a sparrow-optimized random forest model comprising:

[0011] For the target landslide area, a corresponding landslide surge physical model is built, and test groups with different landslide volumes and water depths are set up for testing to obtain the corresponding test data set, which is then scaled according to the Froude similarity criterion.

[0012] The experimental data is preprocessed to obtain the corresponding data set, and the preprocessed data set is divided into a training set and a test set in a ratio of 7:3, that is, the test set data accounts for 30% of the total data;

[0013] Use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set the input values ​​of various parameters and use the training set to train the sparrow optimized random forest model, and use the labeled data set and the trained sparrow optimized random forest model to predict the maximum height of the landslide surge.

[0014] As a further improvement of the present invention, the process of scaling according to the Froude similarity criterion includes:

[0015] Calculate the Froude number of the target landslide area and the model; introduce the characteristic flow frequency F c And the flow resistance factor D:

[0016]

[0017] Matching of Froude numbers of the model and the target landslide area: The Froude numbers of the test model and the target landslide area are equal, that is:

[0018]

[0019] Among them, V m and V p are the flow velocities in the model and target areas respectively; L m and L p are the characteristic lengths of the model and target regions, respectively;

[0020] Determine the ensemble scaling ratio λ of the model and the target landslide area;

[0021] According to the Froude number formula, the scaling factor is defined as:

[0022]

[0023] Update the flow rate of the model to meet the proportional scaling condition and introduce an adjustment coefficient C v Consider the difference between actual flows:

[0024]

[0025] Adjustment factor C v Adjusted based on previous trial data and similarity;

[0026] The test flow rate, pressure, gravitational acceleration and other related physical quantities are adjusted proportionally;

[0027] The influence of the density λ and dynamic viscosity of the introduced fluid on the pressure:

[0028]

[0029] Among them C p is the pressure adjustment factor, which is calibrated by test data;

[0030] After adjusting all relevant physical quantities, tests are conducted on the model, data are collected and recorded accordingly; the test data are scaled to the target landslide area in each test:

[0031] Prediction result = C data Actual test results

[0032] Among them C data is the conversion factor used to fit the model to the experimental data.

[0033] As a further improvement of the present invention, the preprocessed data set is divided into a training set and a test set, including:

[0034] Represent the data set as a set, containing multiple samples, each of which consists of features and corresponding target variables; preprocess the data to generate feature matrices and target variables; calculate a weight for each sample, which reflects the importance of the sample;

[0035] The cumulative distribution function of the samples is calculated based on the weights, and the cumulative distribution function is used for weighted random sampling. Samples are randomly selected as training sets in a ratio of 7:3, and the remaining samples are used as test sets.

[0036] The obtained training set and test set meet the required ratio in terms of sample number.

[0037] As a further improvement of the present invention, the process of predicting the maximum height of the landslide surge includes:

[0038] A performance monitoring layer is introduced into the sparrow optimization algorithm to track the performance of the slope surge height prediction model on the validation set in real time during the optimization process; during the search process, the number of global searches is dynamically increased. Whenever the sparrow optimization algorithm detects a local optimal bottleneck, it enters the global reinforcement stage to increase the mutation rate and crossover rate;

[0039] A feature sharing network is established between individual sparrows, allowing individuals to share and receive feature information through a weighted adjacency graph. Each sparrow receives the excellent features found by its neighbor sparrows through a graph propagation mechanism, and aggregates a set of features that are effective for predicting surge height. After completing their respective tasks, sparrows use feature evaluation and voting algorithms to decide whether to adopt a feature, increase the frequency of use of the optimal feature, and achieve efficient integration of information sharing in the group.

[0040] In the feature integration stage, different sparrow individuals are allowed to introduce heterogeneous features in their own fields to form diversified feature clusters; they are grouped by clustering the effects of different feature combinations, and the optimal feature combination is selected for training through similarity metrics;

[0041] During the operation of the random forest model, the decision tree monitors the performance of the split nodes through weighted hysteresis tracking, and determines in real time whether the nodes under certain conditions need to be reconstructed; each node of the decision tree has a life span, and a new tree structure is created dynamically; when constructing each tree, a feature subset is selected based on feature importance, and a voting mechanism is used to comprehensively weight the important features of each tree; when analyzing features, the introduction and fusion of new features are achieved through sequential dependency selection;

[0042] Generate new samples for the training dataset by combining the generative adversarial network, and construct different versions of the training set by combining the generated samples with the actual samples; set the parameters of the standard distribution selected in the pre-training stage of the generator; implement batch normalization and random dropout strategies in the training of the sparrow optimized random forest model;

[0043] The data including landslide volume and water depth are obtained for each experiment to form an input vector. The corresponding maximum surge height is the label. The input vector and the label are combined to form a label data set. The label data set is represented by a one-dimensional array, in which each element corresponds to the maximum surge height of each set of feature data. The label data set and the trained sparrow optimized random forest model are used to predict the maximum height of landslide surge.

[0044] As a further improvement of the present invention, a process for realizing efficient integration of information sharing in a group includes:

[0045] Suppose there are multiple sparrow individuals, each sparrow individual is connected to its neighbor set, an adjacency matrix is ​​defined, and the feature vector of the sparrow individual is defined at the same time. After one propagation, the individual's features are obtained by weighted average of the features of its neighbors;

[0046] There are N′ sparrow individuals, each sparrow individual a and its neighbor set N′ a We define the adjacency matrix in:

[0047] A ab = {1, if sparrow, b is a sparrow, a's neighbor 0, otherwise

[0048] Define the eigenvector of sparrow individual a as Where M′ is the feature dimension. After one propagation, the features of individual a can be obtained by weighted average of the features of its neighbors:

[0049] f a″ =σ(Σb∈N′ a w ab f b )

[0050] Among them, w ab is the influence weight of sparrow b on sparrow a, σ(·) is the activation function used to introduce nonlinearity;

[0051] For the newly generated features, each sparrow calculates its prediction ability and the prediction error of the sparrow for the new features. All sparrows vote and select features based on the error evaluation results.

[0052] Among them, for the newly generated feature f a″ , each sparrow calculates its prediction ability, let ε a is the prediction error of sparrow a for the new feature, and the formula is as follows:

[0053]

[0054] Among them, K is the number of samples in the validation set, is the output of predicting sample k using the new features, y k is the actual maximum height of the swell;

[0055] All sparrows vote based on the error evaluation results to select features; after the features pass the evaluation, the number of votes for each feature is V c , then the probability P of a feature c being adopted b for:

[0056]

[0057] The sparrow adopts the probability P b The features that are greater than the set threshold θ form a new feature set for subsequent training.

[0058] As a further improvement of the present invention, the process of selecting the optimal feature combination for training by similarity measurement includes:

[0059] Generate various combinations from all available features, each feature combination represents a specific selection of a set of features, using a binary method to indicate whether each feature is selected; use a predefined random forest to train each feature combination and evaluate the performance on the validation set, assigning a performance score to each feature combination based on the evaluation results;

[0060] According to the performance scores, the feature combinations are divided into different groups, and the feature combinations with similar performance are classified into one category. By analyzing the clustering results, the similarity between feature combinations is evaluated and the correlation between features is measured;

[0061] Based on the calculated similarity, a feature combination with a similarity higher than a preset threshold is selected.

[0062] As a further improvement of the present invention, the process of weighting the important features of each tree by using a voting mechanism includes:

[0063] Calculate a performance index for each decision tree based on the performance of the tree on the validation set; assign different voting weights to each tree based on the performance index; establish a feature interaction network, model the relationship between each feature through a graph neural network, and connect the importance value of each tree to other feature nodes as a node to form a feature interaction relationship diagram;

[0064] The prediction results of each tree are analyzed for consistency. If the prediction of a tree in a specific field is inconsistent with other trees, the voting influence weight of the tree is automatically reduced. Each tree gives a prediction value and corresponding confidence when voting. The output is a weighted sum based on the feature weight, the tree's prediction value and the corresponding confidence.

[0065] The features are grouped heterogeneously according to their properties. For example, meteorological factors, terrain features, hydrological conditions, etc. are separated. An independent set of decision trees is designed for each feature group and trained. When making decisions, vote is performed by feature group, and feature selection and evaluation are performed within each feature group. The voting results of each feature group are summarized.

[0066] As a further improvement of the present invention, the process of implementing batch normalization and random dropout strategy includes:

[0067] Before model training, the input data is standardized; based on the structure of the deep neural network, a batch normalization layer is inserted after each hidden layer to ensure that the distribution of features can be adjusted to a more ideal state before the output of each layer is passed to the activation function;

[0068] After each hidden layer is forward propagated, the mean and variance of the hidden layer output are calculated, and the output is standardized using statistics; the standardized output is transformed through the learned scaling and offset parameters, and the global mean and variance are dynamically adjusted using the exponential moving average method;

[0069] The inactivation rate is set. In each training iteration, several neurons are randomly selected and their outputs are set to zero. A mask matrix with the same shape as the output of the current layer is generated. The selected inactivation rate controls which nodes are removed so that the model uses a different network structure during each training process.

[0070] As a further improvement of the present invention, the process of predicting the maximum height of the landslide surge includes:

[0071] Obtain the latest input feature data, including landslide volume, soil type, meteorological factors, water level changes and flow velocity; integrate the collected feature data into an input vector;

[0072] Load the trained and sparrow-optimized random forest model into memory; input the constructed input feature vector into the random forest model, perform inference on each decision tree, and execute the decision process of the tree based on the input features;

[0073] Each tree will traverse downward from the root node according to the value in the feature vector, split according to the feature threshold until it reaches the leaf node; at each leaf node, there is a predicted value, that is, the expected maximum surge height;

[0074] Collect the prediction results of all decision trees and aggregate them into a final prediction through a weighted voting mechanism; combine all trees to get a prediction value to represent the expected maximum surge height under a specific input feature vector; output the maximum surge height prediction results in the format of text, charts or reports.

[0075] To achieve the above object, the present invention also provides the following technical solutions:

[0076] A landslide surge height prediction system based on a sparrow optimized random forest model is applied to the landslide surge height prediction method based on a sparrow optimized random forest model. The landslide surge height prediction system based on a sparrow optimized random forest model includes:

[0077] The data acquisition module is used to build a corresponding landslide surge physical model for the target landslide area, set up test groups with different landslide volumes and water depths for testing, obtain the corresponding test data set, and scale it according to the Froude similarity criterion;

[0078] The data partitioning module is used to perform preprocessing operations on the test data to obtain the corresponding data set, and divide the preprocessed data set into a training set and a test set according to a ratio of 7:3, that is, the test set data accounts for 30% of the total data;

[0079] The landslide surge prediction module is used to use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set the input values ​​of various parameters and use the training set to train the model, and use the labeled data set and the trained sparrow optimized random forest model to predict the maximum height of the landslide surge.

[0080] The present invention can simulate the dynamic changes of ground water bodies when landslides occur more realistically by building a physical model of landslide surges, including the processes of landslide body entering water, water body disturbance, surge formation and propagation, etc., and set up test groups with different landslide volumes and water depths to systematically examine the influence of these key factors on the characteristics of landslide surges, providing rich test data support for subsequent model establishment and data analysis, and scaling based on the Froude similarity criterion to ensure the comparability of test data and the wide application of the model, so that the test results can more accurately reflect the actual landslide surges; through preprocessing operations, noise is removed, filling The missing values ​​are filled, etc., which improves the quality and availability of the data. The preprocessed data set is divided into training set and test set in a ratio of 7:3, which ensures the effectiveness of model training and the independence of test, and helps to evaluate the generalization ability of the model. The sparrow optimization algorithm is used to optimize the parameters of the random forest model to improve the prediction accuracy and stability of the model. As an emerging swarm intelligence optimization algorithm, the sparrow optimization algorithm can find the optimal solution in a complex parameter space. Based on the optimized random forest model, the training set is used for training, and the labeled data set is used for prediction, which can predict the maximum height of the landslide surge. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a schematic diagram of the steps of an embodiment of a method for predicting landslide surge height based on a sparrow-optimized random forest model of the present invention;

[0082] Figure 2 A schematic flow chart of the steps of building a corresponding landslide surge physical model according to an embodiment of the landslide surge height prediction method based on the sparrow-optimized random forest model of the present invention;

[0083] Figure 3 This is a schematic flow chart of the steps of dividing the preprocessed data set into a training set and a test set in one embodiment of the landslide surge height prediction method based on the sparrow optimized random forest model of the present invention;

[0084] Figure 4 A schematic flow chart of the steps of predicting the maximum height of a landslide surge according to an embodiment of the method for predicting the height of a landslide surge based on a sparrow-optimized random forest model of the present invention;

[0085] Figure 5 It is a functional module schematic diagram of an embodiment of a landslide surge height prediction system based on a sparrow-optimized random forest model of the present invention;

[0086] Figure 6 It is a structural schematic diagram of an embodiment of an electronic device of the present invention;

[0087] Figure 7 A schematic diagram of the structure of a storage medium according to an embodiment of the present invention;

[0088] Figure 8 It is a schematic diagram of an embodiment of a method for predicting landslide surge height based on a sparrow-optimized random forest model of the present invention;

[0089] Fig. 9 This is a comparison diagram of prediction results before and after optimization of an embodiment of a method for predicting landslide surge height based on a sparrow-optimized random forest model of the present invention;

[0090] Fig.10 A schematic diagram of a random forest learning curve of an embodiment of a method for predicting landslide surge height based on a sparrow-optimized random forest model of the present invention;

[0091] Fig.11 A schematic diagram of a sparrow optimized random forest learning curve of an embodiment of a method for predicting landslide surge height based on a sparrow optimized random forest model of the present invention;

[0092] Fig.12 This is a comparison diagram of feature importance coefficients of an embodiment of a landslide surge height prediction method based on a sparrow-optimized random forest model of the present invention. DETAILED DESCRIPTION

[0093] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0094] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0095] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0096] like Figure 1 As shown, this embodiment provides an embodiment of a method for predicting the height of landslide surge based on a sparrow-optimized random forest model. In this embodiment, the method for predicting the height of landslide surge based on a sparrow-optimized random forest model specifically includes the following steps:

[0097] Step S1: for the target landslide area, build a corresponding landslide surge physical model, set up test groups with different landslide volumes and water depths for testing, obtain the corresponding test data set, and scale it up and down according to the Froude similarity criterion;

[0098] Step S2: preprocess the test data to obtain a corresponding data set, and divide the preprocessed data set into a training set and a test set in a ratio of 7:3, that is, the test set data accounts for 30% of the total data;

[0099] Step S3: Use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set the input values ​​of various parameters and use the training set to train the sparrow optimized random forest model, and use the labeled data set and the trained sparrow optimized random forest model to predict the maximum height of the landslide surge.

[0100] Preferably, step S1 of this embodiment can simulate the dynamic changes of ground water bodies when landslides occur more realistically by building a physical model of landslide surges, including processes such as landslide body entering water, water body disturbance, surge formation and propagation, and setting test groups with different landslide volumes and water depths, so as to systematically examine the influence of these key factors on the characteristics of landslide surges, provide rich test data support for subsequent model establishment and data analysis, and perform proportional scaling based on the Froude similarity criterion, so as to ensure the comparability of test data and the wide application of models, so that the test results can more accurately reflect the actual landslide surges; step S2 removes the actual landslide surges through preprocessing operations. Noise removal, missing value filling, etc. are performed to improve the quality and availability of the data. The preprocessed data set is divided into a training set and a test set in a ratio of 7:3, which ensures the effectiveness of model training and the independence of test, and helps to evaluate the generalization ability of the model. Step S3 uses the sparrow optimization algorithm to optimize the parameters of the random forest model, which improves the prediction accuracy and stability of the model. The sparrow optimization algorithm, as an emerging swarm intelligence optimization algorithm, can find the optimal solution in a complex parameter space. Based on the optimized random forest model, the training set is used for training, and the labeled data set is used for prediction, which can predict the maximum height of the landslide surge.

[0101] In summary, this embodiment provides a reliable experimental basis for the prediction and evaluation of landslide surges, which is helpful for in-depth understanding of the physical mechanism of landslide surges. Through the accumulation of experimental data, a solid foundation is laid for subsequent data analysis and model training. Data preprocessing is an important link in the machine learning process, which directly affects the training effect and prediction accuracy of the model. Through reasonable data division, the performance of the model can be evaluated more objectively to ensure the reliability of the model in practical applications. The construction of the sparrow optimized random forest model realizes the efficiency and accuracy of landslide surge prediction, and provides strong technical support for the early warning and air defense of landslide disasters. Through the application of the model, the degree of harm of landslide surges can be predicted in advance, and a scientific basis can be provided for relevant departments to formulate emergency plans and take preventive measures, which is helpful to reduce the threat of landslide disasters to the safety of life and property of the people.

[0102] This embodiment proposes a landslide surge height prediction method based on a sparrow optimized random forest model, and establishes a landslide surge physical model experiment based on the Froude similarity criterion; the actual maximum landslide surge height at different points is obtained through experiments, and a sparrow optimized random forest model is established through a random forest algorithm and a sparrow optimization algorithm, which can accurately predict the maximum height of landslide surges at different points in the study area; this embodiment introduces a sparrow optimization algorithm to optimize the random forest model and applies it to actual engineering cases; the research results show that the sparrow optimized random forest model has better performance when processing data with a small deviation rate, and can significantly improve the accuracy of the model; at the same time, the sparrow optimized random forest model can reduce the standard deviation of the predicted value and improve the density of the predicted value; compared with the random forest model before optimization, the performance evaluation indicators of the optimized model are better than those of the model before optimization, and it shows better adaptability in predicting the maximum height of landslide surges, and can more accurately predict the maximum height of landslide surges.

[0103] Furthermore, if Figure 2 As shown, the process of building the corresponding landslide surge physical model in step S1 specifically includes the following steps:

[0104] Step S11: for the target landslide area, collect test data such as landslide volume and water depth, perform fluid-solid coupling simulation on the collected data, and calculate different models of the landslide in the water entry stage and when it is completely immersed in water based on the fluid-solid coupling mathematical model;

[0105] Step S12: according to the characteristics of landslide surge, a three-dimensional landslide surge control equation is established, and a two-dimensional unsteady separated implicit PISO algorithm is used to solve the equation;

[0106] Step S13: according to the scale of the landslide, water entry velocity, water depth, river width, etc., the initial conditions and boundary conditions of the fluid-solid coupling mathematical model are set, and the fluid-solid coupling mathematical model is verified and calibrated through existing test results.

[0107] In this embodiment, step S11 fluid-solid coupling simulation:

[0108] Fluid dynamics equations:

[0109]

[0110] Among them, u represents the fluid velocity vector, p represents the pressure, ρ represents the fluid density, v represents the dynamic viscosity, and g represents the gravitational acceleration vector;

[0111] Solid mechanics equation (dynamic equilibrium equation):

[0112]

[0113] Where: σ represents the stress tensor, b represents the body force (such as gravity), ρ p represents the density of solid material, u p Represents the displacement of solid materials;

[0114] Step S12: Landslide surge control equation:

[0115] Surge governing equations:

[0116]

[0117] Where: η represents the water surface height

[0118] Two-dimensional unsteady separated implicit PISO algorithm:

[0119] Continuity equation for water flow:

[0120]

[0121] The momentum equation is solved in a step-by-step manner, consisting of a predictor-corrector step:

[0122] Prediction step: Calculate the intermediate speed u * ;

[0123] Correction steps: Correct the velocity field by pressure;

[0124] Step S13: Model initial and boundary conditions:

[0125] Initial conditions:

[0126] u(x,y,0)=u0(x,y),η(x,y,0)=eta0(x,y)

[0127] Where u0 and η0 represent the initial velocity and water surface height distribution;

[0128] Boundary conditions:

[0129] Inlet conditions (inflow): set flow rate u = u in ;

[0130] Outlet conditions (outflow): set free flow conditions

[0131] Preferably, in step S11 of this embodiment, data collection and fluid-solid coupling simulation are as follows: by collecting test data such as landslide volume and water depth in the target landslide area, key physical parameters are obtained to provide necessary input information for the model; a fluid-solid coupling mathematical model is constructed to simulate the complex process of landslide movement in water, including different dynamic effects of the water entry stage and the full immersion stage, taking into account the interaction between liquid and solid materials, and providing a physical basis for further analysis. Significance: The collected landslide volume and water depth data provide a reference for the construction of subsequent models, ensuring the scientificity and applicability of the model; the fluid-solid coupling simulation provides a deep understanding of the landslide entry and immersion process, helping to identify the characteristics of landslide movement under different water depths and flow conditions, thereby forming a more realistic physical model. Step S12 establishes and solves the landslide surge control equation. According to the dynamic characteristics of the landslide surge, the landslide surge control equation for three-dimensional flow is established, which can accurately describe the movement and propagation process of the landslide surge; the two-dimensional unsteady separation implicit PISO algorithm is used to solve the control equation, providing an efficient and accurate calculation method for processing complex boundaries and flows. Significance: By establishing professional control equations, the landslide phenomenon is successfully transformed into a mathematical problem, which is convenient for in-depth analysis; using numerical calculation methods, accurate numerical solutions can be obtained in a relatively short time, which is suitable for rapid simulation and prediction under different working conditions. Step S13 sets the initial and boundary conditions and verifies the model. The initial and boundary conditions of the model are set according to physical parameters such as the scale of the landslide body, water entry speed, water depth, and river width to ensure the accuracy and rationality of the simulation process; by comparing with existing test results, the simulation results are combined with the actual situation, and the model is verified and calibrated to improve the credibility of the model. Significance: Ensuring the setting of reasonable initial and boundary conditions makes the model closer to the actual situation, thereby enhancing its adaptability under various conditions; through comparison and verification, it is confirmed that the model can accurately reflect the characteristics of landslide surges and increase its reliability in scientific research and engineering applications.

[0132] In summary, the construction of the landslide surge physical model in this embodiment realizes the whole process from data collection, mathematical model establishment to model verification. It not only provides a rich physical background and data support for the model, but also improves the calculation efficiency and prediction ability of the model. Ultimately, this provides an important scientific basis for the in-depth study of landslide surges, disaster assessment, and the formulation of prevention and control measures.

[0133] Furthermore, the specific steps of the process of performing proportional scaling according to the Froude similarity criterion in step S1 include:

[0134] Step S14: Calculate the Froude number of the target landslide area and the model; introduce the characteristic flow frequency F c And the flow resistance factor D:

[0135]

[0136] The frequency characteristics of the flow and the influence of flow resistance are taken into account, making the similarity of the model more accurate;

[0137] Matching of Froude numbers of the model and the target landslide area: The Froude numbers of the test model and the target landslide area are equal, that is:

[0138]

[0139] Among them, V m and V p are the flow velocities in the model and target areas respectively; L m and L p are the characteristic lengths of the model and target regions, respectively;

[0140] Step S15: determining the set scaling ratio λ of the model and the target landslide area;

[0141] Scaling ratio determination: According to the aforementioned Froude number formula, the scaling ratio is defined as:

[0142]

[0143] Update flow rate: Update the flow rate of the model to meet the proportional scaling condition and introduce an adjustment coefficient C v Consider the difference between actual flows:

[0144]

[0145] Adjustment factor C v Adjusted based on previous trial data and similarities;

[0146] Step S16: the test flow rate, pressure, gravitational acceleration and other related physical quantities are adjusted proportionally;

[0147] The influence of the density (\rho) and dynamic viscosity (\mu) of the introduced fluid on the pressure:

[0148]

[0149] Among them C p is the pressure adjustment factor, which can be calibrated by test data;

[0150] After adjusting all relevant physical quantities, tests are conducted on the model, data are collected and recorded accordingly; the test data are scaled to the target landslide area in each test:

[0151] Prediction result = C data Actual test results

[0152] Among them Cdata is the conversion factor used to fit the model to the experimental data.

[0153] Preferably, step S14 of this embodiment calculates the Froude number of the target landslide area and the model, and by introducing the characteristic flow frequency and the flow resistance factor, the calculation of the traditional Froude number is modified to make it more adaptable and better reflect the characteristics under different flow conditions; by making the Froude number of the test model equal to that of the target landslide area, the consistency of the flow pattern is tested. The significance achieved: the similarity of the model is improved, so that it can accurately simulate the real situation under various fluid conditions; it is crucial to predict the behavior of landslide surges and helps to avoid experimental errors caused by insufficient similarity. Step S15 determines the collective scaling ratio λ of the model and the target landslide area, and by calculating the scaling ratio, the proportional relationship between the model and the target area is clarified, and the consistency of the test flow velocity and geometric features is tested; after the adjustment coefficient is introduced, the flow velocity can be adjusted in real time according to the previous test data to reflect the complexity of the actual conditions. The significance achieved: by matching the flow conditions of the test model with the conditions of the actual landslide area through the appropriate scaling ratio, the practical application value of the test data is improved, and the test can be effectively predicted and analyzed in different scenarios. Step S16: The test flow rate, pressure, gravity acceleration and other related physical quantities are adjusted in proportion. All related physical quantities (flow rate, pressure, gravity, etc.) are adjusted in the same proportion. The test conditions on the test model reflect the real situation to the maximum extent. The influence of the density and dynamic viscosity of the fluid is introduced to increase the accuracy of the description of the flow phenomenon, thereby enhancing the effectiveness of the model. The significance achieved: By accurately adjusting these physical quantities, the test model can truly reflect the physical characteristics of the actual landslide surge, which leads to more credible test results; more accurate dynamic characteristics of landslide surge can be obtained, which helps effective engineering design and safety assessment. Test data collection and result scaling: By collecting model test data and recording them accordingly, the connection between the model test results and the actual landslide area can be established; the reliability and effectiveness of the test results using the adjustment factor in practical applications. The significance achieved: The test data can be effectively converted into the prediction results for the actual landslide area, which improves the accuracy and availability of the model prediction; the guiding significance of the model research for practical engineering applications is increased, so that it can play an important role in the fields of landslide early warning and post-disaster assessment.

[0154] In summary, each step of this embodiment is to enhance the similarity, accuracy and credibility of the model, so that the experiment can obtain meaningful results in landslide surge prediction, help better understand the complexity of landslide surge, and provide reliable data support for dealing with related engineering problems.

[0155] Furthermore, if Figure 3As shown, the process of dividing the preprocessed data set into a training set and a test set in step S2 specifically includes the following steps:

[0156] Step S21: Represent the data set as a set, including multiple samples, each sample consists of a feature and a corresponding target variable (surge height); preprocess the data to generate a feature matrix and a target variable; calculate a weight for each sample, the weight reflects the importance of the sample;

[0157] Step S22: Calculate the cumulative distribution function of the samples based on the weights, use the cumulative distribution function to perform weighted random sampling, randomly select samples with a ratio of 7:3 as training sets, and use the remaining samples as test sets;

[0158] Step S23: The obtained training set and test set satisfy the required ratio in terms of sample numbers.

[0159] Preferably, in step S21 of this embodiment, data representation and preprocessing are performed to represent the data set as a set, form a feature matrix and a target variable, ensure that the data has a clear structure before analysis, and make subsequent operations more systematic; through data preprocessing, ensure that the feature matrix contains all necessary information for modeling, and the target variable clearly indicates the output that the model needs to predict; calculate weights for each sample, and this weight reflects the different importance of the sample in the entire data set, allowing the model to pay more attention to those samples that have a greater impact on the prediction results during training. Significance: A clear data structure provides a basis for subsequent data processing and modeling, ensuring the accuracy of analysis; by setting weights for samples, the model's learning ability for important samples is improved, which is particularly beneficial when the sample distribution is uneven, and can significantly improve the performance of the model. Step S22 Cumulative distribution function of samples and weighted random sampling, calculate the cumulative distribution function (CDF) of each sample based on the weight, this method provides a basis for subsequent sampling, and ensures that the importance of each sample is considered during the sampling process; using cumulative distribution for random sampling, selecting training set and test set samples under the condition of ensuring a 7:3 ratio, is more scientific than simple random sampling, and improves the representativeness after sampling. Significance: Weighted sampling takes into account the importance of samples, so that the training set and test set contain more samples that have a significant impact on the model effect, thereby improving the effectiveness of the model; by introducing weights in sample selection, it avoids the sample selection bias that may be caused by ordinary random sampling, and ensures that the model performs well in both the training and testing stages. Step S23 summarizes the sample quantity ratio to ensure that the final training set and test set precisely meet the set 7:3 ratio in terms of sample quantity, providing a good foundation for model training and evaluation. Significance: By strictly following the proportional division, the sample size of the training and test sets is balanced, which helps the stability of model training and the generalization ability of unknown data; reasonable proportional distribution helps to provide a more objective and comprehensive performance evaluation in the model evaluation stage, making subsequent model adjustments and development more scientific.

[0160] In this embodiment, the data set is represented as follows: Suppose the original data set is D, which contains N samples, each sample is a vector (d i ), (i=1,2,…,N). Assume D=d1,d2,…,d N Represents the data of all original data sets;

[0161] Before partitioning, the data set is preprocessed to obtain the feature matrix F and target variable T:

[0162] Feature Matrix Where M represents the feature dimension;

[0163] Target variable Where T[i] represents d iThe corresponding landslide surge height;

[0164] Introduce a method based on weighted random sampling to divide the data set without affecting the validity of the data; assuming that a weight parameter w is used i Indicates the reliability or importance of each sample. The sample selection is carried out according to the following steps:

[0165] Calculate weight: Calculate the weight w for each sample i , can be determined by the physical parameter influencing factors of the landslide surge model, for example, w i =f(d i ), where f is a nonlinear function determined by the degree of feature influence, that is:

[0166] w i =α·Feature1 i +β·Feature2 i +…+γ·FeatureM i

[0167] α, β, γ are feature weights;

[0168] Total weight calculation: Define the total weight W as the sum of all sample weights:

[0169]

[0170] Calculate the sampling ratio: Based on the ratio of 7:3, the number of samples required for the training set is N train =0.7×N; select N by random sampling train samples, and weighted random sampling is performed considering the influence of weights;

[0171] The steps to use the sampling method are as follows: Generate a cumulative distribution function based on the weights:

[0172]

[0173] Sampling process: for j = 1 to N train , generate a uniformly distributed random number r such that r∈[0,1]; determine the selected sample based on the cumulative distribution function P(i):

[0174] d train,j =d k where k = argmin i (|P(i)-r|)

[0175] Determine the test set: Samples that are not selected as the training set naturally become the test set:

[0176] D test =D\D train

[0177] The final generated training set D train and the test set D test The sample size satisfies |D train |≈0.7×N and |D test |≈0.3×N, and the random sampling of weights ensures that the importance of samples is reflected in the training and testing stages.

[0178] In summary, through the implementation of these three steps, this embodiment can ensure that the division of the data set is not only scientific but also effective. Each step provides a guarantee for the performance improvement and accurate prediction of the model, thereby playing an important role in the prediction of landslide surge height. Through the standardization of the sample structure, the introduction of weights, and the normalization of the proportional division, the overall process lays a solid foundation for subsequent modeling and analysis. Through the above-mentioned weighted random sampling method, not only the training set and the test set are obtained, but also the importance of the sample is fully considered, avoiding the imbalance caused by simple random division; it provides a new idea for the data division process, thereby enhancing the effect of the subsequent landslide surge height prediction model.

[0179] Further, such as Figure 4 As shown, the process of predicting the maximum height of the landslide surge in step S3 specifically includes the following steps:

[0180] Step S31: introducing a performance monitoring layer into the sparrow optimization algorithm to track the performance of the slope surge height prediction model on the validation set in real time during the optimization process; dynamically increasing the number of global searches during the search process, and entering the global reinforcement stage whenever the sparrow optimization algorithm detects a local optimal bottleneck, to increase the mutation rate and crossover rate;

[0181] Step S32: Establish a feature sharing network among individual sparrows, allowing individuals to share and receive feature information through a weighted adjacency graph; each sparrow receives excellent features found by neighboring sparrows through a graph propagation mechanism, and aggregates a feature set that is effective for swell height prediction; after completing their respective tasks, the sparrows decide whether to adopt the features through feature evaluation and voting algorithms, increase the frequency of use of the optimal features, and achieve efficient integration of information sharing in the group;

[0182] Step S33: In the feature integration stage, different sparrow individuals are allowed to introduce heterogeneous features of their own fields (e.g., soil type, meteorological factors, water level changes, etc.) to form diversified feature clusters; grouping is performed by clustering the effects of different feature combinations, and the optimal feature combination is selected for training through similarity measurement;

[0183] Step S34: During the operation of the random forest model, the decision tree monitors the performance of the split nodes through weighted hysteresis tracking, and determines in real time whether the nodes under certain conditions need to be reconstructed; each node of the decision tree has a life span, and a new tree structure is dynamically created; when constructing each tree, a feature subset is selected based on feature importance, and the important features of each tree are weighted by a voting mechanism; when analyzing features, the introduction and fusion of new features are achieved through sequential dependency selection;

[0184] Step S35: Generate new samples for the training data set in combination with the adversarial generative network, and construct different versions of the training set by combining the generated samples with the actual samples; set the parameters of the standard distribution selected in the pre-training stage of the generator; implement batch normalization and random dropout strategies in the training of the sparrow optimized random forest model;

[0185] Step S36: Obtain data including landslide volume and water depth from each experiment to form an input vector. The corresponding maximum surge height is the label. The input vector and the label are combined to form a label data set. The label data set is represented by a one-dimensional array, in which each element corresponds to the maximum surge height of each set of feature data. Use the label data set and the trained sparrow optimized random forest model to predict the maximum height of landslide surges.

[0186] Preferably, step S31 of this embodiment introduces a performance monitoring layer to track the performance of the model on the validation set in real time, allowing dynamic adjustment of the optimization strategy; dynamically increase the number of global searches, and effectively alleviate the local optimal problem. Significance: Improve the adaptive ability of the model so that it can be adjusted in time when the performance degrades to find a better solution; enhance the model's ability to track and predict performance in complex environments, especially when facing changes in landslide characteristics, it can adapt and optimize the search process more quickly. Step S32 establishes a feature sharing network, and each sparrow can efficiently communicate and integrate excellent features; through the graph propagation mechanism, individuals in the group are allowed to share successful features to improve feature utilization efficiency. Significance: Promote group intelligence, improve the overall feature detection ability and learning accuracy of the group; enhance feature diversity, discover more potential important features through collective evaluation and voting mechanisms, and improve the generalization ability of the model. Step S33 introduces heterogeneous features to form a diverse feature cluster, combining knowledge from different fields; selects the optimal feature combination through clustering and similarity metrics. Significance: Enhance the representativeness and integrity of features, fully call on effective information in various fields, and adapt to different prediction scenarios; improve the feature learning ability of the model, and ensure that the model can integrate multiple information to make more accurate predictions of surge height. Step S34 monitors the performance of split nodes in real time, performs dynamic tree reconstruction, and ensures continuous optimization of the model; sets the node life cycle to enhance the flexibility of the tree structure. Significance: Improve the adaptability of the decision tree so that it can self-adjust according to specific data changes and maintain efficient prediction capabilities; through dynamic structural changes, adapt to changes in data in practical applications, and improve the effectiveness of long-term use of the model. Combine adversarial generative networks to generate new samples and expand the diversity of training sets; implement batch normalization and random dropout during training to enhance the robustness of the model. Significance: By generating samples to expand the data set, the model can capture more potential patterns and improve generalization capabilities; through the use of batch normalization and random dropout, the risk of overfitting of the model during training is further reduced, ensuring the effectiveness of the model in a real environment. Step S35 selects feature subsets based on feature importance, and uses a voting mechanism to enhance the scientific nature of feature selection; selects new features through sequential dependencies to achieve flexible introduction and fusion of features. Significance: Enhance the model's sensitivity and responsiveness to features, ensuring that important features can be better utilized; provide a flexible feature engineering mechanism to help the model adapt to new input features more effectively, and help to accurately predict in scenarios with changing data. Step S36 forms an input vector and label data set for model training and testing; the maximum surge height is used as a label to define the prediction target. Significance: Clarify the relationship between the model's learning objectives and input features, and provide a clear data structure and direction for subsequent model training; promote the systematization of the model development stage, so that the data can fully play its role, help establish an effective prediction model, and ultimately improve the warning capability and the scientific nature of the decision-making basis.

[0187] In summary, the prediction process of this embodiment forms a coordinated, efficient, and dynamically adjusted prediction system through various steps, aiming to more accurately predict the maximum height of landslide surges and maximize the adaptability and accuracy of the model.

[0188] Furthermore, the process of realizing efficient integration of information sharing in the group in step S32 specifically includes the following steps:

[0189] Step S321: There are multiple sparrow individuals, each sparrow individual is connected with its neighbor set, an adjacency matrix is ​​defined, and the feature vector of the sparrow individual is defined. After one propagation, the feature of the individual is obtained by weighted average of the features of its neighbors;

[0190] There are N′ sparrow individuals, each sparrow individual a and its neighbor set N′ a We define the adjacency matrix in:

[0191] A ab = {1, if sparrow, b is a sparrow, a's neighbor 0, otherwise

[0192] Define the eigenvector of sparrow individual a as Where M′ is the feature dimension. After one propagation, the features of individual a can be obtained by weighted average of the features of its neighbors:

[0193] f a″ =σ(∑b∈N′ a w ab f b )

[0194] Among them, w ab is the influence weight of sparrow b on sparrow a, σ(·) is the activation function used to introduce nonlinearity;

[0195] Step S322: For the newly generated feature, each sparrow calculates its prediction ability and the prediction error of the sparrow for the new feature. All sparrows vote based on the error evaluation results to select the feature;

[0196] Among them, for the newly generated feature f a″ , each sparrow calculates its prediction ability, let ε a is the prediction error of sparrow a for the new feature, and the formula is as follows:

[0197]

[0198] Among them, K is the number of samples in the validation set, is the output of predicting sample k using the new features, y k is the actual maximum height of the swell;

[0199] All sparrows vote based on the error evaluation results to select features; after the features pass the evaluation, the number of votes for each feature is V c , then the probability P of a feature c being adopted b for:

[0200]

[0201] Step S323: Sparrow passes the adoption probability P b The features that are greater than the set threshold θ form a new feature set for subsequent training.

[0202] Preferably, the feature propagation mechanism of step S321 of this embodiment, by defining the adjacency matrix, establishes the connection relationship between individual sparrows, so that feature sharing is realized on a clear network structure; the feature vector of each individual sparrow is weighted by the features of its neighbors, allowing efficient information propagation within the group, and the aggregation characteristics enable each individual to absorb important feature information from different sources; the activation function is used to introduce nonlinearity, enhance the expressiveness of the model, and make the transformation of features more flexible. Significance: Through the feature propagation mechanism, individual sparrows can share information in the group and improve the overall intelligence level; so that the group can show more accurate aggregation ability when facing such complex problems; because the network connection takes into account the characteristics of multiple neighbors, it reduces the risk caused by the deviation of a single sparrow, and collects information of different features at the same time, promoting diversity. Step S322 feature evaluation and voting mechanism, each sparrow calculates the prediction error based on the new feature, providing a specific quantitative indicator for the effectiveness of the feature; by voting on the evaluation results of the feature, each sparrow provides a collective decision for the selection of the feature, making the screening of the feature more scientific. Significance: Error-based evaluation provides an objective reference, allowing the group to more accurately select effective features, thereby avoiding the risk of personal bias affecting decision-making; through continuous evaluation and voting, the effectiveness of features is constantly tested and adjusted, which improves the model's adaptability to useful features and helps improve the final model performance. Step S323 feature selection and update, Sparrow selects features through the set adoption probability to ensure that only features that exceed the threshold in effectiveness can be adopted for subsequent training; a new feature set is formed to facilitate adaptation to different data scenarios and trends, and to ensure feature updates and iterations of the model at different stages. Significance: By dynamically adopting effective features, the final feature set is more in line with the actual situation, improving the model's ability to cope with changing environments; the selection of effective features reduces unnecessary calculations during the training process, improves training efficiency, makes the model more efficient, and reduces the risk of overfitting.

[0203] In summary, the above steps of this embodiment constitute a collaborative and dynamic feature sharing and selection mechanism, which promotes the effectiveness of the sparrow optimization algorithm in complex scenarios. Through feature propagation, error evaluation and dynamic feature adoption, the group can efficiently integrate information and improve the model's ability to predict the maximum height of landslide surges. It has shown obvious advantages in information sharing, effective decision-making and model optimization, providing a new perspective and method for solving complex problems.

[0204] Furthermore, the process of selecting the optimal feature combination for training by similarity measurement in step S33 specifically includes the following steps:

[0205] Step S331: Generate various combinations from all available features, each feature combination represents a specific selection of a set of features, and uses a binary method to indicate whether each feature is selected; use a predefined random forest to train each feature combination, and evaluate the performance on the validation set, and assign a performance score to each feature combination based on the evaluation results;

[0206] Step S332: according to the performance scores, the feature combinations are divided into different groups, and the feature combinations with similar performance are classified into one category. By analyzing the clustering results, the similarity between the feature combinations is evaluated and the correlation between the features is measured;

[0207]

[0208] In the formula, Sim(C x ,C y ) represents the feature combination C x and C y The higher the value, the more similar the two feature combinations are; C x ·C y Represents the feature combination C x and C y The dot product of (i.e., the intersection between them) is actually the sum of the products of the corresponding eigenvalues ​​in the eigenvectors. x ||C y | respectively represent the feature combination C x and C y The number of features contained in, that is, the norm of the feature vector (the size of the vector), K is the number of samples in the validation set, and represents the total number of features, that is, the number of all possible features. xk and I yk is an indicator variable, indicating the feature combination C x and C y Whether the kth feature is included in the combination C x is included in, then I xk =1, otherwise 0. Similarly, for combination C yThe same is true; Represents combination C x and C y The number of features contained in them is calculated in this part, which is their intersection. and Calculate the combination C of the two items separately x and C y The norm of the feature;

[0209] Step S333: According to the calculated similarity, a feature combination having a similarity higher than a preset threshold is selected.

[0210] Preferably, in step S331 of this embodiment, all possible combinations are generated from all available features, and the selection of features is represented by using a binary method; so that the feature space can be systematically explored, and the interaction between different features can be considered; each feature combination is trained using a predefined random forest model and the model performance is evaluated on a validation set; the evaluation results of the model are quantified as a performance score to provide a data basis for subsequent analysis. Significance: By generating a variety of feature combinations, it can be ensured that the combination of different features is considered, which is crucial in machine learning because the interaction between features may affect the final performance of the model; by training the model for each combination and evaluating its performance, an objective basis can be provided for subsequent feature selection to ensure that the selected combination is verified. Step S332: Feature combination grouping and similarity evaluation; according to the performance score, the feature combinations are divided into different groups, and the combinations with similar performance are grouped together, which helps to identify which combinations perform similarly on certain performance indicators; the similarity between the feature combinations is calculated, and the correlation of the feature combinations is quantified using a custom similarity measurement method. The higher the similarity, the more likely the two combinations contain similar features. Significance: Cluster analysis can help identify feature combinations with similar performance, simplify the subsequent decision-making process, and may reveal potential redundant combinations; similarity assessment provides a tool to understand which feature combinations are functionally similar, which is very important for feature selection and model interpretation; it can reduce model complexity and improve efficiency. Step S333 selects the optimal feature combination, and selects those feature combinations with similarities higher than a preset threshold based on the calculated similarity. This step is the key to achieving feature simplification and optimization, making the model more efficient. Significance: Selecting feature combinations with high similarity can avoid excessive feature redundancy, thereby improving the training and reasoning efficiency of the model. At the same time, this selection ensures the generalization ability of the model, because the selected combination may perform well on their own similar feature sets; by limiting the number of feature combinations and the redundancy of features, the risk of model overfitting is reduced, thereby improving performance on unseen data.

[0211] In summary, this embodiment achieves a systematic discussion and evaluation of feature combinations, ensuring that the selected feature combinations can both improve model performance and optimize model complexity. Through this process, not only good model performance is obtained, but also the relevance of features and the comprehensibility of the model are paid attention to, supporting the effectiveness of subsequent decision-making and application.

[0212] Furthermore, the process of weighting the important features of each tree by using the voting mechanism in step S34 specifically includes the following steps:

[0213] Step S341: Calculate a performance index for each decision tree, the index is based on the performance of the tree on the validation set; assign different voting weights to each tree according to the performance index; establish a feature interaction network, model the relationship between each feature through a graph neural network, and connect the importance value of each tree to the feature as a node to other feature nodes to form a feature interaction relationship diagram;

[0214] Step S342: Perform consistency analysis on the prediction results of each tree. If the prediction of a certain tree in a specific field (such as a certain type of soil condition) is inconsistent with that of other trees, the voting influence weight of the tree is automatically reduced; each tree gives a prediction value and a corresponding confidence level when voting, and the output is a weighted sum based on the feature weight, the tree's prediction value and the corresponding confidence level;

[0215] Step S343: Group the features heterogeneously according to their properties, such as separating meteorological factors, terrain features, hydrological conditions, etc., and design an independent decision tree set for each feature group for training; when making decisions, vote by feature group, perform feature selection and evaluation within each feature group; and summarize the voting results of each feature group.

[0216] Preferably, in step S341 of this embodiment, the performance index calculation and feature interaction network establishment are performed to calculate a performance index for each tree according to its performance on the validation set, involving a comprehensive evaluation of indicators such as accuracy, recall rate, and F1 score. The performance index provides a quantitative standard for the voting weight of each tree in the decision-making process; different voting weights are assigned to different decision trees according to the calculated performance index, and trees with excellent performance obtain higher influence and weak trees obtain lower weights, so that the final decision can better reflect the strengths of the overall model; a relationship model between features is established, and the interaction and influence between each feature is captured by using a graph neural network; the feature importance value of each decision tree is used as a network node, and a feature interaction graph is formed by connecting different feature nodes, allowing the model to understand the complex relationship between features. The significance achieved: By dynamically adjusting the weight of the tree, the performance advantage of the model can be better utilized and the overall prediction performance can be improved. , ensuring the adaptability of the model to new data, and enhancing the intelligence and pertinence of the model; the feature interaction network enables the model to learn and utilize the cooperative and competitive relationships between features, and to gain insight into which features have the greatest impact on decision-making in a specific context, thereby improving the relevance and accuracy of the prediction results. Step S342: Consistency analysis and confidence output. By performing consistency analysis on the prediction results of each tree, the voting weight of trees with large performance differences under specific conditions (such as soil type) is automatically reduced, abnormal trees are clearly identified, and the impact of noise is reduced. In addition to giving the prediction value, each tree also outputs the corresponding confidence, making the final decision more transparent. When weighting the vote, the feature weight, the tree's prediction value and confidence are combined to obtain the final result through weighted summation. Significance achieved: Consistency analysis ensures that the voting of the decision tree is carried out on a more rational basis, thereby improving the stability of the prediction; the weight adjustment of the abnormal performance tree avoids the noise component in the decision; the introduction of confidence not only improves the interpretability of the prediction, but also provides users with a basis for trust in the model decision-making process. For users or domain experts, this transparency helps to make reasonable decisions based on data and facilitates the improvement of subsequent features and models. Step S343 heterogeneous feature grouping and voting mechanism, grouping features according to their classification (such as meteorological factors, terrain features, hydrological conditions, etc.), so that the features can be trained at a more detailed level. Independent decision tree sets can reflect the influence of features under specific fields or conditions; when making decisions, voting is performed by feature group. The features in each feature group are independently evaluated, and their respective voting results are synthesized according to their contributions in specific fields, and then the voting results of all groups are summarized.Significance achieved: Heterogeneous grouping ensures that the importance of features is fully taken into account, especially the influence between features under different conditions; decision trees that perform well on specific subset features can make more targeted predictions for specific situations, improving the adaptability of the model in different scenarios; through cross-group aggregate voting, the diversity between various features is fully utilized, and the potential information in the data can be captured more comprehensively. The generalization ability of the overall model is enhanced, which can better predict the performance of unseen samples, thereby improving the effect of practical applications.

[0217] In summary, the implementation of steps S341, S342 and S343 of this embodiment not only enhances different aspects of the intelligent decision-making process, but also forms a systematic and well-interpretable model integration strategy, which promotes the effective prediction of the maximum height of landslide surge.

[0218] Furthermore, the process of implementing batch normalization and random dropout strategy in step S35 specifically includes the following steps:

[0219] Step S351: Before model training, the input data is standardized; based on the structure of the deep neural network, a batch normalization layer is inserted after each hidden layer to ensure that the distribution of features can be adjusted to a more ideal state before the output of each layer is passed to the activation function;

[0220] Step S352: After forward propagation in each hidden layer, the mean and variance of the hidden layer output are calculated, and the output is standardized using statistics; the standardized output is transformed by the learned scaling parameter and offset parameter, and the global mean and variance are dynamically adjusted using the exponential moving average method;

[0221] Step S353: Set the deactivation rate. In each training iteration, randomly select several neurons and set their outputs to zero. Generate a mask matrix with the same shape as the current layer output. Control which nodes are removed based on the selected deactivation rate so that the model uses a different network structure in each training process.

[0222] Preferably, in step S351 of this embodiment, input data standardization and batch normalization layer insertion are used to standardize input features (for example, normalize to a similar numerical range) so that different features have similar scales and distributions; this will facilitate the subsequent training process, because greatly different features may lead to instability in the training process; a batch normalization layer is inserted after each hidden layer to ensure that the features can be adjusted to an ideal state, i.e., a mean of zero and a variance of one, before the output is passed to the activation function. Significance achieved: By standardizing input data and adjusting feature distribution in a timely manner after each layer output, training fluctuations caused by changes in data distribution can be effectively reduced, and the stability of model training can be improved; batch normalization can accelerate the convergence speed of the network, reduce training time, and enable the deep learning network to learn effective features faster; by ensuring that the activation value is continuously in an appropriate range, the gradient vanishing problem that may occur in the deep network during training is alleviated. Step S352: Application of standardization and learning parameters after forward propagation. During the forward propagation process, the mean and variance of the output of each hidden layer are calculated, and these statistics are used to standardize the output; through the learnable scaling parameters and offset parameters, the standardized output is transformed to a state that adapts to the learning needs of the model, and the global mean and variance are dynamically adjusted using the exponential moving average. Significance achieved: By introducing learnable parameters, the model can not only adapt to different input features, but also self-adjust its feature distribution, enhancing the flexibility and adaptability of the model structure; the standardized features are more concentrated and stable, which helps the model better capture complex patterns and improve prediction performance. Step S353: Implementation of random inactivation, setting the inactivation rate, and randomly selecting some neurons to set the output to zero in each training iteration. Generate a mask matrix to control which nodes are activated or eliminated according to the set inactivation rate. Significance achieved: By breaking the interdependence between neurons through random inactivation, the model is encouraged to learn a more robust and diverse feature combination, effectively reducing overfitting; using different network structures in each round of training, the model can explore richer feature representations during the learning process, thereby enhancing the generalization ability of the model.

[0223] In summary, the training process of the deep learning model is optimized. Through the standardization of input data, the implementation of batch normalization and the introduction of random inactivation mechanism, a more stable, flexible and robust learning environment is constructed, so that the model can more effectively adapt to complex features and make accurate judgments when predicting the maximum height of landslide surges. The performance and generalization ability of the model in various environments are improved, providing a good foundation for practical applications.

[0224] Furthermore, the process of predicting the maximum height of the landslide surge in step S36 specifically includes the following steps:

[0225] Step S361: obtaining the latest input feature data, including landslide volume, soil type, meteorological factors (such as rainfall, temperature), water level change and flow rate, etc.; integrating the collected feature data into an input vector;

[0226] Step S362: Load the trained and sparrow-optimized random forest model into the memory; input the constructed input feature vector into the random forest model, infer each decision tree, and execute the decision process of the tree according to the input feature;

[0227] Each tree will traverse downward from the root node according to the value in the feature vector, split according to the feature threshold until it reaches the leaf node; at each leaf node, there is a predicted value, that is, the expected maximum surge height;

[0228] Step S363: Collect the prediction results of all decision trees and aggregate the results into a final prediction through a weighted voting mechanism; combine all trees to obtain a prediction value to represent the expected maximum surge height under a specific input feature vector; output the maximum surge height prediction result in the format of text, chart or report.

[0229] Preferably, step S361 of this embodiment obtains input feature data and constructs an input vector. By monitoring and collecting the latest feature data (such as landslide volume, soil type, meteorological factors, water level changes and flow rate), it ensures that the model uses current and relevant input information; the collected multi-dimensional features are organized into a unified input vector, making it suitable for subsequent model predictions, and the structured method enables the model to parse and use data more easily. The significance achieved: the latest feature data ensures that the model prediction is based on the current real environment, greatly improving the accuracy and reliability of the prediction; integrating multiple features into a vector facilitates model recognition and processing, promotes the simplification of data preprocessing, and ensures that the input meets the model requirements. Step S362 loads the model and performs decision tree inference, ensuring that the sparrow-optimized random forest model is accurately loaded and ready for inference; after inputting the feature vector, each decision tree in the random forest will make a path decision based on the feature value, traverse from the root node downward, split according to the feature threshold, and finally output the prediction result at the leaf node. Significance achieved: By loading the optimized random forest model, the model can fully apply the previous training results and use the learned feature importance and decision path; the inference process of the decision tree allows the model to estimate the output based on the detailed feature splitting, so that each tree can independently evaluate and predict the target variable, enhancing the dispersion and robustness of predictions. Step S363 results aggregation and output, the prediction values ​​of all decision trees are aggregated together through a weighted voting mechanism to obtain the final overall prediction result; the advantages of each tree can be effectively superimposed, thereby improving the reliability of the final output; the prediction results are intuitively displayed in the form of text, charts or reports for application in actual decision-making. Significance achieved: By aggregating the results of multiple decision trees, the characteristics of ensemble learning significantly enhance the generalization ability of the model and the accuracy of prediction, and reduce the limitations of a single tree; the results are output in a variety of forms, so that users from different backgrounds (such as decision makers, engineers, researchers, etc.) can easily understand the results, and formulate corresponding countermeasures and decisions based on them, promoting the social application value of the results.

[0230] In summary, through the above steps, the process of predicting the maximum height of landslide surge in this embodiment is effectively systematized, making maximum use of existing knowledge and data, and focusing on the real-time and structured nature of data throughout the process. The entire process not only improves the scientificity and accuracy of the prediction, but also provides a more reliable tool for environmental monitoring, risk management and emergency response, which has far-reaching practical significance.

[0231] like Figure 5As shown, this embodiment also provides an embodiment of a landslide surge height prediction system based on a sparrow optimized random forest model. In this embodiment, the landslide surge height prediction system based on a sparrow optimized random forest model is applied to the landslide surge height prediction method based on a sparrow optimized random forest model in the above embodiment. The landslide surge height prediction system based on a sparrow optimized random forest model includes a data acquisition module 1, a data division module 2, and a landslide surge prediction module 3 that are electrically connected in sequence;

[0232] Among them, the data acquisition module 1 is used to build a corresponding landslide surge physical model for the target landslide area, set up test groups with different landslide volumes and water depths for testing, obtain the corresponding test data set, and scale it proportionally according to the Froude similarity criterion; the data division module 2 is used to perform preprocessing operations on the test data to obtain the corresponding data set, and divide the preprocessed data set into a training set and a test set in a ratio of 7:3, that is, the test set data accounts for 30% of the total data; the landslide surge prediction module 3 is used to use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set various parameter input values ​​and use the training set to train the model, and use the labeled data set and the trained sparrow optimized random forest model to predict the maximum height of the landslide surge.

[0233] Preferably, the data acquisition module of this embodiment establishes a corresponding landslide surge physical model for the target landslide area, which can accurately simulate the wave characteristics of the surge during the landslide process; sets different landslide volume, water depth and other conditions, conducts comparative tests, and obtains a rich test data set; the design of the test group ensures that a variety of possible landslide and hydrological conditions are covered, providing a basis for subsequent modeling; the test data is scaled according to the Froude similarity criterion, so that the experimental results can be derived within different scales, making it more widely applicable. The significance achieved: the real data obtained through physical experiments ensures the basis and reliability of subsequent predictions, and can effectively map the landslide surge behavior in the real world; the proportional scaling technique of the similarity criterion is applied, so that the obtained data can be applied to landslide scenes of multiple scales, which improves the versatility of the model. The data partitioning module cleans and preprocesses the obtained test data, removes outliers, fills missing values, standardizes, etc., and lays the foundation for effective data analysis and modeling; the data set is divided into a training set and a test set in a ratio of 7:3, ensuring that the model can learn the features and effectively evaluate the generalization ability of the model through the test set. Significance achieved: The reasonable division method enables the model to have learning ability, and can also test the performance of the model through an independent test set to avoid overfitting and improve the credibility of the model; through independent evaluation of the test set, the real model performance indicators can be obtained, making it more valuable for reference in practical applications. The landslide surge prediction module uses Python language combined with sklearn and mealpy libraries to build a sparrow-optimized random forest model. The model sets the input values ​​of various parameters to ensure adaptation to data characteristics and enhance the performance of the model; the trained model is used to predict the label data set, provide an estimated maximum height of the landslide surge, and make effective predictions based on the new input feature vector. Significance achieved: By utilizing machine learning algorithms, especially the integrated learning characteristics of the random forest model, accurate modeling and processing of complex problems are achieved, which can provide fast and accurate prediction results; the process of building the prediction module demonstrates the application of modern data science and artificial intelligence in complex systems, improves the automation of landslide surge prediction, and promotes the intelligence of landslide disaster management and risk assessment.

[0234] In summary, the various modules in the entire landslide surge prediction system of this embodiment work together to build an important tool that can be used for landslide surge safety assessment. The data acquisition module ensures the quality and applicability of basic data, the data partitioning module ensures the effectiveness of model training and evaluation, and the prediction module realizes efficient landslide surge height prediction. The effective operation of these modules not only improves the systematicness and accuracy of the research, but also provides a scientific basis and decision-making support for future disaster response.

[0235] like Figure 6As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 4 includes a processor 41 and a memory 42 coupled to the processor 41.

[0236] The memory 42 stores program instructions for implementing the landslide surge height prediction method based on the sparrow optimized random forest model according to any of the above embodiments.

[0237] The processor 41 is used to execute the program instructions stored in the memory 42 to predict the landslide surge height based on the sparrow optimized random forest model.

[0238] The processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having signal processing capabilities. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0239] Further, Figure 7 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 5 of the embodiment of the present application stores program instructions 51 that can implement all the above methods, wherein the program instructions 51 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0240] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0241] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0242] like Figure 8 As shown, this embodiment also provides an embodiment of a method for predicting landslide surge height based on a sparrow optimized random forest model. In this embodiment, for a target landslide area, the following steps are performed to obtain a sparrow optimized random forest model for predicting the maximum landslide surge height, and predict the maximum landslide surge height:

[0243] Step 1: Build a corresponding landslide surge physical model for the target landslide area. In this implementation example, a landslide in the reservoir area of ​​a hydropower station on the Jinsha River was selected as the research object. The landslide is 1.5 km away from the study area and about 90 km away from the hydropower station. A corresponding landslide surge physical model was built at a ratio of 1:150 and a landslide surge test was carried out. The landslide was simulated by the free sliding of a pile of stones down the slope. Eight wave height meters were arranged at different locations near the study area. The wave height acquisition system was DYS50-3000. The wave height meters were numbered 8, 9, 14, 15, 16, 17, 18, and 19. Test groups with different landslide volumes and water depths were set up for testing. The test grouping is shown in Table 1. The corresponding test data sets were obtained. There were 112 groups of test data in total. According to the Froude similarity criterion, the test data were geometrically amplified using a length scale and a velocity scale. The data after geometric amplification are shown in Table 2;

[0244] Table 1 Test conditions

[0245] Test No. <![CDATA[Volume (m 3 )]]> Water depth(m) 1 181 800 2 181 815 3 181 825 4 123 800 5 123 815 6 123 825

[0246] Table 2 Test data after proportional enlargement

[0247]

[0248] Step 2: Preprocess the test data, call the LabelEncoder() function to create a "LabelEncoder" object, use the "fit_transform" method to encode the "measurement point label" column, and use the standardization tool "scaler" to scale the features to a mean of 0 and a variance of 1; use the "maximum landslide surge height" column as the label data set, and the remaining columns of data as feature data sets, call the train_test_split() function to divide the data set into training and test sets in a ratio of 7:3, that is, the number of test sets accounts for 30% of the total data set. When dividing the data set, call the parameter shuffle to shuffle the data and randomly group them.

[0249] Step 3: Use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set the input values ​​of various parameters and use the training set to train the model.

[0250] In step 3, the sparrow optimized random forest model for landslide surge height prediction is obtained through the following steps:

[0251] Step 1: Import the sklearn and mealpy libraries, and call the def() function to define the objective function "objective_function". The input value of the objective function is "params". Construct a tuple "params" containing the number of decision trees (n_estimators) and the depth of the decision tree (max_depth), call the RandomForestRegressor() function to build a random forest model containing the number of decision trees and the depth of the decision tree, set the input value of the parameter "random_state" to 1234, and the input value of the parameter "criterion" to "absolute_error", then call the fit() function to train the model, and call the predict() function to predict the result; call the mean_squared_error() function and the sqrt() function to calculate the root mean square error (RMSE) between the predicted result and the true value, call the mean_absolute_error() function to calculate the mean absolute error (MAE), calculate the sum of the two and use it as the return value of the objective function;

[0252] Step 2: Define the problem dictionary "problem_dict", which has three entries: "bounds", "minmax", and "obj_func". "bounds" specifies the value range of the random forest model parameters, the number of decision trees (n_estimators) and the depth of decision trees (max_depth). The value range of the number of decision trees (n_estimators) is 10 to 1000, and the value range of the depth of decision trees (max_depth) is 3 to 10; "minmax" sets the optimization target of the objective function to the minimum value of the root mean square error (RMSE) and the mean absolute error (MAE); "obj_func" specifies the objective function "objective_function" as the optimization target;

[0253] Step 3: Call the SSA.DevSSA() function to build the Sparrow Optimization Algorithm (SSA) optimization model, set the parameter training rounds (epoch) to 5, the population size (pop_size) to 100, the step factor (ST) to 0.8, the exploration factor (PD) to 0.5, and the tolerance factor (SD) to 0.5, and call the solve() method to optimize the model "promblem_dict" and obtain its optimal parameter combination "best_params";

[0254] Step 4: Get the optimal number of decision trees "best_n_estimators" and the optimal decision tree depth "best_max_depth" from the optimal parameter combination "best_params", call the RandomForestRegressor() function according to the optimal parameter combination to recreate a random forest model, call the fit() function to train the model, and obtain the optimized random forest model.

[0255] Step 4: Use the test set and the trained sparrow optimized random forest model to call the predict() function to predict the maximum height of the landslide surge. The comparison between the predicted value and the true value of the model before and after optimization is as follows: Fig. 9 As shown, the random forest model learning curve is as follows Fig.10 As shown, the learning curve of the sparrow optimized random forest model is as follows Fig.11 As shown in the figure, the feature importance coefficient comparison chart is as follows Fig.12 The performance evaluation indicators of the model before and after optimization are shown in Table 3.

[0256] Table 3 SSA-RF model performance evaluation indicators

[0257] Model Type RMSE MAE <![CDATA[R 2 ]]> MAPE RF 1.55075 1.14929 0.56867 35.58368 SSA-RF 1.54120 1.10510 0.57397 31.62375

[0258] This embodiment proposes a landslide surge height prediction method based on a sparrow optimized random forest model, establishes a landslide surge physical model experiment based on the Froude similarity criterion, obtains the actual maximum landslide surge height at different points through the experiment, and establishes a sparrow optimized random forest model through a random forest algorithm and a sparrow optimization algorithm, which can accurately predict the maximum height of landslide surges at different points in the study area; the present invention introduces a sparrow optimization algorithm to optimize the random forest model, and applies it to actual engineering cases. The research results show that the sparrow optimized random forest model has better performance when processing data with a small deviation rate, and can significantly improve the accuracy of the model. At the same time, the sparrow optimized random forest model can reduce the standard deviation of the predicted value and improve the density of the predicted value. Compared with the random forest model before optimization, the performance evaluation indicators of the optimized model are better than those of the model before optimization, and it shows better adaptability in predicting the maximum height of landslide surges, and can more accurately predict the maximum height of landslide surges.

[0259] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. A landslide surge height prediction method based on sparrow optimized random forest model, characterized in that: The landslide surge height prediction method based on the sparrow optimized random forest model includes: For the target landslide area, a corresponding landslide surge physical model is built, and test groups with different landslide volumes and water depths are set up for testing to obtain the corresponding test data set, which is then scaled according to the Froude similarity criterion. The experimental data is preprocessed to obtain the corresponding data set, and the preprocessed data set is divided into a training set and a test set in a ratio of 7:3, that is, the test set data accounts for 30% of the total data; Use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set the input values ​​of various parameters and use the training set to train the sparrow optimized random forest model, and use the labeled data set and the trained sparrow optimized random forest model to predict the maximum height of the landslide surge.

2. The method for predicting landslide surge height based on the sparrow optimized random forest model according to claim 1 is characterized in that: The process of scaling according to the Froude similarity criterion includes: Calculate the Froude number of the target landslide area and the model; introduce the characteristic flow frequency F c And the flow resistance factor D: Matching of the Froude number of the model and the target landslide area: The Froude number of the test model is equal to that of the target landslide area, that is: Among them, V m and V p are the flow velocities in the model and target areas respectively; L m and L p are the characteristic lengths of the model and target regions, respectively; Determine the ensemble scaling ratio λ of the model and the target landslide area; According to the Froude number formula, the scaling factor is defined as: Update the flow rate of the model to meet the proportional scaling condition and introduce an adjustment coefficient C v Consider the difference between actual flows: Adjustment factor C v Adjusted based on previous trial data and similarities; The test flow rate, pressure, gravitational acceleration and other related physical quantities are adjusted proportionally; The influence of the density λ and dynamic viscosity of the introduced fluid on the pressure: Among them C p is the pressure adjustment factor, which is calibrated by test data; After adjusting all relevant physical quantities, tests are conducted on the model, data are collected and recorded accordingly; the test data are scaled to the target landslide area in each test: Prediction result = C data Actual test results Among them C data is the conversion factor used to fit the model to the experimental data.

3. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 1 is characterized in that: The preprocessed dataset is divided into training set and test set, including: Represent the data set as a set, containing multiple samples, each of which consists of features and corresponding target variables; preprocess the data to generate feature matrices and target variables; calculate a weight for each sample, which reflects the importance of the sample; The cumulative distribution function of the samples is calculated based on the weights, and the cumulative distribution function is used for weighted random sampling. Samples are randomly selected as training sets in a ratio of 7:3, and the remaining samples are used as test sets. The obtained training set and test set meet the required ratio in terms of sample number.

4. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 1 is characterized in that: The process of predicting the maximum height of landslide surge includes: A performance monitoring layer is introduced into the sparrow optimization algorithm to track the performance of the slope surge height prediction model on the validation set in real time during the optimization process; during the search process, the number of global searches is dynamically increased. Whenever the sparrow optimization algorithm detects a local optimal bottleneck, it enters the global reinforcement stage to increase the mutation rate and crossover rate; A feature sharing network is established between individual sparrows, allowing individuals to share and receive feature information through a weighted adjacency graph. Each sparrow receives the excellent features found by its neighbor sparrows through a graph propagation mechanism, and aggregates a set of features that are effective for predicting surge height. After completing their respective tasks, sparrows use feature evaluation and voting algorithms to decide whether to adopt a feature, increase the frequency of use of the optimal feature, and achieve efficient integration of information sharing in the group. In the feature integration stage, different sparrow individuals are allowed to introduce heterogeneous features in their own fields to form diversified feature clusters; they are grouped by clustering the effects of different feature combinations, and the optimal feature combination is selected for training through similarity metrics; During the operation of the random forest model, the decision tree monitors the performance of the split nodes through weighted hysteresis tracking, and determines in real time whether the nodes under certain conditions need to be reconstructed; each node of the decision tree has a life span, and a new tree structure is created dynamically; when constructing each tree, a feature subset is selected based on feature importance, and a voting mechanism is used to comprehensively weight the important features of each tree; when analyzing features, the introduction and fusion of new features are achieved through sequential dependency selection; Generate new samples for the training dataset by combining the generative adversarial network, and construct different versions of the training set by combining the generated samples with the actual samples; set the parameters of the standard distribution selected in the pre-training stage of the generator; implement batch normalization and random dropout strategies in the training of the sparrow optimized random forest model; The landslide volume and water depth data are obtained for each experiment to form an input vector. The corresponding maximum surge height is the label. The input vector and the label are combined to form a label data set. The label data set is represented by a one-dimensional array, in which each element corresponds to the maximum surge height of each set of feature data. The label data set and the trained sparrow optimized random forest model are used to predict the maximum height of landslide surges.

5. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 4 is characterized in that: Achieving efficient and integrated process of information sharing in a group, including: Suppose there are multiple sparrow individuals, each sparrow individual is connected to its neighbor set, an adjacency matrix is ​​defined, and the feature vector of the sparrow individual is defined at the same time. After one propagation, the individual's features are obtained by weighted average of the features of its neighbors; There are N′ sparrow individuals, each sparrow individual a and its neighbor set N a ′Connect, define the adjacency matrix in: A ab = {1, if sparrow b is a sparrow, a's neighbor 0, otherwise Define the eigenvector of sparrow individual a as Where M′ is the feature dimension. After one propagation, the feature of individual a is obtained by weighted average of the features of its neighbors: Among them, w ab is the influence weight of sparrow b on sparrow a, σ(·) is the activation function used to introduce nonlinearity; For the newly generated features, each sparrow calculates its prediction ability and the prediction error of the sparrow for the new features. All sparrows vote and select features based on the error evaluation results. Among them, for the newly generated feature f a″ , each sparrow calculates its prediction ability, let ε a is the prediction error of sparrow a for the new feature, and the formula is as follows: Where K is the number of samples in the validation set, is the output of predicting sample k using the new features, y k is the actual maximum height of the swell; All sparrows vote based on the error evaluation results to select features; after the features pass the evaluation, the number of votes for each feature is V c , then the probability P of a feature c being adopted b for: The sparrow adopts the probability P b The features that are greater than the set threshold θ form a new feature set for subsequent training.

6. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 4 is characterized in that: The process of selecting the best feature combination for training through similarity measurement includes: Generate various combinations from all available features, each feature combination represents a specific selection of a set of features, using a binary method to indicate whether each feature is selected; use a predefined random forest to train each feature combination and evaluate the performance on the validation set, assigning a performance score to each feature combination based on the evaluation results; According to the performance scores, the feature combinations are divided into different groups, and the feature combinations with similar performance are classified into one category. By analyzing the clustering results, the similarity between feature combinations is evaluated and the correlation between features is measured; Based on the calculated similarity, a feature combination with a similarity higher than a preset threshold is selected.

7. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 4 is characterized in that: The process of using the voting mechanism to comprehensively consider the important features of each tree for weighting includes: Calculate a performance index for each decision tree based on the performance of the tree on the validation set; assign different voting weights to each tree based on the performance index; establish a feature interaction network, model the relationship between each feature through a graph neural network, and connect the importance value of each tree to other feature nodes as a node to form a feature interaction relationship diagram; The prediction results of each tree are analyzed for consistency. If the prediction of a tree in a specific field is inconsistent with other trees, the voting influence weight of the tree is automatically reduced. Each tree gives a prediction value and corresponding confidence when voting. The output is a weighted sum based on the feature weight, the tree's prediction value and the corresponding confidence. The features are grouped heterogeneously according to their properties, and meteorological factors, terrain features, and hydrological conditions are separated. An independent set of decision trees is designed for each feature group and trained. When making decisions, voting is performed by feature group, and feature selection and evaluation are performed within each feature group. The voting results of each feature group are summarized.

8. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 4 is characterized in that: The process of implementing batch normalization and random dropout strategies includes: Before model training, the input data is standardized; based on the structure of the deep neural network, a batch normalization layer is inserted after each hidden layer to ensure that the distribution of features can be adjusted to a more ideal state before the output of each layer is passed to the activation function; After each hidden layer is forward propagated, the mean and variance of the hidden layer output are calculated, and the output is standardized using statistics; the standardized output is transformed through the learned scaling and offset parameters, and the global mean and variance are dynamically adjusted using the exponential moving average method; The inactivation rate is set. In each training iteration, several neurons are randomly selected and their outputs are set to zero. A mask matrix with the same shape as the output of the current layer is generated. The selected inactivation rate controls which nodes are removed so that the model uses a different network structure during each training process.

9. The method for predicting landslide surge height based on sparrow optimized random forest model according to claim 4 is characterized in that: The process of predicting the maximum height of landslide surge includes: Obtain the latest input feature data, including landslide volume, soil type, meteorological factors, water level changes and flow velocity; integrate the collected feature data into an input vector; Load the trained and sparrow-optimized random forest model into memory; input the constructed input feature vector into the random forest model, perform inference on each decision tree, and execute the decision process of the tree based on the input features; Each tree will traverse downward from the root node according to the value in the feature vector, split according to the feature threshold until it reaches the leaf node; at each leaf node, there is a predicted value, that is, the expected maximum surge height; Collect the prediction results of all decision trees and aggregate them into a final prediction through a weighted voting mechanism; combine all trees to get a prediction value to represent the expected maximum surge height under a specific input feature vector; output the maximum surge height prediction results in the format of text, charts or reports.

10. A landslide surge height prediction system based on sparrow optimized random forest model, which is applied to the landslide surge height prediction method based on sparrow optimized random forest model as claimed in any one of claims 1 to 9, characterized in that: The landslide surge height prediction system based on sparrow optimized random forest model includes: The data acquisition module is used to build a corresponding landslide surge physical model for the target landslide area, set up test groups with different landslide volumes and water depths for testing, obtain the corresponding test data set, and scale it according to the Froude similarity criterion; The data partitioning module is used to perform preprocessing operations on the test data to obtain the corresponding data set, and divide the preprocessed data set into a training set and a test set according to a ratio of 7:3, that is, the test set data accounts for 30% of the total data; The landslide surge prediction module is used to use Python language to build a sparrow optimized random forest model based on sklearn and mealpy libraries, set the input values ​​of various parameters and use the training set to train the model, and use the labeled data set and the trained sparrow optimized random forest model to predict the maximum height of the landslide surge.

Images