Method and system for identifying sediment flux evolution attribution in cold and cold mountainous area

Abstract

The invention provides an alpine mountain area sediment flux evolution attribution identification method and system, and belongs to the technical field of sediment flux evolution attribution identification. Comprising the following steps: carrying out multi-angle mutation point detection according to a driving factor data set by adopting a joint mutation identification method; detecting and identifying a level difference change under distribution mutation by adopting Pettitt so as to determine a distribution mutation year; a Mann-Kendall trend test method is adopted to identify slope change under trend mutation so as to determine the year of the trend mutation; mutation points are detected according to the difference relation between the distribution mutation years and the trend mutation years, and evolution stages are divided; and performing attribution analysis on all driving factors based on a three-stage progressive attribution analysis framework. According to the method, the alpine mountain area sediment attribution recognition framework is established by integrating multivariate statistical learning and path modeling technologies, the stability and accuracy of attribution results are improved, and decision support can be provided for water and soil conservation and regional ecological restoration.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of sediment evolution attribution identification, and particularly relates to a high-cold mountainous area sediment flux evolution attribution identification method and system. BACKGROUND

[0002] The statements in this section merely provide background information related to the application and do not necessarily constitute prior art.

[0003] Sediment flux evolution attribution identification is a core technology for soil and water conservation and ecological restoration, especially in high-cold mountainous areas, where the special climate and topographic conditions (such as freeze-thaw cycle, seasonal snowmelt, and vegetation vulnerability) lead to highly complex sediment transport mechanisms.

[0004] However, the existing sediment flux evolution attribution identification methods for high-cold mountainous areas have some difficult-to-solve technical problems: (1) Existing methods often consider the influence of each driving factor separately and fail to effectively identify the complex interactive effects between driving factors, resulting in incomplete analysis of the influence mechanism of sediment evolution. Sediment evolution is a complex process resulting from the combined action of multiple human factors (such as water conservancy projects, land use, etc.) and nature (such as climate, vegetation, topography, etc.). A single analysis method cannot accurately reveal the interaction and mutual influence between these driving factors.

[0005] (2) In the existing technology, the mutation point identification and evolution stage division of sediment concentration (SSC) data lack accuracy, resulting in unreliable analysis results. For example, existing technology lacks efficient and accurate statistical methods when dealing with the mutation phenomenon in complex sediment evolution processes, and cannot accurately identify mutation points or divide the evolution process into different stages.

[0006] (3) Existing sediment evolution analysis methods often ignore the nonlinear interaction between multiple driving factors, resulting in incomplete analysis of the complex causal relationships in the sediment evolution process, affecting the accuracy of the attribution results. Due to the strong interaction between multiple driving factors in the sediment evolution process, a single model cannot accurately capture the complex relationships between these driving factors, often leading to unstable and erroneous attribution results.

[0007] (4) Existing technology often lacks sufficient verification of the attribution results in the sediment evolution process, especially in complex ecological hydrological systems such as high-cold mountainous areas, where the stability and interpretability of the attribution results are poor. Existing methods may not provide results with strong physical consistency when dealing with multi-factor influence attribution analysis, affecting their application value. SUMMARY

[0008] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a high-cold mountainous area sediment flux evolution attribution identification method and system, which can accurately identify the key driving factors and their interaction relationship in the sediment evolution process by integrating statistical learning and multi-model analysis technology.

[0009] To achieve the above object, one or more embodiments of the present application provide the following technical solutions: The present application provides a high-cold mountainous area sediment flux evolution attribution identification method in the first aspect.

[0010] A high-cold mountainous area sediment flux evolution attribution identification method, comprising: Based on the sediment transport mechanism in the high-cold mountainous area, the main driving factors are identified; The basic data corresponding to the main driving factors are preprocessed to construct a driving factor data set; A joint mutation identification method is used to detect the mutation points from multiple angles according to the constructed driving factor data set: Pettitt test is used to identify the difference change under distribution mutation to determine the distribution mutation year; the Mann-Kendall trend test method is used to identify the slope change under trend mutation to determine the trend mutation year; the difference relationship between the obtained distribution mutation year and the trend mutation year is detected to divide the evolution stage; Based on the three-stage progressive attribution analysis framework, all driving factors are subjected to attribution analysis to quantify the attribution contribution of each driving factor in different evolution stages and different spaces.

[0011] Further, according to the difference relationship between the distribution mutation year and the trend mutation year, the mutation points are detected and the evolution stage is divided, which includes: if the distribution mutation year and the trend mutation year are consistent or differ by 3 years or less, the determined distribution mutation year and trend mutation year are defined as stable mutation points; if the difference between the distribution mutation year and the trend mutation year is greater than 3 years, the test result of the Pettitt test is used.

[0012] Further, according to the difference relationship between the distribution mutation year and the trend mutation year, the mutation points are detected and the evolution stage is divided, which further includes: through Mann-Kendall trend test, if multiple trend change sections are tested, the main mutation section and the secondary stage of the evolution stage are divided according to the significance statistic of the Pettitt test.

[0013] Further, the attribution analysis framework includes a random forest model, a partial least squares structural equation model and a redundancy analysis model; wherein the random forest model is used for variable screening, the partial least squares structural equation model is used for path identification, and the redundancy analysis model is used for spatial attribution.

[0014] Further, variable screening is performed based on the random forest model, including: calculating the relative importance of each driving factor on the change of sediment concentration based on the random forest model, and screening core driving factors to form a variable subset.

[0015] Further, path identification is performed based on the partial least squares structural equation model, including: taking the variable subset output by the random forest model as input for analysis to identify direct causal paths and indirect causal paths.

[0016] Further, spatial attribution is performed based on the redundancy analysis model, including: explaining the spatial distribution of sediment changes based on the redundancy analysis model, extracting the explanation degree of each driving factor on the sediment variation in different regions and forming a unified weighted expression to quantify the attribution contribution of each driving factor in different spaces.

[0017] The second aspect of the present application provides a high-cold mountainous area sediment flux evolution attribution identification system.

[0018] A high-cold mountainous area sediment flux evolution attribution identification system comprises: A main driving factor identification module is configured to identify main driving factors based on the sediment transport mechanism in the high-cold mountainous area. A preprocessing module is configured to preprocess the basic data corresponding to the main driving factors and construct a driving factor dataset. A mutation point detection module is configured to perform multi-angle mutation point detection according to the constructed driving factor dataset using a joint mutation identification method: using Pettitt test to identify the difference change under distribution mutation to determine the distribution mutation year; using Mann-Kendall trend test method to identify the slope change under trend mutation to determine the trend mutation year; detecting the mutation point according to the difference relationship between the obtained distribution mutation year and the trend mutation year, and dividing the evolution stage. An attribution identification module is configured to perform attribution analysis on all driving factors based on a three-stage progressive attribution analysis framework to quantify the attribution contribution of each driving factor in different evolution stages and different spaces. The third aspect of the present application provides a computer readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps of the high-cold mountainous area sediment flux evolution attribution identification method according to the first aspect of the present application.

[0019] The fourth aspect of the present application provides an electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the high-cold mountainous area sediment flux evolution attribution identification method according to the first aspect of the present application when executing the program.

[0020] The one or more technical solutions have the following beneficial effects: (1) The present application constructs a three-stage progressive attribution analysis framework by fusing random forest, partial least squares structural equation model (PLS-SEM) and redundancy analysis (RDA) three methods, to comprehensively analyze the interaction between each driving factor, which can accurately identify the different influence degrees of each driving factor on sediment evolution, and make up for the deficiencies of the prior art in analyzing the interaction of driving factors.

[0021] (2) The present application uses a joint mutation identification method for multi-angle mutation point detection, that is, Pettitt test is used to identify the difference change under distribution mutation to determine the distribution mutation year, Mann-Kendall trend test method is used to identify the slope change under trend mutation to determine the trend mutation year, and the difference relationship between the distribution mutation year and the trend mutation year is used to detect the mutation point and divide the evolution stage. Therefore, compared with the prior art, the present application can effectively divide the evolution stage and provide more reliable basic data for subsequent attribution analysis.

[0022] (3) The present application provides a comprehensive analysis framework by combining random forest, partial least squares and redundancy analysis three different analysis methods, which can not only effectively evaluate the independent influence of each driving factor, but also reveal the mutual relationship and interaction effect between each driving factor, and improve the accuracy and stability of attribution analysis.

[0023] (4) The present application solves the defects of the prior art in multi-driving factor synergistic effect analysis, mutation point identification, attribution result stability, etc. by proposing a multi-model fusion analysis framework (attribution analysis framework), effectively improves the attribution identification accuracy, stability and physical consistency of the sediment evolution process in the alpine mountainous area, and provides a scientific basis for soil and water conservation and regional ecological restoration.

[0024] The advantages of the additional aspects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be known by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0025] The drawings accompanying the specification of the present application form a part thereof, serve to provide further understanding of the present application, and together with the description of the exemplary embodiments of the present application and their description serve to explain the present application, and do not constitute an improper limitation of the present application.

[0026] Figure 1 A flowchart of a high-cold mountainous area sediment flux evolution attribution identification method in the embodiment one of the present application. DETAILED DESCRIPTION

[0027] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0028] It should be noted that the terms used herein are only intended to describe specific embodiments and are not intended to limit the exemplary embodiments according to the present application.

[0029] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0030] The present application provides a high-cold mountainous area sediment flux evolution attribution recognition method, and the general idea of the method can be summarized as follows: S1, analyzing the sediment transport mechanism in the high-cold mountainous area, identifying the main driving factors, generally including precipitation, snowmelt, temperature, vegetation index, land use, etc.; S2, collecting and preprocessing the basic data of the driving factors, and constructing a complete data set; S3, identifying the mutation point in the sediment transport process, and dividing the evolution stage; S4, constructing an attribution framework integrating random forest, PLS-SEM and redundancy analysis, and evaluating the importance, path dependence relationship and spatial pattern of the driving factors; S5, integrating the results of the three methods, and quantitatively identifying the influence degree and action path of the driving factors on the sediment evolution.

[0031] Embodiment one The embodiment discloses a high-cold mountainous area sediment flux evolution attribution recognition method.

[0032] As shown in Figure 1 A high-cold mountainous area sediment flux evolution attribution recognition method comprises the following steps: Step S1, identifying the main driving factors based on the sediment transport mechanism in the high-cold mountainous area; Step S2, obtaining the basic data corresponding to the main driving factors for preprocessing, and constructing a driving factor data set; Step S3, using a joint mutation recognition method to detect the mutation point from multiple angles according to the constructed driving factor data set: using Pettitt test to identify the difference change under distribution mutation to determine the distribution mutation year; using Mann-Kendall trend test method to identify the slope change under trend mutation to determine the trend mutation year; detecting the mutation point according to the difference relationship between the obtained distribution mutation year and trend mutation year, and dividing the evolution stage; Step S4, performing attribution analysis on all driving factors based on a three-stage progressive attribution analysis framework to quantify the attribution contribution of each driving factor in different evolution stages and different spaces.

[0033] Based on the above process, the application establishes a high-cold mountainous area sediment attribution recognition framework by integrating multivariate statistical learning and path modeling technology, improves the stability and accuracy of the attribution results, and can provide decision support for soil and water conservation and regional ecological restoration. In order to facilitate the understanding of the technical scheme of the application, the specific implementation method in the technical scheme of the application will be further explained and described below.

[0034] In step S1, based on the sediment transport mechanism in high-cold mountainous area, the main driving factors are identified.

[0035] Firstly, the sediment transport mechanism in high-cold plateau area is analyzed in depth, and the main driving factors that may affect sediment evolution are identified, including natural factors and human factors, such as precipitation, snowmelt, air temperature, vegetation index (NDVI), land use change and water conservancy engineering disturbance. It should be noted that the identification of main driving factors based on the sediment transport mechanism in high-cold mountainous area is not the main technical point of the application, so in this embodiment, the identification results based on the sediment transport mechanism in high-cold mountainous area in the prior art are integrated to determine the main driving factors.

[0036] In step S2, the basic data corresponding to the main driving factors are preprocessed to construct the driving factor data set.

[0037] According to the determined main driving factors, the corresponding basic data such as meteorological, surface condition, terrain, hydrological data are collected. The data are preprocessed, and the preprocessing operations include missing value filling, standardization, normalization, etc., to ensure data quality and construct complete driving factor data set.

[0038] In step S3, a joint mutation identification method is used to detect the multi-angle mutation points according to the established driving factor data set.

[0039] Pettitt test and Mann-Kendall trend test (M-K) are used to detect the multi-angle mutation points of sediment concentration time series (SSC), which can be realized by the following method: 1) Pettitt test (suitable for detecting mean value mutation or "structural jump" phenomenon in time series) is used to identify the difference of level under distribution mutation, to determine the distribution mutation year, that is: ; In the formula, represents the difference between the rank sum of the observation value of the previous year and the observation value of the following year, represents the mutation significance statistic. When P<0.05, it is considered that a significant mutation occurs; wherein, P value is obtained by table lookup or calculation, which is the probability of observing the current P < 0.05, indicating that the mutation is significant, and that the time series has a non-random structural jump.

[0040] On this basis, the distribution mutation year can be identified, that is: ; wherein, represents the distribution mutation year, represents the time point that makes the maximum .

[0041] 2) Mann-Kendall trend test (suitable for identifying long-term trend mutations, such as from increasing to decreasing) is used to identify the slope change under the trend mutation to determine the trend mutation year, that is: ; wherein, represents the observation value of the time series in the year (e.g. sediment concentration SSC of a certain station); represents the observation value of the time series in the year ; ; is a trend statistic, which is used to represent the monotonic change direction of the entire time series. If , it means that the sequence as a whole shows an upward trend; if , it means that the sequence as a whole shows a downward trend. represents the sign function, which is used to determine the trend direction, and is defined as: .

[0042] Through Mann-Kendall trend test, UF (forward sequence) and UB (reverse sequence) are generated, and the intersection point of UF and UB curves is the trend mutation year, which can be used to assist in determining the mutation "direction" (such as increasing decreasing or decreasing increasing).

[0043] 3) According to the difference relationship between the distribution mutation year and the trend mutation year, the mutation point is detected, and the evolution stage is divided.

[0044] If the mutation years identified by Pettitt test and M-K test are consistent or similar (the difference is 3 years), the year is defined as the "stable mutation point"; if the difference between the distribution mutation year and the trend mutation year is more than 3 years, the result of Pettitt test is preferred (suitable for jump mutation), and M-K is used for trend direction auxiliary explanation.

[0045] In addition, if MK detects multiple trend change segments, it will be combined with Pettitt's significance level (i.e., significance statistic) to assist in dividing the main mutation segment and secondary stage. Specifically: First, obtain the set of trend mutation points detected by Mann-Kendall ;in, Indicates the first trend mutation point in the set Trend mutation points. Then, for each trend mutation point, calculate its relationship with the Pettitt mutation point. The difference, that is On this basis, if a trend mutation point satisfy ,and Significant (i.e. ), then this point is the main mutation point; other mutation points are used as secondary stage division nodes, and the stage sections are divided in chronological order (such as P1, P2, P3).

[0046] Furthermore, the stage division rule of the present invention is: with the main mutation point as the boundary, the sediment evolution process is divided into different time periods (such as P1: 1981–2000, P2: 2001–2020); the sediment trend remains relatively consistent within each stage.

[0047] The present invention uses methods such as the Pettitt test and the Mann-Kendall test to detect mutation points in the sediment concentration (SSC) time series, identify key change nodes in the sediment evolution process, and divide the evolution into different stages, which can provide an accurate time frame for subsequent attribution analysis.

[0048] In step S4, attribution analysis is performed on all driving factors based on the three-stage progressive attribution analysis framework to quantify the attribution contribution of each driving factor at different evolution stages and in different spaces.

[0049] To systematically identify the driving mechanisms of sediment flux changes in alpine mountainous areas, this study developed a three-stage progressive fusion modeling approach, sequentially integrating random forest (RF), partial least squares structural equation modeling (PLS-SEM), and redundancy analysis (RDA). These three methods are used for variable screening, path identification, and spatial attribution, respectively, ultimately achieving a unified expression output. This can be achieved through the following methods: 1) Variable screening based on random forest model.

[0050] The random forest model was used to train all driving factors and calculate their relative importance to the change of sediment concentration (SSC), namely: ; in, indicates the first driving factor, such as air temperature (T), precipitation (P), NDVI, snowmelt, land use index, etc. indicates the contribution score of the variable to the target variable. Thus, the top variables with the highest importance can be output to form a variable subset for the next step of path modeling analysis. In the present application, a random forest (RF) model is used to train all the candidate driving factors to identify the most significant factors affecting the change in sediment concentration (SSC). This algorithm belongs to a non-parametric supervised classification / regression algorithm in ensemble learning, which has the advantages of strong modeling ability for non-linear relationships and stable feature importance identification.

[0051] 2) Identify direct and indirect causal paths based on partial least squares structural equation model, i.e. ; wherein, indicates the intermediate variable (such as MDVI, snowmelt, etc.), indicates the direct path coefficient of SSC, indicates the path coefficient of the intermediate path to SSC; indicates the error term. and are obtained automatically by fitting the PLS-SEM model, and the modeling process is as follows: First, construct a structural path model diagram (T, P NDVI SSC), and import tools such as SmartPLS for modeling; then, output the regression coefficient and statistical significance (such as P value) of each path. On this basis, the total effect is ( is the intermediate path coefficient).

[0052] 3) Spatial attribution based on redundancy analysis model.

[0053] Input the key variables confirmed by PLS-SEM into the redundancy analysis model to explain the spatial distribution of sediment change, extract the explanation degree (contribution rate) of each factor to the sediment variation in different regions, and form a unified weighted expression.

[0054] The redundancy analysis (RDA) model can be expressed as: ; wherein, indicates the sediment flux response variable of each region (such as the SSC of multiple basins, sub-regions), is a real number field, indicating that the variable takes continuous real number type data; is the number of response variables, usually corresponding to multiple sub-basins or sections in space (such as SSC_1, SSC_2,..., SSC_p); represents the key driving factor matrix confirmed by RF and PLS; represents the contribution coefficient of the variable to each response item (similar to the multiple regression coefficient); represents the residual matrix.

[0055] On this basis, the multi-factor fusion expression (final output) can be expressed as: ; ; Among them, represents the final attribution contribution degree, 、 and represent the weighted coefficients (default equal weight or set through cross-validation); represents the load value of the variable on the principal axis; represents the fitting sediment concentration or flux value calculated by the model, and the unit is consistent with the original SSC; represents the path coefficient of the variable in PLS-SEM. In redundancy analysis (RDA), the principal axis load value represents the explanation or projection weight of each variable in the principal component direction. is the load value of the variable on the first principal axis. Specifically, the larger the value (positive or negative), the stronger the explanation of the spatial variation of the sediment. The value is usually derived from the ordering analysis output (such as biplot graph) of RDA. In the present application, the is used as a weighted factor and included in the multi-factor fusion expression to generate the final attribution contribution weight.

[0056] The three-step fusion framework integrates variable screening (RF), causal identification (PLS-SEM) and spatial explanation (RDA) in order, outputs an interpretable expression similar to multiple linear regression, and quantifies the attribution contribution of each driving factor at different stages and in different spatial units, greatly improving the interpretability, stability and practicality of the model.

[0057] Through the above technical solutions, the present application first realizes multi-dimensional and all-round attribution analysis of sediment evolution in alpine mountainous areas, greatly improves the stability and accuracy of the analysis results, and provides a scientific basis for the formulation of water and soil conservation, sediment regulation and regional ecological restoration strategies.

[0058] Example Two The embodiment discloses a high-cold mountainous area sediment flux evolution attribution identification system.

[0059] The high-cold mountainous area sediment flux evolution attribution identification system comprises: A main driving factor identification module is configured to identify main driving factors based on a high-cold mountainous area sediment transport mechanism. A preprocessing module is configured to preprocess basic data corresponding to the main driving factors and construct a driving factor data set. A mutation point detection module is configured to perform multi-angle mutation point detection according to the constructed driving factor data set by using a joint mutation identification method; perform differential change under distribution mutation by using a Pettitt test to determine a distribution mutation year; perform slope change under trend mutation by using a Mann-Kendall trend test method to determine a trend mutation year; detect a mutation point according to a difference relationship between the obtained distribution mutation year and the trend mutation year, and divide evolution stages. An attribution identification module is configured to perform attribution analysis on all driving factors based on a three-stage progressive attribution analysis framework to quantize attribution contributions of each driving factor in different evolution stages and different spaces. Embodiment three The purpose of the embodiment is to provide a computer-readable storage medium.

[0060] The computer-readable storage medium stores a computer program, and the program is executed by a processor to implement the steps in the high-cold mountainous area sediment flux evolution attribution identification method according to the embodiment one of the present disclosure.

[0061] Embodiment four The purpose of the embodiment is to provide an electronic device.

[0062] The electronic device comprises a memory, a processor, and a program stored in the memory and executable on the processor, and the processor executes the program to implement the steps in the high-cold mountainous area sediment flux evolution attribution identification method according to the embodiment one of the present disclosure.

[0063] The steps and methods involved in the devices of the above embodiments two, three and four correspond to the embodiment one, and the specific embodiments can be referred to the related description part of the embodiment one. The term "computer-readable storage medium" should be understood as including a single medium or multiple media of one or more instruction sets; it should also be understood as including any medium capable of storing, encoding or carrying instruction sets for execution by a processor and causing the processor to perform any method in the present disclosure.

[0064] Those skilled in the art should understand that the modules or steps of the present application described above can be realized by general computer devices, or alternatively, they can be realized by program codes executable by the computer devices, so that they can be stored in the storage devices and executed by the computer devices, or they can be respectively manufactured into individual integrated circuit modules, or a plurality of modules or steps among them can be manufactured into a single integrated circuit module. The present application is not limited to any specific combination of hardware and software.

[0065] The specific embodiments of the present application described above with reference to the accompanying drawings are not intended to limit the protection scope of the present application, and those skilled in the art should understand that various modifications or changes made on the basis of the technical solutions of the present application without creative labor are still within the protection scope of the present application.

Claims

1. A method for identifying the causes of sediment flux evolution in alpine mountainous areas, characterized by: include: Identify the main driving factors based on the sediment transport mechanism in alpine mountainous areas; Obtain the basic data corresponding to the main driving factors for preprocessing and construct the driving factor dataset; A joint mutation identification method was used to detect mutation points from multiple angles based on the established driver factor dataset. The Pettitt test was used to identify the differential change under distribution mutation to determine the distribution mutation year. The Mann-Kendall trend test was used to identify the slope change under trend mutation to determine the trend mutation year. Mutation points were detected based on the difference between the distribution mutation year and the trend mutation year, and the evolution stages were divided. Attribution analysis is performed on all driving factors based on a three-stage progressive attribution analysis framework to quantify the attribution contribution of each driving factor at different evolution stages and in different spaces.

2. The method for attributing and identifying sediment flux evolution in alpine mountainous areas according to claim 1, characterized in that: Mutation points were detected based on the difference between the distribution mutation year and the trend mutation year, and the evolution stages were divided, including: if the distribution mutation year was the same as the trend mutation year or the difference was within 3 years, the determined distribution mutation year and trend mutation year were defined as stable mutation points; if the difference between the distribution mutation year and the trend mutation year was greater than 3 years, the test results of the Pettitt test were used.

3. The method for attributing and identifying sediment flux evolution in alpine mountainous areas according to claim 2, characterized in that: The mutation points are detected and the evolution stages are divided based on the difference between the distribution mutation year and the trend mutation year. It also includes: using the Mann-Kendall trend test, if multiple trend change segments are detected, the evolution stage is divided into primary mutation segments and secondary stages based on the significance statistics of the Pettitt test.

4. The method for attributing and identifying sediment flux evolution in alpine mountainous areas according to claim 1, characterized in that: The attribution analysis framework includes a random forest model, a partial least squares structural equation model and a redundancy analysis model; wherein the random forest model is used for variable screening, the partial least squares structural equation model is used for path identification, and the redundancy analysis model is used for spatial attribution.

5. The method for attributing and identifying sediment flux evolution in alpine mountainous areas according to claim 4, characterized in that: Variable screening was performed based on the random forest model, including: calculating the relative importance of each driving factor to the change in sediment concentration based on the random forest model, and screening out the core driving factors to form a variable subset.

6. The method for attributing and identifying sediment flux evolution in alpine mountainous areas according to claim 4, characterized in that: Path identification is performed based on the partial least squares structural equation model, including: using the subset of variables output by the random forest model as input for analysis to identify direct causal paths and indirect causal paths.

7. The method for attributing and identifying sediment flux evolution in alpine mountainous areas according to claim 4, characterized in that: Spatial attribution is performed based on the redundancy analysis model, including: explaining the spatial distribution of sediment changes based on the redundancy analysis model, extracting the explanatory power of each driving factor on sediment variation in different regions and forming a unified weighted expression to quantify the attribution contribution of each driving factor in different spaces.

8. A sediment flux evolution attribution identification system in alpine mountainous areas, characterized by: include: The main driving factor identification module is configured to: identify the main driving factors based on the sediment transport mechanism in alpine mountainous areas; The preprocessing module is configured to: obtain basic data corresponding to the main driving factors, perform preprocessing, and construct a driving factor data set; The mutation point detection module is configured to: use a joint mutation identification method to perform multi-angle mutation point detection based on the established driving factor dataset; use the Pettitt test to identify the differential change under the distribution mutation to determine the distribution mutation year; use the Mann-Kendall trend test method to identify the slope change under the trend mutation to determine the trend mutation year; detect mutation points based on the difference between the obtained distribution mutation year and the trend mutation year, and divide the evolution stage; The attribution identification module is configured to perform attribution analysis on all driving factors based on a three-stage progressive attribution analysis framework to quantify the attribution contribution of each driving factor at different evolution stages and in different spaces.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for attributing and identifying the evolution of sediment flux in alpine mountainous areas as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for attributing and identifying the evolution of sediment flux in alpine mountainous areas as described in any one of claims 1 to 7 are implemented.

Images