A mangrove forest growth monitoring method and system

Abstract

The application provides a mangrove growth monitoring method and system, comprising: acquiring a mangrove multi-temporal remote sensing image of a target monitoring area, extracting a spectral feature index of the mangrove multi-temporal remote sensing image, and obtaining a leaf area index based on a leaf area index model; obtaining a water body suspended sediment concentration inversion result based on a sediment content inversion model; performing spatial statistical analysis on the leaf area index and the water body suspended sediment concentration inversion result to obtain a spatial statistical index; analyzing a stress degree of water body suspended sediment on mangrove growth according to the leaf area index and the water body suspended sediment concentration inversion result to obtain a mangrove growth condition change parameter; and dividing the stress degree level of the target monitoring area according to the spatial statistical index and the mangrove growth condition change parameter, and generating a corresponding early warning instruction. The problem that water body suspended sediment cannot timely identify the influence on mangrove growth is solved, and the accuracy of mangrove growth monitoring is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographic information, in particular to a mangrove growth monitoring method and system. BACKGROUND

[0002] Mangrove is the core barrier of coastal ecosystem, which has the key functions of wave protection, carbon fixation and storage, and water purification. However, due to the superimposed effects of human activities (such as reclamation and port construction) and natural factors (such as sea level rise and extreme climate), mangrove often faces water-sediment environmental stress such as suspended sediment deposition and water turbidity increase, which leads to its growth inhibition or even degradation. Therefore, real-time monitoring of the growth state of mangrove and early warning of stress risk are the core needs of coastal ecological protection and restoration.

[0003] At present, the conventional method mainly relies on remote sensing technology and uses the static threshold segmentation of vegetation index (such as NDVI) to classify and monitor mangrove. However, it does not consider the influence of periodic tidal inundation on mangrove growth. During the tidal inundation process, the suspended sediment in the water will quickly deposit in the mangrove area. When the suspended sediment in the water stays at a high concentration for a long time, it will cause certain harm to the growth of mangrove. Since the suspended sediment in the water has a certain lag on the growth of mangrove, for example, the crown layer has not yet shown symptoms in the initial stage of root oxygen deficiency caused by the accumulation of suspended sediment in the water, the use of vegetation index for mangrove growth monitoring cannot timely identify this hidden stress, and there is a problem of low accuracy of mangrove monitoring. SUMMARY

[0004] In view of the problems in the prior art, the present application provides a mangrove growth monitoring method and system which can effectively improve the accuracy of mangrove monitoring by analyzing the stress degree of suspended sediment in water on the growth of mangrove.

[0005] A mangrove growth monitoring method, comprising:

[0006] obtaining multi-temporal remote sensing images of a target monitoring area, and extracting spectral feature indexes of the multi-temporal remote sensing images, wherein the target monitoring area includes a mangrove area and a non-mangrove area;

[0007] classifying the multi-temporal remote sensing images based on a preset mangrove classification model according to the spectral feature indexes, to generate mangrove multi-temporal remote sensing images including only the mangrove area;

[0008] analyzing the canopy coverage degree of mangrove based on a preset leaf area index model according to the spectral feature indexes of the mangrove multi-temporal remote sensing images, to obtain a leaf area index;

[0009] extracting a sediment sensitive reflectance in the mangrove multi-temporal remote sensing image, and based on a preset sediment content inversion model, inversing a water body suspended sediment content in the water body to obtain a water body suspended sediment concentration inversion result, wherein the sediment sensitive reflectance is a remote sensing reflectance of a wave band sensitive to the water body suspended sediment in the mangrove multi-temporal remote sensing image;

[0010] performing spatial statistical analysis on the leaf area index and the water body suspended sediment concentration inversion result to obtain a spatial statistical index;

[0011] based on a preset mangrove-water body suspended sediment stress coupling model, analyzing a stress degree of the water body suspended sediment on the mangrove growth according to the leaf area index and the water body suspended sediment concentration inversion result to obtain a mangrove growth condition change parameter;

[0012] based on a preset stress level division rule, dividing a stress level of the target monitoring area according to the spatial statistical index and the mangrove growth condition change parameter;

[0013] generating a warning instruction corresponding to the stress level according to the stress level division result of the target monitoring area, and transmitting the warning instruction to a mangrove growth warning device.

[0014] The application also provides a mangrove growth monitoring system, comprising:

[0015] a multi-temporal remote sensing image acquisition module, configured to acquire multi-temporal remote sensing images of a target monitoring area and extract spectral feature indexes of the multi-temporal remote sensing images, wherein the target monitoring area comprises a mangrove area and a non-mangrove area;

[0016] a mangrove classification module, configured to classify the multi-temporal remote sensing images based on a preset mangrove classification model according to the spectral feature indexes to generate mangrove multi-temporal remote sensing images comprising only the mangrove area;

[0017] a leaf area index calculation module, configured to analyze a canopy coverage degree of the mangrove based on a preset leaf area index model according to the spectral feature indexes of the mangrove multi-temporal remote sensing images to obtain a leaf area index;

[0018] a water body suspended sediment concentration inversion module, configured to extract a sediment sensitive reflectance in the mangrove multi-temporal remote sensing image, and based on a preset sediment content inversion model, inversing a water body suspended sediment content in the water body to obtain a water body suspended sediment concentration inversion result, wherein the sediment sensitive reflectance is a remote sensing reflectance of a wave band sensitive to the water body suspended sediment in the mangrove multi-temporal remote sensing image;

[0019] The spatial statistical index calculation module is configured to perform spatial statistical analysis on the leaf area index and the water body suspended sediment concentration inversion result to obtain a spatial statistical index.

[0020] The mangrove growth condition change parameter calculation module is configured to analyze a stress degree of the water body suspended sediment on the growth of the mangrove based on a preset mangrove-water body suspended sediment stress coupling model according to the leaf area index and the water body suspended sediment concentration inversion result, to obtain a mangrove growth condition change parameter.

[0021] The stress degree grade division module is configured to divide the target monitoring area into different stress degree grades based on a preset stress degree grade division rule according to the spatial statistical index and the mangrove growth condition change parameter.

[0022] The early warning instruction transmission module is configured to generate an early warning instruction corresponding to the stress degree grade according to the stress degree grade division result of the target monitoring area, and transmit the early warning instruction to a mangrove growth early warning device.

[0023] Compared with the prior art, the present application uses multi-temporal remote sensing images and analyzes the canopy coverage of the mangrove by introducing a leaf area index model to obtain the leaf area index as a direct indicator of the growth state of the mangrove. Meanwhile, the water body suspended sediment content in the water body is accurately inverted based on a sediment sensitive reflectivity and sediment content inversion model, the areas of the mangrove affected by the suspended sediment are determined by combining the spatial statistical analysis of the leaf area index and the water body suspended sediment content, and the stress degree of the water body suspended sediment on the growth of the mangrove is analyzed based on a preset mangrove-water body suspended sediment stress coupling model, so that the dynamic division of the stress grades of the mangrove areas is realized, the early warning instruction is automatically generated, the problem that the water body suspended sediment, a hidden stress, cannot be timely identified when the growth of the mangrove is monitored by relying on the vegetation index is effectively solved, and the accuracy of the growth monitoring of the mangrove is significantly improved.

[0024] In order to more clearly understand the present application, the specific embodiments of the present application will be described below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 A flowchart of a mangrove growth monitoring method of the present application;

[0026] Figure 2 A flowchart of a method for constructing a mangrove classification model in a mangrove growth monitoring method of the present application;

[0027] Figure 3 A flowchart of a method for evaluating the precision of a mangrove classification model in a mangrove growth monitoring method of the present application;

[0028] Figure 4A method flow chart for constructing a leaf area index model in a mangrove growth monitoring method of the present application;

[0029] Figure 5 A method flow chart for constructing a sediment content inversion model in a mangrove growth monitoring method of the present application;

[0030] Figure 6 A method flow chart for constructing a sediment sensitive reflectivity-optical parameter coupling model in a mangrove growth monitoring method of the present application;

[0031] Figure 7 A method flow chart for spatial statistical analysis of leaf area index and water suspended sediment concentration inversion results in a mangrove growth monitoring method of the present application;

[0032] Figure 8 A method flow chart for constructing a mangrove-water suspended sediment stress coupling model in a mangrove growth monitoring method of the present application;

[0033] Figure 9 A method flow chart for stress degree grade division of a target monitoring area in a mangrove growth monitoring method of the present application;

[0034] Figure 10 A schematic diagram of a mangrove growth monitoring system of the present application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0036] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowcharts or one or more operations can be removed from the flowcharts by those skilled in the art under the guidance of the content of the present application.

[0037] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. As will be apparent to those of ordinary skill in the art, embodiments described herein can be combinable with other embodiments.

[0038] Embodiment 1

[0039] Reference is made to Figure 1 , Figure 1 A flow chart of a mangrove growth monitoring method of the application.

[0040] The application provides a mangrove growth monitoring method, specifically comprising the following steps:

[0041] S1: acquiring multi-temporal remote sensing images of a target monitoring area, and extracting spectral feature indexes of the multi-temporal remote sensing images, wherein the target monitoring area comprises a mangrove area and a non-mangrove area;

[0042] S2: according to the spectral feature indexes, classifying the multi-temporal remote sensing images based on a preset mangrove classification model, to generate mangrove multi-temporal remote sensing images comprising only the mangrove area;

[0043] S3: according to spectral feature indexes of the mangrove multi-temporal remote sensing images, analyzing a canopy coverage degree of the mangrove based on a preset leaf area index model, to obtain a leaf area index;

[0044] S4: extracting a sediment sensitive reflectance in the mangrove multi-temporal remote sensing images, and based on a preset sediment content inversion model, inverting a water body suspended sediment content in a water body to obtain a water body suspended sediment concentration inversion result, wherein the sediment sensitive reflectance is a remote sensing reflectance of a wave band sensitive to the water body suspended sediment in the mangrove multi-temporal remote sensing images;

[0045] S5: performing spatial statistical analysis on the leaf area index and the water body suspended sediment concentration inversion result, to obtain a spatial statistical index;

[0046] S6: according to the leaf area index and the water body suspended sediment concentration inversion result, analyzing a stress degree of the water body suspended sediment on the mangrove growth based on a preset mangrove-water body suspended sediment stress coupling model, to obtain a mangrove growth condition change parameter;

[0047] S7: according to the spatial statistical index and the mangrove growth condition change parameter, classifying a stress degree level of the target monitoring area based on a preset stress degree level classification rule;

[0048] S8: generating a warning instruction corresponding to the stress degree level according to the stress degree level division result of the target monitoring area, and transmitting the warning instruction to a mangrove growth warning device;

[0049] Compared with the prior art, the scheme accurately distinguifies the mangrove area and the non-mangrove area by using the multi-temporal remote sensing image, and avoids the influence of the vegetation in the non-mangrove area on the mangrove monitoring. Secondly, the canopy coverage degree of the mangrove is analyzed by introducing the leaf area index model, and the leaf area index is obtained as a direct index of the growth state of the mangrove. At the same time, the water suspended sediment content in the water body is accurately inversed based on the sediment sensitive reflectivity and the sediment content inversion model, and the mangrove area affected by the suspended sediment is determined by combining the spatial statistical analysis of the leaf area index and the water suspended sediment content, and the stress degree of the water suspended sediment on the growth of the mangrove is analyzed based on the preset mangrove-water suspended sediment stress coupling model, the dynamic division of the stress level of the mangrove area is realized, and the warning instruction is automatically generated, thereby effectively solving the problem that the water suspended sediment, which is a hidden stress, cannot be timely identified when the growth of the mangrove is monitored by relying on the vegetation index, and the accuracy of the growth monitoring of the mangrove is significantly improved.

[0050] The mangrove growth monitoring method of the present application can be executed by the following computer system, which comprises a mangrove growth monitoring database server, a data acquisition server and a mangrove growth monitoring server. The mangrove growth monitoring database server is used to store the multi-temporal remote sensing image information of the target monitoring area, so as to construct the mangrove growth monitoring database.

[0051] The data acquisition server is used to acquire the multi-temporal remote sensing image information of the target monitoring area from the mangrove growth monitoring database server, and send it to the mangrove growth monitoring server for processing.

[0052] The mangrove growth monitoring server executes the mangrove growth monitoring method of the present application, divides the stress degree level of the target monitoring area, generates a warning instruction corresponding to the stress degree level, and transmits it to the mangrove growth warning device.

[0053] For step S1, in the present embodiment, the target monitoring area comprises a mangrove area and a non-mangrove area, and the multi-temporal remote sensing image can be the four-season image of Landsat satellite or Sentinel-2 satellite. For example, the time span covers the complete annual cycle, and the time points are March (spring), June (summer), September (autumn) and December (winter) every year.

[0054] The multi-temporal remote sensing image of the Sentinel-2 satellite has a time resolution of 5 days and a spatial resolution of 10 m or 20 m. The multi-temporal remote sensing image of the Sentinel-2 satellite includes a blue band Band2 with a center wavelength of 490 nm, a green band Band3 with a center wavelength of 560 nm, a red band Band4 with a center wavelength of 665 nm, a red edge band Band7 with a center wavelength of 783 nm, a wide near-infrared band Band8 with a center wavelength of 842 nm, a narrow near-infrared band Band8A with a center wavelength of 865 nm, and a short-wave infrared band, which can be obtained from the official website of the European Space Agency.

[0055] The spectral feature index is a numerical index calculated by the remote sensing reflectance of a specified band in the multi-temporal remote sensing image, including a normalized vegetation index, a water body index, and a mangrove extraction index. The mangrove region refers to a geographical region where mangrove vegetation grows, and the non-mangrove region refers to other geographical regions other than the mangrove region, including other types of vegetation, water bodies, construction land, etc.

[0056] The satellite multi-temporal remote sensing image can be sequentially preprocessed by radiation calibration, geometric precise correction, and atmospheric correction. Among them, radiation calibration is to convert the original digital value recorded by the sensor into radiance or apparent reflectance; the purpose of geometric precise correction is to eliminate geometric distortion caused by sensor attitude, platform motion or terrain undulation, and to ensure the accuracy of image spatial position; atmospheric correction is to remove the influence of atmospheric scattering and absorption, and to convert apparent reflectance into real ground reflectance.

[0057] For step S2, in the present embodiment, the mangrove multi-temporal remote sensing image only including the mangrove region refers to a multi-temporal remote sensing image obtained after labeling the pixels of the mangrove region in the multi-temporal remote sensing image as 1 and the pixels of the non-mangrove region as 0. Please refer to Figure 2 , Figure 2 The present application is a method flow chart for constructing a mangrove classification model in a mangrove growth monitoring method. The mangrove classification model is constructed, including:

[0058] S21: Obtain a plurality of historical multi-temporal remote sensing images of the target monitoring region, wherein the historical mangrove multi-temporal remote sensing image includes a green band, a short-wave infrared band, a red edge band, a wide near-infrared band, and a narrow near-infrared band;

[0059] S22: Label the mangrove region and the non-mangrove region in the historical multi-temporal remote sensing image to obtain a standard historical multi-temporal remote sensing image;

[0060] S23: Based on the remote sensing reflectance of the green light band, shortwave infrared band, red edge band, wide near-infrared band and narrow near-infrared band, and based on the preset water body index calculation formula and mangrove extraction index calculation formula, the water body index and mangrove extraction index are calculated.

[0061] S24: Using the normalized vegetation index, water index and mangrove extraction index as input features and the standard historical multi-temporal remote sensing imagery as output features, construct sample data, and divide the sample data into training sample dataset and test sample dataset in an 8:2 ratio.

[0062] S25: Based on the input and output features of the training sample dataset, construct the mangrove classification model using a machine learning algorithm;

[0063] S26: Based on the input features of the test sample dataset and the mangrove classification model, obtain the test results of the multi-temporal remote sensing images of mangroves corresponding to the test sample dataset;

[0064] S27: By statistically analyzing the number of correctly classified mangrove areas and non-mangrove areas in the test results of the multi-temporal remote sensing images of mangroves, the accuracy of the mangrove classification model is evaluated, and the accuracy evaluation result of the mangrove classification model is obtained.

[0065] S28: When the accuracy evaluation result of the mangrove classification model is lower than the preset accuracy threshold of the mangrove classification model, the hyperparameters of the mangrove classification model are adjusted using an optimization algorithm.

[0066] For steps S21 and S22, the historical multi-temporal remote sensing images of the target monitoring area refer to satellite multi-temporal remote sensing images of the target monitoring area acquired through remote sensing technology at multiple past time points or time periods. Software such as ArcGIS or QGIS can be used to determine whether an area is a mangrove forest based on visual interpretation, such as color differences and texture features. This allows for the labeling of mangrove and non-mangrove areas within the historical multi-temporal remote sensing images, specifically labeling mangrove areas as 1 and non-mangrove areas as 0, thus obtaining the standard historical multi-temporal remote sensing image.

[0067] For step S23, the historical mangrove multi-temporal remote sensing imagery includes: green band, shortwave infrared band, red-edge band, wide near-infrared band, and narrow near-infrared band. The water index calculation formula is:

[0068]

[0069] In the formula, The water index is mentioned above. The remote sensing reflectance of the green light band is given. The remote sensing reflectance of the wide near-infrared band;

[0070] The formula for calculating the mangrove extraction index is as follows:

[0071]

[0072] In the formula, The mangrove extraction index is... The remote sensing reflectance of the shortwave infrared band is given. The remote sensing reflectance of the red-edge band is given. The remote sensing reflectance of the wide near-infrared band is given. The remote sensing reflectance of the narrow near-infrared band is given.

[0073] For steps S24 and S25, the training sample dataset is used to construct a mangrove classification model, enabling the model to learn the spectral characteristics of mangrove and non-mangrove regions. The test sample dataset is used to evaluate the performance of the mangrove classification model. The machine learning algorithms include Support Vector Machine (SVM) and Random Forest.

[0074] By using the normalized vegetation index, water index, and mangrove extraction index of the training sample dataset as input features, and the standard historical multi-temporal remote sensing images of the training sample dataset as output features to provide supervision signals, a mapping relationship is established between the input and output features using machine learning algorithms such as vector machine (SVM) or random forest. By iteratively adjusting model hyperparameters, such as the penalty parameter and kernel function parameter in SVM or the number and depth of trees in random forest, the difference between the predicted label and the true label is minimized, thus constructing the mangrove classification model. Here, the predicted label refers to the training result of the mangrove multi-temporal remote sensing images corresponding to the training sample dataset output by the model during training, and the true label refers to the standard historical multi-temporal remote sensing images of the training sample dataset.

[0075] For steps S26 and S27, please refer to Figure 3 , Figure 3 This is a flowchart illustrating the method for evaluating the accuracy of a mangrove classification model in a mangrove growth monitoring method according to this application. The method involves evaluating the accuracy of the mangrove classification model by statistically analyzing the number of correctly classified mangrove and non-mangrove areas in the multi-temporal remote sensing image test results, thereby obtaining the mangrove classification model accuracy evaluation result. This includes:

[0076] S271: Randomly generate several test points in the test results of the multi-temporal remote sensing images of the mangroves;

[0077] S272: Count the number of test points that correctly classify mangrove areas and the number of test points that correctly classify non-mangrove areas in the test results of the multi-temporal remote sensing images of mangroves;

[0078] S273: Based on the total number of test points, the number of test points correctly classified in mangrove areas, and the number of test points correctly classified in non-mangrove areas, the accuracy evaluation result of the mangrove classification model is obtained using the following formula:

[0079]

[0080] In the formula, OA represents the accuracy evaluation result of the mangrove classification model. The number of checkpoints correctly classified for mangrove areas. N represents the number of checkpoints that correctly classified non-mangrove areas, and N is the total number of checkpoints.

[0081] For steps S271-S273, the test results of the multi-temporal remote sensing image of the mangrove forest can be read using geographic information system software such as ArcGIS, and the test points can be randomly generated using tools such as creating random points. In this embodiment, the total number of test points can be set to 200. To avoid the random points being too dense, a minimum distance between two random test points can also be set.

[0082] The judgment rule can be specifically based on the inventive concept of this application and common knowledge in the field, by human judgment of whether each test point in the multi-temporal remote sensing image test results of mangroves belongs to mangrove areas or non-mangrove areas, and statistically calculate the number of test points correctly classified as mangrove areas and the number of test points correctly classified as non-mangrove areas.

[0083] In other embodiments, the accuracy of the mangrove classification model can be evaluated by calculating coefficients such as Kappa and F1-Score, and the accuracy evaluation result of the mangrove classification model can be obtained.

[0084] For step S28, the accuracy threshold of the mangrove classification model is preferably set to 85%, and the second optimization algorithm can be an iterative algorithm such as grid search, Bayesian optimization, genetic algorithm, or gradient boosting. Of course, the accuracy threshold of the mangrove classification model can be adaptively modified according to actual needs.

[0085] For step S3, in one embodiment, based on the spectral characteristic indices of the multi-temporal remote sensing images of mangroves, and using a preset leaf area index (LAI) model, the canopy cover of the mangroves is analyzed to obtain the LAI corresponding to each season. For the LAI corresponding to each season, interpolation can also be used to obtain the change in LAI between two seasons. The LAI model refers to a model used to estimate the leaf area density of the mangrove canopy based on the spectral characteristic indices of the multi-temporal remote sensing images of mangroves. The LAI refers to half the total leaf area per unit surface area of ​​plants and is used to measure the mangrove canopy structure. (See also...) Figure 4 , Figure 4 This is a flowchart illustrating the method for constructing a leaf area index (LAI) model in a mangrove growth monitoring method according to this application. Constructing the LAI model includes:

[0086] S31: Acquire several historical mangrove multi-temporal remote sensing images and measured leaf area index values ​​of the same period, wherein the historical mangrove multi-temporal remote sensing images include wide near-infrared band and red light band.

[0087] S32: Based on the remote sensing reflectance of the near-infrared and red bands, the normalized vegetation index is obtained using the normalized vegetation index calculation formula, which is as follows:

[0088]

[0089] In the formula, The normalized vegetation index is... The remote sensing reflectance of the wide near-infrared band is given. The remote sensing reflectance of the red light band is denoted as .

[0090] S33: Based on the measured leaf area index and the normalized vegetation index, an empirical inversion model is established through linear regression to obtain the leaf area index model, the expression of which is:

[0091]

[0092] In the formula, The leaf area index, The normalized vegetation index is... The weighting coefficients of the normalized vegetation index, This is the second empirical coefficient.

[0093] For step S31, the historical mangrove multi-temporal remote sensing image refers to the satellite multi-temporal remote sensing image of the target monitoring area obtained by remote sensing technology at multiple time points or time periods in the past. The measured leaf area index refers to the leaf area index obtained by on-site measurement, and the time point of obtaining the measured leaf area index is synchronized with the time point of obtaining the historical mangrove multi-temporal remote sensing image.

[0094] For step S33, the leaf area index model is a univariate linear regression model. The weight coefficient and second empirical coefficient of the normalized vegetation index can be calculated by minimizing the sum of squared residuals between the predicted and measured values. The leaf area index model can be evaluated by calculating the coefficient of determination and root mean square error, etc.

[0095] In other embodiments, the leaf area index model can also be a multiple linear regression equation, and the historical mangrove multi-temporal remote sensing imagery also includes the blue light band. Based on the remote sensing reflectance of the near-infrared band, red band, and blue light band, and using the calculation formula for the enhanced vegetation index, the enhanced vegetation index is obtained:

[0096]

[0097] In the formula, EVI is the enhanced vegetation index. The remote sensing reflectance of the wide near-infrared band is given. The remote sensing reflectance of the red light band is given. Where is the remote sensing reflectance of the blue light band, G is the gain factor, which can be 2.5, C1 and C2 are atmospheric correction coefficients, which can be 6.0 and 7.5 respectively, and L is the background adjustment parameter, which can be 1.0.

[0098] Combining the measured leaf area index, normalized difference vegetation index, and enhanced vegetation index, a multiple linear regression model is constructed, the specific expression of which is:

[0099]

[0100] In the formula, A1 and A2 are the regression coefficients of the normalized vegetation index and the enhanced vegetation index, respectively, which can also be calculated by minimizing the sum of squared residuals between the predicted and measured values.

[0101] For step S4, in this embodiment, based on a preset sediment content inversion model, the suspended sediment content in the water body is inverted to obtain the suspended sediment concentration inversion results for each season. For the suspended sediment concentration inversion results for each season, interpolation can also be used to obtain the change in the suspended sediment concentration inversion results between two seasons. Please refer to... Figure 5 , Figure 5This is a flowchart illustrating the method for constructing a sediment content inversion model in a mangrove growth monitoring method according to this application. Constructing the sediment content inversion model includes:

[0102] S41: Obtain historical multi-temporal remote sensing images of mangrove forests in the mangrove area and the measured concentration of suspended sediment in water bodies during the same period;

[0103] S42: Based on the sediment-sensitive reflectance in the historical mangrove multi-temporal remote sensing images, and based on the preset sediment-sensitive reflectance-optical parameter coupling model, the absorption coefficient of suspended sediment in water and the backscattering coefficient of suspended sediment in water are obtained.

[0104] S43: Based on the sediment-sensitive reflectance in the historical mangrove multi-temporal remote sensing images, the suspended sediment index of water body is obtained based on the formula for calculating the suspended sediment index of water body.

[0105] S44: Based on the inverted values ​​of the measured concentration of suspended sediment in the water body, the absorption coefficient of suspended sediment in the water body, the backscattering coefficient of suspended sediment in the water body, and the suspended sediment index in the water body, the sediment content inversion model is constructed through linear regression:

[0106]

[0107] In the formula, This refers to the measured concentration of suspended sediment in the water body or the inversion result of the suspended sediment concentration in the water body. The suspended sediment index of the water body. It is a wavelength of The following is the absorption coefficient of suspended sediment in the water body. It is a wavelength of The backscattering coefficient of suspended sediment in the water body is as follows. , and These are the weighting coefficients for the suspended sediment index, suspended sediment absorption coefficient, and suspended sediment backscattering coefficient of the water body, respectively. This is the first empirical coefficient.

[0108] For step S42, please also refer to Figure 6 , Figure 6 This is a flowchart illustrating the method for constructing a sediment-sensitive reflectance-optical parameter coupling model in a mangrove growth monitoring method according to this application. The construction of the sediment-sensitive reflectance-optical parameter coupling model includes:

[0109] S421: Simplify the water body radiation field into upward and downward radiation flows, and establish a set of approximate two-flow radiative transfer equations:

[0110]

[0111] In the formula, It is an upward radiative flow with a water depth of z and a wavelength of λ. It is a downward radiative flow with a water depth of z and a wavelength of λ. It is the upward diffuse attenuation coefficient for a water depth of z and a wavelength of λ. It is the downward diffusion attenuation coefficient for a water depth of z and a wavelength of λ. It is an upward source function with a water depth of z and a wavelength of λ. It is a downward source function with a water depth of z and a wavelength of λ;

[0112] S422: When the medium is homogeneous, the two-stream approximate radiative transfer equations are simplified to obtain the simplified two-stream approximate radiative transfer equations:

[0113]

[0114] In the formula, The total absorption coefficient is 1. , The preset wavelength is The pure water absorption coefficient at the following values, It is a wavelength of The absorption coefficient of suspended sediment in the water body. The total backscattering coefficient is... + , The preset wavelength is The backscattering coefficient of pure water at this temperature. It is a wavelength of Backscattering coefficient of suspended sediment in the water body;

[0115] S423: Combining the simplified two-stream approximate radiative transfer equations, and based on the integral factor method and preset boundary conditions, establish the sediment-sensitive reflectivity-optical parameter coupling model, the expression of which is:

[0116]

[0117] In the formula, It is a wavelength of The reflectivity of mud and sand , , The wavelength attenuation index is the preset sediment absorption coefficient. The wavelength attenuation index is the preset backscattering coefficient of sediment. is the proportionality constant of the sediment absorption coefficient. It is the proportionality constant of the sediment backscattering coefficient.

[0118] For steps S421 and S422, in this embodiment, under the two-flow approximation, assuming a homogeneous medium, optical parameters such as the total absorption coefficient and total backscattering coefficient do not change with depth. = = For the upward source function, the backscattering contribution from the downward light is considered. = For the downward source function, the forward scattering contribution from the upward light is usually neglected in the two-stream approximation. Therefore, the two-stream approximate radiative transfer equations are simplified to obtain the simplified two-stream approximate radiative transfer equations.

[0119] For step S423, the preset wavelength is The absorption coefficient of pure water can be determined based on the specific wavelength. The wavelength was obtained from standard water optical parameters published by the International Organization for Ocean Color Coordination (IOCCG). The backscattering coefficient of pure water can be calculated using the following formula:

[0120]

[0121] In the formula, The total scattering coefficient of pure water can be obtained by retrieving the pure water optical parameters built into the radiative transfer simulation software HydroLight, or from the standard water body optical parameters published by the International Organization for Harmonization of Ocean Color (IOCCG). Let be the backscattering probability, in the Rayleigh scattering phase function of pure water. ≈0.5.

[0122] The sediment-sensitive reflectance is defined as the ratio of the upward light intensity to the downward light intensity at the water surface (z=0):

[0123]

[0124] The boundary conditions are that the depth of the water body tends to be infinite and the depth of the water body is 0. Based on the ratio of the upward light intensity to the downward light intensity at the water surface and the boundary conditions, the coupling model of sediment-sensitive reflectivity and optical parameters is obtained based on the integral factor method.

[0125] The wavelength attenuation index of the sediment absorption coefficient indicates that the sediment absorption coefficient decreases as the wavelength increases, and the wavelength attenuation index of the sediment backscattering coefficient indicates that the sediment backscattering coefficient decreases as the wavelength increases. Different types of suspended sediment in water bodies, such as clay, silt, and sand, have different wavelength attenuation indices for both the sediment absorption coefficient and the sediment backscattering coefficient. Based on empirical methods, the wavelength attenuation indices for the sediment absorption coefficient and the sediment backscattering coefficient can be preset according to the type of suspended sediment in the water body.

[0126] The sediment-sensitive reflectance includes remotely sensed reflectance in the broad near-infrared band and the blue light band. Substituting the remotely sensed reflectance in the broad near-infrared band and the blue light band into the sediment-sensitive reflectance-optical parameter coupling model and solving the equations yields the proportionality constants of the sediment absorption coefficient and the sediment backscattering coefficient. This allows for the retrieval of the inversion values ​​of the suspended sediment absorption coefficient and the suspended sediment backscattering coefficient in the water body.

[0127] For step S43, the formula for calculating the suspended sediment index of the water body is:

[0128]

[0129] In the formula, The suspended sediment index of the water body. The remote sensing reflectance of the wide near-infrared band is given. The remote sensing reflectance of the blue light band is given.

[0130] For step S44, a multiple linear regression model is constructed by combining the inverted values ​​of the measured concentration of suspended sediment in the water body, the absorption coefficient of suspended sediment in the water body, and the backscattering coefficient of suspended sediment in the water body, along with the suspended sediment index, to obtain the sediment content inversion model. The weighting coefficients of the suspended sediment index, the absorption coefficient of suspended sediment in the water body, and the backscattering coefficient of suspended sediment in the water body, as well as the first empirical coefficient, can be calculated by minimizing the sum of squared residuals between the predicted and measured values.

[0131] For step S5, in one embodiment, the spatial statistical index includes the Pearson correlation coefficient of the leaf area index and the inversion result of suspended sediment concentration in water, as well as the spatial autocorrelation index, which are used to classify the stress level of the target monitoring area.

[0132] Please see Figure 7 , Figure 7This is a flowchart illustrating the method for spatial statistical analysis of leaf area index (LAI) and suspended sediment concentration in water body inversion results in a mangrove growth monitoring method according to this application. The step of performing spatial statistical analysis on the LAI and suspended sediment concentration inversion results to obtain a spatial statistical index includes:

[0133] S51: Random sampling is performed based on the multi-temporal remote sensing images of the mangrove forest to obtain observation datasets at different sampling points. The observation datasets at any sampling point include the leaf area index and suspended sediment concentration inversion results at the same location and time.

[0134] S52: Based on the observed dataset, and using the Pearson correlation coefficient calculation formula, obtain the Pearson correlation coefficients for the leaf area index and suspended sediment concentration inversion results:

[0135]

[0136] In the formula, The Pearson correlation coefficient is the result of the inversion of leaf area index and suspended sediment concentration in water. The leaf area index is the value of the i-th observation dataset. The suspended sediment content in the water body in the i-th observation dataset. The leaf area index is the average value of the observed datasets. is the average value of suspended sediment content in the water body for each of the aforementioned observation datasets, and n is the number of the aforementioned observation datasets;

[0137] S53: Based on the observed dataset, using the inverse distance weighted interpolation method, a continuous spatial distribution surface of the leaf area index and suspended sediment concentration in water body inversion results is generated, and the interpolation of the leaf area index and suspended sediment concentration in water body inversion results in several spatial cells is obtained. The specific formula is as follows:

[0138]

[0139] In the formula, This is the interpolation of the leaf area index or suspended sediment concentration in water body in spatial cell P. The leaf area index or suspended sediment content in the water body in the i-th observation dataset. Let be the distance from the acquisition point corresponding to the i-th observation dataset to the spatial unit P. = , and Let be the coordinates of the collection point corresponding to the i-th observation dataset. and Let P be the coordinates of the spatial unit P;

[0140] S54: Based on the spatial cell interpolation corresponding to the inversion results of the leaf area index and suspended sediment concentration in water, perform bivariate spatial autocorrelation analysis on the inversion results of the leaf area index and suspended sediment concentration in water to obtain the spatial autocorrelation index of the inversion results of the leaf area index and suspended sediment concentration in water. The specific formula is as follows:

[0141]

[0142] In the formula, The spatial autocorrelation index is given. The interpolation of the leaf area index in the i-th spatial unit is given. The value is the interpolation of the suspended sediment content in the water body in the j-th spatial unit. This is the average of the interpolated leaf area index across all the aforementioned spatial units. The value represents the average interpolated suspended sediment content in the water body across all the aforementioned spatial units, where m is the number of the spatial units. This is a preset spatial weight matrix.

[0143] According to steps S51-S54, the Pearson correlation coefficient between the leaf area index and the suspended sediment concentration in water is a statistical indicator that measures the degree of linear correlation between the leaf area index and the suspended sediment concentration in water. Its value is between -1 and 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0144] Based on the inverse distance weighted interpolation method, the inversion results of the leaf area index and suspended sediment concentration in water at discrete sampling points are converted into a continuous spatial distribution surface. Bivariate spatial autocorrelation analysis is then performed to analyze the collaborative variation pattern of the inversion results of the leaf area index and suspended sediment concentration in water on this spatial distribution surface.

[0145] For example, if the leaf area index and the inversion results of suspended sediment concentration in water body show a significant negative correlation in space (the spatial autocorrelation index is negative and the Pearson correlation coefficient r < 0), it indicates that there is an inverse correlation pattern between the two in spatial distribution. This inverse correlation pattern may be due to: areas with high leaf area index reducing the sediment-carrying capacity of water flow through the blocking effect of mangroves, thus reducing the suspended sediment concentration; or areas with low suspended sediment concentration in water body due to decreased light transmittance or sediment cover inhibiting mangrove growth, resulting in a low leaf area index.

[0146] For step S6, in this embodiment, the parameters for changes in mangrove growth status can also be calculated based on the following formula:

[0147]

[0148] In the formula, These are the parameters representing the changes in the growth status of the mangroves. and These are the parameters representing the mangrove growth status for any two seasons.

[0149] Please see Figure 8 , Figure 8 This is a flowchart illustrating the method for constructing a mangrove-water suspended sediment stress coupling model in a mangrove growth monitoring method according to this application. Constructing the mangrove-water suspended sediment stress coupling model includes:

[0150] S61: Based on the historical mangrove multi-temporal remote sensing images, obtain the leaf area index and suspended sediment concentration in water body inversion results at multiple historical time points;

[0151] S62: Obtain the mangrove canopy width, soil moisture, and temperature at each of the historical time points in the mangrove area;

[0152] S63: Based on the inversion results of mangrove canopy width, leaf area index, suspended sediment concentration in water, soil moisture, and temperature, the mangrove-water suspended sediment stress coupling model is constructed through linear regression, and its expression is as follows:

[0153]

[0154] In the formula, Nm can be a parameter representing the mangrove canopy width, changes in mangrove growth status, or a parameter representing the mangrove growth status. The results of the inversion of suspended sediment concentration in the water body are as follows. The leaf area index is mentioned above. The soil moisture, Where b is the temperature, and b3 is the third empirical coefficient. , and These are the weighting coefficients for the leaf area index, soil moisture, and temperature, respectively.

[0155] For step S61, specifically, based on the historical mangrove multi-temporal remote sensing images, for each pixel or quadrat area, the leaf area index of the later temporal phase is subtracted from the leaf area index of the previous temporal phase to obtain the change in leaf area index of the area between two historical time points. This calculation process is also applicable to calculating the change in the inversion result of the suspended sediment concentration in the water body, as well as the changes in mangrove canopy width, soil moisture, and temperature described below.

[0156] For step S62, the mangrove canopy width, soil moisture, and temperature can be obtained from local environmental monitoring agencies. Specifically, the leaf area index, water suspended sediment concentration inversion results, mangrove canopy width, soil moisture, and temperature must be obtained based on the same historical time point.

[0157] For step S63, based on the inversion results of mangrove canopy width, leaf area index, suspended sediment concentration in water, soil moisture, and temperature, a multiple linear regression model is constructed as the mangrove-water suspended sediment stress coupling model. The weighting coefficients for leaf area index, soil moisture, and temperature can be calculated by minimizing the sum of squared residuals between predicted and measured values.

[0158] Nm can be a parameter representing changes in mangrove canopy width, mangrove growth status, or other mangrove growth status parameters. When the changes in leaf area index, the changes in suspended sediment concentration in water, and the changes in mangrove canopy width, soil moisture, and temperature are input into the mangrove-suspended sediment stress coupling model, the output parameters are the parameters representing changes in mangrove growth status.

[0159] For step S7, please refer to [link to relevant documentation] in this embodiment. Figure 9 , Figure 9 This is a flowchart illustrating the method for classifying the stress level of a target monitoring area in a mangrove growth monitoring method according to this application. The step of classifying the stress level of the target monitoring area based on the spatial statistical index and mangrove growth status change parameters, and according to a preset stress level classification rule, includes:

[0160] S71: Based on the analytic hierarchy process, the spatial statistical index and mangrove growth status change parameters are divided into several ranges of variation.

[0161] S72: Based on the aforementioned range of variation, the target monitoring area is divided into levels of coercion.

[0162] For steps S71 and S72, for example, the spatial statistical index and mangrove growth status change parameters are divided into four ranges of variation based on the analytic hierarchy process, and the target monitoring area is divided into four stress levels, as shown in Table 1 below:

[0163] Table 1:

[0164]

[0165] When r≤-0.7, I<-0.3 and Nm≤-30%, it indicates that the concentration of suspended sediment in the water body is strongly negatively correlated with the growth status of mangroves, and that sediment significantly suppresses mangrove growth and causes severe decline in mangrove growth. In this case, the target monitoring area is classified as a severe stress level.

[0166] When -0.7 < r ≤ -0.4, -0.3 ≤ I < -0.1, and -30% < Nm ≤ -10%, it indicates a moderately negative correlation between the concentration of suspended sediment in water and the growth status of mangroves. The sediment shows a weak spatial suppression on the growth of mangroves and the growth status of mangroves is moderately declining. At this time, the target monitoring area is divided into the moderate stress level.

[0167] When -0.4 < r ≤ -0.2, -0.1 ≤ I < 0, and -10% < Nm ≤ 0%, it indicates a weak negative correlation between the concentration of suspended sediment in water and the growth status of mangroves. The sediment has no spatial suppression on the growth of mangroves and the growth status of mangroves is slightly declining. At this time, the target monitoring area is divided into the mild stress level.

[0168] When r > -0.2, I ≥ 0, and Nm > 0%, it indicates a relatively weak negative correlation between the concentration of suspended sediment in water and the growth status of mangroves. The sediment has no spatial association with the growth of mangroves and the growth status of mangroves is normal. At this time, the target monitoring area is divided into the non - stress level.

[0169] In other embodiments, according to actual needs, the number of the range of change amplitudes can also be adaptively modified, and the thresholds of the Pearson correlation coefficient r, the spatial autocorrelation index I, and the mangrove growth status change parameter Nm in the range of change amplitudes can be adaptively modified. For example, in a strong tidal area, the sediment is easily washed away, and the threshold of the spatial autocorrelation index I can be relaxed. Let I corresponding to the severe stress level be < -0.5, etc. According to the range of change amplitudes, the classification of the stress degree level of the target monitoring area is adaptively modified.

[0170] For step S8, in this embodiment, the warning instruction includes the generation time, the geographical coordinates of the target monitoring area, the stress degree level, the key parameters, and the warning suggestions, etc. Among them, the stress degree level includes the severe stress, the moderate stress, the mild stress, and the non - stress. The key parameters include the Pearson correlation coefficient r, the spatial autocorrelation index I, and the mangrove growth status change parameter Nm.

[0171] When the classification result of the stress degree level of the target monitoring area is non - stress, the warning suggestion can be to maintain regular monitoring, record the mangrove growth data, and there is no need to initiate an emergency response. When the classification result of the stress degree level of the target monitoring area is mild stress, the warning suggestion can be to increase the frequency of patrol monitoring and submit a monitoring report to the management department. When the classification result of the stress degree level of the target monitoring area is moderate stress, the warning suggestion can be to initiate ecological restoration measures, manually clean the silt on the surface layer (area with a thickness > 15 cm) of the mangrove root area to promote root ventilation.

[0172] When the stress level classification result of the target monitoring area is severe stress, the early warning suggestion may be to initiate emergency intervention measures, such as manually clearing the surface silt (area with a thickness >30cm) of mangrove root zone, replanting mangrove species tolerant to high siltation (such as Avicennia marina and Sorbus amurensis), using container seedlings to improve the survival rate, implementing watershed sediment interception projects (such as ecological sand-blocking dams), and reducing upstream sediment input, etc.

[0173] The mangrove growth monitoring server can push the early warning instructions to the mangrove growth early warning device via a wireless network. The mangrove growth early warning device can be a display screen, a mobile terminal, etc. Alternatively, the mangrove growth monitoring server can be interfaced with the early warning device system. In other embodiments, the early warning instructions can be adapted to meet actual monitoring needs.

[0174] Example 2

[0175] Please see Figure 10 , Figure 10 This is a schematic diagram of a mangrove growth monitoring system according to this application.

[0176] This application also provides a mangrove growth monitoring system, including:

[0177] Multi-temporal remote sensing image acquisition module 1: used to acquire multi-temporal remote sensing images of the target monitoring area and extract the spectral feature index of the multi-temporal remote sensing images, wherein the target monitoring area includes mangrove areas and non-mangrove areas;

[0178] Mangrove classification module 2: is used to classify the multi-temporal remote sensing images based on the spectral feature index and a preset mangrove classification model, and generate multi-temporal remote sensing images of mangroves that only include the mangrove area;

[0179] Leaf area index calculation module 3: It is used to analyze the canopy coverage of mangroves based on the spectral characteristic index of the multi-temporal remote sensing images of mangroves and a preset leaf area index model to obtain the leaf area index.

[0180] Water body suspended sediment concentration inversion module 4: used to extract the sediment-sensitive reflectance in the mangrove multi-temporal remote sensing image, and based on the preset sediment content inversion model, invert the suspended sediment content in the water body to obtain the suspended sediment concentration inversion result. The sediment-sensitive reflectance is the remote sensing reflectance of the band sensitive to suspended sediment in the mangrove multi-temporal remote sensing image.

[0181] Spatial statistical index calculation module 5: used to perform spatial statistical analysis on the inversion results of the leaf area index and suspended sediment concentration in water body to obtain spatial statistical index;

[0182] Mangrove growth status change parameter calculation module 6: Based on the inversion results of the leaf area index and suspended sediment concentration in water, and based on the preset mangrove-suspended sediment stress coupling model, it analyzes the stress degree of suspended sediment in water on mangrove growth and obtains mangrove growth status change parameters.

[0183] Stress Level Classification Module 7: Used to classify the stress level of the target monitoring area according to the spatial statistical index and the mangrove growth status change parameters, based on the preset stress level classification rules;

[0184] Early warning instruction transmission module 8: is used to generate an early warning instruction corresponding to the stress level based on the stress level classification result of the target monitoring area, and transmit the early warning instruction to the mangrove growth early warning device.

[0185] It should be noted that the data obtained by the mangrove growth monitoring system provided in this application when implementing a mangrove growth monitoring method are stored in the system's memory in a one-to-one correspondence. When relevant calculations are required, the data required for the calculation can be directly obtained from the memory.

[0186] It should also be noted that the mangrove growth monitoring system provided in the above embodiments, when implementing a mangrove growth monitoring method, is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the mangrove growth monitoring system provided in the above embodiments and the mangrove growth monitoring method in Embodiment 1 belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0187] This application is not limited to the above-described embodiments. If any modifications or variations to this application do not depart from the spirit and scope of this application, and if such modifications and variations fall within the scope of the claims and equivalent technologies of this application, then this application also intends to include such modifications and variations.

Claims

1. A method for monitoring mangrove growth, characterized in that, Includes the following steps: Acquire multi-temporal remote sensing images of the target monitoring area and extract the spectral feature index of the multi-temporal remote sensing images, wherein the target monitoring area includes mangrove areas and non-mangrove areas; Based on the spectral feature index and a preset mangrove classification model, the multi-temporal remote sensing images are classified to generate multi-temporal remote sensing images of mangroves that only include the mangrove area. Based on the spectral characteristic indices of the multi-temporal remote sensing images of mangroves, and using a preset leaf area index model, the canopy coverage of mangroves is analyzed to obtain the leaf area index. The sediment-sensitive reflectance in the multi-temporal remote sensing images of the mangroves is extracted. Based on the preset sediment content inversion model, the suspended sediment content in the water body is inverted to obtain the suspended sediment concentration inversion result. The sediment-sensitive reflectance is the remote sensing reflectance of the bands in the multi-temporal remote sensing images of the mangroves that are sensitive to suspended sediment in the water body. Spatial statistical analysis was performed on the inversion results of the leaf area index and suspended sediment concentration in water to obtain the spatial statistical index; Based on the leaf area index and the inversion results of suspended sediment concentration in water, and based on the preset mangrove-suspended sediment stress coupling model, the stress degree of suspended sediment in water on mangrove growth is analyzed, and parameters of mangrove growth status change are obtained. Based on the spatial statistical index and the mangrove growth status change parameters, and according to the preset stress level classification rules, the target monitoring area is classified into stress levels. Based on the stress level classification results of the target monitoring area, an early warning instruction corresponding to the stress level is generated and transmitted to the mangrove growth early warning device; The construction of the mangrove-water suspended sediment stress coupling model includes: The leaf area index and suspended sediment concentration in water body at multiple historical time points were obtained from historical multi-temporal remote sensing images of mangroves. Obtain the mangrove canopy width, soil moisture, and temperature at each of the historical time points in the mangrove region; Based on the inversion results of mangrove canopy width, leaf area index, suspended sediment concentration in water, soil moisture, and temperature, a mangrove-water suspended sediment stress coupling model was constructed through linear regression, and its expression is as follows: In the formula, Nm is a parameter representing the change in mangrove canopy width or mangrove growth status. The results of the inversion of suspended sediment concentration in the water body are as follows. The leaf area index is mentioned above. The soil moisture, The temperature is [temperature value]. , and b1, b2, and b3 are the weighting coefficients for the leaf area index, soil moisture, and temperature, respectively, and b4 is the third empirical coefficient.

2. The mangrove growth monitoring method according to claim 1, characterized in that, Constructing the sediment content inversion model includes: Acquire historical multi-temporal remote sensing images of mangrove forests in the mangrove area and measured concentrations of suspended sediment in water bodies during the same period; Based on the sediment-sensitive reflectance in the historical mangrove multi-temporal remote sensing images, and based on the preset sediment-sensitive reflectance-optical parameter coupling model, the absorption coefficient of suspended sediment in water and the backscattering coefficient of suspended sediment in water are obtained. Based on the sediment-sensitive reflectance in the historical mangrove multi-temporal remote sensing images, the suspended sediment index of water body is obtained based on the calculation formula of the suspended sediment index of water body. Based on the measured concentration of suspended sediment in the water body, the absorption coefficient of suspended sediment in the water body, the backscattering coefficient of suspended sediment in the water body, and the suspended sediment index in the water body, a sediment content inversion model is constructed through linear regression: In the formula, This refers to the measured concentration of suspended sediment in the water body or the inversion result of the suspended sediment concentration in the water body. The suspended sediment index of the water body. It is a wavelength of The following is the absorption coefficient of suspended sediment in the water body. It is a wavelength of The backscattering coefficient of suspended sediment in the water body is as follows. , and These are the weighting coefficients for the suspended sediment index, suspended sediment absorption coefficient, and suspended sediment backscattering coefficient of the water body, respectively. This is the second empirical coefficient.

3. The mangrove growth monitoring method according to claim 2, characterized in that, The construction of the sediment-sensitive reflectivity-optical parameter coupling model includes: The water radiation field is simplified into upward and downward radiative flows, and a set of approximate two-flow radiative transfer equations is established: In the formula, It is an upward radiative flow with a water depth of z and a wavelength of λ. It is a downward radiative flow with a water depth of z and a wavelength of λ. It is the upward diffuse attenuation coefficient for a water depth of z and a wavelength of λ. It is the downward diffusion attenuation coefficient for a water depth of z and a wavelength of λ. It is an upward source function with a water depth of z and a wavelength of λ. It is a downward source function with a water depth of z and a wavelength of λ; When the medium is homogeneous, the two-stream approximate radiative transfer equations are simplified to obtain the simplified two-stream approximate radiative transfer equations: In the formula, The total absorption coefficient is 1. , The preset wavelength is The pure water absorption coefficient at the following values, It is a wavelength of The absorption coefficient of suspended sediment in the water body. The total backscattering coefficient is... + , The preset wavelength is The backscattering coefficient of pure water at this temperature. It is a wavelength of Backscattering coefficient of suspended sediment in the water body; By simultaneously applying the simplified two-stream approximate radiative transfer equations, and based on the integral factor method and preset boundary conditions, the sediment-sensitive reflectivity-optical parameter coupled model is established, and its expression is: In the formula, It is a wavelength of The reflectivity of mud and sand , , The wavelength attenuation index is the preset sediment absorption coefficient. The wavelength attenuation index is the preset backscattering coefficient of sediment. is the proportionality constant of the sediment absorption coefficient. It is the proportionality constant of the sediment backscattering coefficient.

4. The mangrove growth monitoring method according to claim 1, characterized in that, The spatial statistical index includes the leaf area index and the Pearson correlation coefficient of the inversion results of suspended sediment concentration in water body; The spatial statistical analysis of the leaf area index and suspended sediment concentration inversion results yields spatial statistical indices, including: Random sampling was performed on the multi-temporal remote sensing images of the mangrove forest to obtain observation datasets at different sampling points. The observation datasets at any sampling point include the leaf area index and suspended sediment concentration inversion results at the same location and time. Based on the observed dataset, and using the Pearson correlation coefficient calculation formula, the Pearson correlation coefficients for the leaf area index and suspended sediment concentration in water inversion results are obtained as follows: In the formula, The Pearson correlation coefficient is the result of the inversion of leaf area index and suspended sediment concentration in water. The leaf area index is the value of the i-th observation dataset. The suspended sediment content in the water body in the i-th observation dataset. The leaf area index is the average value of the observed datasets. is the average value of suspended sediment content in the water body for each of the aforementioned observation datasets, and n is the number of the aforementioned observation datasets.

5. The mangrove growth monitoring method according to claim 4, characterized in that, The spatial statistical index also includes the spatial autocorrelation index of the leaf area index and the inversion result of suspended sediment concentration in water body; The spatial statistical analysis of the leaf area index and suspended sediment concentration inversion results to obtain spatial statistical indices also includes: Based on the observed dataset, a continuous spatial distribution surface of the leaf area index and suspended sediment concentration in water is generated using the inverse distance weighted interpolation method. The interpolation of the leaf area index and suspended sediment concentration in water in several spatial cells is then obtained, using the following formula: In the formula, This is the interpolation of the leaf area index or suspended sediment concentration in water body in spatial cell P. The leaf area index or suspended sediment content in the water body in the i-th observation dataset. Let be the distance from the acquisition point corresponding to the i-th observation dataset to the spatial unit P. = , and Let be the coordinates of the collection point corresponding to the i-th observation dataset. and Let P be the coordinates of the spatial unit P; Based on the spatial cell interpolation corresponding to the inversion results of leaf area index and suspended sediment concentration in water, a bivariate spatial autocorrelation analysis is performed on the inversion results of leaf area index and suspended sediment concentration in water to obtain the spatial autocorrelation index of the inversion results of leaf area index and suspended sediment concentration in water. The specific formula is as follows: In the formula, The spatial autocorrelation index is given. The interpolation of the leaf area index in the i-th spatial unit is given. The value is the interpolation of the suspended sediment content in the water body in the j-th spatial unit. This is the average of the interpolated leaf area index across all the aforementioned spatial units. The value represents the average interpolated suspended sediment content in the water body across all the aforementioned spatial units, where m is the number of the spatial units. This is a preset spatial weight matrix.

6. The mangrove growth monitoring method according to claim 4, characterized in that, The step of classifying the target monitoring area into stress levels based on the spatial statistical index and mangrove growth status change parameters, according to a preset stress level classification rule, includes: Based on the analytic hierarchy process, the spatial statistical index and mangrove growth status change parameters are divided into several ranges of variation. Based on the aforementioned ranges of change, the target monitoring area is classified into different levels of coercion.

7. The mangrove growth monitoring method according to claim 2, characterized in that, The spectral characteristic indices include at least: the normalized vegetation index; Constructing the leaf area index model includes: Acquire several multi-temporal remote sensing images of the historical mangrove forests and measured leaf area index values ​​of the same period, wherein the multi-temporal remote sensing images of the historical mangrove forests include wide near-infrared band and red band. Based on the remote sensing reflectance of the near-infrared and red bands, the normalized vegetation index is obtained using the normalized vegetation index calculation formula. Based on the measured leaf area index and the normalized vegetation index, an empirical inversion model was established through linear regression to obtain the leaf area index model, the expression of which is: In the formula, The leaf area index, The normalized vegetation index is... The weighting coefficient of the normalized vegetation index, b1 is the first empirical coefficient.

8. The mangrove growth monitoring method according to claim 7, characterized in that, The spectral characteristic indices also include: water body index and mangrove extraction index; Constructing the mangrove classification model includes: Acquire historical multi-temporal remote sensing images of several target monitoring areas, wherein the historical mangrove multi-temporal remote sensing images include: green light band, shortwave infrared band, red edge band, wide near-infrared band and narrow near-infrared band; The historical multi-temporal remote sensing images are labeled with mangrove areas and non-mangrove areas to obtain standard historical multi-temporal remote sensing images; Based on the remote sensing reflectance of the green light band, shortwave infrared band, red edge band, wide near-infrared band and narrow near-infrared band, the water body index and mangrove extraction index are calculated according to the preset water body index calculation formula and mangrove extraction index calculation formula. Normalized vegetation index, water body index and mangrove extraction index are used as input features, and standard historical multi-temporal remote sensing images are used as output features to construct sample data. The sample data is then divided into training sample dataset and test sample dataset in an 8:2 ratio. Based on the input and output features of the training sample dataset, the mangrove classification model is constructed using a machine learning algorithm. Based on the input features of the test sample dataset and the mangrove classification model, the test results of the multi-temporal remote sensing images of mangroves corresponding to the test sample dataset are obtained. By statistically analyzing the number of correctly classified mangrove areas and non-mangrove areas in the test results of the multi-temporal remote sensing images of mangroves, the accuracy of the mangrove classification model is evaluated, and the accuracy evaluation result of the mangrove classification model is obtained. When the accuracy evaluation result of the mangrove classification model is lower than the preset accuracy threshold of the mangrove classification model, the hyperparameters of the mangrove classification model are adjusted using an optimization algorithm.

9. A mangrove growth monitoring system, characterized in that, include: Multi-temporal remote sensing image acquisition module: used to acquire multi-temporal remote sensing images of the target monitoring area and extract the spectral feature index of the multi-temporal remote sensing images, wherein the target monitoring area includes mangrove areas and non-mangrove areas; Mangrove classification module: used to classify the multi-temporal remote sensing images based on the spectral feature index and a preset mangrove classification model, and generate multi-temporal remote sensing images of mangroves that only include the mangrove area; Leaf area index calculation module: used to analyze the canopy coverage of mangroves based on the spectral characteristic indices of the multi-temporal remote sensing images of mangroves and a preset leaf area index model to obtain the leaf area index; Water body suspended sediment concentration inversion module: used to extract the sediment-sensitive reflectance in the multi-temporal remote sensing image of the mangrove forest, and based on the preset sediment content inversion model, to invert the suspended sediment content in the water body and obtain the suspended sediment concentration inversion result. The sediment-sensitive reflectance is the remote sensing reflectance of the bands in the multi-temporal remote sensing image of the mangrove forest that are sensitive to suspended sediment in the water body. Spatial statistical index calculation module: used to perform spatial statistical analysis on the inversion results of the leaf area index and suspended sediment concentration in water body to obtain spatial statistical index; The mangrove growth status change parameter calculation module is used to analyze the stress degree of suspended sediment on mangrove growth based on the leaf area index and suspended sediment concentration inversion results, and on a preset mangrove-suspended sediment stress coupling model, to obtain mangrove growth status change parameters. The construction of the mangrove-suspended sediment stress coupling model includes: obtaining the leaf area index and suspended sediment concentration inversion results at multiple historical time points based on historical multi-temporal remote sensing images of mangroves; obtaining the mangrove canopy width, soil moisture, and temperature at each historical time point in the mangrove area; and constructing the mangrove-suspended sediment stress coupling model through linear regression based on the mangrove canopy width, leaf area index, suspended sediment concentration inversion results, soil moisture, and temperature. The expression of the mangrove-suspended sediment stress coupling model is as follows: In the formula, Nm is a parameter representing the change in mangrove canopy width or mangrove growth status. The results of the inversion of suspended sediment concentration in the water body are as follows. The leaf area index is mentioned above. The soil moisture, The temperature is [temperature value]. , and b1, b2, and b3 are the weighting coefficients for the leaf area index, soil moisture, and temperature, respectively, and b3 is the third empirical coefficient. Stress Level Classification Module: This module is used to classify the stress level of the target monitoring area based on the spatial statistical index and mangrove growth status change parameters, according to a preset stress level classification rule. Early warning instruction transmission module: used to generate early warning instructions corresponding to the stress level based on the stress level classification results of the target monitoring area, and transmit the early warning instructions to the mangrove growth early warning device.

Images