A method and system for quickly identifying a mangrove forest ecological restoration area

Abstract

The present application relates to the field of remote sensing images, and provides a kind of mangrove ecological restoration area fast identification method and system, by obtaining the hyperspectral image of mangrove area and being recorded as first multi-source image, the grid division is carried out to mangrove area, obtain mangrove grid distribution, according to the first multi-source image, the vegetation information of mangrove grid distribution is counted, according to vegetation information, locate the stress unit and mark as ecological restoration area.The method can realize the fast positioning of repair area, the hyperspectral information of different regions is segmented using grid, and the stress unit is identified by combining the vegetation information difference between grids, so as to ensure that the repair work remains high pertinence, avoid waste of repair resources, provide key intervention target points for large-scale repair engineering in complex environment, and fully improve the repair efficiency of mangrove ecological damaged area.

Description

Technical Field

[0001] This invention relates to the field of remote sensing imagery, and in particular to a rapid identification method for mangrove ecological restoration areas. Background Technology

[0002] Mangroves are rare ecosystems unique to tropical and subtropical coastal zones, possessing irreplaceable ecological value in mitigating storm surges, sequestering and storing carbon, and maintaining biodiversity. However, due to human activities and environmental changes, mangrove belts generally face the risk of degradation, making ecological restoration an urgent need for sustainable coastal development. Traditional mangrove monitoring methods mainly rely on manual field surveys, which are limited by the complex topography and dynamic hydrological conditions of the intertidal zone, resulting in low efficiency, high cost, and limited spatial coverage, making it difficult to meet the needs of accurate identification and dynamic assessment for large-scale restoration projects.

[0003] In recent years, remote sensing technology has been increasingly applied to mangrove monitoring. However, conventional multispectral remote sensing, due to insufficient band resolution, struggles to effectively capture subtle spectral changes during mangrove degradation, such as leaf water loss and canopy structure damage—key ecological indicators. Furthermore, existing vegetation indices are mostly designed for terrestrial vegetation and lack specificity for mangroves' unique waterlogging environment and salt stress adaptation mechanisms, leading to insufficient accuracy in identifying degraded areas. While hyperspectral remote sensing possesses nanometer-level spectral resolution capabilities, revealing deeper information about vegetation physiological states, its application in the complex environment of the land-sea transition zone still faces technical bottlenecks, including difficulties in mixed pixel decomposition and poor comparability of time-series data under tidal interference. Therefore, there is an urgent need to develop a rapid identification method that integrates the ecological characteristics of mangroves with the advantages of hyperspectral data to provide technical support for the precise location and scientific management of ecological restoration areas. Summary of the Invention

[0004] The purpose of this invention is to propose a rapid identification method and system for mangrove ecological restoration areas, in order to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.

[0005] This invention provides a rapid identification method and system for mangrove ecological restoration areas. The method involves acquiring hyperspectral images of mangrove areas and recording them as the first multi-source image. The mangrove area is then divided into grids to obtain the mangrove grid distribution. Based on the first multi-source image, vegetation information within the mangrove grid distribution is statistically analyzed. Based on this vegetation information, stress units are located and marked as ecological restoration areas. This method enables rapid location of restoration areas. By segmenting hyperspectral information from different regions using a grid and combining the differences in vegetation information between grids, stress units are identified. This ensures highly targeted restoration work, avoids wasting restoration resources, provides key intervention targets for large-scale restoration projects in complex environments, and significantly improves the restoration efficiency of damaged mangrove ecosystems.

[0006] To achieve the above objectives, according to one aspect of the present invention, a method for rapid identification of mangrove ecological restoration areas is provided, the method comprising the following steps:

[0007] Acquire a hyperspectral image of the mangrove region and record it as the first multi-source image;

[0008] The mangrove area is divided into grids to obtain the mangrove grid distribution;

[0009] Based on the first multi-source image, statistical vegetation information of the mangrove grid distribution was obtained;

[0010] Based on vegetation information, stress units were located and marked as ecological restoration areas.

[0011] Preferably, the method for acquiring hyperspectral images of the mangrove area and recording them as the first multi-source image is as follows: acquiring hyperspectral images of the mangrove area by using a satellite or drone equipped with a hyperspectral imager, recording the acquired hyperspectral images as the first multi-source image, and sending them to the cloud.

[0012] Furthermore, the method for dividing the mangrove area into grids to form a mangrove grid distribution is as follows: import the vector data of the mangrove area into professional geographic information software, and generate the mangrove grid distribution using the grid division tool in the software; wherein, the shape type of the grid division is selected as hexagonal.

[0013] Furthermore, the method for statistically analyzing the vegetation information of the mangrove grid distribution based on the first multi-source image is as follows: the mangrove grid distribution consists of a total of N grids. The mangrove grid distribution is mapped onto the first multi-source image. Based on the hyperspectral data of the first multi-source image, the near-infrared band value and vegetation index of each grid (in the N grids) are statistically analyzed. The near-infrared band value and vegetation index of the N grids are recorded as the vegetation information of the mangrove grid distribution.

[0014] Furthermore, the method for calculating the near-infrared band value of each grid based on the hyperspectral data of the first multi-source image is as follows: the average value of the corresponding values ​​(i.e., reflectance, in nm) of all pixels in each grid in the near-infrared band is recorded as the near-infrared band value of each grid; or, the sum of the corresponding values ​​of all pixels in each grid in the near-infrared band is recorded as the near-infrared band value of each grid.

[0015] The corresponding values ​​of the pixels in the near-infrared band are obtained from the spectral reflectance characteristics in the hyperspectral data of the first multi-source image.

[0016] Furthermore, the vegetation index of each grid is calculated based on the hyperspectral data of the first multi-source image. The vegetation index refers to the Normalized Difference Vegetation Index (NDVI) or the Mangrove Vegetation Index (MVI). The band reflectance used to calculate the vegetation index of the grid refers to the sum of the corresponding values ​​of all pixels in each band within the grid.

[0017] Furthermore, based on vegetation information, the method for locating stress units is as follows: for N grids in the mangrove grid distribution, each grid corresponds to a unique stress factor. Grids with stress factors lower than the stress mean are marked as stress units. The stress mean is the average of the stress factors of the N grids.

[0018] The stress factor corresponding to the grid is calculated as follows: let cor(u) represent any grid in N grids, and let corF(u) represent the stress factor corresponding to cor(u). corF(u) = IndexV(u) × (NIR(u) ÷ S1(u)), where IndexV(u) represents the vegetation index of cor(u), NIR(u) represents the near-infrared band value of cor(u), and S1(u) represents the sum of the near-infrared band values ​​of all grids in N grids whose vegetation index is less than or equal to IndexV(u).

[0019] The beneficial effects of this step are as follows: Mangrove degradation often exhibits spatial heterogeneity. Identifying specific restoration target areas can improve the restoration efficiency of functions such as mangrove bank protection and biological habitats. The method in this step uses hyperspectral satellite remote sensing combined with image extraction technology to obtain the vegetation index and near-infrared band values ​​of each grid area in the mangrove region. By using stress factors, grids with near-infrared reflectance significantly lower than the overall near-infrared level of the vegetation area are selected as stress units, thereby more accurately identifying ecological restoration areas and avoiding inefficient restoration.

[0020] Because the vegetation ecology within the mangrove area is highly interconnected, factors such as hydrological conditions, salinity, and vegetation cover will influence each other spatially. Considering the changes in vegetation information between grids can better reflect the degree of ecological damage in different areas.

[0021] Preferably, the method for locating stress units based on vegetation information is as follows:

[0022] Let cor(j) be the j-th grid in N grids, and let corB(j) be the vegetation index of cor(j). If there are grids with a vegetation index less than corB(j) in the four neighborhoods of cor(j) (i.e., the four adjacent grids located in the horizontal and vertical directions of cor(x)), then the stress path is generated by the first algorithm.

[0023] Cor(j) is traversed from j=1 to j=N to obtain all stress paths; if any one of the N grids appears on two different stress paths at the same time, then that grid is marked as a stress cell.

[0024] The beneficial effects of this step are as follows: By introducing the changes in vegetation index differences between grids, stress paths can be generated using degraded grids, avoiding misidentification caused by the screening method of normalization calculation based on single grids and the entire grid. During the generation of stress paths, stress paths are continuously grown radially. If the second stress factor of the degraded grid (equivalent to the numerical increase of its vegetation index) is still higher than that of its neighboring grids, it indicates that the spatial transmission effect of vegetation activity decline in this area has not been interrupted. When the growth of stress paths stops, the vegetation activity of the neighboring grids of the grid at the end of the path is much higher than that of the grid at the end of the path itself (the increased vegetation index, i.e., the second stress factor, is still less than the vegetation index of the neighboring grids). Therefore, this method can reduce the limitations of isolated area analysis in traditional mangrove remote sensing image recognition. By locating the overlapping units of stress paths, ecological restoration areas eroded by multi-directional degradation pressure can be identified, realizing the long-term maintenance of mangrove ecosystem stability through restoration projects.

[0025] Furthermore, the first algorithm is as follows:

[0026] S1. Select the grid with the lowest vegetation index among the four neighbors of cor(j) and denote it as the degraded grid. Take the direction of cor(j) pointing to the degraded grid as the radial direction. Create an empty queue Que(j) (to store continuously updated degraded grids). Add cor(j) to the queue Que(j) and go to S2.

[0027] S2, calculate the second stress factor SFG of the degraded grid, add the degraded grid to the queue Que(j), if the value of SFG is greater than the vegetation index of the adjacent grid of the degraded grid, mark the adjacent grid of the degraded grid as a new degraded grid and re-execute S2; if the value of SFG is less than or equal to the vegetation index of the adjacent grid of the degraded grid, go to S3.

[0028] S3, the path consisting of all grids in queue Que(j) is taken as the stress path;

[0029] In this context, the adjacent grid of a degraded grid refers to the grid adjacent to the degraded grid in the radial direction; the SFG calculation method is: SFG=IndexV(Deg)+IndexV(Qend)×T0, where IndexV(Deg) refers to the vegetation index of the degraded grid, IndexV(Qend) refers to the vegetation index of the last grid in the queue Que(j), and T0 refers to the value obtained by dividing the smaller value of NIR(Deg) and NIR(Que(j)) by the larger value of NIR(Deg) and NIR(Que(j)); NIR(Deg) and NIR(Que(j)) represent the near-infrared band value of the degraded grid and the near-infrared band value of the last grid in the queue Que(j), respectively.

[0030] Furthermore, the method for locating stress units and marking them as ecological restoration areas is as follows: stress units are highlighted in professional geographic information software, and ecological restoration areas are marked in satellite images of mangrove areas according to the location of stress units in the mangrove grid distribution.

[0031] This invention also provides a rapid identification system for mangrove ecological restoration areas. The rapid identification system for mangrove ecological restoration areas includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a rapid identification method for mangrove ecological restoration areas. The rapid identification system for mangrove ecological restoration areas can run on computing devices such as desktop computers, laptops, mobile phones, handheld phones, tablets, PDAs, and cloud data centers. The runnable system may include, but is not limited to, processors, memory, and server clusters. The processor executes the computer program within the following system units:

[0032] The image acquisition unit is used to acquire a hyperspectral image of the mangrove area and record it as the first multi-source image;

[0033] Grid division unit is used to divide the mangrove area into grids to obtain the mangrove grid distribution;

[0034] The information statistics unit is used to statistically analyze the vegetation information of the mangrove grid distribution based on the first multi-source image;

[0035] Regional marker units are used to locate stress units and mark them as ecological restoration areas based on vegetation information.

[0036] The beneficial effects of the present invention are as follows: the method can achieve rapid positioning of the restoration area, segment the hyperspectral information of different areas using a grid, and identify stress units by combining the differences in vegetation information between grids, thereby ensuring that the restoration work remains highly targeted, avoiding waste of restoration resources, providing key intervention targets for large-scale restoration projects in complex environments, and fully improving the restoration efficiency of mangrove ecologically damaged areas. Attached Figure Description

[0037] The above and other features of the present invention will become more apparent from the detailed description of the embodiments shown in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar elements. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. In the drawings:

[0038] Figure 1 The diagram shows a flowchart of a method for rapid identification of mangrove ecological restoration areas;

[0039] Figure 2 The diagram shows the system structure of a rapid identification system for mangrove ecological restoration areas. Detailed Implementation

[0040] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with the embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0041] In the description of this invention, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0042] like Figure 1 The diagram shown is a flowchart of a rapid identification method for mangrove ecological restoration areas according to the present invention. The following is a summary of the method. Figure 1 This paper describes a rapid identification method for mangrove ecological restoration areas according to an embodiment of the present invention.

[0043] This invention proposes a rapid identification method for mangrove ecological restoration areas, the method comprising the following steps:

[0044] Acquire a hyperspectral image of the mangrove region and record it as the first multi-source image;

[0045] The mangrove area is divided into grids to obtain the mangrove grid distribution;

[0046] Based on the first multi-source image, statistical analysis was conducted on the vegetation information of the mangrove grid distribution.

[0047] Based on vegetation information, stress units were located and marked as ecological restoration areas.

[0048] Specifically, the method for acquiring hyperspectral images of mangrove areas and recording them as the first multi-source images is as follows: hyperspectral images of mangrove areas are acquired by satellites or drones equipped with hyperspectral imagers, the acquired hyperspectral images are recorded as the first multi-source images and sent to the cloud.

[0049] Furthermore, the method for dividing the mangrove area into grids to form a mangrove grid distribution is as follows: import the vector data of the mangrove area into professional geographic information software, and generate the mangrove grid distribution using the grid division tool in the software; wherein, the shape type of the grid division is selected as hexagonal.

[0050] Specifically, the method for obtaining vector data of mangrove areas is as follows:

[0051] Specifically, the professional geographic information software is ArcGIS, and the grid generation tool is Generate Tessellation.

[0052] Furthermore, the method for statistically analyzing the vegetation information of the mangrove grid distribution based on the first multi-source image is as follows: the mangrove grid distribution consists of a total of N grids. The mangrove grid distribution is mapped onto the first multi-source image. Based on the hyperspectral data of the first multi-source image, the near-infrared band value and vegetation index of each grid (in the N grids) are statistically analyzed. The near-infrared band value and vegetation index of the N grids are recorded as the vegetation information of the mangrove grid distribution.

[0053] By extracting images from high-resolution localized images of mangrove grids, hyperspectral data of vegetation within the region can be accurately obtained.

[0054] The mangrove grid distribution is mapped onto the first multi-source image. The mapping is defined as spatially corresponding the mangrove grid distribution to the pixel region in the hyperspectral image. The range of each grid has a corresponding region in the pixel coordinates of the hyperspectral image, so that the near-infrared band value and vegetation index can be extracted from the hyperspectral image based on the value of the pixel in the near-infrared band of each grid.

[0055] Furthermore, the method for calculating the near-infrared band value of each grid based on the hyperspectral data of the first multi-source image is as follows: the average value of the corresponding values ​​(i.e., reflectance, in nm) of all pixels in each grid in the near-infrared band is recorded as the near-infrared band value of each grid; or, the sum of the corresponding values ​​of all pixels in each grid in the near-infrared band is recorded as the near-infrared band value of each grid.

[0056] The corresponding values ​​of the pixels in the near-infrared band are obtained from the spectral reflectance characteristics in the hyperspectral data of the first multi-source image.

[0057] Furthermore, the vegetation index of each grid is calculated based on the hyperspectral data of the first multi-source image. The vegetation index refers to the Normalized Difference Vegetation Index (NDVI) or the Mangrove Vegetation Index (MVI). The band reflectance used to calculate the vegetation index of the grid refers to the sum of the corresponding values ​​of all pixels in each band within the grid.

[0058] Specifically, for any given grid, let NDVI be the vegetation index of that grid. The formula for calculating NDVI is: NDVI = NIR - RED / (NIR + RED), where NIR represents the sum of the corresponding values ​​of all pixels in the grid in the near-infrared band, and RED represents the sum of the corresponding values ​​of all pixels in the grid in the red band.

[0059] Furthermore, based on vegetation information, the method for locating stress units is as follows: for N grids in the mangrove grid distribution, each grid corresponds to a unique stress factor. Grids with stress factors lower than the stress mean are marked as stress units. The stress mean is the average of the stress factors of the N grids.

[0060] The stress factor corresponding to the grid is calculated as follows: let cor(u) represent any grid in N grids, and let corF(u) represent the stress factor corresponding to cor(u). corF(u) = IndexV(u) × (NIR(u) ÷ S1(u)), where IndexV(u) represents the vegetation index of cor(u), NIR(u) represents the near-infrared band value of cor(u), and S1(u) represents the sum of the near-infrared band values ​​of all grids in N grids whose vegetation index is less than or equal to IndexV(u).

[0061] Because the vegetation ecology within the mangrove area is highly interconnected, factors such as hydrological conditions, salinity, and vegetation cover will influence each other spatially. Considering the changes in vegetation information between grids can better reflect the degree of ecological damage in different areas.

[0062] Preferably, the method for locating stress units based on vegetation information is as follows:

[0063] Let cor(j) be the j-th grid in N grids, where j is the index, j=1,2,…,N; take corB(j) as the vegetation index of cor(j). If there are grids with a vegetation index less than corB(j) in the four neighborhoods of cor(j) (i.e., the four adjacent grids located in the horizontal and vertical directions of cor(x)), then the stress path is generated by the first algorithm.

[0064] Cor(j) is traversed from j=1 to j=N to obtain all stress paths; if any one of the N grids appears on two different stress paths at the same time, then that grid is marked as a stress cell.

[0065] Furthermore, the first algorithm is as follows:

[0066] S1. Select the grid with the lowest vegetation index in the four neighborhoods of cor(j) and denote it as the degraded grid. Take the direction of cor(j) pointing to the degraded grid as the radial direction. Create an empty queue Que(j) and add cor(j) to the queue Que(j). Go to S2.

[0067] S2, calculate the second stress factor SFG of the degraded grid, add the degraded grid to the queue Que(j), if the value of SFG is greater than the vegetation index of the adjacent grid of the degraded grid, mark the adjacent grid of the degraded grid as a new degraded grid and re-execute S2; if the value of SFG is less than or equal to the vegetation index of the adjacent grid of the degraded grid, go to S3.

[0068] S3, the path consisting of all grids in queue Que(j) is taken as the stress path;

[0069] In this context, the adjacent grid of a degraded grid refers to the grid adjacent to the degraded grid in the radial direction; the SFG calculation method is: SFG=IndexV(Deg)+IndexV(Qend)×T0, where IndexV(Deg) refers to the vegetation index of the degraded grid, IndexV(Qend) refers to the vegetation index of the last grid in the queue Que(j), and T0 refers to the value obtained by dividing the smaller value of NIR(Deg) and NIR(Que(j)) by the larger value of NIR(Deg) and NIR(Que(j)); NIR(Deg) and NIR(Que(j)) represent the near-infrared band value of the degraded grid and the near-infrared band value of the last grid in the queue Que(j), respectively.

[0070] Furthermore, the method for locating stress units and marking them as ecological restoration areas is as follows: stress units are highlighted in professional geographic information software, and ecological restoration areas are marked in satellite images of mangrove areas according to the location of stress units in the mangrove grid distribution.

[0071] The rapid identification system for mangrove ecological restoration areas includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the above-described embodiment of the rapid identification method for mangrove ecological restoration areas. The rapid identification system for mangrove ecological restoration areas can run on computing devices such as desktop computers, laptops, mobile phones, handheld phones, tablets, PDAs, and cloud data centers. The running system may include, but is not limited to, processors, memory, and server clusters.

[0072] An embodiment of the present invention provides a rapid identification system for mangrove ecological restoration areas, such as... Figure 2 As shown, this embodiment of a rapid identification system for mangrove ecological restoration areas includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps described in the above embodiment of a rapid identification method for mangrove ecological restoration areas. The processor executes the computer program within the following system units:

[0073] An image acquisition unit is used to acquire a hyperspectral image of the mangrove area and record it as the first multi-source image;

[0074] Grid division unit is used to divide the mangrove area into grids to obtain the mangrove grid distribution;

[0075] The information statistics unit is used to statistically analyze the vegetation information of the mangrove grid distribution based on the first multi-source image;

[0076] Regional marker units are used to locate stress units and mark them as ecological restoration areas based on vegetation information.

[0077] The rapid identification system for mangrove ecological restoration areas described above can run on computing devices such as desktop computers, laptops, handheld computers, and cloud data centers. The rapid identification system for mangrove ecological restoration areas includes, but is not limited to, a processor and a memory. Those skilled in the art will understand that the example described is merely an illustration of a rapid identification method and system for mangrove ecological restoration areas and does not constitute a limitation on such a method and system. It may include more or fewer components, or combine certain components, or use different components. For example, the rapid identification system for mangrove ecological restoration areas may also include input / output devices, network access devices, buses, etc.

[0078] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete component gate circuits, transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the rapid identification system for mangrove ecological restoration areas, connecting various sub-regions of the system via various interfaces and lines.

[0079] The memory can be used to store the computer program and / or modules. The processor, by running or executing the computer program and / or modules stored in the memory, and by calling the data stored in the memory, realizes various functions of the rapid identification method and system for mangrove ecological restoration areas. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0080] This invention provides a rapid identification method and system for mangrove ecological restoration areas. The method involves acquiring hyperspectral images of mangrove areas and recording them as first multi-source images. The mangrove areas are then divided into grids to obtain a mangrove grid distribution. Based on the first multi-source images, vegetation information within the mangrove grid distribution is statistically analyzed. Based on this vegetation information, stress units are located and marked as ecological restoration areas. This method enables rapid location of restoration areas. By segmenting hyperspectral information from different areas using a grid and combining the differences in vegetation information between grids, stress units are identified. This ensures highly targeted restoration work, avoids wasting restoration resources, provides key intervention targets for large-scale restoration projects in complex environments, and significantly improves the restoration efficiency of damaged mangrove ecosystems. Although the description of this invention is quite detailed and particularly focuses on several embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiments, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors for the purpose of providing a useful description, and non-substantial modifications to the invention that are not currently foreseen may still represent equivalent modifications.

Claims

1. A rapid identification method for mangrove ecological restoration areas, characterized in that, The method includes the following steps: Acquire a hyperspectral image of the mangrove region and record it as the first multi-source image; The mangrove area is divided into grids to obtain the mangrove grid distribution; Based on the first multi-source image, statistical analysis was conducted on the vegetation information of the mangrove grid distribution. Based on vegetation information, stress units were located and marked as ecological restoration areas; Based on vegetation information, the method for locating stress units is as follows: For N grids in the mangrove grid distribution, each grid corresponds to a unique stress factor. Grids with stress factors lower than the stress mean are marked as stress units. The stress mean is the average of the stress factors of the N grids. The stress factor corresponding to the grid is calculated as follows: Let cor(u) represent any grid in the N grids, and let corF(u) represent the stress factor corresponding to cor(u). corF(u) = IndexV(u) × (NIR(u) ÷ S1(u)), where IndexV(u) represents the vegetation index of cor(u), NIR(u) represents the near-infrared band value of cor(u), and S1(u) represents the sum of the near-infrared band values ​​of all grids in the N grids whose vegetation indices are less than or equal to IndexV(u).

2. The method for rapid identification of mangrove ecological restoration areas according to claim 1, characterized in that, The specific method for dividing the mangrove area into grids to form a mangrove grid distribution is as follows: import the vector data of the mangrove area into professional geographic information software, and generate the mangrove grid distribution using the grid division tool in the software; wherein, the shape type of the grid division is selected as hexagonal.

3. The method for rapid identification of mangrove ecological restoration areas according to claim 1, characterized in that, The method for statistically analyzing the vegetation information of the mangrove grid distribution based on the first multi-source image is as follows: the mangrove grid distribution consists of N grids in total. The mangrove grid distribution is mapped onto the first multi-source image. The near-infrared band value and vegetation index of each grid are statistically analyzed based on the hyperspectral data of the first multi-source image. The near-infrared band value and vegetation index of the N grids are recorded as the vegetation information of the mangrove grid distribution.

4. The method for rapid identification of mangrove ecological restoration areas according to claim 3, characterized in that, The method for calculating the near-infrared band value of each grid based on the hyperspectral data of the first multi-source image is as follows: the average value of the corresponding values ​​of all pixels in the near-infrared band within each grid is recorded as the near-infrared band value of each grid; or, the sum of the corresponding values ​​of all pixels in the near-infrared band within each grid is recorded as the near-infrared band value of each grid.

5. The method for rapid identification of mangrove ecological restoration areas according to claim 3, characterized in that, The vegetation index of each grid is calculated based on the hyperspectral data of the first multi-source image. The vegetation index refers to the normalized vegetation index or the mangrove vegetation index. The band reflectance used to calculate the vegetation index of the grid refers to the sum of the corresponding values ​​of all pixels in each band within the grid.

6. The method for rapid identification of mangrove ecological restoration areas according to claim 1, characterized in that, The method for locating stress units and marking them as ecological restoration areas is as follows: highlight the stress units in professional geographic information software, and mark the ecological restoration areas in the satellite images of the mangrove area according to the location of the stress units in the mangrove grid distribution.

7. A rapid identification system for mangrove ecological restoration areas, characterized in that, The rapid identification system for mangrove ecological restoration areas includes: a processor, a memory, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the rapid identification method for mangrove ecological restoration areas according to any one of claims 1-6. The rapid identification system for mangrove ecological restoration areas runs on a desktop computer, laptop computer, handheld computer, or cloud data center computing device.

Images