Mangrove forest identification and area change analysis method, system and device based on satellite remote sensing image, medium and product

Abstract

The invention discloses a mangrove forest identification and area change analysis method, system and device based on a satellite remote sensing image, a medium and a product, and relates to the field of image processing, and the method comprises the steps: obtaining satellite remote sensing images of different time periods in a preset time interval of a research region, and carrying out the preprocessing of the satellite remote sensing images of different time periods; determining an optimal classification model; based on the satellite remote sensing images preprocessed in different time periods, carrying out ground feature classification by adopting an optimal classification model; the ground objects comprise mangrove forests, water bodies, buildings and other vegetation except the mangrove forests; and calculating the mangrove forest area in different time periods, and determining the area change of the mangrove forest in a preset time interval. According to the method, the mangrove forest can be accurately identified, the area change of the mangrove forest can be determined, and the evolution condition of a typical mangrove forest ecosystem can be known and researched.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, system, equipment, medium and product for mangrove identification and area change analysis based on satellite remote sensing images. Background Art

[0002] Mangroves are a key ecosystem in coastal areas. They maintain the stability and balance of coastal ecosystems, provide wind and wave protection, combat soil erosion, and purify surrounding seawater. They are effective in protecting the ecological environment and addressing global warming. Mangroves hold significant research value, and understanding their distribution is crucial for effective conservation and resource utilization.

[0003] Traditional methods for identifying and monitoring mangroves rely primarily on manual field surveys, visual interpretation of remote sensing imagery, and simple image processing techniques. While manual field surveys can yield relatively accurate mangrove information, they suffer from inefficiencies, high costs, and difficulty covering large areas. For example, when surveying features on mudflats or islands, manual surveys are time-consuming, labor-intensive, and pose safety risks due to inconvenient transportation and complex terrain. Visual interpretation of remote sensing images relies on the experience and subjective judgment of professionals and is susceptible to human influence, making it difficult to ensure the accuracy and consistency of interpretation results. Furthermore, with the increasing volume of remote sensing imagery data, manual interpretation alone can no longer meet the demands for fast and efficient data processing. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, equipment, medium and product for mangrove identification and area change analysis based on satellite remote sensing images, which can identify mangroves and determine their area changes, and help understand and study the evolution of typical mangrove ecosystems.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In the first aspect, this application provides a method for mangrove identification and area change analysis based on satellite remote sensing images, comprising:

[0007] Obtain satellite remote sensing images of different periods within a preset time interval of the study area, and preprocess the satellite remote sensing images of different periods;

[0008] Determine the optimal classification model;

[0009] Based on pre-processed satellite remote sensing images at different time periods, the optimal classification model is used to classify land features; the land features include mangroves, water bodies, buildings, and other vegetation except mangroves;

[0010] Calculate the mangrove area at different time periods and determine the change in mangrove area within a preset time interval.

[0011] Secondly, this application provides a mangrove identification and area change analysis system based on satellite remote sensing images, including:

[0012] The data acquisition module is used to obtain satellite remote sensing images of different time periods within a preset time interval of the study area and pre-process the satellite remote sensing images of different time periods;

[0013] A determination module, used to determine the optimal classification model;

[0014] A ground feature recognition module is used to classify ground features using an optimal classification model based on pre-processed satellite remote sensing images from different time periods; the ground features include mangroves, water bodies, buildings, and other vegetation except mangroves;

[0015] The mangrove area change determination module is used to calculate the mangrove area in different time periods and determine the area change of the mangrove within a preset time interval.

[0016] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned mangrove identification and area change analysis method based on satellite remote sensing images.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned mangrove identification and area change analysis method based on satellite remote sensing images.

[0018] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned mangrove identification and area change analysis method based on satellite remote sensing images.

[0019] According to the specific embodiments provided in this application, this application has the following technical effects:

[0020] The present application provides a method, system, equipment, medium and product for mangrove identification and area change analysis based on satellite remote sensing images. By using satellite remote sensing images of a preset time interval and a classification model, mangroves can be accurately and quickly identified, and by calculating the area of mangroves in different time periods, the area changes of mangroves can be determined, which helps to understand and study the evolution of typical mangrove ecosystems, thereby providing a practical basis and experience reference for ecological restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of a method for mangrove identification and area change analysis based on satellite remote sensing images provided in one embodiment of the present application;

[0023] Figure 2 This is a schematic diagram of the cropped satellite remote sensing image;

[0024] Figure 3 This is a schematic diagram of water-land separation;

[0025] Figure 4 This is a schematic diagram of vegetation index enhancement;

[0026] Figure 5 This is a schematic diagram of the ground feature classification results;

[0027] Figure 6 A statistical diagram of the area of mangroves and other landforms in a certain study area at different time periods;

[0028] Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0031] In an exemplary embodiment, Figure 1 As shown, a method for mangrove identification and area change analysis based on satellite remote sensing images is provided. The method is executed by a computer device, and can be executed separately by a computer device such as a terminal or a server, or can be executed jointly by a terminal and a server. In the embodiment of the present application, the method is applied to a server as an example for explanation, including the following steps S1 to S4.

[0032] in:

[0033] S1: Obtain satellite remote sensing images of the study area at different time periods within a preset time interval and preprocess the satellite remote sensing images at different time periods. Preprocessing includes radiometric calibration, atmospheric correction, resampling, and band fusion.

[0034] Satellite remote sensing images can be downloaded from the European Space Agency's Copernicus Data Center (Copernicus Data Space Ecosystem | Europe's Eyes on Earth). These L1C products are atmospheric apparent reflectance products that have undergone orthorectification and sub-pixel geometric correction. Sen2Cor is used to perform radiometric calibration and atmospheric correction. SNAP (Sentinel Application Platform) is used to resample the images. ENVI 5.3 (The Environment for Visualizing Images) is used to perform band fusion on the resampled data.

[0035] (1) Radiation calibration

[0036] In satellite remote sensing images, the brightness value of a satellite remote sensing image element is a record of the grayscale value of the ground object and has no actual physical meaning. It needs to be converted into the radiation brightness or reflectivity value of the upper atmosphere through radiometric calibration, so as to establish a quantitative relationship between the digital quantization value and the radiation brightness value in the corresponding field, so as to eliminate the error caused by the sensor itself.

[0037] (2) Atmospheric correction

[0038] The primary purpose of atmospheric correction is to eliminate the effects of atmospheric and lighting factors on object reflectance, thereby obtaining formal physical model parameters such as object reflectance, emissivity, and surface temperature. This includes eliminating the effects of atmospheric substances such as oxygen, water vapor, carbon dioxide, methane, and ozone on object reflectance, as well as the scattering effects of atmospheric molecules and aerosols.

[0039] The European Space Agency (ESA) has only released L1C-level multispectral data (MSI) from the Sentinel-2 (S2) satellite. L1C data are geometrically corrected orthophotos, without radiometric or atmospheric correction. ESA has also defined S2 L2A-level data, which primarily includes radiometrically and atmospherically corrected bottom-of-atmosphere reflectance data. However, users must produce this L2A data on demand. To this end, ESA has released Sen2Cor, a plug-in specifically for producing L2A data. Radiometric calibration and atmospheric correction of Sentinel-2 data are performed within the Sen2Cor plug-in.

[0040] (2) Resampling and band fusion

[0041] The primary purpose of resampling Sentinel-2 data using SNAP is to unify the resolution of all bands for ease of subsequent analysis and processing. Sentinel-2's various bands have different spatial resolutions, including 10 meters, 20 meters, and 60 meters. This difference in resolution can hinder data analysis and application. Therefore, resampling can bring the resolution of all bands to a uniform level, typically a higher resolution such as 10 meters, making the data easier to process and analyze.

[0042] S2: Determine the optimal classification model. Specifically, the process includes: obtaining sample satellite remote sensing images and preprocessing the sample satellite remote sensing images; obtaining sample satellite remote sensing images and preprocessing the sample satellite remote sensing images; extracting water body information and vegetation information based on the preprocessed sample satellite remote sensing images; determining mangrove information and other vegetation information excluding mangroves from the vegetation information through the contrast of visible light-near infrared and shortwave infrared band spectra, with the remainder being building information; annotating the preprocessed sample satellite remote sensing images with water body information, vegetation information, other vegetation information excluding mangroves, and building information, and training multiple classification models to select the optimal classification model.

[0043] In a specific embodiment, the vector data clipping method is first used to clip the sample satellite remote sensing image to remove the interval outside the study area. The endpoint coordinates are processed using Arcgis 10.8 software and imported into ENV 15.3 for image clipping. Figure 2 Then, the sample satellite remote sensing image is processed for water-land separation and vegetation enhancement. The NDWI (Normalized Difference Water Index, Normalized Water Index) extraction method is used to extract water body information, and the NDVI (Normalized Difference Vegetation Index, Normalized Vegetation Index) extraction method is used to extract vegetation information, thereby obtaining a water-land separation map (as shown in Figure 1). Figure 3 ) and vegetation index enhancement map (as shown in Figure 4 Then, mangroves can be distinguished from other vegetation by comparing the spectra in the visible-near infrared and shortwave infrared bands.

[0044] In this embodiment, three classification models, namely, maximum likelihood estimation function, neural network model, and support vector machine, are trained respectively, and the optimal classification model is selected to classify land features.

[0045] Land features are roughly divided into four categories: mangroves, water bodies, buildings, and other vegetation except mangroves (as shown in Table 1). Figure 5 This is a schematic diagram of the land feature classification in a certain study area, where blue represents water bodies, red represents mangroves, green represents other vegetation, and yellow represents buildings.

[0046] Table 1

[0047]

[0048]

[0049] The confusion matrix method was used to evaluate the accuracy of each classification model. This method combines overall accuracy, Kappa coefficient, producer accuracy, and user accuracy in a single matrix. Classification accuracy was evaluated using the confusion matrix method using the 2023 classified data as the source data. Statistical analysis of the confusion matrix yielded classification accuracies that met various requirements.

[0050] The overall accuracies of the support vector machine, maximum likelihood estimation function, and neural network model were 99.49%, 99.21%, and 99.38%, respectively, and the Kappa coefficients were 0.99, 0.95, and 0.98, respectively. The results showed that the support vector machine had the best classification effect.

[0051] As shown in Table 2, the support vector machine (SVM) performed best in mangrove classification, while the maximum likelihood estimation function (MLE) performed worst, with a misclassification error of 11.21%. All three methods performed well in water classification, with relatively low misclassification and omission errors. For other vegetation classification, the SVM performed best, while the other two methods gave similar results. Investigation revealed that the machine misclassified some other vegetation as mangroves and buildings, significantly increasing the misclassification error. For building extraction, the MLE performed worst. Investigation revealed that the presence of aquaculture ponds on the shoreline easily misclassified some water bodies as buildings and land. Overall, the SVM achieved the highest classification accuracy.

[0052] Table 2

[0053]

[0054]

[0055] This example uses satellite remote sensing imagery from 2019 to 2023 as source data. The maximum likelihood estimation function, neural network model, and support vector machine (SVM) are used to classify features in a specific study area. The confusion matrix method is used to evaluate classification accuracy. The support vector machine (SVM) achieves the highest overall accuracy and Kappa coefficient, and the classification results meet expectations in terms of accuracy. The SVM is used to evaluate the accuracy of data from 2019, 2021, and 2023, yielding classification results, overall accuracy, and Kappa coefficients for different years, as shown in Table 3.

[0056] Table 3

[0057] years Overall accuracy / % Kappa coefficient 2019 99.94 0.99 2021 99.49 0.99 2023 99.49 0.98

[0058] S3: Based on the pre-processed satellite remote sensing images at different time periods, the optimal classification model is used to classify the land features; the land features include mangroves, water bodies, buildings and other vegetation except mangroves.

[0059] S4: Calculate the mangrove area at different time periods and determine the change in the mangrove area within a preset time interval.

[0060] In this embodiment, the classification results of the support vector machine in 2019, 2021, and 2023 are statistically analyzed, and the total number of pixels of mangroves and other landforms is calculated. Since the spatial resolution of the image is 10 meters, the actual area of a single pixel is 100 square meters. The area of mangroves and other landforms in the three years is summarized and a summary table is prepared, as shown in Table 4. The area statistics of mangroves and other landforms in the three years are as follows: Figure 6 shown.

[0061] Table 4

[0062]

[0063] From Table 4, we can see that from 2019 to 2023, the area of mangroves increased by about 2016.51 hectares, and the water area decreased by 1206.85 hectares; while other vegetation decreased by 2067.42 hectares from September 2019 to 2021, and increased by 1296.46 hectares from 2021 to 2023; the area of buildings increased by 2404.77 hectares from September 2019 to 2021, and decreased by 2443.47 hectares from 2021 to 2023.

[0064] Based on the same inventive concept, embodiments of the present application also provide a system for implementing the aforementioned satellite remote sensing image-based mangrove identification and area change analysis. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following embodiments of the system for mangrove identification and area change analysis based on satellite remote sensing images can be found in the aforementioned definitions of the method for mangrove identification and area change analysis based on satellite remote sensing images, and will not be further elaborated here.

[0065] In an exemplary embodiment, a system for mangrove identification and area change analysis based on satellite remote sensing images is provided, comprising:

[0066] The data acquisition module is used to obtain satellite remote sensing images of different time periods within a preset time interval of the study area and preprocess the satellite remote sensing images of different time periods.

[0067] The determination module is used to determine the optimal classification model.

[0068] The object recognition module is used to classify objects based on satellite remote sensing images pre-processed at different time periods using the optimal classification model; the objects include mangroves, water bodies, buildings and other vegetation except mangroves.

[0069] The mangrove area change determination module is used to calculate the mangrove area in different time periods and determine the area change of the mangrove within a preset time interval.

[0070] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-mentioned method embodiments. The computer device can be a server or a terminal, and its internal structure can be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data to be processed. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for mangrove identification and area change analysis based on satellite remote sensing images is implemented.

[0071] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0072] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0073] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0074] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0075] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0076] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0077] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for mangrove identification and area change analysis based on satellite remote sensing images, characterized in that: include: Obtain satellite remote sensing images of different periods within a preset time interval of the study area, and preprocess the satellite remote sensing images of different periods; Determine the optimal classification model; Based on pre-processed satellite remote sensing images at different time periods, the optimal classification model is used to classify land features; the land features include mangroves, water bodies, buildings, and other vegetation except mangroves; Calculate the mangrove area at different time periods and determine the change in mangrove area within a preset time interval.

2. The method for mangrove identification and area change analysis based on satellite remote sensing images according to claim 1, characterized in that: Preprocess satellite remote sensing images at different time periods, including: Perform radiometric calibration, atmospheric correction, resampling and band fusion on satellite remote sensing images of different time periods.

3. The method for mangrove identification and area change analysis based on satellite remote sensing images according to claim 1, characterized in that: Determine the optimal classification model, including: Acquiring sample satellite remote sensing images and preprocessing the sample satellite remote sensing images; Extract water body information and vegetation information based on preprocessed sample satellite remote sensing images; Determining mangrove information and other vegetation information other than mangroves from the vegetation information by contrasting visible light-near infrared and short-wave infrared band spectra, with the remainder being building information; The pre-processed sample satellite remote sensing images are annotated by water body information, vegetation information, information of vegetation other than mangroves, and building information, and multiple classification models are trained to screen out the optimal classification model.

4. The method for mangrove identification and area change analysis based on satellite remote sensing images according to claim 3 is characterized in that: Extract water body information and vegetation information based on the preprocessed sample satellite remote sensing images, including: Based on the preprocessed sample satellite remote sensing images, the NDWI extraction method is used to extract water body information; Based on the preprocessed sample satellite remote sensing images, the NDVI extraction method is used to extract vegetation information.

5. The method for mangrove identification and area change analysis based on satellite remote sensing images according to claim 3 is characterized in that: Multiple classification models include maximum likelihood estimation function, neural network model and support vector machine.

6. The method for mangrove identification and area change analysis based on satellite remote sensing images according to claim 3, characterized in that: The optimal classification model is a support vector machine.

7. A mangrove identification and area change analysis system based on satellite remote sensing images, characterized in that: include: The data acquisition module is used to obtain satellite remote sensing images of different time periods within a preset time interval of the study area and pre-process the satellite remote sensing images of different time periods; A determination module, used to determine the optimal classification model; A ground feature recognition module is used to classify ground features using an optimal classification model based on pre-processed satellite remote sensing images from different time periods; the ground features include mangroves, water bodies, buildings, and other vegetation except mangroves; The mangrove area change determination module is used to calculate the mangrove area in different time periods and determine the area change of the mangrove within a preset time interval.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the mangrove identification and area change analysis method based on satellite remote sensing images as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for mangrove identification and area change analysis based on satellite remote sensing images according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for mangrove identification and area change analysis based on satellite remote sensing images according to any one of claims 1 to 6 is implemented.

Images