Methods, devices, equipment, storage media, and software products for monitoring algal bloom areas.

Abstract

This application relates to a method, apparatus, equipment, storage medium, and program product for monitoring algal bloom areas. Based on satellite remote sensing imagery of a target lake, the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing imagery in the XYZ color space are obtained. Using a pre-set algal bloom identification model and the horizontal axis chromaticity coordinates of the two-dimensional chromaticity coordinates, the predicted algal bloom boundary value for each pixel is obtained. Based on the vertical axis chromaticity coordinates of each pixel and the predicted algal bloom boundary value, the monitoring result of the algal bloom area of ​​the target lake is determined. This method is applicable to all optical satellite remote sensing data and lakes with different hydrological environments, exhibiting good versatility.

Description

Technical Field

[0001] This application relates to the field of environmental monitoring technology, and in particular to a method, apparatus, equipment, storage medium, and program product for monitoring algal bloom areas. Background Technology

[0002] With the concentration of water pollution, eutrophication of lakes is becoming increasingly severe, and algal blooms pose a serious threat to lake water quality.

[0003] Therefore, monitoring algal blooms in lakes has become a current hot topic. Because satellite remote sensing technology can effectively distinguish algal blooms from other background objects in lakes from images and achieve large-scale lake area monitoring, related technologies are mainly based on remote sensing to monitor algal blooms in lakes.

[0004] However, the remote sensing monitoring methods for algal blooms in related technologies are not applicable to all satellite remote sensing data and lakes with different hydrological environments. They have poor versatility and are difficult to achieve long-term monitoring of algal blooms in lakes with different hydrological environments. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, equipment, storage medium, and program product for monitoring algal bloom areas that can be applied to all satellite remote sensing data and lakes with different hydrological environments, in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for monitoring algal bloom areas, the method comprising:

[0007] Based on satellite remote sensing images of the target lake, obtain the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing images in the XYZ color space;

[0008] The predicted value of the water bloom boundary for each pixel is obtained by using the preset water bloom recognition model and the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value. The water bloom recognition model is a model constructed based on satellite remote sensing images of multiple different lakes at different times. The water bloom recognition model represents the water bloom region boundary value corresponding to the horizontal axis chromaticity coordinate value of the pixel in the satellite remote sensing images of multiple different lakes at different times in the XYZ color space.

[0009] Based on the vertical axis chromaticity coordinate value of each pixel and the predicted value of the algal bloom boundary of each pixel, the monitoring results of the algal bloom area of ​​the target lake are determined.

[0010] In one embodiment, based on satellite remote sensing imagery of the target lake, the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing imagery in the XYZ color space are obtained, including:

[0011] Based on the satellite remote sensing image of the target lake, determine the red, green and blue reflectance values ​​of each pixel in the satellite remote sensing image of the target lake;

[0012] Based on the reflectance values ​​of the red, green, and blue bands, the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space are determined.

[0013] In one embodiment, the process of constructing the algal bloom recognition model includes:

[0014] Acquire sample satellite remote sensing images corresponding to multiple different lakes, and determine sample algal bloom pixels based on the sample satellite remote sensing images corresponding to multiple different lakes; the sample algal bloom pixels include multiple algal bloom pixels;

[0015] Obtain the red, green, and blue reflectance values ​​of the sample water bloom pixels;

[0016] Based on the red, green and blue reflectance values ​​of the sample water bloom pixels, determine the corresponding two-dimensional chromaticity coordinates of the sample water bloom pixels in the XYZ color space.

[0017] A model for identifying algal blooms is constructed based on the two-dimensional chromaticity coordinates of the samples.

[0018] In one embodiment, determining sample algal bloom pixels based on sample satellite remote sensing images corresponding to multiple different lakes includes:

[0019] Obtain the phytoplankton index of each pixel in satellite remote sensing images corresponding to multiple different lakes;

[0020] Based on the phytoplankton index of each pixel in satellite remote sensing images corresponding to multiple different lakes, the sample algal bloom areas of satellite remote sensing images corresponding to multiple different lakes are determined.

[0021] Based on the sample algal bloom regions of satellite remote sensing images corresponding to multiple different lakes, sample algal bloom pixels are determined.

[0022] In one embodiment, an algal bloom recognition model is constructed based on the two-dimensional chromaticity coordinates of the samples, including:

[0023] Based on the sample's two-dimensional chromaticity coordinate values, scatter points of water bloom pixels are plotted in the two-dimensional chromaticity coordinate system.

[0024] Obtain the lower boundary line of the scattered pixels of algal bloom, fit the lower boundary line, and determine the algal bloom recognition model.

[0025] In one embodiment, the monitoring results of the algal bloom region of the target lake are determined based on the ordinate chromaticity coordinate value of each pixel in the two-dimensional chromaticity coordinate values ​​and the algal bloom boundary prediction value of each pixel, including:

[0026] The vertical axis chromaticity coordinate value of each pixel is compared with the predicted value of the water bloom boundary corresponding to each pixel. For any pixel, if the vertical axis chromaticity coordinate value is greater than or equal to the predicted value of the water bloom boundary, the pixel is determined to be a water bloom pixel.

[0027] Based on all the algal bloom pixels in the satellite remote sensing image of the target lake, the monitoring results of the algal bloom area of ​​the target lake are obtained.

[0028] Secondly, this application also provides a monitoring device for algal bloom areas, the device comprising:

[0029] The first acquisition module is used to acquire the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake in the XYZ color space.

[0030] The second acquisition module is used to obtain the predicted value of the water bloom boundary of each pixel through the preset water bloom recognition model and the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value; the water bloom recognition model is a model constructed based on satellite remote sensing images of multiple different lakes at different times, and the water bloom recognition model represents the water bloom region boundary value corresponding to the horizontal axis chromaticity coordinate value of the pixel in the satellite remote sensing images of multiple different lakes at different times in the XYZ color space.

[0031] The first determining module is used to determine the monitoring results of the algal bloom area of ​​the target lake based on the vertical axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value of each pixel and the algal bloom boundary prediction value of each pixel.

[0032] Thirdly, embodiments of this application provide a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods provided in the first aspect of the embodiments described above.

[0033] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods provided in the first aspect of the embodiments described above.

[0034] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the methods provided in the first aspect of the embodiments described above.

[0035] This application provides a method, apparatus, device, storage medium, and program product for monitoring algal bloom areas. Based on satellite remote sensing images of a target lake, it acquires the two-dimensional chromaticity coordinates of each pixel in the XYZ color space. Through a preset algal bloom identification model and the horizontal axis chromaticity coordinates of the two-dimensional chromaticity coordinates, it acquires the predicted algal bloom boundary value of each pixel. Based on the vertical axis chromaticity coordinates of each pixel and the predicted algal bloom boundary value of each pixel, it determines the monitoring result of the algal bloom area of ​​the target lake. In this method, the algal bloom identification model is constructed based on satellite remote sensing images of multiple lakes at different times. The model represents the boundary value of the algal bloom region corresponding to the horizontal axis chromaticity coordinates of pixels in the XYZ color space of the satellite remote sensing images of multiple lakes at different times. When monitoring algal bloom regions using satellite remote sensing images, it is only necessary to obtain the predicted algal bloom boundary value corresponding to each pixel in the satellite remote sensing image based on the algal bloom identification model. This allows for the automatic determination of whether each pixel in the satellite remote sensing image is an algal bloom pixel, thereby determining the algal bloom region monitoring result of the target lake. This method is applicable to satellite remote sensing images of all freshwater lakes and requires no human intervention. Furthermore, the two-dimensional chromaticity coordinate value corresponding to each pixel in the XYZ color space can be obtained for all types of satellite remote sensing images. By comparing this value with the predicted algal bloom boundary value determined by this method, the algal bloom region monitoring result of the target lake can be determined. This makes it applicable to different types of satellite remote sensing data. Therefore, this method is applicable to all satellite remote sensing data and lakes with different hydrological environments, demonstrating its versatility. Attached Figure Description

[0036] Figure 1a This is an application environment diagram of the algal bloom area monitoring method in one embodiment;

[0037] Figure 1b This is a schematic diagram illustrating the principle of a method for monitoring algal bloom areas in one embodiment;

[0038] Figure 1c This is a schematic diagram illustrating the principle of the algal bloom area monitoring method in another embodiment;

[0039] Figure 1d This is a schematic diagram illustrating the principle of the algal bloom area monitoring method in another embodiment;

[0040] Figure 1e This is a schematic diagram of the monitoring results of the algal bloom monitoring method in one embodiment;

[0041] Figure 1f This is a schematic diagram of the monitoring results of the algal bloom area monitoring method in another embodiment;

[0042] Figure 2 This is a flowchart illustrating a method for monitoring algal bloom areas in one embodiment;

[0043] Figure 3 This is an environmental schematic diagram of a method for monitoring algal bloom areas in one embodiment;

[0044] Figure 4 This is an environmental schematic diagram of the algal bloom area monitoring method in another embodiment;

[0045] Figure 5 This is a schematic diagram of the monitoring results of the algal bloom area monitoring method in another embodiment;

[0046] Figure 6 This is a flowchart illustrating the method for monitoring algal bloom areas in another embodiment;

[0047] Figure 7 This is a colorimetric schematic diagram of a method for monitoring algal bloom areas in one embodiment;

[0048] Figure 8 This is a flowchart illustrating the method for monitoring algal bloom areas in another embodiment;

[0049] Figure 9 This is a flowchart illustrating the method for monitoring algal bloom areas in another embodiment;

[0050] Figure 10 This is a pixel scatter plot of a method for monitoring algal bloom areas in one embodiment;

[0051] Figure 11 This is a flowchart illustrating the method for monitoring algal bloom areas in another embodiment;

[0052] Figure 12 This is a flowchart illustrating the method for monitoring algal bloom areas in another embodiment;

[0053] Figure 13 This is a flowchart illustrating the method for monitoring algal bloom areas in another embodiment;

[0054] Figure 14 This is a structural block diagram of a monitoring device for algal bloom areas in one embodiment;

[0055] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The algal bloom area monitoring method provided in this application embodiment can be as follows: Figure 1aIn the application environment shown, satellite 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers.

[0058] Satellite 102 sends satellite remote sensing images to server 104. Server 104 obtains the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space based on the satellite remote sensing image of the target lake. Then, through a preset algal bloom recognition model and the horizontal axis chromaticity coordinates of the two-dimensional chromaticity coordinates, it obtains the algal bloom boundary prediction value of each pixel. Finally, based on the vertical axis chromaticity coordinates of each pixel and the algal bloom boundary prediction value of each pixel, it determines the algal bloom area monitoring result of the target lake.

[0059] Satellite 102 can be, but is not limited to, resource satellites, meteorological satellites, BeiDou satellites, small satellites, high-resolution satellites, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0060] Typically, when conducting remote sensing monitoring of algal blooms in lakes, methods such as Normalized Difference Vegetation Index (NDVI), Maximum Chlorophyll Index (MCI), Maximum Peak Height Index (MPH), Cyanobacteria Index (CI), and Floating Algal Index (FAI) can be used to monitor algal bloom areas in lakes.

[0061] The NDVI index is calculated by dividing the difference between the reflectance values ​​in the near-infrared and red light bands by the sum of the two, thereby enhancing the contrast between the reflectance in the near-infrared and red light bands. NDVI can be used to monitor the state and coverage of algal blooms. Essentially, it is based on the fact that algal blooms exhibit signals similar to vegetation in the near-infrared band; a positive NDVI value indicates the presence of algal blooms, while a negative NDVI value indicates the presence of water bodies. However, NDVI is susceptible to the influence of satellite observation geometry and the surrounding environment, resulting in poor robustness when used over a wide area.

[0062] The MCI index is the maximum chlorophyll index based on MERIS satellite remote sensing imagery. The MCI is immune to interference from dissolved organic matter, suspended minerals in water, and atmospheric correction errors. Figure 1bAs shown, the horizontal axis represents wavelength, and the vertical axis represents remote sensing reflectance. The principle is to measure the intensity of algal blooms by estimating the height difference between the 9th band of MERIS (center wavelength approximately 705 nm) and a baseline constructed using the 8th band (center wavelength 681 nm) and the 10th band (center wavelength 753 nm). MCI is used for high chlorophyll concentrations (10-300 mg / m³). 3 The MCI algorithm is effective in monitoring strong algal blooms, but not so effective in monitoring weak algal blooms with low chlorophyll concentrations. Furthermore, changes in chlorophyll concentration and other water quality parameters can cause the position of the MCI peak to shift, which hinders the universality of the MCI algorithm.

[0063] MPH (Maximum Peak Height Index) is an algorithm based on MERIS satellite remote sensing imagery. It uses baseline subtraction to calculate the peak height between red (664nm) and near-infrared (885nm) light in MERIS satellite remote sensing imagery, caused by solar-induced chlorophyll fluorescence and particulate backscattering. MPH can be directly calculated using MERIS TOA data corrected for gas molecule absorption and Rayleigh scattering, effectively avoiding interference from atmospheric aerosol correction errors. MPH can monitor algal blooms in eutrophic, oligotrophic, and mesotrophic water bodies, and it can effectively identify cyanobacterial blooms. However, MPH is highly sensitive to solar flares. While a complete atmospheric correction product is not required, pre-treatment to remove the effects of solar flares is essential. Currently, however, there is no universally applicable solar flare removal algorithm in the field of water color remote sensing.

[0064] The CI index is an index that distinguishes cyanobacteria from other planktonic algae based on spectral shape changes at the 681nm band in MERIS satellite remote sensing imagery. Figure 1c As shown, the horizontal axis represents wavelength, and the vertical axis represents water emissivity (mW / cm²). 2 The principle behind the CI index (681 nm / sr) is that when cyanobacteria grow in large quantities, their scattering is stronger than the fluorescence signal, resulting in a negative spectral shape relative to the baseline near the 681 nm band. Based on this characteristic, cyanobacteria can be well distinguished from other ground features. However, when cyanobacteria appear in water bodies with strong scattering, such as water bodies with high concentrations of suspended sediment, a high peak will also appear near 709 nm, which will interfere with the use of the CI index.

[0065] The FAI index is a phytoplankton identification index constructed based on the red (645nm), near-infrared (859nm), and short-wave infrared (1240 or 1640nm) bands of MODIS satellite remote sensing imagery. Its principle is to identify algae by estimating the difference between the near-infrared band and the baseline constructed from the red and short-wave infrared bands. Figure 1dAs shown, the horizontal axis represents wavelength, the vertical axis represents water reflectance, the curve corresponding to Algae represents pixels containing algae, the curve corresponding to Water represents freshwater pixels, and the curve corresponding to Difference represents the reflectance difference between algae pixels and freshwater pixels. When determining whether a pixel is a bloom pixel, it is necessary to calculate not only the FAI index of algae pixels but also the FAI index between freshwater pixels. The FAI index corresponding to a bloom pixel represents the boundary threshold of the bloom. If the FAI index of a pixel is greater than the boundary threshold, then the pixel is determined to be a bloom pixel.

[0066] But from Figure 1e and Figure 1f It can be observed that the FAI index exhibits significant fluctuations in its boundary threshold across different lake water environments due to varying background conditions; it should be noted that, in this application, Figure 1e and Figure 1f It is displayed as a grayscale image, but in practical applications, it can be... Figure 1e and Figure 1f Stretching and color rendering are performed to differentiate the size of the FAI value through different colors.

[0067] The NDVI index method listed above is easily affected by observation geometry and atmospheric environment, and is not robust to large-scale algal bloom extraction. While the MCI, MPH, and CI algorithms can effectively extract algal blooms, they are all based on the narrow spectral resolution of the MERIS band. Commonly used wideband satellite data such as MODIS and Landsat do not have corresponding band settings, making them difficult to apply. The FAI algorithm exhibits large fluctuations in values ​​in different water bodies due to different background environments, requiring the acquisition of the corresponding FAI threshold for each image to achieve algal bloom extraction. This makes long-term, large-scale algal bloom monitoring in different lakes difficult. Therefore, the remote sensing monitoring methods for algal bloom outbreaks in related technologies are not applicable to all satellite remote sensing data and different lakes, and have poor versatility.

[0068] Based on this, embodiments of this application provide a method, apparatus, equipment, storage medium, and program product applicable to monitoring algal bloom areas of all satellite remote sensing data and different lakes.

[0069] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0070] In one embodiment, a method for monitoring algal bloom areas is provided. Taking the application environment shown in Figure 1 as an example, this embodiment involves determining the predicted algal bloom boundary value of each pixel in the XYZ color space based on the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake and a preset algal bloom identification model. The specific process of determining the monitoring results of the algal bloom area of ​​the target lake is then described, based on the vertical axis chromaticity coordinates of each pixel and the predicted algal bloom boundary value. Figure 2 As shown, this embodiment includes the following steps:

[0071] S201. Based on the satellite remote sensing image of the target lake, obtain the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space.

[0072] Lakes are relatively enclosed natural depressions on the Earth's surface that can store water, formed by the combined effects of internal and external forces. Lakes can be classified according to their formation as tectonic lakes, crater lakes, glacial lakes, barrier lakes, karst lakes, fluvial lakes, aeolian lakes, marine lakes, and artificial lakes (reservoirs). They can also be classified according to their discharge capacity as outflow lakes (throughflow / outflow lakes) and inland lakes; and according to their salinity as freshwater lakes (salinity less than 1 g / L), saline lakes (salinity 1-35 g / L), and salt lakes (salinity greater than 35 g / L).

[0073] Algal blooms in freshwater lakes are a phenomenon in which excessive algae grow and accumulate on the water surface to form a dense algal layer. This is a manifestation of severe eutrophication of the water body. Therefore, effective monitoring of algal blooms in freshwater lakes plays an important role in protecting and restoring lake water quality.

[0074] Therefore, the target lake can be any freshwater lake that needs to be monitored for algal blooms. It should be noted that the target lake in this application embodiment includes at least one or more lakes.

[0075] In practical applications, satellite remote sensing images of the target lake are required before monitoring algal blooms in freshwater lakes.

[0076] Remote sensing images refer to films or photographs that record the magnitude of electromagnetic waves emitted by various ground features, while satellite remote sensing images are remote sensing images acquired through satellites, including Landsat and MODIS satellites. It should be noted that the type of satellite used in acquiring satellite remote sensing images in this application embodiment is not limited in any way.

[0077] Satellite remote sensing data includes multiple pixels, also known as image units. A pixel is an important marker reflecting image characteristics and is a data element that simultaneously possesses spatial and spectral features.

[0078] To obtain the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space, specifically, each pixel in the satellite remote sensing image is transformed into a two-dimensional chromaticity coordinate form according to a preset transformation method of the XYZ color space. The two-dimensional chromaticity coordinate value represents the chromaticity of each pixel in the satellite remote sensing image, and the two-dimensional chromaticity coordinate value corresponds to the horizontal axis chromaticity coordinate and the vertical axis chromaticity coordinate; it can be understood that one pixel corresponds to one two-dimensional chromaticity coordinate value.

[0079] Among them, the XYZ color space can be a color system proposed by the International Commission on Illumination (CIE) that uses three hypothetical primary colors XYZ to replace the three primary colors of the RGB system, and is abbreviated as CIE color system.

[0080] The CIE color system is based on the RGB model. It uses mathematical methods to derive the theoretical three primary colors from the real primary colors, creating a new color system that enables industries such as pigments, dyes, and printing to clearly specify the colors of their products.

[0081] S202, by using the preset water bloom recognition model and the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value, the predicted value of the water bloom boundary of each pixel is obtained.

[0082] The algal bloom identification model is a model constructed based on satellite remote sensing images of multiple lakes at different times. The algal bloom identification model represents the boundary value of the algal bloom region corresponding to the horizontal axis chromaticity coordinate value of the pixel in the XYZ color space of the satellite remote sensing images of multiple lakes at different times.

[0083] Algal blooms refer to a phenomenon that occurs directly or indirectly due to a sudden and massive proliferation of plankton. In freshwater lakes, the water surface often appears green during an algal bloom. Figure 3 As shown, Figure 3 This is a schematic diagram of lake water and algal blooms. Figure 3 In lakes, algae blooms appear green, while the water itself appears blue. Therefore, when monitoring algae bloom areas using satellite remote sensing imagery of lakes, one can consider distinguishing them by color intensity in the imagery. This involves comparing the color intensity value of each algae bloom pixel in the imagery with the color intensity boundary value of the algae bloom to determine whether each pixel is an algae bloom pixel. However, it should be noted that some aquatic vegetation in lakes may also appear green, such as... Figure 4 As shown, Figure 4 This is a schematic diagram of aquatic vegetation and algal blooms. Figure 4 In satellite remote sensing images of lakes, algae blooms are green, and aquatic vegetation is also green. Therefore, when monitoring algae blooms in these images, it is necessary to effectively distinguish them from other background features in the lake. However, the specific algorithm for distinguishing algae blooms from aquatic vegetation is not detailed in this invention. It should be noted that... Figure 3and Figure 4 In this application embodiment, a grayscale image is used as an example, but in practical applications, Figure 3 and Figure 4 This is a chromatic image.

[0084] Specifically, the boundary value of the water bloom region corresponding to each pixel in the XYZ color space can be determined based on the water bloom recognition model. The water bloom recognition model refers to a model that can identify whether water bloom exists in the satellite remote sensing image, and the boundary value of the water bloom region is the value that distinguishes water bloom pixels from non-water bloom pixels.

[0085] It should be noted that each pixel has a two-dimensional chromaticity coordinate value in the XYZ color space.

[0086] Therefore, based on the aforementioned preset water bloom recognition model and the horizontal axis chromaticity coordinates in the two-dimensional chromaticity coordinates, the horizontal axis chromaticity coordinates of each pixel are used as the input parameters of the preset water bloom recognition model to train the water bloom recognition model and obtain the predicted water bloom boundary value of each pixel.

[0087] S203, the vertical axis chromaticity coordinate value of each pixel in the two-dimensional chromaticity coordinate value and the predicted value of the algal bloom boundary of each pixel are used to determine the monitoring results of the algal bloom area of ​​the target lake.

[0088] The results of the algal bloom monitoring area of ​​the target lake indicate whether algal blooms exist in the target lake, and can include the area where algal blooms exist and the time of the bloom.

[0089] It should be noted that the satellite remote sensing image of the target lake includes the time when the satellite remote sensing image was acquired. Therefore, when monitoring the target lake with satellite remote sensing image, by acquiring satellite remote sensing images of the target lake for multiple consecutive days, the specific date of the algal bloom phenomenon can also be determined when determining the monitoring results of the algal bloom area of ​​the target lake, thus determining the time of the algal bloom outbreak.

[0090] For example, the method for determining the monitoring results of the algal bloom area of ​​the target lake may include: comparing the vertical axis chromaticity coordinate value of each pixel with the algal bloom boundary prediction value corresponding to each pixel; for any pixel, if the vertical axis chromaticity coordinate value is greater than or equal to the corresponding boundary prediction value, the pixel is determined to be an algal bloom pixel; and then, based on all algal bloom pixels in the satellite remote sensing image of the target lake, the monitoring results of the algal bloom area of ​​the target lake are obtained.

[0091] Specifically, the vertical axis chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake are compared with the corresponding boundary prediction values ​​to obtain all the algal bloom pixels in the satellite remote sensing image of the target lake.

[0092] By combining all the algal bloom pixels in the satellite remote sensing images of the target lake, the monitoring results of the algal bloom area of ​​the target lake are obtained. The monitoring results of the algal bloom area of ​​the target lake refer to the corresponding algal bloom area and non-algal bloom area in the target lake.

[0093] like Figure 5 As shown, Figure 5 This diagram illustrates the monitoring results of the target lake environment and the corresponding algal bloom areas. Image 601 shows a satellite remote sensing image of Hongze Lake taken on October 27, 2006; image 602 shows the algal bloom extent of Hongze Lake extracted from the same image; image 603 shows a satellite remote sensing image of Lake Okeechobee taken on August 21, 2005; and image 604 shows the algal bloom extent of Lake Okeechobee extracted from the same image. In the algal bloom lake area monitoring results diagram, bright colors represent algal bloom areas, and dark colors represent non-algal bloom areas.

[0094] It should be noted that, in the embodiments of this application, Figure 5 For grayscale images, in practical applications, Figure 5 The picture should be in color. Figure 5 In the corresponding monitoring results map of algal bloom lake areas, algal bloom areas are represented in green, and non-algal bloom areas are represented in dark blue.

[0095] The above describes in detail how to determine water bloom pixels. The following example illustrates how to determine non-water bloom pixels.

[0096] In one embodiment, if the vertical axis chromaticity coordinate value of a pixel's two-dimensional chromaticity coordinates is less than the corresponding boundary prediction value, then the pixel is determined to be a non-blooming pixel.

[0097] The above-mentioned method for monitoring algal bloom areas obtains the two-dimensional chromaticity coordinates of each pixel in the XYZ color space based on satellite remote sensing images of the target lake. By using a preset algal bloom identification model and the horizontal axis chromaticity coordinates of the two-dimensional chromaticity coordinates, the predicted algal bloom boundary value of each pixel is obtained. Based on the vertical axis chromaticity coordinates of each pixel and the predicted algal bloom boundary value of each pixel, the monitoring results of the algal bloom area of ​​the target lake are determined. In this method, the algal bloom identification model is constructed based on satellite remote sensing images of multiple lakes at different times. The model represents the boundary value of the algal bloom region corresponding to the horizontal axis chromaticity coordinates of pixels in the XYZ color space of the satellite remote sensing images of multiple lakes at different times. When monitoring algal bloom regions using satellite remote sensing images, it is only necessary to obtain the predicted algal bloom boundary value corresponding to each pixel in the satellite remote sensing image based on the algal bloom identification model. This allows for the automatic determination of whether each pixel in the satellite remote sensing image is an algal bloom pixel, thereby determining the algal bloom region monitoring result of the target lake. This method is applicable to satellite remote sensing images of all freshwater lakes and requires no human intervention. Furthermore, the two-dimensional chromaticity coordinate value corresponding to each pixel in the XYZ color space can be obtained for all types of satellite remote sensing images. By comparing this value with the predicted algal bloom boundary value determined by this method, the algal bloom region monitoring result of the target lake can be determined. This makes it applicable to different types of satellite remote sensing data. Therefore, this method is applicable to all satellite remote sensing data and lakes with different hydrological environments, demonstrating its versatility.

[0098] Based on the above embodiments, one embodiment describes how to obtain the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake in the XYZ color space. Figure 6 As shown, this embodiment includes the following steps:

[0099] S601. Based on the satellite remote sensing image of the target lake, determine the red, green and blue band reflectance values ​​of each pixel in the satellite remote sensing image of the target lake.

[0100] Before determining the two-dimensional chromaticity coordinates of each pixel in the XYZ color space based on the satellite remote sensing image of the target lake, it is necessary to obtain the red, green, and blue reflectance values ​​of each pixel in the satellite remote sensing image of the target lake. In a true-color satellite image, the color of a pixel is synthesized from the reflectance values ​​of the red, green, and blue bands. That is, the color value of a pixel is determined by the magnitude of the red, green, and blue reflectance values ​​of that pixel. For example, if the red, green, and blue reflectance values ​​of a pixel are all 0, then the pixel is displayed as black. If the red, green, and blue reflectance values ​​of a pixel are all 255, then the pixel is displayed as white.

[0101] Optionally, the red, green and blue band reflectance values ​​of the target lake corresponding to the satellite remote sensing image can be obtained by using a color sampling tool; alternatively, the satellite remote sensing image of the target lake can be used as the input of a preset acquisition algorithm, and the red, green and blue band reflectance values ​​of each pixel in the satellite remote sensing image of the target lake can be determined by running the algorithm.

[0102] S602, based on the reflectance values ​​of the red, green and blue bands, determines the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space.

[0103] After obtaining the red, green, and blue reflectance values ​​of each pixel in the satellite remote sensing image of the target lake, each pixel in the satellite remote sensing image is represented by two-dimensional chromaticity coordinates in the XYZ color space based on the red, green, and blue reflectance values ​​of each pixel in the satellite remote sensing image of the target lake.

[0104] Specifically, the changes can be made using the following formula.

[0105] X0=2.7689R+1.7517G+1.1302B (1)

[0106] Y0=1.0000R+4.5907G+0.0601B (2)

[0107] Z0=0.0000R+0.0565G+5.5943B (3)

[0108] x=X0 / (X0+Y0+Z0) (4)

[0109] y=Y0 / (X0+Y0+Z0) (5)

[0110] Where x and y represent the two-dimensional chromaticity coordinates of the XYZ color space, and R, G, and B represent the red, green, and blue reflectance values ​​of each pixel.

[0111] Taking the reflectance values ​​of the red, green, and blue bands corresponding to a pixel as R = n1, G = n2, and B = n3 as an example, then X0 = 2.7689n1 + 1.7517n2 + 1.1302n3, Y0 = 1.0000n1 + 4.5907n2 + 0.0601n3, Z0 = 0.0000n1 + 0.0565n2 + 5.5943n3, then...

[0112] x=(2.7689n1+1.7517n2+1.1302n3) / (3.7689n1+6.3989n2+6.7846n3);

[0113] y=(1.0000n1+4.5907n2+0.0601n3) / (3.7689n1+6.3989n2+6.7846n3).

[0114] The obtained x and y values ​​are the two-dimensional chromaticity coordinates (x, y) in the XYZ color space corresponding to the red, green and blue three-band reflectance values ​​of the pixel, R for n1, G for n2, and B for n3.

[0115] It should be noted that one pixel corresponds to one two-dimensional chromaticity coordinate value, and the number of two-dimensional chromaticity coordinate values ​​is equal to the number of pixels.

[0116] like Figure 7 As shown in the figure, which is a chromaticity diagram in the XYZ color space, the color of the lake can be easily visualized by converting the red, green and blue reflectance values ​​of each pixel in the satellite remote sensing image of the target lake into the corresponding two-dimensional chromaticity coordinate values ​​in the XYZ color space.

[0117] It should be noted that, Figure 7 In this embodiment, a grayscale image is used; however, in practical applications, Figure 7 For color images, Figure 7 Each point in the two-dimensional coordinates corresponds to a chromaticity.

[0118] In the aforementioned method for monitoring algal bloom areas, the reflectance values ​​of each pixel in the satellite remote sensing image of the target lake are determined based on the red, green, and blue bands. Then, based on these reflectance values, the corresponding two-dimensional chromaticity coordinates of each pixel in the XYZ color space are determined. This method converts the three-dimensional reflectance information of each pixel in the satellite remote sensing image of the target lake into two-dimensional chromaticity coordinates in the XYZ color space, making the satellite remote sensing image of the target lake more visual and improving the accuracy of monitoring the target lake.

[0119] Based on any of the above embodiments, the construction process of the algal bloom recognition model is described. In one embodiment, such as... Figure 8 As shown, the construction process of the algal bloom recognition model includes the following steps:

[0120] S801: Acquire sample satellite remote sensing images corresponding to multiple different lakes, and determine sample algal bloom pixels based on the sample satellite remote sensing images corresponding to multiple different lakes.

[0121] Among them, the sample water bloom pixels include multiple water bloom pixels.

[0122] Before constructing an algal bloom identification model, it is necessary to determine the sample algal bloom pixels for constructing the algal bloom identification model. Before determining the sample algal bloom pixels, it is necessary to obtain sample satellite remote sensing data and determine the sample algal bloom pixels from the sample satellite remote sensing data.

[0123] Understandably, the sample satellite remote sensing data includes multiple different lakes, and the sample algal bloom pixels also include multiple algal bloom pixels.

[0124] Specifically, sample satellite remote sensing images corresponding to multiple different lakes were acquired, and sample algal bloom pixels were identified within these images. These sample algal bloom pixels are those pixels exhibiting algal bloom phenomena within the sample satellite remote sensing images corresponding to the multiple different lakes.

[0125] To ensure the representativeness of the geographical distribution of lakes, several representative lakes worldwide that exhibit algal blooms were selected. For example, 22 lakes globally that have already experienced algal blooms were selected for algal bloom sampling, with a total area of ​​142 km². 2 up to 67166km 2 The results are not equal; moreover, when acquiring sample images corresponding to 22 lakes, satellite remote sensing algal bloom sample data corresponding to the same lake at different times can be obtained.

[0126] Optionally, sample satellite remote sensing images corresponding to multiple different lakes can be obtained from the database.

[0127] In one embodiment, sample water bloom pixels are determined by a preset neural network model. Based on the sample satellite remote sensing image, the sample satellite remote sensing image is used as the input of the preset neural network model. By training the neural network model, the sample water bloom pixels are output.

[0128] S802, obtain the red, green and blue reflectance values ​​of the sample water bloom pixels.

[0129] Based on the above sample water bloom pixels, the red, green and blue reflectance values ​​of the sample water bloom pixels can be obtained by using a color sampling tool; alternatively, the sample water bloom pixels can be used as input to a preset acquisition algorithm, and the red, green and blue reflectance values ​​of each pixel in the sample water bloom pixels can be determined by running the algorithm.

[0130] S803, based on the red, green and blue reflectance values ​​of the sample water bloom pixel, determine the corresponding two-dimensional chromaticity coordinates of the sample water bloom pixel in the XYZ color space.

[0131] Based on the red, green, and blue reflectance values ​​of the sample water bloom pixels mentioned above, the method for determining the corresponding two-dimensional chromaticity coordinates of the sample water bloom pixels in the XYZ color space is the same as the method for determining the corresponding two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space based on the red, green, and blue reflectance values, and will not be elaborated here.

[0132] Alternatively, a preset neural network model can be used to determine the two-dimensional chromaticity coordinates of the sample water bloom pixel in the XYZ color space. The red, green and blue reflectance values ​​of the sample water bloom pixel are used as the input to the neural network model. By training the neural network model, the two-dimensional chromaticity coordinates of the sample water bloom pixel in the XYZ color space are output.

[0133] S804, based on the two-dimensional chromaticity coordinates of the samples, constructs an algal bloom recognition model.

[0134] As can be seen from the above description, the algal bloom identification model is constructed by obtaining sample algal bloom pixels from satellite remote sensing images of different lakes at different times, and converting the red, green and blue reflectance of the sample algal bloom pixels into sample two-dimensional coordinate values.

[0135] The following example illustrates the process of constructing an algal bloom recognition model based on sample two-dimensional coordinate values. In one embodiment, as follows... Figure 9 As shown, an algal bloom recognition model is constructed based on the two-dimensional chromaticity coordinates of the samples, including the following steps:

[0136] S901, based on the sample two-dimensional chromaticity coordinate values, plots the scatter points of water bloom pixels in the two-dimensional chromaticity coordinate system.

[0137] The sample water bloom pixels include multiple pixels, therefore, the sample two-dimensional chromaticity coordinate values ​​also include multiple two-dimensional chromaticity coordinate values. The multiple two-dimensional chromaticity coordinate values ​​are plotted in the two-dimensional chromaticity coordinate system to obtain multiple water bloom pixel scatter points.

[0138] In one embodiment, a two-dimensional chromaticity coordinate system including multiple foliation pixel points is obtained by using a preset drawing algorithm with the sample two-dimensional chromaticity coordinate values ​​as input to the drawing algorithm and running the drawing algorithm.

[0139] S902, obtain the lower boundary line of the scatter points of water bloom pixels, fit the lower boundary line, and determine the water bloom recognition model.

[0140] Based on the scattered pixels of water bloom in the aforementioned two-dimensional chromaticity coordinate system, the lower boundary of the scattered pixels of water bloom is obtained. Specifically, in the two-dimensional chromaticity coordinate system, the horizontal axis coordinate is divided into statistical units at intervals of 0.005. The vertical axis coordinate value corresponding to each horizontal axis coordinate value in the unit is counted. After arranging the vertical axis coordinate values ​​from largest to smallest, the vertical axis coordinate value ranked at the 99th percentile is selected as the vertical axis coordinate value corresponding to each unit.

[0141] For example, if each unit has 200 horizontal axis coordinate values ​​and corresponding vertical axis coordinate values, then the 198th vertical axis coordinate value, ranked from largest to smallest, is selected as the vertical axis coordinate value for each unit. Each unit corresponds to one vertical axis coordinate value, and these vertical axis coordinate values ​​are connected sequentially according to the horizontal axis coordinates to form a lower boundary line. For example... Figure 10 As shown, Figure 10 Figure a in the diagram is a two-dimensional chromaticity coordinate diagram of the XYZ color space. Figure 10 Figure b in the figure is an enlarged view of the scatter plot drawn on a two-dimensional chromaticity coordinate graph based on the sample's two-dimensional chromaticity coordinate values. Its location can be found in [the figure]. Figure 10 The black circle in image a. Figure 10 The curve in Figure b is the lower boundary line drawn based on the scatter points of the water bloom pixels, where the color of the scatter points indicates the degree of aggregation of the scatter points.

[0142] It should be noted that, in the embodiments of this application, Figure 10 It's a grayscale image, but in practical applications, Figure 10 For color images, Figure 10 Figure a represents the color corresponding to the two-dimensional chromaticity coordinate values. Figure 10 The b-map uses different colors to represent the degree of clustering of water bloom pixel points.

[0143] Based on the lower boundary line of the aforementioned scatter plot of water bloom pixels, a water bloom recognition model can be obtained by fitting the lower boundary line using a trinomial polynomial regression. Specifically, the water bloom recognition model obtained by fitting the lower boundary line using trinomial polynomial regression is as follows:

[0144] y=223.201344*x3-189.247165*x2+51.708314*x-4.108605 (6)

[0145] Where x is the x in formula (4), which refers to the horizontal axis chromaticity coordinate of the pixel in the two-dimensional chromaticity coordinate value in the XYZ color space, and y refers to the boundary value of the algal bloom region of the corresponding pixel.

[0146] In the aforementioned method for monitoring algal bloom areas, sample satellite remote sensing images corresponding to multiple different lakes are acquired. Based on these images, sample algal bloom pixels are determined. Each sample algal bloom pixel comprises multiple algal bloom pixels. The red, green, and blue band reflectance values ​​of these pixels are obtained. Based on these values, the corresponding two-dimensional chromaticity coordinates of each pixel in the XYZ color space are determined. An algal bloom identification model is then constructed based on these two-dimensional chromaticity coordinates. This method is an algal bloom identification model determined from sample algal bloom pixels in sample satellite remote sensing images corresponding to multiple different lakes. This model is applicable to different satellite remote sensing images, and because the training samples used in its construction were collected from satellite remote sensing images of different lakes at different times, it has good applicability in lakes with different hydrological environments.

[0147] In one embodiment, such as Figure 11 As shown, the determination of sample algal bloom pixels based on sample satellite remote sensing images corresponding to multiple different lakes includes the following steps:

[0148] S1101, obtain the phytoplankton index of each pixel in satellite remote sensing images corresponding to multiple different lakes.

[0149] Phytoplankton in lakes include various phyla such as cyanobacteria, cryptophytes, dinoflagellates, xanthophytes, chrysophytes, diatoms, euglenoids, and chlorophytes, with cyanobacteria, diatoms, and chlorophytes being the most numerous. A sudden increase in phytoplankton can cause algal blooms. Therefore, when monitoring algal bloom areas in lakes, the phytoplankton index of each pixel in the corresponding satellite remote sensing image of the lake can be obtained to determine the algal bloom area in the lake.

[0150] Based on the mapping relationship between the wavebands reflected by each pixel in satellite remote sensing images corresponding to multiple different lakes and the corresponding water-free reflectance obtained by satellite sensors, a phytoplankton identification index is constructed using the red light 645nm, near-infrared 859nm, and short-wave infrared 1240 or 1640nm wavebands of each pixel in satellite remote sensing images corresponding to multiple different lakes. Specifically, the phytoplankton index of each pixel in satellite remote sensing images corresponding to multiple different lakes is determined by estimating the difference between the near-infrared waveband and the baseline constructed by the red light waveband and the short-wave infrared waveband.

[0151] S1102, Based on the phytoplankton index of each pixel in the satellite remote sensing images corresponding to multiple different lakes, determine the sample algal bloom areas of the satellite remote sensing images corresponding to multiple different lakes.

[0152] Based on the above, the phytoplankton index of each pixel in the satellite remote sensing images corresponding to multiple different lakes is determined, and the sample algal bloom areas in the satellite remote sensing images corresponding to multiple different lakes are determined. Specifically, pixels with a phytoplankton index greater than 0 and algal bloom pixels can be identified. Thus, based on the phytoplankton index of each pixel in the satellite remote sensing images corresponding to multiple different lakes, all algal bloom pixels in the satellite remote sensing images corresponding to multiple different lakes can be identified. All algal bloom pixels are plotted in the satellite remote sensing images corresponding to multiple different lakes, thereby determining the sample algal bloom area in the satellite remote sensing images corresponding to each lake.

[0153] S1103, determine the sample algal bloom pixels based on the sample algal bloom areas of satellite remote sensing images corresponding to multiple different lakes.

[0154] Based on the sample algal bloom regions from satellite remote sensing images of multiple different lakes, a predetermined number of pixels can be selected as sample algal bloom pixels. When selecting sample algal bloom pixels, factors such as the satellite remote sensing time and the different regions of different lakes are considered. For example, if 1000 sample algal bloom pixels are selected from the satellite remote sensing image of Lake A in 1990, then another 1000 sample algal bloom pixels from the satellite remote sensing image of Lake A in 2000 should also be selected; another example is selecting 1000 sample algal bloom pixels from the satellite remote sensing image of Lake A in 2010, and then selecting another 1000 sample algal bloom pixels from the satellite remote sensing image of Lake B in 2010.

[0155] Alternatively, a preset number of algal bloom pixels can be randomly selected from the sample algal bloom areas of satellite remote sensing images corresponding to multiple different lakes, and the randomly selected preset number of pixels can be determined as sample algal bloom pixels.

[0156] The preset quantity can be 67,966 water bloom pixels, meaning the sample water bloom pixels include 67,966 water bloom pixels.

[0157] The aforementioned method for monitoring algal bloom areas acquires the phytoplankton index of each pixel in satellite remote sensing images corresponding to multiple different lakes. Based on the phytoplankton index of each pixel in these images, sample algal bloom areas are determined from the satellite remote sensing images of the multiple lakes. Then, sample algal bloom pixels are identified based on these sample algal bloom areas. In this method, the sample algal bloom pixels for the algal bloom identification model are collected from sample algal bloom areas in satellite remote sensing images corresponding to multiple different lakes, thus improving the universality and accuracy of the algal bloom identification model across different lakes.

[0158] In one embodiment, this embodiment provides a method for monitoring algal bloom areas. Considering that algal blooms in freshwater bodies are often green, this method uses the CIE color system to identify and monitor algal blooms from satellite remote sensing data of freshwater lakes, thus solving the problem of algal bloom identification in freshwater lakes under different hydrological environments. This embodiment includes an algorithm training process and an extraction process, such as... Figure 12 As shown.

[0159] Specifically, during the training process, training samples are first input, which include algal bloom pixels from satellite remote sensing images of multiple different lakes. Based on the corresponding satellite remote sensing images, the red, green, and blue band reflectance values ​​of the training samples are extracted. The three-band reflectance values ​​of all samples are then converted into scatter points in a two-dimensional color space using the CIE color system. The lower boundary of these scatter points is obtained as the algal bloom extraction model. During the extraction process, the red, green, and blue band reflectance of the remote sensing images of the lake to be monitored are first extracted. Then, the three-dimensional red, green, and blue band information is converted into two-dimensional color values ​​using the CIE color system. Finally, the color values ​​are evaluated based on the constructed algal bloom model to achieve algal bloom extraction.

[0160] This embodiment converts the red, green, and blue reflectance values ​​of satellite remote sensing data of the lake to be monitored into single color values ​​based on the CIE color system, and then filters the green values ​​to identify algal blooms. This method is computationally simple, requiring only the red, green, and blue reflectance values ​​as input parameters. It is applicable to data from different satellite sensors and has good applicability in lakes with varying hydrological environments. It can achieve fully automated algal bloom extraction for long-term, large-scale remote sensing data.

[0161] In addition, the specific implementation is as follows Figure 13 As shown, taking 22 different lakes as examples, with 67,966 pixels of sample algal bloom data, Landsat satellite remote sensing data, and CIE color system in XYZ color space, this embodiment includes the following steps:

[0162] S1301 first selects Landsat satellite remote sensing images of 22 lakes worldwide where algal blooms have occurred as sample satellite remote sensing images.

[0163] S1302, based on RGB true-color images of sample satellite remote sensing images combined with FAI values, the algal bloom region where algal blooms occur is drawn.

[0164] S1303: Select 67,966 algal bloom pixels in all algal bloom areas, and extract the red, green and blue band reflectance values ​​of the corresponding sample satellite remote sensing images based on the 67,966 algal bloom pixels.

[0165] S1304 converts the red, green and blue reflectance values ​​of 67966 water bloom pixels into two-dimensional color coordinates based on the CIE color system, thus obtaining the two-dimensional coordinates of 67966 water bloom pixels.

[0166] S1305: Based on the two-dimensional coordinate values ​​of the water bloom pixels, scatter points are plotted to obtain the lower boundary of the scatter points and determine the water bloom extraction model.

[0167] S1306 Select the target Landsat satellite remote sensing image of the lake to be identified, and extract the red, green and blue band reflectance of each pixel in the target Landsat satellite remote sensing image.

[0168] S1307, based on the red, green and blue reflectance of each pixel, obtains the two-dimensional chromaticity coordinates of each pixel according to the CIE color system.

[0169] S1308, determine the boundary value corresponding to each pixel based on the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value corresponding to each pixel and the algal bloom extraction model.

[0170] S1309, compare the vertical axis chromaticity coordinate of each pixel with the corresponding boundary value. If the vertical axis chromaticity coordinate of each pixel is greater than or equal to the corresponding boundary value, then the pixel is a bloom pixel; otherwise, it is a non-bloom pixel.

[0171] S1310: Based on all identified algal bloom pixels and non-algal bloom pixels, obtain the algal bloom area monitoring results of the target Landsat satellite remote sensing image of the lake to be identified.

[0172] The specific limitations of the algal bloom area monitoring method provided in this embodiment can be found in the step limitations of each embodiment of the algal bloom area monitoring method above, and will not be repeated here.

[0173] It should be understood that although the steps in the flowcharts attached to the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures attached to the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0174] In one embodiment, such as Figure 14As shown in the figure, this application embodiment also provides an algal bloom area monitoring device 1400, which includes: a first acquisition module 1401, a second acquisition module 1402 and a first determination module 1403, wherein;

[0175] The first acquisition module 1401 is used to acquire the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake in the XYZ color space.

[0176] The second acquisition module 1402 is used to acquire the predicted value of the water bloom boundary of each pixel through a preset water bloom recognition model and the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value; the water bloom recognition model is a model constructed based on satellite remote sensing images of multiple different lakes at different times, and the water bloom recognition model represents the water bloom region boundary value corresponding to the horizontal axis chromaticity coordinate value of the pixel in the satellite remote sensing images of multiple different lakes at different times in the XYZ color space.

[0177] The first determining module 1403 is used to determine the monitoring results of the algal bloom area of ​​the target lake based on the vertical axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value of each pixel and the algal bloom boundary prediction value of each pixel.

[0178] In one embodiment, the first acquisition module 1401 includes:

[0179] The first determining unit is used to determine the red, green and blue band reflectance values ​​of each pixel in the satellite remote sensing image of the target lake based on the satellite remote sensing image of the target lake.

[0180] The second determining unit is used to determine the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space based on the reflectance values ​​of the red, green and blue bands.

[0181] In one embodiment, the device 1400 further includes:

[0182] The second determining module is used to acquire sample satellite remote sensing images corresponding to multiple different lakes, and to determine sample algal bloom pixels based on the sample satellite remote sensing images corresponding to multiple different lakes; the sample algal bloom pixels include multiple algal bloom pixels;

[0183] The third acquisition module is used to acquire the red, green and blue reflectance values ​​of the sample water bloom pixels;

[0184] The third determining module is used to determine the sample two-dimensional chromaticity coordinates of the sample water bloom pixel in the XYZ color space based on the red, green and blue three-band reflectance values ​​of the sample water bloom pixel.

[0185] The module is used to build an algal bloom recognition model based on the two-dimensional chromaticity coordinates of the samples.

[0186] In one embodiment, the second determining module includes:

[0187] The first acquisition unit is used to acquire the phytoplankton index of each pixel in satellite remote sensing images corresponding to multiple different lakes;

[0188] The third determining unit is used to determine the sample algal bloom area of ​​the satellite remote sensing images corresponding to multiple different lakes based on the phytoplankton index of each pixel in the satellite remote sensing images corresponding to multiple different lakes.

[0189] The fourth determining unit is used to determine the sample algal bloom pixels based on the sample algal bloom regions of satellite remote sensing images corresponding to multiple different lakes.

[0190] In one embodiment, the building module includes:

[0191] The drawing unit is used to draw scatter points of water bloom pixels in a two-dimensional chromaticity coordinate system based on the sample two-dimensional chromaticity coordinate values.

[0192] The fifth determining unit is used to obtain the lower boundary line of the scattered points of the algal bloom pixels, fit the lower boundary line, and determine the algal bloom recognition model.

[0193] In one embodiment, the first determining module 1403 includes:

[0194] The sixth determining unit is used to compare the vertical axis chromaticity coordinate value of each pixel with the corresponding predicted value of the water bloom boundary. For any pixel, if the vertical axis chromaticity coordinate value is greater than or equal to the corresponding predicted value of the water bloom boundary, the pixel is determined to be a water bloom pixel.

[0195] The seventh determining unit is used to obtain the monitoring results of the algal bloom area of ​​the target lake based on all algal bloom pixels in the satellite remote sensing image of the target lake.

[0196] Specific limitations regarding the algal bloom area monitoring device can be found in the limitations of each step in the algal bloom area monitoring method described above, and will not be repeated here. Each module in the aforementioned algal bloom area monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the target device in hardware form, or stored in the target device's memory in software form, so that the target device can invoke and execute the operations corresponding to each module.

[0197] In one embodiment, a computer device is provided, such as Figure 15As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for monitoring algal bloom areas. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0198] Those skilled in the art will understand that the above structural description of the computer device is only a partial structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0199] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0200] The implementation principles and technical effects of each step in this embodiment are similar to those of the above-mentioned algal bloom area monitoring method, and will not be repeated here.

[0201] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0202] The implementation principles and technical effects of each step in this embodiment when the computer program is executed by the processor are similar to those of the above-mentioned algal bloom area monitoring method, and will not be repeated here.

[0203] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0204] The implementation principles and technical effects of each step in this embodiment when the computer program is executed by the processor are similar to those of the above-mentioned algal bloom area monitoring method, and will not be repeated here.

[0205] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0206] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can 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 can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0207] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0208] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring algal bloom areas, characterized in that, The method includes: Based on the satellite remote sensing image of the target lake, obtain the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space; The predicted boundary value of the algal bloom for each pixel is obtained by using a preset algal bloom recognition model and the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value. The algal bloom recognition model is a model constructed based on satellite remote sensing images of multiple different lakes at different times, and the algal bloom recognition model represents the boundary value of the algal bloom region corresponding to the horizontal axis chromaticity coordinate value of the pixel in the satellite remote sensing images of multiple different lakes at different times in the XYZ color space. The construction of the algal bloom recognition model includes: acquiring sample satellite remote sensing images corresponding to multiple different lakes, and determining sample algal bloom pixels based on the sample satellite remote sensing images corresponding to multiple different lakes; the sample algal bloom pixels include multiple algal bloom pixels. Obtain the red, green, and blue reflectance values ​​of the sample water bloom pixels; Based on the red, green and blue reflectance values ​​of the sample water bloom pixel, determine the sample two-dimensional chromaticity coordinate value of the sample water bloom pixel in the XYZ color space; Based on the two-dimensional chromaticity coordinate values ​​of the sample, scatter points of water bloom pixels are plotted in the two-dimensional chromaticity coordinate system; Obtain the lower boundary line of the scattered pixels of the algal bloom, fit the lower boundary line, and determine the algal bloom recognition model; Based on the ordinate chromaticity coordinate value of each pixel in the two-dimensional chromaticity coordinates and the predicted algal bloom boundary value of each pixel, the monitoring results of the algal bloom area of ​​the target lake are determined, including: The vertical axis chromaticity coordinate value of each pixel is compared with the predicted value of the water bloom boundary corresponding to each pixel. For any pixel, if the vertical axis chromaticity coordinate value is greater than or equal to the predicted value of the water bloom boundary, the pixel is determined to be a water bloom pixel. Based on all the algal bloom pixels in the satellite remote sensing image of the target lake, the monitoring results of the algal bloom area of ​​the target lake are obtained.

2. The method according to claim 1, characterized in that, The step of obtaining the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake in the XYZ color space includes: Based on the satellite remote sensing image of the target lake, determine the red, green and blue band reflectance values ​​of each pixel in the satellite remote sensing image of the target lake; Based on the red, green, and blue reflectance values, the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space are determined.

3. The method according to claim 1, characterized in that, The step of determining sample algal bloom pixels based on sample satellite remote sensing images corresponding to the multiple different lakes includes: Obtain the phytoplankton index of each pixel in the satellite remote sensing images corresponding to the multiple different lakes; Based on the phytoplankton index of each pixel in the satellite remote sensing images corresponding to the multiple different lakes, the sample algal bloom areas of the satellite remote sensing images corresponding to the multiple different lakes are determined. The sample algal bloom pixels are determined based on the sample algal bloom regions of the satellite remote sensing images corresponding to the multiple different lakes.

4. A monitoring device for algal bloom areas, characterized in that, The device includes: The first acquisition module is used to acquire the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image of the target lake in the XYZ color space. The second acquisition module is used to acquire the predicted value of the water bloom boundary of each pixel through a preset water bloom recognition model and the horizontal axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value; the water bloom recognition model is a model constructed based on satellite remote sensing images of multiple different lakes at different times, and the water bloom recognition model represents the water bloom region boundary value corresponding to the horizontal axis chromaticity coordinate value of the pixel in the satellite remote sensing images of multiple different lakes at different times in the XYZ color space; The first determining module is used to determine the monitoring results of the algal bloom area of ​​the target lake based on the vertical axis chromaticity coordinate value in the two-dimensional chromaticity coordinate value of each pixel and the algal bloom boundary prediction value of each pixel. The second determining module is used to acquire sample satellite remote sensing images corresponding to multiple different lakes, and determine sample algal bloom pixels based on the sample satellite remote sensing images corresponding to the multiple different lakes; the sample algal bloom pixels include multiple algal bloom pixels; The third acquisition module is used to acquire the red, green and blue reflectance values ​​of the sample water bloom pixels; The third determining module is used to determine the sample two-dimensional chromaticity coordinate value of the sample water bloom pixel in the XYZ color space based on the red, green and blue three-band reflectance values ​​of the sample water bloom pixel. The module is used to build an algal bloom recognition model based on the two-dimensional chromaticity coordinates of the samples. A drawing unit is used to draw scattered water bloom pixels in a two-dimensional chromaticity coordinate system based on the sample's two-dimensional chromaticity coordinate values; the construction module includes the drawing unit. The fifth determining unit is used to obtain the lower boundary line of the scattered points of the algal bloom pixels, fit the lower boundary line, and determine the algal bloom recognition model; the construction module includes the fifth determining unit; The sixth determining unit is used to compare the vertical axis chromaticity coordinate value of each pixel with the predicted value of the algal bloom boundary corresponding to each pixel. For any pixel, if the vertical axis chromaticity coordinate value is greater than or equal to the predicted value of the algal bloom boundary, the pixel is determined to be an algal bloom pixel. The first determining module includes the sixth determining unit. The seventh determining unit is used to obtain the monitoring results of the algal bloom area of ​​the target lake based on all algal bloom pixels in the satellite remote sensing image of the target lake. The first determining module includes the seventh determining unit.

5. The apparatus according to claim 4, characterized in that, The first acquisition module includes: The first determining unit is used to determine the red, green and blue band reflectance values ​​of each pixel in the satellite remote sensing image of the target lake based on the satellite remote sensing image of the target lake. The second determining unit is used to determine the two-dimensional chromaticity coordinates of each pixel in the satellite remote sensing image in the XYZ color space based on the red, green and blue three-band reflectance values.

6. The apparatus according to claim 4, characterized in that, The second determining module includes: The first acquisition unit is used to acquire the phytoplankton index of each pixel in the satellite remote sensing images corresponding to the multiple different lakes; The third determining unit is used to determine the sample algal bloom area of ​​the satellite remote sensing images corresponding to the multiple different lakes based on the phytoplankton index of each pixel in the satellite remote sensing images corresponding to the multiple different lakes. The fourth determining unit is used to determine the sample algal bloom pixels based on the sample algal bloom regions of the satellite remote sensing images corresponding to the multiple different lakes.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images