Remote sensing monitoring method for total algae in the euphotic zone of eutrophic lakes

Abstract

The present invention provides a remote sensing monitoring method for the total amount of algae in the euphotic layer of eutrophic lakes, comprising: based on a field satellite-ground synchronous experiment, comparative analysis of the water body R under different vertical distribution types of algae in the euphotic layer of highly turbid eutrophic water bodies; rs Spectral characteristics, select MODIS B1-B7 band R rc The data and phytoplankton index, high turbidity index and near infrared to red light ratio index were used to construct a rc A random forest machine learning algorithm based on the data of total algal abundance in the euphotic zone has enabled satellite remote sensing monitoring of algal abundance in the euphotic zone of eutrophic lakes. This method can accurately capture the interannual and intermonth variations and spatial distribution of algal abundance in the euphotic zone of eutrophic lakes.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing technology, in particular to a satellite remote sensing monitoring method for the total amount of algae in the euphotic layer of a large eutrophic lake. Background Art

[0002] Remote sensing technology offers the potential for rapid, large-scale monitoring of cyanobacteria. When cyanobacteria blooms occur, chlorophyll levels in the water increase significantly, leading to changes in the water's spectral characteristics. Typically, the spectral characteristics of cyanobacteria-covered areas differ significantly from those of algae-free lakes. Lake water color remote sensing can utilize a variety of sensors to detect and invert chlorophyll and other water color parameters in inland waters. Therefore, satellite remote sensing data can be used to monitor cyanobacteria blooms. Currently, remote sensing data from MODIS, CBERS-1, TM, ETM, IRS-P6, and LISS-3 are widely used for cyanobacteria bloom monitoring (Duan Hongtao, 2008).

[0003] Currently, researchers have developed various methods for estimating algal abundance in lake surface waters (Ma Ronghua et al., 2010). In reality, the area of ​​algal blooms monitored by remote sensing can fluctuate significantly over short periods of time. Furthermore, changes in external hydrodynamics or environmental factors can alter the vertical distribution of algae, causing seemingly short bursts or disappearances of algal blooms (Beaver et al., 2013; Blottière et al., 2013; Ndong et al., 2014). Consequently, changes in the vertical structure of algal blooms mean that monitoring only the surface of the water cannot accurately reflect the eutrophication of the entire water column. This also affects the accuracy of remote sensing inversion of water optical parameters (Stramska and Stramski, 2005) and estimates of pigment biomass (Silulwane et al., 2010).

[0004] Remote sensing signals not only reflect surface water information but also the structure of the underwater light field at a specific depth. Remote sensing reflectance responds to the vertically nonuniform distribution of optical components within the euphotic zone (Xue, 2016). Compared to the vertically uniform distribution of algae, this nonuniform distribution affects the magnitude and spectral shape of remote sensing reflectance (Kutser et al., 2008). Therefore, calculating the total algal abundance within the euphotic zone forms the basis for remote sensing estimation of algal abundance throughout the water column.

[0005] Current methods for estimating algal abundance rely primarily on empirical algorithms. Not only does the accuracy of surface chlorophyll concentration estimation need to be improved, but the definition of "surface" depth also requires further clarification. The influence of different vertical distribution types of algae on the apparent optical density of water bodies is complex, and empirical algorithms cannot fully explain the underlying mechanisms and interactions. Furthermore, extensive field monitoring data demonstrates that the vertical distribution of algae is complex, and existing classification results no longer capture the true distribution of algae, resulting in significant errors in existing empirical algorithms. The continuous development of machine learning algorithms has provided important technical support for the research on machine learning algorithms for algal abundance. For eutrophic lakes, constructing a model for estimating algal abundance within the euphotic zone based on remote sensing reflectance and inverting the cyanobacteria abundance in Chaohu Lake using satellite remote sensing will not only provide information on the variability and spatiotemporal distribution of algal abundance in Chaohu Lake, but will also better reflect the eutrophic status of the entire lake, providing important technical support for monitoring and early warning of cyanobacterial blooms. Summary of the Invention

[0006] The purpose of the present invention is to provide a remote sensing estimation method for the total amount of algae in the euphotic zone of eutrophic lake water bodies based on a machine learning algorithm.

[0007] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0008] A remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake, characterized in that the method comprises the following steps:

[0009] 1) Based on the field satellite-ground synchronous monitoring data, the vertical distribution of algae in the euphotic layer of highly turbid and eutrophic water bodies was clustered and analyzed to screen out the main vertical distribution types of algae and analyze the R of water bodies with different vertical distribution types of algae. rs spectral characteristics;

[0010] 2) From the perspective of different algae vertical distribution types, the water body R rs The input parameters of the model are screened from two perspectives: spectral characteristics and easily confused objects.

[0011] Taking full consideration of spatial resolution and band settings, the Rrc data of MODIS B1 to B7 bands were selected as alternative input parameters to reflect the visible-near-infrared reflectance spectral characteristics of algae under different vertical distributions.

[0012] Considering that the spectral characteristics of highly turbid water bodies in the red and near-infrared bands are similar to those of water bodies with high algae content, as well as the differences in the remote sensing reflectance spectral characteristics of water bodies under the vertical distribution types of algae, the floating algae index FAI, the high turbidity index TWI and the near-infrared to red light ratio index are selected as alternative input parameters. The near-infrared to red light ratio index refers to the near-infrared band R rc Data and red light band Rrc Ratio of data;

[0013] 3) The alternative input parameters were arranged and combined to obtain a variety of model input parameters. The random forest machine learning algorithm was selected, and the model construction data set was combined with the model selected from the field ground-satellite synchronous monitoring data to construct multiple remote sensing estimation models for the total amount of algae in the euphotic layer. The accuracy of the above multiple models was tested using validation data, and the optimal model was selected as the final remote sensing estimation model for the total amount of algae in the euphotic layer based on the calculation accuracy and speed, so as to obtain the total amount of algae in the euphotic layer of the entire lake water area and its spatial distribution.

[0014] As a further improvement of the present invention, in step 1), based on the field synchronous satellite-ground experimental data, the vertical distribution type of algae is determined by performing cluster analysis on the vertical distribution of chlorophyll a.

[0015] As a further improvement of the present invention, in step 1), the vertical distribution of algae is divided into three categories: uniform type, surface accumulation type, and subsurface highest type;

[0016] Among them: exponential, power exponential and Gaussian distributions with the highest surface concentration are classified as surface accumulation type;

[0017] The Gaussian type with the highest concentration at 25-50 cm below the water surface is defined as the subsurface highest type.

[0018] As a further improvement of the present invention, in step 2), R rc The data are corrected for Rayleigh scattering and are not precisely atmospheric corrected data.

[0019] In step 2), the FAI, TWI, and near-infrared to red light ratio index based on MODIS Rrc data are calculated as follows:

[0020] FAI=R rc (B2)-R rc (B1)-[R rc (B5)-R rc (B5)]×(λ B2 -λ B1 ) / (λ B5 -λ B1 )

[0021] TWI=R rc (B1)-R rc (B5)

[0022] BR=R rc (B2) / R rc (B1) (2)

[0023] Where B1, B2, and B5 refer to the MODIS bands with central wavelengths of 645 nm, 859 nm, and 1240 nm, respectively; λ is the central wavelength of each MODIS band; BR refers to the near-infrared to red light ratio index. The two BR bands, B1 and B2, have the best spatial resolution.

[0024] As a further improvement of the present invention, in step 3), the candidate model input parameters (4 bands R rc data and three remote sensing indices), and construct a variety of random forest machine learning algorithms through permutations and combinations.

[0025] As a further improvement of the present invention, in step 3), based on the verification data in the field satellite-ground synchronous monitoring data, by evaluating the determination coefficient R2, the root mean square error RMSE and the relative analysis error RPD, a random forest machine learning algorithm with the highest prediction accuracy is jointly selected as the final inversion model.

[0026] In step 3), the method for calculating the total amount of algae in the euphotic zone of the entire lake is as follows:

[0027] 3.1) Acquire remote sensing images and perform image preprocessing;

[0028] 3.2) Obtaining R based on remote sensing images rc Data, calculate FAI, TWI, near infrared and red light ratio index pixel by pixel;

[0029] 3.3) Run the remote sensing estimation model for the total amount of euphotic algae on a pixel-by-pixel basis;

[0030] According to the above process, the spatial distribution of the total amount of algae in the euphotic layer of the entire lake was obtained.

[0031] As a further improvement of the present invention, in step 3.1), the acquired image is geometrically corrected and radiometrically calibrated; the geometric correction adopts Geographic Lat / Lon projection and is corrected in combination with the latitude and longitude information in the 1B data; and the lake vector boundary is used in ERDAS to extract the lake water area through masking technology to remove the influence of islands; combined with the spatial distribution characteristics of lake aquatic plants from 2000 to 2020, the aquatic plant distribution vector boundary is determined, and the influence of aquatic plants is removed through masking technology.

[0032] As a further improvement of the present invention, step 3) further includes obtaining the inter-annual and inter-month variation patterns of the total amount of algae in the euphotic layer of eutrophic lakes and their spatial distribution after processing multiple time series satellite images.

[0033] Based on the field synchronous experiment of space and ground, this paper compares and analyzes the R distribution of water bodies under different vertical distribution types of algae in the euphotic layer of highly turbid and eutrophic water bodies.rs Spectral characteristics, select MODIS B1-B7 band R rc The data and phytoplankton index, high turbidity index and near infrared to red light ratio index were used to construct a rc A random forest machine learning algorithm based on the data of total algal abundance in the euphotic zone has enabled satellite remote sensing monitoring of algal abundance in the euphotic zone of eutrophic lakes. This method can accurately capture the interannual and intermonth variations and spatial distribution of algal abundance in the euphotic zone of eutrophic lakes.

[0034] It should be understood that all combinations of the foregoing concepts and the additional concepts described in more detail below, as long as such concepts are not mutually inconsistent, can be considered part of the inventive subject matter of this disclosure. In addition, all combinations of the claimed subject matter are considered part of the inventive subject matter of this disclosure.

[0035] The foregoing and other aspects, embodiments, and features of the present invention will be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as features and / or beneficial effects of the exemplary embodiments, will become apparent from the following description or through practice of specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are not intended to be drawn to scale. In the accompanying drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For the sake of clarity, not every component is labeled in every figure. Now, embodiments of various aspects of the present invention will be described by way of example and with reference to the accompanying drawings, in which:

[0037] Figure 1 It is the vertical distribution type of algae based on field monitoring data.

[0038] Figure 2 is the water body R under different vertical types of algae rs Spectral curve.

[0039] Figure 3 This is a comparison between the prediction results of the top twelve models with the highest accuracy and the measured results.

[0040] Figure 4 is the random forest regression model structure.

[0041] Figure 5 This is a schematic diagram of the application of remote sensing monitoring of the total amount of algae in the euphotic zone based on MODIS satellite data.

[0042] In the aforementioned Figures 1-4, the coordinates, symbols or other expressions expressed in English are all well known in the art and will not be described in detail in this example. DETAILED DESCRIPTION

[0043] In order to better understand the technical content of the present invention, specific embodiments are given and described below with reference to the accompanying drawings.

[0044] Various aspects of the present invention are described in this disclosure with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. The embodiments of the present disclosure are not necessarily intended to include all aspects of the present invention. It should be understood that the various concepts and embodiments introduced above, as well as those described in more detail below, can be implemented in any of many ways, and that the concepts and embodiments disclosed herein are not limited to any implementation. In addition, some aspects of the present disclosure may be used alone or in any appropriate combination with other aspects of the present disclosure.

[0045] This embodiment takes Chaohu Lake as an example to further describe the method of the present invention.

[0046] The present invention provides a satellite remote sensing monitoring method for the total amount of algae in the euphotic zone of eutrophic lakes. The above-mentioned object is achieved by: constructing a machine learning algorithm for the total amount of algae in eutrophic lake water bodies based on satellite-ground synchronous monitoring data;

[0047] Based on field measurement data, the R distribution of water bodies under different vertical distribution types of algae in the euphotic layer of highly turbid and eutrophic water bodies was analyzed. rs Spectral characteristics;

[0048] Screen model input parameters and construct different input parameter combinations;

[0049] The random forest machine learning algorithm was selected, and multiple remote sensing estimation models for the total amount of algae in the euphotic zone were constructed based on different input parameter combinations.

[0050] Based on field satellite and ground monitoring data, the random forest algorithm with the highest accuracy and fastest calculation speed was selected as the final remote sensing estimation method for the total amount of euphotic algae.

[0051] As an exemplary description, the implementation of the above method is described in detail below with reference to the accompanying drawings.

[0052] Step 1: Analyze the R distribution of water bodies under different vertical distribution types of algae in the euphotic layer of highly turbid and eutrophic water bodies. rs Spectral characteristics;

[0053] Water body R under different vertical distribution types of algae in the euphotic layer of highly turbid and eutrophic water bodies rs Based on the spectral characteristics and field satellite-ground synchronous data, the vertical distribution of algae was clustered and analyzed, and three main vertical distribution types of algae were screened out: Figure 1), namely uniform type, surface accumulation type and subsurface highest type. The surface accumulation type mainly refers to the highest algae content in the surface layer, and the content gradually decreases with the increase of water depth. Specifically, it includes the Gaussian type with the highest surface concentration in the original classification results, as well as the exponential type and power exponential type. The subsurface highest type mainly refers to the Gaussian type with the highest concentration located 25-50 cm below the water surface. The specific expression form is shown in Table 1. Analysis of water body R with different algae vertical distribution types rs Spectral characteristics provide a theoretical basis for determining model input parameters;

[0054] Table 1 Vertical distribution types of algae

[0055]

[0056] In Table 1, z is the water depth, z0 is the depth at the highest concentration, C is the chlorophyll concentration, h is a parameter related to the peak intensity, σ is the standard deviation, and C0, m1, m2, n1, and n2 are structural parameters.

[0057] Step 2: Screening model input parameters;

[0058] The model input parameters were selected from the perspectives of reflection spectrum characteristics and easily confused ground objects: the R of MODIS B1 to B7 bands was selected based on full consideration of spatial resolution and band settings. rc The data reflects the visible-near-infrared reflectance spectral characteristics of algae under different vertical distributions. Considering that the spectral characteristics of highly turbid water bodies in the red and near-infrared bands are similar to those of water bodies with high algae content, the floating algae index FAI, the high turbidity index TWI, and the near-infrared to red light ratio index BR are selected as one of the input parameters.

[0059] The calculation methods of FAI, TWI and BR based on MODIS Rrc data are as follows:

[0060] FAI=R rc (B2)-R rc (B1)-[R rc (B5)-R rc (B5)]×(λ B2 -λ B1 ) / (λ B5 -λ B1 )

[0061] TWI=R rc (B1)-R rc (B5)

[0062] BR=R rc (B2) / R rc (B1) (1)

[0063] Where B1, B2, and B5 refer to the MODIS bands with central wavelengths of 645 nm, 859 nm, and 1240 nm, respectively; λ is the central wavelength of each MODIS band.

[0064] Step 3: Construct remote sensing inversion algorithm;

[0065] The alternative model input parameters (7-band Rrc data and 3 remote sensing indices) are constructed through permutation and combination to form a variety of random forest machine learning algorithms.

[0066] In this example, MODIS images are corrected only for Rayleigh scattering. This means that the optical information at the top of the atmosphere is free of the effects of Rayleigh scattering, while still containing aerosol and ground information. For inland water bodies, precise atmospheric correction algorithms are not yet fully mature, and there is no universal, classical atmospheric correction algorithm for inland water bodies. Using a precise atmospheric correction algorithm is highly likely to introduce significant errors and uncertainties, thus affecting the accuracy of the final analysis results. The Rayleigh scattering correction process is as follows (Hu et al., 2004):

[0067]

[0068] Where, is the sensor emissivity after correction for ozone and other gas absorption effects, F0 is the solar irradiance outside the atmosphere when the data was acquired, θ0 is the solar zenith angle, and R r is the Rayleigh reflectivity predicted using 6S (Vermote et al., 1997).

[0069] Based on the radiative transfer theory and assuming an uncoupled ocean-atmosphere system, R rc It can be expressed as:

[0070] R rc =R a +t0tR target (3)

[0071] Where R a is the aerosol reflectivity (including the interaction from aerosol molecules), R target is the surface reflectivity of the target measured in the field, t0 is the atmospheric transmittance from the sun to the target, and t is the atmospheric transmittance from the target to the satellite sensor.

[0072] Step 4: Determine a remote sensing estimation model for the total amount of algae in the euphotic zone based on a machine learning algorithm;

[0073] ① Perform geometric correction and radiometric calibration calculations on the acquired MODIS images.

[0074] Geometric correction was performed using the Geographic Lat / Lon projection, combined with the latitude and longitude information in the 1B data. The resulting positional accuracy reached 0.5 pixels. Lake vector boundaries were used in ERDAS to extract lake waters using masking techniques, removing the influence of island vegetation. Based on the spatial distribution characteristics of aquatic plants in Taihu Lake from 2000 to 2020, a unified vector boundary for aquatic plant distribution was determined, and masking techniques were used to remove the influence of aquatic plants.

[0075] ② Calculate the R values ​​of each pixel in the MODIS image at B1 (645nm), B2 (859nm), B3 (469nm), B4 (555nm), B5 (1240nm), B6 ​​(1640nm), and B7 (2140nm) rc value;

[0076] ③ Calculate FAI, TWI, and BR values ​​pixel by pixel according to formula (1);

[0077] ④ The random forest machine learning algorithm with the highest pixel-by-pixel accuracy;

[0078] The above method is used to construct the remote sensing estimation model. The input parameters of each model are shown in Table 2. The model structure is shown in Figure 4 shown.

[0079] Table 2 Input parameters of each model

[0080] Model enter N Tree num <![CDATA[R 2 ]]> RMSE(mg) RPD MAE MAPE (%) RF1 7bands 90 80 0.6813 9.8932 1.7735 7.2415 33.35 RF2 7bands+FAI 90 60 0.8273 7.2593 2.4169 5.4101 23.77 RF3 7bands+TWI 90 60 0.6570 10.239 1.7136 7.0304 32.56 RF4 7bands+FAI+TWI 90 90 0.8214 7.3793 2.3770 5.4751 24.02 RF5 5bands+FAI+TWI 90 70 0.8371 7.0454 2.4903 5.3441 24.66 RF6 4bands+FAI+TWI 90 60 0.8347 7.1095 2.4679 5.3745 25.64 RF7 4bands+FAI+BR+TWI 90 60 0.8447 6.8795 2.5504 5.0584 22.68 RF8 5bands+FAI+BR+TWI 90 60 0.8363 7.0601 2.4852 5.1587 22.85 RF9 4bands+FAI+BR 90 90 0.8355 7.0825 2.4773 5.1164 23.27 RF10 4bands+BR+TWI 90 70 0.7643 8.4790 2.0693 6.0875 27.85 RF11 4bands+TWI 90 60 0.7228 9.2357 1.8997 6.6528 32.12 RF12 4bands+BR 90. 80 0.7812 8.1711 2.1473 5.8702 26.37

[0081] The remote sensing monitoring image of the total amount of algae in the euphotic layer based on MODIS satellite data is as follows Figure 5 shown.

[0082] Based on the above steps and methods, they were applied to MODIS satellite image data that had been corrected for Rayleigh scattering. Based on the above method, after processing multiple time series satellite images, the interannual and monthly variations in the total amount of algae in the euphotic layer of eutrophic lakes and their spatial distribution were obtained.

[0083] While the present invention has been disclosed above with reference to preferred embodiments, this is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations can be made without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake, characterized in that: The following steps are involved: 1) Based on the field satellite-ground synchronous monitoring data, the vertical distribution of algae in the euphotic layer of highly turbid and eutrophic water bodies was clustered and analyzed to screen out the main vertical distribution types of algae and analyze the R of water bodies with different vertical distribution types of algae. rs spectral characteristics; 2) Water bodies R with different vertical distribution types of algae rs The input parameters of the model are screened from two perspectives: spectral characteristics and easily confused objects. The R rc Data, phytoplankton index FAI, high turbidity index TWI and near infrared to red light ratio index BR are used as alternative input parameters; the near infrared to red light ratio index refers to the near infrared band R rc Data and red light band R rc The ratio of the data; wherein the R of the B1~B7 band rc The data were selected from R wavelengths of 645 nm, 859 nm, 469 nm, 555 nm, 1240 nm, 1640 nm, and 2140 nm. rc data; 3) We permuted and combined candidate input parameters to obtain a variety of model input parameters, selected a random forest machine learning algorithm, combined it with a model constructed dataset from field satellite-ground synchronous monitoring data, and constructed multiple remote sensing estimation models for the total algal abundance in the euphotic zone; The accuracy of the above models was tested using validation data. The optimal model was selected as the remote sensing estimation model for the total amount of algae in the euphotic layer based on calculation accuracy and speed. The total amount of algae in the euphotic layer of the entire lake water area and its spatial distribution were obtained as follows: 3.1) Acquire remote sensing images and perform image preprocessing; 3.2) Obtaining R based on remote sensing images rc Data, calculate FAI, TWI, near infrared and red light ratio index pixel by pixel; 3.3) Execute the remote sensing estimation model for the total amount of euphotic algae on a pixel-by-pixel basis; According to the above process, the spatial distribution of the total amount of algae in the euphotic layer of the entire lake was obtained.

2. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: In the step 1), based on the field synchronous satellite-ground experimental data, the vertical distribution type of algae is determined by performing cluster analysis on the vertical distribution of chlorophyll a.

3. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: In step 1), the vertical distribution of algae is divided into three categories: uniform type, surface accumulation type, and subsurface highest type; Among them: exponential, power exponential and Gaussian distributions with the highest surface concentration are classified as surface accumulation type; The Gaussian type with the highest concentration at 25-50 cm below the water surface is defined as the subsurface highest type.

4. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: In step 2), R rc The data are corrected for Rayleigh scattering and are not precisely atmospheric corrected data.

5. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: In step 2), the MODIS-based R rc The FAI, TWI and near infrared to red light ratio index of the data are calculated as follows: FAI=R rc (B2)-R rc (B1)-[R rc (B5)- R rc (B5)]×(λ B2 -l B1 ) / ( λ B5 -l B1 ) TWI=R rc (B1)-R rc (B5) BR=R rc (B2) / R rc (B1) (1) Where B1, B2, and B5 refer to the MODIS bands with central wavelengths of 645 nm, 859 nm, and 1240 nm, respectively; λ is the central wavelength of each MODIS band; and BR refers to the near-infrared to red light ratio index.

6. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: In step 3), the candidate model input parameters, namely the 7 bands R rc Data and three remote sensing indices are used to construct a variety of random forest machine learning algorithms through permutations and combinations.

7. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: In step 3), based on the verification data in the field satellite-ground synchronous monitoring data, the determination coefficient R is evaluated. 2 , root mean square error RMSE and relative analytical error RPD, and jointly select a random forest machine learning algorithm with the highest prediction accuracy as the final inversion model.

8. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: Geometric correction uses Geographic Lat / Lon projection and is combined with the latitude and longitude information in the 1B data for correction; the lake vector boundary is used in ERDAS, and the lake water area is extracted through masking technology to remove the influence of islands; combined with the spatial distribution characteristics of lake aquatic plants from 2000 to 2020, the aquatic plant distribution vector boundary is determined, and the influence of aquatic plants is removed through masking technology.

9. The remote sensing monitoring method for the total amount of algae in the euphotic zone of a eutrophic lake according to claim 1, characterized in that: The step 3) further includes obtaining the inter-annual and inter-monthly variation patterns and spatial distribution of the total amount of algae in the euphotic zone of eutrophic lakes after processing a plurality of time series satellite images.

Images