Eutrophication index inversion method and system based on resource No.1 hyperspectral data

Abstract

The invention provides a eutrophication index inversion method based on resource No.1 hyperspectral data, and the method comprises the following steps: 1, obtaining remote sensing data, and carrying out the preprocessing of the remote sensing data, and the preprocessing comprises the radiometric calibration, FLAASH atmospheric correction and image cutting; step 2, carrying out resampling on the actually measured spectral reflectivity; 3, constructing a sensitive wave band combination; 4, a CatBoost model is trained; and 5, calculating the eutrophication index. By applying the technical scheme, the product synergistic effect of COD, DIN and PO4 < 3-> can be accurately reflected, and evaluation deviation of a single parameter or a linear model is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental remote sensing, and in particular to a method and system for inverting eutrophication index based on the hyperspectral data of Ziyuan-1 satellite. Background Art

[0002] In the prior art, empirical formulas or semi-empirical models (such as band ratio method, multiple regression) are generally used to invert single water quality parameters. For example, using the data of Gaofen-1 satellite, a soft classification model is constructed through the non-linear relationship between band reflectance and turbidity to invert the total suspended solids concentration; or based on Sentinel-2 data, an inversion formula is established using the exponential relationship between band combination (such as B4 / B3) and chlorophyll a concentration. Such technologies manually select features, have insufficient generalization ability for complex type-II waters (containing a mixture of multiple pollutants), and cannot reflect the comprehensive state of eutrophication.

[0003] Model deviation caused by parameter singularity: Only relying on chlorophyll a concentration as the eutrophication determination index, without considering the synergistic effect of chemical oxygen demand (COD), dissolved inorganic nitrogen (DIN), and reactive phosphate (PO4 3- ). Since eutrophication is essentially a comprehensive effect caused by excessive input of nutrients, a single parameter cannot characterize the non-linear coupling relationship between pollutants, resulting in a systematic deviation between the evaluation result and the true eutrophication state.

[0004] Insufficient band adaptability: The spectral range of Sentinel-2 (400 - 2200 nm) is not optimized for the hyperspectral characteristics of coastal type-II waters. Especially for the short-wave infrared band (1200 - 1300 nm) sensitive to PO43-, the spectral resolution is insufficient, resulting in the inability to effectively extract spectral features related to PO43- concentration.

[0005] Limitations of linear models: Using a linear regression model (such as the linear relationship between NDCI and chlorophyll a), without considering the non-linear interference of suspended solids and colored dissolved organic matter (CDOM) in type-II waters on optical signals, resulting in the inversion error being transmitted to the eutrophication evaluation result through a single-parameter model. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method and system for inverting eutrophication index based on the hyperspectral data of Ziyuan-1 satellite, so as to accurately reflect the multiplicative synergistic effect of COD, DIN, and PO4 3- and avoid the evaluation deviation of single parameters or linear models.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions: A method for inverting eutrophication index based on the hyperspectral data of Ziyuan-1 satellite, comprising the following steps:

[0008] Step 1: Obtain remote sensing data and perform preprocessing on it. The preprocessing includes radiometric calibration, FLAASH atmospheric correction, and image cropping;

[0009] Step 2: Resample the measured spectral reflectance;

[0010] Step 3: Construct a sensitive band combination;

[0011] Step 4: Train the CatBoost model;

[0012] Step 5: Calculate the eutrophication index.

[0013] In a preferred embodiment, the radiometric calibration in Step 1 specifically includes the following processing steps:

[0014] For the radiometric calibration processing of the Ziyuan-1 AHSI image in the present invention, in the Radiometric Calibration parameter setting panel in the remote sensing image processing platform ENVI, click the Apply FLAASH Settings button, and the remaining parameters will be automatically adjusted to the data input format required by FLAASH atmospheric correction. Click OK to perform the radiometric calibration processing.

[0015] In a preferred embodiment, the FLAASH atmospheric correction in Step 1 specifically includes the following processing steps:

[0016] In the remote sensing image processing platform ENVI, select the FLAASH atmospheric correction function. In the pop-up interface, set the satellite altitude Sensor Altitude to 778 km, the regional ground average elevation Ground Elevation to 0.023, the pixel size Pixel Size to 30 m, the atmospheric model Atmospheric Model to Tropical, the water vapor retrieval WaterRetrieval to Yes, select the water vapor absorption band as 940 nm, the aerosol model Aerosol Model to Martime, the spectral smoothing Spectral Polishing to Yes, and the width Width to 3. After setting the parameters, click the apply button to perform the FLAASH atmospheric correction processing.

[0017] In a preferred embodiment, the image cropping in Step 1 specifically includes the following processing steps:

[0018] Adopt the method of approximately estimating the remote sensing reflectance of the image to remove the influence of skylight on the surface reflectance image after FLAASH atmospheric correction. The calculation formula is shown in Equation (1):

[0019] (1)

[0020] In the formula, λ is the band of the remote sensing image, that is, each original spectral value, represents the remotely sensed reflectance approximately estimated on the image, represents the surface reflectance, represents the smaller value of the near-infrared and short-wave infrared surface reflectances, and π is the pi; the image after atmospheric correction processing is cropped by NDWI to obtain the water area of the study area, which is used as the image for inverting the water quality parameter concentration and input into the constructed CatBoost model; the NDWI calculation formula is as follows:

[0021]

[0022] In the formula, b20 is the 20th band of Ziyuan-1 AHSI, and b41 is the 41st band of Ziyuan-1 AHSI; the area with pixel value greater than 0.5 in the processed image is extracted, that is, the water area of the study area is obtained.

[0023] In a preferred embodiment, in the step 2, the true water body reflectance is also required for inverting the water quality parameter concentration; taking the true water body reflectance as a medium, a non-linear relationship model between the satellite image and the measured water quality parameter concentration is established by resampling the true water body reflectance to the remotely sensed reflectance of Ziyuan-1 AHSI; through the 1 nm resolution spectral curve measured by the ASD spectrometer, the measured spectral reflectance is resampled to the 10 nm spectral interval of Ziyuan-1 AHSI by using the linear interpolation method;

[0024] That is, for each sample j, the original spectrum is defined as: λ = [λ 1 , λ 2 ,..., λ n ] , corresponding to the spectral value S j (λ) = [S j1 , S j2 ,...,S jn ] , and the target wavelength sequence is defined as λ * = [λ 1 * , λ 2 * ,..., λ n* ] , after interpolation, the spectral value at each is:

[0025]

[0026] In the formula, is the target interpolation wavelength, is the estimated spectral value of the j-th sample after interpolation at the target interpolation wavelength , and are respectively the two adjacent wavelengths closest to , and are respectively the spectral values of the j-th sample at wavelengths and ; finally, the chemical oxygen demand concentration COD, the inorganic nitrogen concentration DIN, and the reactive phosphate concentration PO4 3- are processed by taking the logarithm to the base 10, that is, lg(COD), lg(DIN), lg(PO4 3- ).

[0027] In a preferred embodiment, in step 3, a combination of ratio, normalization, three-band and ratio, and three-band reciprocal difference product satellite bands is constructed, and the Pearson correlation coefficient is used to calculate the correlation coefficients between the band combination and lg(COD), lg(DIN), lg(PO4 3- ); combinations with an absolute value of the correlation coefficient > 0.6 are selected, and combinations with a band interval < 20 nm are excluded:

[0028] (2)

[0029] In the formula, is the covariance, is the product of the standard deviations between two variables; the detailed calculation formula is:

[0030]

[0031] where X is the combined result of the reflectances of each band, and R COD , R DIN , R PO4 3- respectively represent the correlations between COD, DIN, PO4 3- and the combined result of the band reflectances.

[0032] In a preferred embodiment, in step 4, the resampled AHSI reflectance and its corresponding water quality parameters are divided into a training set and a test set at a ratio of 8:2; import the CatBoost library in python, and use the selected parameters to invert the concentrations of lg(COD), lg(DIN), and lg(PO4 3- )

[0033] There are two hyperparameters Parme1 and Parme2, and the parameter values corresponding to the two hyperparameters are a1, a2 and b1, b2, b3 respectively, that is:

[0034]

[0035] Traverse all combinations , perform training analysis on all parameter combinations, and finally select the parameters of the model.

[0036] In a preferred embodiment, in step 5, according to the CatBoost inversion model obtained in step 4, input the AHSI remote sensing image after atmospheric correction, and the values of lg(COD), lg(DIN), and lg(PO4 3- ) are obtained, perform mathematical operations on them, convert them to the values before taking the logarithm, and calculate using the eutrophication index calculation formula as shown in formula (3):

[0037] (3)

[0038] In the formula, E is the eutrophication index, dimensionless; COD is the chemical oxygen demand concentration obtained by inversion; PO4 3- is the reactive phosphate concentration obtained by inversion; DIN is the inorganic nitrogen concentration obtained by inversion.

[0039] The present invention also provides a eutrophication index inversion system based on the high-spectral data of Ziyuan-1 satellite, which runs the above-mentioned eutrophication index inversion method based on the high-spectral data of Ziyuan-1 satellite.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. Realize non-linear eutrophication evaluation with multi-parameter coordination

[0042] Accurately reflect the product synergy effect of COD, DIN, and PO4 3- , and avoid the evaluation deviation of single parameters or linear models.

[0043] 2. Accurate feature extraction of hyperspectral band combinations

[0044] Based on the 330-band data of Ziyuan-1 AHSI, four types of combinations are constructed, namely band ratio (R), normalization (ND), sum ratio (SR), and reciprocal difference product (RDP), to improve the inversion accuracy of COD, DIN, and PO4 3- and reduce spectral noise interference.

[0045] 3. Dynamic monitoring of eutrophication with high spectral resolution

[0046] Utilize the advantages of the large swath width (60 km) and high spectral resolution (10 nm) of Ziyuan-1 AHSI images to cover the entire study area. Description of the drawings

[0047] Figure 1 It is a schematic flowchart of a preferred embodiment of the present invention. Detailed implementation manners

[0048] The present invention will be further described below in conjunction with the drawings and embodiments.

[0049] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanations for the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0050] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present application; as used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or their combinations.

[0051] A method for inverting eutrophication index based on Ziyuan-1 hyperspectral data, referring to Figure 1 , includes the following steps:

[0052] Step 1: Acquisition and preprocessing of remote sensing data

[0053] Since satellites are vulnerable to atmospheric influence during signal transmission, atmospheric correction is required to mitigate the atmospheric influence and convert the pixel values of satellite images into true water reflectance. The present invention converts the original pixel values of the Ziyuan-1 AHSI image into radiance values. First, radiometric calibration is used to convert the original reflectance recorded by the sensor into the surface reflectance of the atmosphere. Then, the FLAASH (Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes) algorithm is used to eliminate the interference of aerosols, water vapor, etc., and convert the surface reflectance of the atmosphere into the true surface reflectance.

[0054] For the radiometric calibration process of the Ziyuan-1 AHSI image in the present invention, in the Radiometric Calibration parameter setting panel in the ENVI software, click the Apply FLAASH Settings button, and the remaining parameters will be automatically adjusted to the data input format required for FLAASH atmospheric correction. Click OK to perform the radiometric calibration process.

[0055] For the FLAASH atmospheric correction of the Ziyuan-1 AHSI image in the present invention, set the satellite altitude (SensorAltitude) to 778 km, the average ground elevation of the area (Ground Elevation) to 0.023, the pixel size (PixelSize) to 30 m, the atmospheric model (Atmospheric Model) to Tropical, the water vapor retrieval (WaterRetrieval) to Yes, select the water vapor absorption band to be 940 nm, the aerosol model (Aerosol Model) to Maritime, the spectral polishing (Spectral Polishing) to Yes, and the width (Width) to 3. After setting the parameters, click the apply button to perform the FLAASH atmospheric correction process.

[0056] For the surface reflectance image after FLAASH atmospheric correction, the influence of skylight needs to be removed. For the Ziyuan-1 AHSI image, the present invention adopts a method for approximately estimating the remote sensing reflectance based on the image, and the calculation formula is shown in Equation (1):

[0057] (1)

[0058] In the formula, represents the remotely sensed reflectance approximately estimated on the image, represents the surface reflectance, represents the smaller value of the near-infrared and short-wave infrared surface reflectances. In the present invention, Set as the average value of each wavelength band in the range of 730 - 760 nm, and set as the average reflectance of each wavelength band in the range of 1530 - 1630 nm. Use the NDWI to crop the water area of the study area from the image after atmospheric correction, which is used as the image for inverting the concentration of water quality parameters, and input it into the constructed CatBoost model. The NDWI calculation formula is as follows:

[0059]

[0060] In the formula, b20 is the 20th band of Ziyuan-1 AHSI, and b41 is the 41st band of Ziyuan-1 AHSI. Extract the area where the pixel value in the processed image is greater than 0.5 to obtain the water area of the study area.

[0061] Step 2: Resampling of measured data

[0062] In addition to satellite images, real water reflectance is also required for inverting the concentration of water quality parameters. Through resampling the real water reflectance to the remote sensing reflectance of Ziyuan-1 AHSI, a non-linear relationship model between satellite images and the measured concentration of water quality parameters can be established. In the present invention, the 1 nm resolution spectral curve measured by the ASD spectrometer is resampled to the 10 nm spectral interval of Ziyuan-1 AHSI (covering the range of 400 - 2500 nm) by the linear interpolation method.

[0063] That is, for each sample j, the original spectrum is defined as: λ = [λ 1 , λ 2 ,..., λ n ] , corresponding spectral value S j (λ) = [S j1 , S j2 ,...,S jn ] , define the target wavelength (Ziyuan-1 hyperspectral AHSI) sequence as λ * = [λ 1 * , λ 2 * ,..., λ n * ] , then after interpolation, at each The spectral value at

[0064]

[0065] In the formula, is the target interpolation wavelength, is the estimated spectral value of the j-th sample after interpolation at the target wavelength , , are the two adjacent wavelengths closest to , , are the spectral values of the j-th sample at wavelengths , . Finally, since the true value ranges of the measured water quality parameters COD, DIN, and PO4 3- are small, the three elements COD, DIN, and PO4 3- need to be processed by taking the logarithm to the base 10, i.e., lg(COD), lg(DIN), lg(PO4 3- ), to ensure the accuracy of the model modeling results.

[0066] Step 3: Construction of sensitive band combinations

[0067] Constructing four band combinations (ratio, normalization, three-band ratio, and three-band reciprocal difference product) from different satellite bands through conventional mathematical operations can help improve the accuracy of model inversion. The present invention calculates the correlation coefficients of all possible band combinations with lg(COD), lg(DIN), and lg(PO4 3- ) according to the Pearson correlation coefficient (Equation 2). Combinations with an absolute value of the correlation coefficient > 0.6 are selected, and combinations with a band interval < 20 nm are excluded (to avoid multicollinearity caused by spectral overlap).

[0068] (2)

[0069] In the formula, is the covariance, is the product of the standard deviations between two variables. For the present invention, the detailed formula for calculation is:

[0070]

[0071] where X is the combined result of the reflectances of each band. The present invention finally selects four types of band combinations, namely 567nm / 533nm, (585nm - 473nm) / (585nm + 473nm), (438nm + 516nm) / 473nm, and (1 / 670nm - 1 / 695nm) × 816nm, as the characteristic variables for inversion.

[0072] Step 4. CatBoost Model Training and Analysis

[0073] Divide the resampled AHSI reflectance and its corresponding water quality parameters into a training set (39 samples) and a test set (10 samples) at a ratio of 8:2. Import the CatBoost library in Python and use the grid search method to determine the optimal parameters (as shown) to invert the concentrations of lg(COD), lg(DIN), and lg(PO4 3- ).

[0074] Table Optimal Parameter Settings for CatBoost

[0075] parameter value iterations 600 learning_rate 0.01 l2_leaf_reg 2 max_depth 3 loss_function RMSE eval_metric R2 verbose 0

[0076] The grid search method is an exhaustive search algorithm that tries all possible combinations in a predefined parameter space to find the parameter configuration that gives the best performance of the model on the validation set. That is, assume there are two hyperparameters Parme1 and Parme2, and the possible parameter values corresponding to the two hyperparameters are a1, a2 and b1, b2, b3 respectively, i.e.:

[0077]

[0078] Then the grid search will traverse all combinations . The grid search method will perform model training and analysis on all parameter combinations, and finally select a parameter combination with the highest accuracy on the training set and the test set as the optimal parameters of the model.

[0079] Step 5. Calculation of Eutrophication Index

[0080] According to the CatBoost inversion model obtained in the above steps, input the corrected AHSI remote sensing image to obtain the values of the three water quality parameters lg(COD), lg(DIN), and lg(PO4 3- ), perform mathematical operations on them to convert them to the values before taking the logarithm, and use the eutrophication index calculation formula as shown in Equation (3) to calculate:

[0081] (3)

[0082] In the formula, E is the eutrophication index, dimensionless; COD is the chemical oxygen demand concentration (mg / L) obtained by inversion; PO4 3- is the reactive phosphate concentration (mg / L) obtained by inversion; DIN is the inorganic nitrogen concentration (mg / L) obtained by inversion.

[0083] Key points and points to be protected proposed in this application

[0084] 1. Sensitive band screening method for hyperspectral data

[0085] Based on 330 hyperspectral bands of Ziyuan-1 AHSI, construct a feature set through the following four types of combinations, and screen the band combination with the highest correlation coefficient and no redundancy ( )

[0086] Table 2 Reflectance combinations of characteristic bands and corresponding formulas

[0087]

[0088] Existing technologies mostly use single-band ratios (such as NDCI) or original band reflectances, and do not optimize the combination types for multi-parameter inversion requirements. This method solves the problem of feature redundancy caused by the blindness of band selection in traditional methods through band combinations (such as reciprocal difference product) and Pearson correlation coefficient threshold screening (|r|>0.6).

[0089] Utilize the high hyperspectral resolution (330 bands) of Ziyuan-1 AHSI images, combine with the inversion process, calculate the E value pixel by pixel and generate a spatial distribution map of the eutrophication index.

[0090] Existing technologies (such as UAV hyperspectral) have a small coverage area (<10 km²) and cannot meet the large-scale monitoring requirements of coastal aquaculture areas. The present invention solves the problem of insufficient resolution of wide-band satellites such as Sentinel-2 in the short-wave infrared (PO4 3- sensitive area) through the hyperspectral adaptability of Ziyuan-1 AHSI (band coverage 400-2500 nm).

Claims

1. A method for retrieving eutrophication index based on Ziyuan-1 hyperspectral data, characterized in that The following steps are involved: Step 1: Acquire remote sensing data and preprocess it, including radiometric calibration, FLAASH atmospheric correction, and image cropping. Step 2: Resample the measured spectral reflectance; Step 3: Construct sensitive band combination; Step 4: Train the CatBoost model. Step 5: Calculate the eutrophication index.

2. The eutrophication index inversion method based on Resource No. 1 hyperspectral data according to claim 1 is characterized in that: The radiation calibration in step 1 specifically includes the following processing steps: For the radiometric calibration processing of the Resource No. 1 AHSI image in the present invention, you can directly click the Apply FLAASH Settings button in the Radiometric Calibration parameter setting panel of the remote sensing image processing platform ENVI. The remaining parameters will be automatically adjusted to the data input format required by FLAASH atmospheric correction. Click OK to perform radiometric calibration processing.

3. A method for inverting eutrophication index based on Ziyuan-1 hyperspectral data according to claim 1, characterized in that, The FLAASH atmospheric correction in step 1 specifically includes the following processing steps: In the remote sensing image processing platform ENVI, select the FLAASH atmospheric correction function. In the pop-up interface, set the satellite altitude Sensor Altitude to 778km, the regional average ground elevation to 0.023, the pixel size to 30m, the atmospheric model Atmospheric Model to Tropical, the water vapor inversion WaterRetrieval to Yes, and select the water vapor absorption band to 940nm, the Aerosol Model to Martime, the spectral smoothing to Yes, and the width to 3. After setting the parameters, click the Apply button to perform the FLAASH atmospheric correction processing.

4. The method for inverting the eutrophication index based on the hyperspectral data of Ziyuan-1 according to claim 1, characterized in that The image cropping in step 1 specifically includes the following processing steps: The image remote sensing reflectance approximate estimation method is used to remove the influence of sky light on the surface reflectance image after FLAASH atmospheric correction. The calculation formula is shown in formula (1): （1） Where λ is the band of the remote sensing image, that is, the original spectral value, Represents the remote sensing reflectance estimated approximately on the image, represents the surface reflectivity, represents the smaller value of the near-infrared and short-wave infrared surface reflectance, and π is the circumference of the circle. The atmospheric correction image is clipped using NDWI to identify the water area of the study area. This image is used to invert the concentration of water quality parameters and is input into the constructed CatBoost model. The NDWI calculation formula is as follows: In the formula, b20 is the 20th band of Ziyuan-1 AHSI, and b41 is the 41st band of Ziyuan-1 AHSI; the areas in the processed image with pixel values greater than 0.5 are extracted, and thus the water areas of the study area are obtained.

5. A method for retrieving eutrophication index based on Ziyuan-1 hyperspectral data according to claim 1, characterized in that, In step 2, the inversion of water quality parameter concentrations also requires real water body reflectance; using the real water body reflectance as a medium, a nonlinear relationship model between satellite images and measured water quality parameter concentrations is established by resampling the real water body reflectance to the Resource-1 AHSI remote sensing reflectance; using the 1 nm resolution spectral curve measured by the ASD spectrometer, the measured spectral reflectance is resampled to the 10 nm spectral interval of the Resource-1 AHSI using a linear interpolation method; That is, for each sample j , define the original spectrum as: λ=[λ 1 ,λ 2 ,...,λ n ] , corresponding to the spectral value S j (λ) = [S j1 , S j2 ,...,S jn ] , define the target wavelength sequence as λ * = [λ 1 * ,λ 2 * ,...,λ n * ] , then after interpolation, at each The spectral value at is: In the formula, is the target interpolation wavelength, is the estimated spectral value of the j-th sample after interpolation at the target interpolation wavelength ; , are respectively the two adjacent wavelengths closest to ; , are respectively the spectral values of the j-th sample at wavelengths , ; finally, the chemical oxygen demand concentration COD, the inorganic nitrogen concentration DIN, and the reactive phosphate concentration PO4 3- are processed by taking the logarithm to the base 10, i.e., lg(COD), lg(DIN), lg(PO4 3- ).

6. The method for inverting the eutrophication index based on the hyperspectral data of Ziyuan-1 according to claim 1, wherein In step 3, combinations of satellite bands of ratio, normalization, three-band and ratio, and three-band reciprocal difference product are constructed, and the Pearson correlation coefficient is used to calculate the correlation coefficients between the band combinations and lg(COD), lg(DIN), lg(PO4 3- ) ; select the combinations with the absolute value of the correlation coefficient > 0.6, and exclude the combinations with a band interval < 20 nm: （2） In the formula, is the covariance, is the product of the standard deviations of the two variables; the detailed calculation formula is: Among them, X is the combined result of the reflectivity of each band, R COD , R DIN , R PO4 3- Represents COD, DIN, PO4 3- Correlation with the combined results of the band reflectances.

7. The eutrophication index inversion method based on Resource No. 1 hyperspectral data according to claim 1, characterized in that: In step 4, the resampled AHSI reflectance and its corresponding water quality parameters are divided into a training set and a test set at a ratio of 8:2; import the CatBoost library in python and use the selected parameters to invert the concentrations of lg(COD), lg(DIN), and lg(PO4 3- ) Suppose there are two hyperparameters Parme1 and Parme2, and the parameter values corresponding to the two hyperparameters are a1, a2 and b1, b2, b3, namely: Traverse all combinations , perform training analysis on all parameter combinations for the model, and finally select the parameters of the model.

8. The method for inverting the eutrophication index based on the hyperspectral data of Ziyuan-1 according to claim 1, wherein, In step 5, the CatBoost inversion model obtained in step 4 is used to input the atmospherically corrected AHSI remote sensing image, and the lg(COD), lg(DIN), lg(PO4 3- ) value, perform mathematical operations on it, convert it into a logarithmic value, and use the eutrophication index calculation formula as shown in formula (3): （3） Where E is the eutrophication index, dimensionless; COD is the chemical oxygen demand concentration obtained by inversion; PO4 3- is the reactive phosphate concentration obtained by inversion; DIN is the inorganic nitrogen concentration obtained by inversion.

9. An eutrophication index inversion system based on the hyperspectral data of Ziyuan-1, characterized in that Run the eutrophication index inversion method based on Resource No. 1 hyperspectral data as described in any one of claims 1 to 8.

Images