A mangrove leaf chlorophyll estimation method for improving radiation transfer model

Abstract

The present application relates to a kind of improved radiation transmission model mangrove chlorophyll estimation method, comprising: the measured data of the tree height, crown width and leaf area index of mangrove are collected;Mathematical relationship between leaf area index and tree height, crown width is constructed;Simulated spectral data is generated as training set using improved radiation transmission model;The sensitive feature screening of mangrove functional traits is carried out;Random forest inversion model based on physical constraint is constructed;The present application estimates the chlorophyll content of mangrove using the random forest inversion model based on physical constraint.The beneficial effects of the present application are: the present application can effectively improve the precision of chlorophyll inversion, provide scientific basis for the fine inversion of mangrove chlorophyll, provide data support and decision-making reference for the protection and scientific management of mangrove.

Description

Technical Field

[0001] This invention belongs to the field of remote sensing inversion technology of vegetation parameters, and particularly relates to an improved radiative transfer model for estimating chlorophyll in mangroves. Background Technology

[0002] Mangroves play crucial ecological roles in seawater purification, wave protection, maintaining ecosystem diversity, and carbon storage, making them one of the most biodiverse ecosystems in tropical and subtropical coastal zones. Chlorophyll is a key component of photosynthesis in plants, directly determining plant growth, productivity, and ecological functions, and is an important biophysical parameter for evaluating ecosystem function. Accurately estimating the chlorophyll content of mangroves is of great significance for understanding the dynamic changes in mangrove ecosystems and assessing environmental stresses.

[0003] Traditional field sampling methods are destructive and limited in sample size, making it difficult to obtain regional-scale mangrove chlorophyll content. Existing methods can be categorized into empirical, physical, and hybrid approaches. The first approach, vegetation indices, is the simplest form of empirical methods, requiring only a few different calculation methods for the same bands. While fast and convenient, this method has significant limitations. Firstly, vegetation indices are based on specific band calculation formulas, making it difficult to adapt to the diversity of all plant species, especially at different growth stages or under different environmental conditions. Taking mangroves as a special ecosystem as an example, due to their complex canopy structure, vegetation indices cannot fully account for them, resulting in low inversion accuracy and large errors. The second approach uses physical models to consider the impact of canopy structure on chlorophyll estimation. The PROSAIL model is a common radiative transfer model capable of simulating the spectral response of different vegetation types. However, the PROSAIL model itself does not directly include actual growth parameters such as tree height and canopy width. Therefore, how to integrate these parameters into the model is key to further improving model performance and prediction accuracy. The third approach is the hybrid approach, which, compared to a single empirical method or physical model, combines the advantages of both, allowing for more accurate chlorophyll estimation. This type of method typically utilizes multivariate statistical analysis or machine learning techniques (such as partial least squares regression and support vector machines) to handle richer spectral information. However, hybrid approaches also present certain challenges, particularly in the selection of vegetation structure parameters. For example, while this method can reduce the impact of canopy structure on chlorophyll retrieval accuracy to some extent, many models only use the leaf area index (LAI) as a single canopy structure parameter. Given the difficulty in obtaining the LAI in practice, this can negatively impact model accuracy in certain situations. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide an improved method for estimating chlorophyll in mangroves using a radiative transfer model.

[0005] Firstly, an improved method for estimating chlorophyll in mangroves based on the radiative transfer model is provided, including:

[0006] Step 1: Collect measured data on tree height, crown width, and leaf area index of mangroves, and remove outlier data;

[0007] Step 2: Construct the mathematical relationship between leaf area index and tree height and crown width, and substitute this relationship into the radiative transfer model to improve the model;

[0008] Step 3: Use the improved radiative transfer model to generate simulated spectral data as training samples;

[0009] Step 4: Screen sensitive features of mangrove functional traits to determine input features;

[0010] Step 5: Based on the training set, construct a Physically Constrained Random Forest Inversion Model (PIRF);

[0011] Step 6: Estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

[0012] Preferably, in step 2, the mathematical relationship between the leaf area index and tree height and crown width is expressed as follows:

[0013]

[0014] Where Y is the leaf area index, X1 is the tree height, X2 is the crown width, and a, m, and n are undetermined coefficients.

[0015] Preferably, in step 2, the radiative transfer model is the PROSAIL model.

[0016] Preferably, step 4 also includes: using filtering techniques to denoise the simulated spectral data.

[0017] Preferably, it also includes: step 7, using R 2 The accuracy of the physical constraint-based random forest inversion model is evaluated using RMSE.

[0018] As a preferred embodiment, step 8 involves selecting at least one vegetation index to construct a vegetation index inversion model; and comparing the accuracy of the physical constraint-based random forest inversion model with that of the vegetation index inversion model.

[0019] In a second aspect, an improved mangrove chlorophyll estimation device based on a radiative transfer model is provided for performing any of the methods described in the first aspect, including:

[0020] The data collection module is used to collect measured data on tree height, crown width, and leaf area index of mangroves, and to remove outlier data.

[0021] A module is built to construct the mathematical relationship between leaf area index and tree height and crown width, and this relationship is then substituted into the radiative transfer model to improve the model.

[0022] The generation module is used to generate simulated spectral data as a training set using the improved radiative transfer model.

[0023] The filtering module is used to filter sensitive features of mangrove functional traits to determine input features;

[0024] A building module is used to construct a physically constrained random forest inversion model based on the training set;

[0025] The estimation module is used to estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

[0026] Thirdly, a computer storage medium is provided, wherein a computer program is stored therein; when the computer program is run on a computer, the computer causes the computer to perform any of the methods described in the first aspect.

[0027] Fourthly, an electronic device is provided, comprising:

[0028] Memory, used to store computer programs;

[0029] A processor for executing the computer program to implement the method as described in any of the first aspects.

[0030] The beneficial effects of this invention are as follows: First, this invention establishes the relationship between mangrove leaf area index (LAI) and tree height and crown width based on measured data, and introduces this relationship into the PROSAIL model, which allows for simple and efficient estimation of mangrove leaf area index. Then, based on the improved PROSAIL model, a method for estimating mangrove chlorophyll is proposed, and validated using UAV data and measured data. This method can effectively improve the accuracy of chlorophyll inversion, providing a scientific basis for the refined inversion of mangrove chlorophyll, and offering data support and decision-making reference for the protection, restoration, and scientific management of mangroves. Therefore, the method proposed in this invention has significant practical application value. Attached Figure Description

[0031] Figure 1 This is a flowchart of an improved radiative transfer model for estimating chlorophyll in mangroves, provided by the present invention.

[0032] Figure 2 This is a schematic diagram of the global sensitivity analysis of the PROSAIL model parameters provided by the present invention;

[0033] Figure 3This is a schematic diagram of the structure of a mangrove chlorophyll estimation device based on an improved radiative transfer model provided by the present invention. Detailed Implementation

[0034] The present invention will be further described below with reference to embodiments. The description of the embodiments below is only for the purpose of helping to understand the present invention. It should be noted that those skilled in the art can make several modifications to the present invention without departing from the principle of the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

[0035] Example 1:

[0036] Leaf area index (LAI), crown width, and tree height are all important parameters describing mangrove canopy structure. LAI is a crucial parameter for measuring the number and distribution of plant leaves, widely used in vegetation monitoring, crop growth research, and ecological environment assessment. However, direct measurement of LAI is often complex, costly, and affected by factors such as light conditions, leaf morphology, and distribution, leading to inaccurate chlorophyll estimation. Therefore, how to accurately and efficiently estimate LAI has become a key research issue. Tree height and crown width are fundamental indicators of canopy structure and are easily obtained through remote sensing imagery or ground measurements. In practical applications, tree height and crown width are usually correlated with LAI. Using these readily available indicators to estimate LAI can not only reduce measurement costs but also improve data timeliness and accuracy. Most existing LAI estimation methods neglect the influence of tree height and crown width, failing to establish a relationship between LAI and these parameters to improve the accuracy of chlorophyll estimation.

[0037] Therefore, in order to solve the problems of difficulty in obtaining the leaf area index of mangroves and low accuracy of physical models, Embodiment 1 of this application provides an improved radiative transfer model for estimating chlorophyll in mangroves. First, the relationship between leaf area index (LAI) and tree height and crown width is established based on measured data, and this relationship is introduced into the PROSAIL model. Then, a random forest inversion method based on physical constraints is constructed and compared with vegetation indices. The method is verified by combining UAV data and measured data.

[0038] Specifically, this invention provides an improved radiative transfer model for estimating chlorophyll in mangroves. Taking the Aojiang Estuary mangrove data as an example, it is implemented based on the PROSAIL model, such as... Figure 1 As shown, it includes:

[0039] Step 1: Collect measured data on tree height, crown width, and leaf area index of mangroves, and remove outlier data.

[0040] Specifically, we collected measured data on mangrove parameters, including tree height, east-west crown width, north-south crown width, and leaf area index. We calculated the average of the east-west and north-south crown widths as the tree crown width and used the three-σ principle to remove abnormal parameter groups.

[0041] Step 2: Construct the mathematical relationship between leaf area index and tree height and crown width, and substitute this relationship into the radiative transfer model to improve the model.

[0042] In step 2, the radiative transfer model is the PROSAIL model.

[0043] In step 2, the mathematical relationship between the leaf area index and tree height and crown width is expressed as follows:

[0044]

[0045] Where Y is the leaf area index, X1 is the tree height, X2 is the crown width, and a, m, and n are undetermined coefficients.

[0046] Step 3: Use the improved radiative transfer model to generate simulated spectral data as training samples.

[0047] For example, simulated spectral data were obtained using SIMLAB software and an improved PROSAIL model as training samples.

[0048] Step 3 also includes: using filtering techniques to reduce random noise in the spectral data.

[0049] For example, the obtained simulated spectral data are shown in Table 1.

[0050] Table 1

[0051]

[0052] Step 4: Screen sensitive features of mangrove functional traits to determine input features.

[0053] For example, such as Figure 2 As shown, the SIMLAB software was used to screen sensitive features of mangrove functional traits, which were then applied to the training set to determine the input features for the next model step.

[0054] Step 5: Based on the training set, construct a Physically Constrained Random Forest Inversion Model (PIRF).

[0055] Specifically, based on the traditional Random Forest (RF), physical constraints are systematically integrated into a series of strategies and steps in the construction, training, and prediction process of the Random Forest inversion model. The physical mechanism of the PROSAIL model is deeply integrated, and a physically interpretable architecture is designed to replace the simple application of existing RF / SVM / PLS.

[0056] Step 6: Estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

[0057] Example 2:

[0058] Based on Example 1, Example 2 of this application provides a more specific improved radiative transfer model for estimating chlorophyll in mangroves, including:

[0059] Step 1: Collect measured data on tree height, crown width, and leaf area index of mangroves, and remove outlier data.

[0060] Step 2: Construct the mathematical relationship between leaf area index and tree height and crown width, and substitute this relationship into the radiative transfer model to improve the model.

[0061] Step 3: Use the improved radiative transfer model to generate simulated spectral data as a training set.

[0062] Step 4: Screen sensitive features of mangrove functional traits to determine input features.

[0063] Step 5: Based on the training set, construct a physical constraint-based random forest inversion model.

[0064] Step 6: Estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

[0065] Step 7: Use R 2 The accuracy of the physical constraint-based random forest inversion model is evaluated using RMSE.

[0066] For example, as shown in Table 2, using R 2 And RMSE to evaluate model accuracy.

[0067] Table 2

[0068] Traditional RF Physically Constrained Random Forest CIgreen VOG2 <![CDATA[R 2 ]]> 0.71 0.82 0.75 0.91 <![CDATA[RMSE(μg / cm 2 )]]> 15.2 10.2 28.42 30.17

[0069] Step 8: Select at least one vegetation index to construct a vegetation index inversion model; compare the accuracy of the physical constraint-based random forest inversion model with that of the vegetation index inversion model.

[0070] For example, vegetation indices CIgreen and VOG2 are used, as shown in Table 3.

[0071] Table 3

[0072] Vegetation Index Calculation formula Inversion model CIgreen <![CDATA[R 780 / R 550 –1]]> y = 26.705x + 26.421 VOG2 <![CDATA[(R 734 –R 747 ) / (R 715 +R 726 )]]> y = –512.21x + 35.888

[0073] Among them, R n This represents the reflectivity of the band with wavelength n.

[0074] It should be noted that the parts in this embodiment that are the same as or similar to those in Embodiment 1 can be referred to each other, and will not be repeated in this application.

[0075] Example 3:

[0076] Based on Example 1, Example 3 of this application provides a mangrove chlorophyll estimation device with an improved radiative transfer model, comprising:

[0077] The data collection module is used to collect measured data on tree height, crown width, and leaf area index of mangroves, and to remove outlier data.

[0078] A module is built to construct the mathematical relationship between leaf area index and tree height and crown width, and this relationship is then substituted into the radiative transfer model to improve the model.

[0079] The generation module is used to generate simulated spectral data as a training set using the improved radiative transfer model.

[0080] The filtering module is used to filter sensitive features of mangrove functional traits to determine input features;

[0081] A construction module is used to construct a physically constrained random forest inversion model based on the training samples;

[0082] The estimation module is used to estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

[0083] It should be noted that the system provided in this embodiment is the same as the device corresponding to the method provided in embodiment 1. Therefore, the parts that are the same as or similar to those in embodiment 1 in this embodiment can be referred to each other, and will not be described again in this application.

[0084] In summary, this invention proposes an improved radiative transfer model for estimating chlorophyll in mangroves, combining the radiative transfer model with machine learning. This method effectively improves the accuracy of chlorophyll retrieval, providing a scientific basis for refined chlorophyll retrieval. It also provides data support and decision-making reference for the protection, restoration, and scientific management of mangroves. Therefore, the method proposed in this invention has significant practical application value.

Claims

1. A method for estimating chlorophyll in mangroves using an improved radiative transfer model, characterized in that, include: Step 1: Collect measured data on tree height, crown width, and leaf area index of mangroves, and remove outlier data; Step 2: Construct the mathematical relationship between leaf area index and tree height and crown width, and substitute this relationship into the radiative transfer model to improve the model; Step 3: Use the improved radiative transfer model to generate simulated spectral data as a training set; Step 4: Screen sensitive features of mangrove functional traits to determine input features; Step 5: Based on the training set, construct a physical constraint-based random forest inversion model; Step 6: Estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

2. The mangrove chlorophyll estimation method based on the improved radiative transfer model according to claim 1, characterized in that, In step 2, the mathematical relationship between the leaf area index and tree height and crown width is expressed as follows: Where Y is the leaf area index, X1 is the tree height, X2 is the crown width, and a, m, and n are undetermined coefficients.

3. The mangrove chlorophyll estimation method based on the improved radiative transfer model according to claim 2, characterized in that, In step 2, the radiative transfer model is the PROSAIL model.

4. The mangrove chlorophyll estimation method based on the improved radiative transfer model according to claim 3, characterized in that, Step 3 also includes: using filtering techniques to denoise the simulated spectral data.

5. The mangrove chlorophyll estimation method based on the improved radiative transfer model according to claim 4, characterized in that, It also includes: Step 7, using R 2 The accuracy of the physical constraint-based random forest inversion model is evaluated using RMSE.

6. The method for estimating chlorophyll in mangroves using the improved radiative transfer model according to claim 5, characterized in that, It also includes: Step 8, selecting at least one vegetation index to construct a vegetation index inversion model; comparing the accuracy of the physical constraint-based random forest inversion model with the vegetation index inversion model.

7. A mangrove chlorophyll estimation device based on an improved radiative transfer model, characterized in that, For performing the method according to any one of claims 1 to 6, comprising: The data collection module is used to collect measured data on tree height, crown width, and leaf area index of mangroves, and to remove outlier data. A module is built to establish the mathematical relationship between leaf area index and tree height and crown width, and this relationship is then substituted into the radiative transfer model to improve the model. The generation module is used to generate simulated spectral data as a training set using the improved radiative transfer model. The filtering module is used to filter sensitive features of mangrove functional traits to determine input features; A building module is used to construct a physically constrained random forest inversion model based on the training set; The estimation module is used to estimate the chlorophyll content of mangroves using the physical constraint-based random forest inversion model.

8. A computer storage medium, characterized in that, The computer storage medium stores a computer program; when the computer program is run on the computer, it causes the computer to perform the method described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method as described in any one of claims 1 to 6.

Images