Large-scale mangrove forest canopy height accurate inversion method based on multi-source remote sensing image and XGBoost regression model

Abstract

The invention provides a mangrove forest canopy height remote sensing accurate inversion method based on multi-source remote sensing data and an XGBoost regression model, and the method comprises the steps: firstly carrying out image collection and preprocessing: obtaining UAV-LiDAR data of a typical region in a low tide period, and carrying out the preprocessing of the collected UAV-LiDAR data; the method comprises the following steps: screening a high-quality SDGSAT-1 image and a time sequence Sentinel-1 / 2 image, and extracting feature parameters based on a satellite image to construct a mangrove forest canopy height inversion initial feature set; secondly, constructing a mangrove forest canopy height inversion optimal feature set based on an XGBoost regression model, a cross validation recursive feature elimination method and an SHAP interpretation framework; and finally, accurately inverting the mangrove forest canopy height based on an XGBoost regression model and the optimal feature set, and drawing a large-scale mangrove forest canopy height spatial distribution map. According to the method, rapid and accurate inversion of the large-scale mangrove forest canopy height is realized by applying a remote sensing technology, the precision and credibility of mangrove forest canopy height remote sensing inversion are improved, the method has repeatability, and the result can provide important information for restoration and management of a mangrove forest ecosystem.

Description

Technical Field

[0001] The present invention relates to the field of accurate inversion of large-scale mangrove structural parameters, and in particular to a method for rapid and accurate inversion of mangrove canopy height based on multi-source remote sensing data and an XGBoost regression model. Background Art

[0002] As a unique transitional wetland between land and sea, mangrove ecosystems have multiple ecological values, such as resisting storm surges, slowing down sea level rise and coastal erosion, and regulating water quality and nutrient cycles in coastal areas. In addition, mangroves can fix and store carbon in the atmosphere and ocean, reducing the negative impact of global climate change, and are therefore called "blue carbon ecosystems." Although mangroves only account for 0.5% of the global coastal area, their contribution to the burial of organic carbon in the coastal zone is as high as 10% to 15% (24TgCy -1 ). Canopy height is a necessary parameter for characterizing mangrove biomass, directly reflects the carbon sink potential of mangrove ecosystems, and is a key factor in determining carbon storage and carbon sinks in mangrove ecosystems. Therefore, accurate inversion of large-scale mangrove canopy height is of great scientific significance for the accurate calculation of mangrove biomass and carbon storage in China, and is an important basis for formulating sustainable management policies.

[0003] Mangroves are mostly located in intertidal areas with poor accessibility. The traditional canopy height survey method based on the plot scale is time-consuming, labor-intensive, costly, and has a small monitoring range. It is also insufficient to reflect the distribution law of the spatial pattern of mangrove canopy height at a large scale. Remote sensing has become the preferred means of monitoring and evaluating mangrove resources due to its large coverage, low labor cost, and high spatiotemporal resolution. Since remote sensing data cannot simultaneously have the characteristics of high spatial resolution, high spectral resolution, high temporal resolution, and large area coverage, multi-source remote sensing data collaboration can take into account the characteristics of image time, spectrum, coverage, and resolution. However, the current research on inverting mangrove canopy height using multi-source remote sensing data has problems such as low spatial resolution, unsatisfactory model inversion accuracy, and unclear inversion mechanism of mangrove canopy height, which makes it difficult to meet the requirements of fine accounting of mangrove biomass and carbon storage.

[0004] In summary, how to fully explore the key remote sensing characteristics of mangrove canopy height based on the complex nonlinear characteristics of large-scale mangroves and relying on high spatial resolution remote sensing data, introduce high-performance interpretable models to construct a remote sensing inversion model suitable for large-scale mangrove canopy height, and improve the inversion accuracy of mangrove canopy height, is an urgent problem to be solved in the research on accurate inversion of mangrove canopy height. Summary of the invention

[0005] In order to solve the problems of low spatial resolution, unsatisfactory model inversion accuracy, unclear key features of mangrove canopy height inversion, etc. in the existing remote sensing technology when inverting the large-scale mangrove canopy height, the present invention provides a method for quickly and accurately inverting the large-scale mangrove canopy height based on UAV-LiDAR, SDGSAT-1 and time-series Sentinel-1 / 2 images combined with XGBoost regression model.

[0006] The technical solution of the present invention for quickly and accurately inverting the canopy height of large-scale mangroves based on UAV-LiDAR, SDGSAT-1 and time-series Sentinel-1 / 2 images combined with the XGBoost regression model is:

[0007] Step 1: Collect UAV-LiDAR point cloud data of mangroves in typical areas during low tide, pre-process the collected point cloud data, and use the canopy height data generated after processing as training data and verification data for the mangrove canopy height inversion model;

[0008] Step 2: Screen the SDGSAT-1 images and time-series Sentinel-1 / 2 images of low tide and cloudless areas in the mangrove area, extract image features and construct the initial feature set of the mangrove canopy height inversion model;

[0009] Step 3: Construct the optimal feature set for mangrove canopy height inversion based on the initial feature set, XGBoost regression model, RFECV method and SHAP interpretation framework;

[0010] Step 4: Based on the training data obtained in step 1, the optimal feature set for mangrove canopy height inversion obtained in step 3, and the XGBoost regression model, a mangrove canopy height inversion model is constructed, and the model parameters are optimized;

[0011] Step 5: Migrate the mangrove canopy height inversion model to other areas and draw a large-scale mangrove canopy height spatial distribution map; based on the verification data obtained in step 1, use the ten-fold crossover method to verify the inversion results and evaluate the model accuracy.

[0012] A further improvement of the present invention is that step one is specifically as follows:

[0013] 1. The point cloud data preprocessing steps include point cloud denoising: removing errors caused by high-order and low-order errors; point cloud filtering: dividing the denoised point cloud data into ground points and objects; generating digital model products: based on the classified ground points, interpolation is performed based on the Inverse Distance Weighted (IDW) algorithm to generate digital elevation models (DEM) and digital surface models (DSM). According to the research spatial scale, DEM and DSM are exported to raster data with a spatial resolution of 10m. The true value of the mangrove canopy height is calculated based on DEM and DSM, and the calculation formula is as follows:

[0014] H ture =DSM-DEM;

[0015] Among them, H ture is the true value of canopy height;

[0016] 2 Based on the true value of mangrove canopy height, sampling points were selected using uniform distribution random sampling method, 80% of which were used for model training and 20% for model verification.

[0017] The further improvement of the present invention is that step 2 is specifically as follows:

[0018] 1. Extract spectral reflectance of 7 bands as initial features based on SDGSAT-1 images;

[0019] 2 Based on the time series Sentinel-1 images, the time series VV polarization and VH polarization are extracted, and the time series NDI, RVI and RI radar index are calculated and extracted as the initial features. The calculation formula is as follows;

[0020]

[0021] ③ Based on the time series Sentinel-2 images, the spectral reflectance of 10 bands including visible light, near infrared and short-wave infrared is extracted, and the time series NDVI, GCI, MVI, LSWI, mNDWI and EVI index are calculated and extracted as the initial features. The calculation formula is as follows:

[0022]

[0023] The further improvement of the present invention is that step three is as follows:

[0024] 1 Input the initial feature set into the XGBoost regression model and the SHAP interpretation framework to obtain the Shapley value of each feature, and delete the features with a Shapley value of 0;

[0025] 2. Combined with RFECV, the feature input models with the lowest Shapley value are deleted one by one to evaluate the model inversion accuracy. When the model inversion accuracy reaches the maximum value and tends to be stable, the feature set output by the model is the optimal feature set.

[0026] For a feature in a feature set, the Shapley value is calculated as follows:

[0027]

[0028] Where N is the feature set, S is any feature subset that does not contain feature i, S is the number of features in set S, υ(S) is the contribution of feature set S to model prediction, and υ(S∪{i}) is the contribution of feature set S∪{i} containing feature i to model prediction.

[0029] The large-scale mangrove canopy height accurate inversion method based on multi-source remote sensing images and XGBoost regression model provided by the present invention has at least the following technical effects:

[0030] 1. The present invention uses UAV-LiDAR data as model training data, which can match the canopy height inversion of various spatial scales and can compress the workload of 10 days of field sampling to 1 day.

[0031] 2. The present invention provides a methodological approach for achieving accurate inversion of large-scale mangrove canopy height, and collaborates with the currently easily accessible and high-spatial-resolution multi-source remote sensing data to improve the spatial resolution of large-scale mangrove canopy height inversion results; combined with the SHAP interpretation framework, the key features of mangrove canopy height inversion are clarified.

[0032] 3. The present invention combines the advanced XGBoost regression model to construct a mangrove canopy height inversion model, thereby improving the model inversion efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following drawings required for use in the implementation are introduced. The following drawings are used together with the embodiments of the present invention to explain the present invention, but not to limit the present invention. In the drawings:

[0034] Figure 1 This is the UAV-LiDAR point cloud data of Zhenhaiwan Mangrove Reserve in Jiangmen City, Guangdong Province. The left side is a flat map and the right side is a cross-section map.

[0035] Figure 2 The actual mangrove canopy height generated based on UAV-LiDAR point cloud data. The left side is the Gaoqiao Mangrove Reserve in Zhanjiang City, Guangdong Province, and the right side is the Zhenhaiwan Mangrove Reserve in Jiangmen City, Guangdong Province.

[0036] Figure 3 These are the 20 key features of mangrove canopy height inversion;

[0037] Figure 4 This is the spatial distribution map of mangrove canopy height in Guangdong Province;

[0038] Figure 5(a) shows the model self-validation result in the accuracy evaluation result of inverting the mangrove canopy height based on the XGBoost regression model;

[0039] Figure 5(b) is the independent validation data verification result of the accuracy evaluation result of inverting the mangrove canopy height based on the XGBoost regression model. DETAILED DESCRIPTION

[0040] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the embodiment of the present invention will be described clearly and completely in conjunction with the accompanying drawings of the embodiment of the present invention. The described embodiment is only a part of the embodiment of the present invention, not all of the embodiments.

[0041] This implementation method relies on multi-source remote sensing data with high spatial resolution, fully exploits the key remote sensing features of mangrove canopy height inversion, and introduces a high-performance interpretable model to achieve accurate inversion of large-scale mangrove canopy height:

[0042] Step 1: Collect UAV-LiDAR point cloud data of mangroves in the Gaoqiao Mangrove Nature Reserve in Zhanjiang City, Guangdong Province and the Zhenhaiwan Mangrove Nature Reserve in Jiangmen City, Guangdong Province during the low tide period in 2023, referring to Figure 1 The collected point cloud data is preprocessed. The preprocessing steps include point cloud denoising: removing errors caused by high-order and low-order errors; point cloud filtering: dividing the denoised point cloud data into ground points and ground objects; generating digital model products: interpolating the classified ground points based on the inverse distance weighted (IDW) algorithm to generate digital elevation models (DEM) and digital surface models (DSM). According to the research spatial scale, DEM and DSM are exported to raster data with a spatial resolution of 10m, referring to Figure 2 .

[0043] The true value of mangrove canopy height is calculated based on DEM and DSM. The calculation formula is as follows:

[0044] H ture =DSM-DEM;

[0045] Among them, H ture is the true value of canopy height;

[0046] Based on the true value of mangrove canopy height, sampling points were selected using uniform distribution random sampling method, 80% of which were used for model training and 20% for model verification.

[0047] Step 2: Screen the SDGSAT-1 images of Guangdong Province at low tide and without clouds in 2023, and extract the spectral reflectance of 7 bands as the initial features. The band introduction refers to Table 1;

[0048] The 2023 time-series Sentinel-1 images of Guangdong Province were screened, the time-series VV polarization and VH polarization were extracted based on the time-series Sentinel-1 images, and the time-series NDI, RVI and RI radar indexes were calculated and extracted as initial features. The calculation formula is as follows;

[0049]

[0050] The 2023 time series Sentinel-2 images of Guangdong Province were screened. First, the low-tide images were screened to obtain the images with the largest NDVI average value among all images in each month of 2023. The low-tide images were combined with the s2cloudless declouding algorithm to detect whether there were clouds, and the images with cloud cover were declouded. Other cloud-free images of the month were screened to fill the holes and extract image features to construct the initial feature set of the mangrove canopy height inversion model.

[0051] Based on the time series Sentinel-2 images, the spectral reflectance of 10 bands such as visible light, near infrared and short-wave infrared is extracted as the initial features. The band introduction is shown in Table 1. The time series NDVI, GCI, MVI, LSWI, mNDWI and EVI index are calculated and extracted as the initial features. The calculation formula is as follows:

[0052]

[0053] Table 1 Introduction to the bands of Sentinel-1, Sentinel-2 and SDGSAT-1 satellite images

[0054]

[0055] Step 3: Construct the optimal feature set for mangrove canopy height inversion based on the initial feature set, XGBoost algorithm, RFECV and SHAP interpretation framework; specifically: input the initial feature set into the XGBoost algorithm and SHAP interpretation framework to obtain the Shapley value of each feature, and delete the features with a Shapley value of 0; for the features in the feature set, the Shapley value is calculated as follows:

[0056]

[0057] Where N is the feature set, S is any feature subset that does not contain feature i, S is the number of features in set S, v(S) is the contribution of feature set S to model prediction, and v(S∪{i}) is the contribution of feature set S∪{i} containing feature i to model prediction.

[0058] Combined with the RFECV algorithm, the feature input model with the lowest Shapley value is deleted in turn to evaluate the model inversion accuracy. When the model inversion accuracy reaches the maximum value and tends to be stable, the feature set output by the model is the optimal feature set; combined with the SHAP interpretation framework, the top 20 parameters in the optimal feature set are output. Figure 3 .

[0059] Step 4: Based on the training data obtained in step 1, the optimal feature set for mangrove canopy height inversion obtained in step 3, and the XGBoost algorithm, a mangrove canopy height inversion model is constructed, and the model parameters are optimized at the same time; the model parameters are divided into general parameters, Booster parameters, and objective function parameters. The general parameters and target parameters can be kept at the default parameters to ensure the optimization of the model; when adjusting the Booster parameters, step-by-step control adjustment is adopted. According to the parameter weight, one of them is optimized in turn while the others remain unchanged. The order of parameter adjustment and the final result are: max_depth: 6; min_child_weight: 0; gamma: 1.1; subsample: 0.8; colsample_bytree: 0.8; eta: 0.1.

[0060] Step 5: Migrate the mangrove canopy height inversion model to the entire study area and draw the spatial distribution map of mangrove canopy height in Guangdong Province. Figure 4 ; Based on the verification data obtained in step 1, the inverted mangrove canopy height data of Guangdong Province was verified to evaluate the model accuracy, referring to Figure 5(a) and Figure 5(b), where Figure 5(a) is the model self-verification result and Figure 5(b) is the independent verification data verification result.

Claims

1. A large-scale mangrove canopy height accurate inversion method based on multi-source remote sensing images and XGBoost regression model, which includes the following steps: Step 1: Collect UAV-LiDAR point cloud data of mangroves in typical areas during low tide, pre-process the collected point cloud data, and use the canopy height data generated after processing as training data and verification data for the mangrove canopy height inversion model; Step 2: Screen the SDGSAT-1 images and time-series Sentinel-1 / 2 images of low tide and cloudless areas in the mangrove area, extract image features and construct the initial feature set of the mangrove canopy height inversion model; Step 3: Construct the optimal feature set for mangrove canopy height inversion based on the initial feature set, XGBoost regression model, RFECV and SHAP interpretation framework; Step 4: Based on the training data obtained in step 1, the optimal feature set for mangrove canopy height inversion obtained in step 3, and the XGBoost regression model, a mangrove canopy height inversion model is constructed, and the model parameters are optimized; Step 5: Migrate the mangrove canopy height inversion model to other areas and draw a large-scale mangrove canopy height spatial distribution map; Based on the verification data obtained in step 1, use the ten-fold crossover method to verify the inversion results and evaluate the model accuracy; The step 1 is specifically as follows: ①The point cloud data preprocessing steps include point cloud denoising: removing errors caused by high-order and low-order gross errors; point cloud filtering: dividing the denoised point cloud data into ground points and ground objects; generating digital model products: interpolating the classified ground points based on the inverse distance weighted algorithm to generate digital elevation models and digital surface models; according to the research spatial scale, DEM and DSM are exported to raster data with a spatial resolution of 10m; the true value of the mangrove canopy height is calculated based on DEM and DSM, and the calculation formula is as follows: H ture =DSM-DEM; in, H ture is the true value of canopy height; ② Based on the true value of mangrove canopy height, uniformly distributed random sampling method was used to select sampling points, of which 80% were used for model training and 20% for model verification; The step 2 is specifically as follows: ① Extract spectral reflectance of seven bands as initial features based on SDGSAT-1 images; ② Based on the time series Sentinel-1 images, the time series VV polarization and VH polarization are extracted, and the time series NDI, RVI and RI radar index are calculated and extracted as the initial features. The calculation formula is as follows; ③ Based on the time series Sentinel-2 images, the spectral reflectance of 10 bands including visible light, near infrared and short-wave infrared is extracted, and the time series NDVI, GCI, MVI, LSWI, mNDWI and EVI index are calculated and extracted as the initial features. The calculation formula is as follows: The step three is specifically as follows: ① Input the initial feature set into the XGBoost algorithm and the SHAP interpretation framework to obtain the Shapley value of each feature, and delete the features with a Shapley value of 0; ② Combined with the RFECV algorithm, the feature input model with the lowest Shapley value is deleted in turn to evaluate the model inversion accuracy. When the model inversion accuracy reaches the maximum value and tends to be stable, and the feature set input when the model accuracy is the largest after tending to be stable is the optimal feature set.

2. The large-scale mangrove canopy height accurate inversion method based on multi-source remote sensing images and XGBoost regression model according to claim 1 is characterized in that: In step one, using UAV-LiDAR data as model training data can match canopy height inversion at multiple spatial scales and compress the workload of 10 days of field sampling to 1 day.

3. The large-scale mangrove canopy height accurate inversion method based on multi-source remote sensing images and XGBoost regression model according to claim 1 is characterized in that: In step 2, the low tide time series Sentinel-2 images are obtained by screening the images with the largest NDVI average among all images of each month; the cloud-free images are detected based on the low tide images combined with the s2cloudless declouding algorithm to detect whether there are clouds, and the images obscured by clouds are declouded, and other cloud-free images of the month are screened to fill the gaps.

4. The large-scale mangrove canopy height accurate inversion method based on multi-source remote sensing images and XGBoost regression model according to claim 1 is characterized in that: In step 3, for the features in the feature set, the Shapley value is calculated as follows: Where N is the feature set, S is any feature subset that does not contain feature i, |S| is the number of features in set S, υ(S) is the contribution of feature set S to model prediction, and v(S∪{i}) is the contribution of feature set S∪{i} containing feature i to model prediction.

5. The large-scale mangrove canopy height accurate inversion method based on multi-source remote sensing images and XGBoost regression model according to claim 1 is characterized in that: In step 4, the parameters and order of model optimization are: max_depth, min_child_weight, gamma, subsample, colsample_bytree and eta.

Images