A remote sensing statistical joint estimation method for the storage volume of pit ponds with classified processing

Abstract

The present invention discloses a remote sensing statistical joint estimation method for classified treatment of water storage capacity in pit ponds, which relates to the technical field of remote sensing monitoring of water resources and includes: calculating the pit pond density and determining the grid width; calculating the normalized water body index and extracting the water surface boundary of the pit pond; dividing the pit ponds into invertible pit ponds and non-invertible pit ponds according to the water surface area and width of the pit ponds; calculating the water storage capacity of the invertible pit ponds in combination with the area of the invertible pit ponds; calculating the water storage capacity of the non-invertible pit ponds by using the relationship between the water surface area of the non-invertible pit ponds and the statistical model; calculating the total water storage capacity of the region and generating a spatial distribution map of the water storage capacity. The present invention applies remote sensing inversion and statistical model methods to estimate the water storage capacity, can perform targeted treatment for different types of pit ponds, and the remote sensing images combined with the measured data can effectively improve the water depth inversion accuracy of the invertible pit ponds, thereby providing a more reliable water storage capacity estimation result.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing monitoring of water resources. Specifically, it relates to a remote sensing statistical joint estimation method for the water storage capacity of ponds with classified processing. Background Art

[0002] As an important water resource on the earth, the accurate estimation of the water storage capacity of ponds is of great significance for water resource management, ecological environment protection, cultivated land protection and other fields. The traditional method for estimating the water storage capacity of water bodies mainly relies on observing water level data and measuring underwater terrain data. Although this method is accurate, it faces many limitations in practical applications. This method has high costs and limited coverage. Problems such as equipment failures and data transmission make it difficult to achieve large-area dynamic monitoring. The statistical model (area-storage relationship) is applicable to the estimation of the water storage capacity of ponds in large areas, but it cannot reflect the spatial change trend of ponds.

[0003] With the development of remote sensing technology, satellite inversion bathymetry technology has gradually been applied to the fields of water depth and water storage capacity estimation. However, the conventional remote sensing inversion method is affected by image resolution, aquatic plants and water quality, resulting in insufficient accuracy. Especially in shallow ponds, narrow ponds and small-area ponds, the error is significant. Moreover, most of the existing technologies are based on the research of water storage capacity using statistical models and do not integrate multi-source remote sensing data. As a result, the estimation accuracy of the water storage capacity of ponds in large areas under complex environments (diverse types, large quantity, wide area, aquatic plant coverage, shadow interference) is low and the adaptability is poor.

[0004] In view of the problems in the related art, no effective solution has been proposed yet. Summary of the Invention

[0005] In view of the problems in the related art, the present invention proposes a remote sensing statistical joint estimation method for the water storage capacity of ponds with classified processing to overcome the above technical problems existing in the existing related technologies.

[0006] For this purpose, the specific technical solution adopted by the present invention is as follows:

[0007] A remote sensing statistical joint estimation method for the water storage capacity of ponds with classified processing, comprising:

[0008] Based on the dynamic adjustable grid sampling method, sampling surveys are carried out on the ponds in the test area, the pond density is calculated, and the grid width is determined;

[0009] Calculate the normalized water body index, determine the water body boundary by the threshold method, and perform masking processing on the survey data to extract the water surface boundary of the ponds;

[0010] According to the water surface area and width of the ponds, the ponds are divided into ponds that can be inverted and ponds that cannot be inverted;

[0011] The water depth of ponds that can be inverted is calculated using remote sensing image technology, and the water storage volume of ponds that can be inverted is calculated by combining with the area of ponds that can be inverted;

[0012] A statistical model is constructed to estimate the water storage volume of ponds that cannot be inverted, and the water storage volume of ponds that cannot be inverted is calculated using the relationship between the water surface area of ponds that cannot be inverted and the statistical model;

[0013] The water storage volumes of ponds that can be inverted and ponds that cannot be inverted are fused to calculate the total regional water storage volume, and a spatial distribution map of the water storage volume is generated.

[0014] Furthermore, based on the dynamic adjustable grid sampling method, sampling surveys are conducted on the ponds in the test area, and the pond density is calculated and the grid width is determined, including:

[0015] The ponds in the test area are classified into aquaculture ponds and natural ponds according to their types, and a preset sampling ratio is determined to determine the total sampling numbers of aquaculture ponds and natural ponds and the overall total sampling number;

[0016] The width of the grid is determined by the density of the ponds in the test area, and sample ponds are assigned to each grid;

[0017] The grids are sorted according to the number of sample ponds in the grids, and the grids with zero sample pond numbers are removed;

[0018] Traverse the valid grids and sequentially extract one pond from each grid until the overall sample quantity requirement is met.

[0019] Furthermore, the calculation formula for the density of ponds is:

[0020] ;

[0021] The calculation formula for the grid width is:

[0022] ;

[0023] In the formula, p represents the pond density in the test area; N represents the total number of ponds in the test area; S 1 represents the national land area in the test area; a represents the width of the grid; represents the number of sample ponds in the grid; k represents the sampling ratio.

[0024] Furthermore, the normalized water body index is calculated, the water body boundary is determined by the threshold method, and the survey data is masked to extract the pond water surface boundary, including the following steps:

[0025] Use remote sensing images to calculate the normalized water index and obtain initial information on the water bodies in the test area;

[0026] The threshold value of the normalized water index is determined by the threshold method. If the threshold value is greater than or equal to the preset value, the water body boundary in the test area is extracted and the boundary smoothing is performed;

[0027] Based on geographic information technology, the non-pond water body types in the survey data were masked and the pond water surface boundaries were extracted.

[0028] Furthermore, the water depth of the invertible pond is calculated using remote sensing imaging technology, and the water storage capacity of the invertible pond is calculated in combination with the area of the invertible pond, including:

[0029] Obtain multispectral remote sensing images and use custom geographic transformation to convert the universal transverse Mercator projection coordinates of the multispectral remote sensing images into Gauss-Krüger projection coordinates;

[0030] The normalized vegetation index and normalized water turbidity were calculated using multispectral remote sensing images, redundant points were eliminated, measured points were thinned out, and pixel grids and measured points were matched one by one.

[0031] Extract water body reflectance, generate band combination inversion factors through band calculation, and calculate the characteristic importance of each inversion factor in combination with measured point data;

[0032] The measured point data were divided into training set and validation set, and a water depth inversion model was constructed to invert the water depth of the invertible ponds. The inverted water depth value was compared with the actual measured water depth to calculate the determination coefficient and root mean square error of the evaluation index.

[0033] According to the inversion results, the water depth data of each invertible pond area is extracted, the average water depth of each invertible pond is calculated, and the water storage capacity of the invertible pond is calculated by combining the water surface area and the average water depth.

[0034] Furthermore, the calculation formula of the determination coefficient of the evaluation index is:

[0035] ;

[0036] The formula for calculating the root mean square error is:

[0037] ;

[0038] In the formula, y i Indicates i a truth value; Indicates i An estimated value; represents the average of the true values; Represents the total number of true values.

[0039] Furthermore, the formula for calculating the average water depth value of each invertible pond is:

[0040] ;

[0041] In the formula, represents the average water depth value of the i th invertible pond; represents the measured water depth value of the i th invertible pond at the u th measurement point; num represents the total number of measurement points.

[0042] Furthermore, the formula for calculating the water storage capacity of an invertible pond is:

[0043] ;

[0044] In the formula, V 1 represents the total water storage capacity of the invertible pond; represents the average water depth value of the i th invertible pond; s i represents the area of the i th invertible pond; m represents the total number of invertible ponds.

[0045] Furthermore, the formula for calculating the water storage capacity of a non-invertible pond is:

[0046] ;

[0047] ;

[0048] In the formula, z represents the water storage capacity; x represents the area; a , b , c all represent the fitting parameters of the quadratic polynomial function; V 2 represents the total water storage capacity of the non-invertible pond; z j represents the water storage capacity of the j th non-invertible pond; n represents the total number of non-invertible ponds.

[0049] Furthermore, the water storage capacities of the invertible ponds and non-invertible ponds are fused to calculate the total regional water storage capacity, and the spatial distribution map of the water storage capacity is generated, including:

[0050] The calculation results of the water storage of the retrievable ponds and non-retrievable ponds are fused using the average value method and the statistical model method to obtain the total water storage in the test area;

[0051] Based on geographic information technology and the water surface boundary of the ponds, an average water depth field is added, and the average water depth value of each pond is assigned to the vector pond surface to generate a visualized regional pond water storage distribution map.

[0052] The beneficial effects of the present invention are as follows:

[0053] 1. By dividing the ponds into retrievable ponds and non-retrievable ponds, and applying remote sensing inversion and statistical model methods to estimate the water storage respectively, the present invention can conduct targeted processing for different types of ponds. The combination of remote sensing images and measured data can effectively improve the accuracy of water depth inversion of retrievable ponds, while the estimation of non-retrievable ponds by the statistical model ensures the accuracy of water storage estimation for the entire region, thus providing a more reliable water storage estimation result.

[0054] 2. Through refined classification estimation and generation of spatial distribution maps, the present invention provides specific spatial references and data supports for regional water resource management. The water storage of retrievable ponds and non-retrievable ponds is calculated separately, which helps to accurately grasp the water volume distribution of different types of ponds. Combined with the visualized regional water storage distribution map, it can provide more intuitive and detailed data bases for water resource managers, and contribute to the implementation of more accurate water resource scheduling and water area protection strategies.

[0055] 3. By combining dynamic adjustable grid sampling and remote sensing data, the present invention ensures adaptability under different geographical conditions and pond types. Through technologies such as grid sampling surveys, NDWI and water depth inversion, and statistical models, it can cover various complex terrains and water body changes, and has wide applicability. Whether it is aquaculture ponds or natural ponds, they can be flexibly processed and estimated according to specific situations, thus improving the overall efficiency and accuracy of water storage estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0057] Figure 1 is a flowchart of a remote sensing and statistical joint estimation method for pond water storage with classified processing according to an embodiment of the present invention;

[0058] Figure 2It is a flow chart of grid method sample extraction according to an embodiment of the present invention;

[0059] Figure 3 It is a schematic diagram of pond classification according to an embodiment of the present invention;

[0060] Figure 4 It is a schematic diagram of remote sensing water depth inversion principle according to an embodiment of the present invention;

[0061] Figure 5 It is a schematic diagram of comparison of importance of inversion factor features according to an embodiment of the present invention;

[0062] Figure 6 It is a schematic diagram of fitting curve of area - water storage statistical model according to an embodiment of the present invention;

[0063] Figure 7 It is a schematic diagram of comparison of cross - section and longitudinal - section shapes of ponds according to an embodiment of the present invention;

[0064] Figure 8 It is a schematic diagram of inversion result according to an embodiment of the present invention;

[0065] Figure 9 It is a schematic diagram of accuracy verification comparison according to an embodiment of the present invention;

[0066] Figure 10 It is a schematic diagram of fitting curve of area - water storage statistical model of training set according to an embodiment of the present invention;

[0067] Figure 11 It is a schematic diagram of verification result of pond water storage according to an embodiment of the present invention. Detailed implementation manners

[0068] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used to explain the operation principle of the embodiments in conjunction with the relevant descriptions in the specification. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention.

[0069] According to an embodiment of the present invention, a remote sensing statistical joint estimation method for pond water storage with classification processing is provided.

[0070] Now, the present invention will be further described in combination with the drawings and specific implementation manners. As Figure 1 shown, the remote sensing statistical joint estimation method for pond water storage with classification processing according to an embodiment of the present invention includes:

[0071] S1. Based on the dynamic adjustable grid sampling method, sample the ponds in the test area, calculate the pond density and determine the grid width;

[0072] S2. Calculate the normalized difference water index, determine the water body boundary through the threshold method, and perform masking processing on the survey data to extract the water surface boundary of the ponds;

[0073] S3. Divide the ponds into retrievable ponds and non - retrievable ponds according to the water surface area and width of the ponds;

[0074] It should be noted that according to the water body morphological parameters (water surface area, width), the ponds are divided into two categories: The first is retrievable ponds (pure water surface, area ≥ 2000 m², width ≥ 20 m), including two types: aquaculture ponds and natural ponds (as shown at b in the figure, retrievable type); The second is non - retrievable ponds (interfered by aquatic plants, shadows, or small area, narrow width, covered by greenhouses), including narrow ponds, shallow ponds, small ponds, greenhouse - covered ponds, etc. (as shown at a in the figure, non - retrievable type), providing a basis for subsequent differential modeling. Figure 3 shown, the non - retrievable type at a); Figure 3 shown, the retrievable type at b), providing a basis for subsequent differential modeling.

[0075] S4. Use remote sensing image technology to calculate the water depth of retrievable ponds, and calculate the water storage volume of retrievable ponds in combination with the area of retrievable ponds;

[0076] S5. Construct a statistical model to estimate the water storage volume of non - retrievable ponds, and calculate the water storage volume of non - retrievable ponds using the relationship between the water surface area of non - retrievable ponds and the statistical model;

[0077] S6. Integrate the water storage volumes of retrievable ponds and non - retrievable ponds, calculate the total regional water storage volume, and generate a spatial distribution map of the water storage volume.

[0078] In this alternative embodiment, based on the dynamic adjustable grid sampling method, sampling surveys are conducted on the ponds in the test area, and calculating the pond density and determining the grid width includes:

[0079] Divide the ponds in the test area into aquaculture ponds and natural ponds according to types, preset the sampling ratio, and determine the total sampling numbers of aquaculture ponds and natural ponds as well as the overall total sampling number;

[0080] Determine the width of the grid based on the density of the ponds in the test area, and allocate sample ponds to each grid;

[0081] Sort the grids according to the number of sample ponds in the grids, and remove the grids with zero sample pond numbers;

[0082] Traverse the valid grids, and sequentially extract one pond from each grid until the overall sample quantity requirement is met.

[0083] It should be noted that, in accordance with the principles of comprehensiveness, typicality, and balance between quality and efficiency, a certain proportion of sample ponds are selected within the experimental area, and a single-beam instrument is used to conduct on-site sampling surveys. The grid method is used to select sample ponds. First, the pond density is calculated. Second, the grid width is determined. Finally, samples are drawn from each grid, which can make the samples evenly distributed in space.

[0084] It should be noted that, as Figure 2 shown, the grid method for extracting sample ponds includes: First, the ponds in the area are divided into two categories: aquaculture ponds and natural ponds; Second, the sampling ratio is determined by oneself, and the total number of sampled aquaculture ponds, the total number of sampled natural ponds, and the total number of overall samples are determined respectively; Then, the grid width is determined based on the pond density within the jurisdiction; Third, the grids are sorted according to the number of ponds in the grid, and the grids with zero pond numbers are removed; Then, the grids are traversed in a loop, and one pond is drawn from each grid in turn until the quantity requirement is met.

[0085] In this optional embodiment, the density calculation formula of the pond is:

[0086] ;

[0087] The calculation formula of the grid width is:

[0088] ;

[0089] In the formula, p represents the pond density within the experimental area; N represents the total number of ponds within the experimental area; S 1 represents the land area within the experimental area, with the unit of square kilometers; a represents the width of the grid, with the unit of kilometers; represents the number of sample ponds in the grid; n is set to 2, representing that 2 sample ponds are drawn from each grid; k represents the sampling ratio and is a constant.

[0090] In this optional embodiment, calculating the Normalized Difference Water Index (NDWI), determining the water body boundary through the threshold method, and masking the survey data to extract the water surface boundary of the pond includes the following steps:

[0091] Calculate the Normalized Difference Water Index using remote sensing images (high-resolution optical remote sensing images) and obtain the initial information of the water body within the experimental area;

[0092] Determine the threshold of the Normalized Difference Water Index through the threshold method. If the threshold is greater than or equal to the preset value, extract the water body boundary within the experimental area and perform boundary smoothing processing;

[0093] Based on geographic information technology (geographic information software), mask the non-pond water body types (vector layers of reservoirs, lakes, rivers, and ditches) in the survey data (the latest annual land use change survey data), and extract the water surface boundary of the ponds.

[0094] It should be noted that based on high-resolution optical remote sensing images (such as the high-resolution series, resource series, Sentinel-2, etc.), after radiometric calibration and atmospheric correction, calculate the normalized difference water index NDWI, and use the threshold method to determine the threshold of NDWI. When the threshold ≥ 0.2 (preset value), identify all water body boundaries in the study area, smooth the boundaries to remove jagged edges, collect the vector layers of reservoirs, lakes, rivers, and ditches in the latest annual land use change survey data, and use geographic information software to mask these non-pond water body types to accurately extract the water surface boundary of the pond types in the area. The formula for calculating the normalized difference water index NDWI is:

[0095] ;

[0096] In the formula, ρ represents the spectral reflectance; Green represents the green light band; NIR represents the near-infrared band.

[0097] In this alternative embodiment, using remote sensing image technology to calculate the water depth of ponds that can be inverted, and combining the area of ponds that can be inverted to calculate the water storage capacity of ponds that can be inverted includes:

[0098] Obtain multi-spectral remote sensing images (Sentinel-2 images), and use a custom geographic transformation to convert the Universal Transverse Mercator projection coordinates of the multi-spectral remote sensing images into Gaussian-Kruger projection coordinates;

[0099] Use the multi-spectral remote sensing images to calculate the normalized difference vegetation index and the normalized water turbidity, remove redundant points, thin the measured points, and make the pixel grid correspond to the measured points one by one;

[0100] Extract the water body reflectance, generate band combination inversion factors through band calculation, and calculate the characteristic importance of each inversion factor in combination with the measured point data;

[0101] Divide the measured point data into a training set and a validation set, construct a water depth inversion model to invert the water depth of ponds that can be inverted, and calculate the evaluation indicators of the coefficient of determination and the root mean square error by comparing the inverted water depth value with the actually measured water depth;

[0102] According to the inversion results, extract the water depth data of each pond area that can be inverted, calculate the average water depth value of each pond that can be inverted, and calculate the water storage capacity of ponds that can be inverted by multiplying the water surface area by the average water depth.

[0103] It should be noted that for the invertible ponds, the water depth inversion experiment is carried out according to the inversion process (as Figure 4 shown). Obtain Sentinel-2 images with close dates, create a custom geotransformation (from WGS1984 geographic coordinate system to CGCS2000 geographic coordinate system), use the geographic information raster projection tool, load the custom geotransformation, and convert the UTM projection coordinates (Universal Transverse Mercator projection coordinates) to the Gauss-Kruger projection coordinates of the 3-degree zone of CGCS2000 (Gauss-Kruger projection coordinates), so as to ensure that the converted projection is consistent with the measured data projection. Combine the measured data and inversion factors to generate the input data set.

[0104] It should be noted that for the preprocessing of input data. Redundant points are removed, the measured points are thinned, and the pixel raster and the measured points are made to correspond one by one to avoid data redundancy and overfitting. The Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Turbidity Index (NDTI) are calculated using Sentinel-2 images to preprocess the input data. Points within the vegetation coverage area (NDVI greater than 0.1), high turbidity areas (NDTI>0), and mixed pixel areas (points within 10 meters from the shore) are removed, as well as points with relatively shallow water depths (below 0.6 meters), and points with large changes in the water body state of the pond due to the inconsistency between the measured time and the image time are removed to improve the reliability of the inversion model. The formulas for calculating the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Turbidity Index (NDTI) are as follows:

[0105] ;

[0106] ;

[0107] In the formulas, ρ represents the spectral reflectance; Green represents the green light band; NIR represents the near-infrared band; Red represents the red light band.

[0108] It should be noted that the water body reflectance of the preprocessed image is extracted as a single-band inversion factor according to the spatial position of the measured water depth sample points, and the reflectance after band calculation (logarithm, ratio, log-ratio, etc.) is used as a band combination inversion factor. A total of 20 inversion factors are formed (as shown in Table 1). Combining the measured point data, calculate the feature importance of each inversion factor (as Figure 5 shown). The higher the feature importance value, the higher the correlation between the factor and the water depth.

[0109] Table 1. Comparison of calculation methods and feature importance of each inversion factor

[0110] Serial number Inversion factor Feature importance Serial number Inversion factor Feature importance 1 B1 0.09 11 Ln(B1) / Ln(B2) 0.08 2 B2 0.04 12 Ln(B1) / Ln(B3) 0.04 3 B3 0.04 13 Ln(B1) / Ln(B4) 0.02 4 B4 0.05 14 Ln(B2) / Ln(B3) 0.05 5 B1 / B2 0.08 15 Ln(B2) / Ln(B4) 0.04 6 B1 / B3 0.04 16 Ln(B3) / Ln(B4) 0.03 7 B1 / B4 0.02 17 B1 + B2 0.03 8 B2 / B3 0.05 18 B1 + B3 0.04 9 B2 / B4 0.04 19 B2 + B3 0.06 10 B3 / B4 0.03 20 B1 + B4 0.12

[0111] Note: B1, B2, B3, and B4 represent the reflectance in the blue, green, red, and near-infrared bands, respectively.

[0112] It should be explained that the measured data after processing are divided into a training set and a validation set. Combining the results of data preprocessing, a water depth inversion model controlled and constrained by multiple factors such as NDVI, NDTI, water depth range, and spatial distance is constructed using the training set. Based on the correlation between water depth and reflectance, the water depth of the pond is inverted. The inversion models include random forest, GBDT, XGBoost, BP neural network model, etc. Other machine learning and deep learning models can also be tried. The accuracy of the inversion results is evaluated using the validation set, and the coefficient of determination (R 2 ) and root mean square error (RMSE) of the evaluation index are calculated by the inversion water depth value and the actual water depth. The calculation formula for the coefficient of determination of the evaluation index is:

[0113] ;

[0114] The calculation formula for the root mean square error is:

[0115] ;

[0116] In the formula, y i represents the i th true value ( i = 1, 2,..., n ); represents the i th estimated value; represents the average value of the true values; represents the total number of true values.

[0117] It should be explained that using the masking extraction tool of the geographic information software and the obtained vector map patches of ponds that can be inverted, the masking extraction of the inversion results is carried out, and the formula for calculating the average water depth of the ponds:

[0118] ;

[0119] In the formula, represents the average water depth value of the i th pond that can be inverted; represents the measured water depth value of the i th pond that can be inverted at the u th measurement point, u = 1, 2,..., num ; num represents the total number of measurement points.

[0120] It should be noted that the water storage volume of the pond can be inverted by multiplying the water surface area by the average water depth. The formula for calculating the water storage volume of the pond that can be inverted is as follows:

[0121] ;

[0122] In the formula, V 1 represents the total water storage volume of the pond that can be inverted; represents the average water depth value of the i th pond that can be inverted; s i represents the area of the i th pond that can be inverted, i = 1, 2,..., m ; m represents the total number of ponds that can be inverted.

[0123] It should be noted that for ponds that cannot be inverted, first use all the measured ponds as samples to establish a quadratic polynomial function relationship between area and water storage volume, and obtain the parameters a , b , c through regression fitting. Input the water surface area of the non-invertible pond type extracted into the pre-trained statistical model (as shown in Figure 6 ), and the formula for calculating the water storage volume of the non-invertible pond is as follows:

[0124] ;

[0125] ;

[0126] In the formula, z represents the water storage volume; x represents the area; a , b , c all represent the fitting parameters of the quadratic polynomial function; V 2 represents the total water storage volume of the non-invertible pond; z j represents the water storage volume of the j th non-invertible pond, j = 1, 2,..., n ; n represents the total number of non-invertible ponds.

[0127] It should be noted that in the method for estimating the water storage volume of pit ponds based on a statistical model, the cross-sectional shape of the pit ponds has a certain impact on the construction and accuracy of the model. If the shapes of the pit ponds are similar (for example, most aquaculture pit ponds are regular rectangles), the area-water storage volume relationship is more stable. Shallow flat pit ponds with a depth of less than 2.5 meters generally have uniform water depths, and the linear relationship between area and storage volume is strong. According to field research, most artificial aquaculture pit ponds are regular geometric shapes (rectangles, circles), with flat bottoms or gentle slopes and neat slopes. The common types of natural pit ponds are dish-shaped, pot-shaped, and long-strip-shaped. As Figure 7 shown, three typical cross-sectional views of pit ponds are presented, indicating a positive correlation between area and water storage volume.

[0128] In this alternative embodiment, the water storage volumes of the retrievable and non-retrievable pit ponds are fused to calculate the total water storage volume of the region, and the spatial distribution map of the water storage volume is generated, including:

[0129] The calculation results of the water storage volumes of the retrievable and non-retrievable pit ponds are fused using the average value method and the statistical model method to obtain the total water storage volume within the test area;

[0130] Based on geographic information technology and the water surface boundary of the pit ponds, a new field of average water depth is added, and the average water depth value of each pit pond is assigned to the vector pit pond surface to generate a visualized spatial distribution map of the water storage volume of the regional pit ponds.

[0131] It should be noted that by fusing the results of the average value method (for retrievable pit ponds) and the statistical model method (for non-retrievable pit ponds), the total value of the regional water storage volume is calculated. Using geographic information software and the pit pond surface (the water surface boundary of the pit ponds), a new field of "average water depth" is added, and the average water depth value of each pit pond is assigned to the vector pit pond surface, thereby generating a visualized spatial distribution map of the water storage volume of the regional pit ponds. The formula for calculating the total value of the water storage volume of the region (test area) is:

[0132] ;

[0133] In the formula, V represents the total water storage volume within the working area, V 1 and V 2 are the water storage volumes of the retrievable category (retrievable pit ponds) and the non-retrievable category of pit ponds (non-retrievable pit ponds), respectively.

[0134] It should be noted that one cloud-free Sentinel-2 image with a resolution of 10 meters is obtained, and 71 pit pond water depth data are collected in the field. The water surface data of the pit ponds in the study area are extracted, and the pit pond patches in the study area are divided into two categories: retrievable and non-retrievable. Four inversion models, namely, the random forest, GBDT, XGboost, and BP neural network models, are used for the retrievable pit ponds. The verification results show (as Figure 8As shown in the figure, the XGboost model has the best effect, and the inversion result is relatively consistent with the measured water depth (R 2 = 0.88). Ponds that cannot be inverted are sampled typically, and the measured water depth and bottom elevation data are obtained in the field. The longitudinal and transverse cross-sectional profiles of each type of pond are explored, the functional relationship between the water surface area and water storage is calculated, and the quadratic polynomial function fitting of the statistical model is performed. The results are verified by comparing with the measured data (as Figure 9 shown). The root mean square error (RMSE) of the inversion result of the XGBoost model is 0.12 m.

[0135] It should be noted that in order to verify the effect of the remote sensing inversion and statistical model fusion method (abbreviated as the "fusion method") for estimating water storage, two experiments were conducted. Experiment 1: The single statistical model method was used to estimate the water storage of regional ponds. It was assumed that the water storage of all ponds in the working area was calculated using the statistical model. The sample patches were randomly divided into a training set and a validation set. As Figure 10 shown, the fitting curve of the training set area - water storage statistical model. Figure 10 In (a) of , it is the fitting curve of the training set model of the single statistical model method. Experiment 2: The fusion method was used to estimate the water storage of regional ponds. It was assumed that the ponds in the working area were divided into two categories: "invertible class" and "non - invertible class". The sample patches were divided into a training set and a validation set. The validation set only included the "non - invertible class", and the patches outside the validation set were the training set. Figure 10 In (b) of , it is the fitting curve of the training set model of the fusion method. As Figure 11 shown, the verification results of the pond water storage. Figure 11 In (a), (c), and (e) of , they are the verification scatter plots of the three models: the single statistical model method, the statistical model in the fusion method, and the inversion model in the fusion method, respectively. Figure 11 In (b), (d), and (f) of , they are the comparison curves of the measured and estimated water storage of the three models: the single statistical model method, the statistical model in the fusion method, and the inversion model in the fusion method, respectively. It can be found that the root mean square error of the single statistical model method is relatively large, which is 50355.06 m 3 , and the water storage estimated by the fusion method is in good agreement with the measured value. The RMSEs are 6507.98 and 10604.76 m 3 , respectively. Since the ponds using the statistical model in the fusion method are generally patches with smaller areas, the obvious water storage estimation error is smaller. In addition, the remote sensing inversion method based on dynamically adjustable grid sampling can not only improve the accuracy of water storage estimation, but also depict the details of the water depth change and the trend of underwater terrain change of each pond.

[0136] In summary, by means of the above technical solutions of the present invention, through refined classification estimation and spatial distribution map generation, the present invention provides specific spatial references and data supports for regional water resources management. The water storage capacities of retrievable and non-retrievable ponds can be calculated separately, which helps to accurately grasp the water volume distribution of different types of ponds. Combined with the visualized regional water storage capacity distribution map, it can provide more intuitive and detailed data bases for water resources managers, and contribute to the implementation of more precise water resources scheduling and water area protection strategies. By combining dynamic adjustable grid sampling with remote sensing data, the present invention ensures adaptability under different geographical conditions and pond types. Through technologies such as grid sampling surveys, NDWI and water depth inversion, and statistical models, it can cover various complex terrains and water body changes, and has wide applicability. Whether it is a farming pond or a natural pond, it can be flexibly processed and estimated according to specific circumstances, thus improving the overall efficiency and accuracy of water storage capacity estimation.

[0137] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A remote sensing statistical joint estimation method for the storage volume of pond water with classified processing, characterized in that, Including: Based on the dynamic adjustable grid sampling method, conduct sampling surveys on the ponds in the test area, calculate the pond density, and determine the grid width; Calculate the normalized difference water index, determine the water body boundary through the threshold method, and perform masking processing on the survey data to extract the water surface boundary of the ponds; According to the water surface area and width of the ponds, divide the ponds into ponds with retrievable water depth and ponds with non-retrievable water depth; Use remote sensing image technology to calculate the water depth of the ponds with retrievable water depth, and calculate the water storage volume of the ponds with retrievable water depth in combination with the area of the ponds with retrievable water depth; Construct a statistical model to estimate the water storage volume of the ponds with non-retrievable water depth, and calculate the water storage volume of the ponds with non-retrievable water depth by using the relationship between the water surface area of the ponds with non-retrievable water depth and the statistical model; Fuse the water storage volumes of the ponds with retrievable water depth and the ponds with non-retrievable water depth, calculate the total regional water storage volume, and generate a spatial distribution map of the water storage volume.

2. The remote sensing statistical joint estimation method for the storage capacity of pond water with classification processing according to claim 1, characterized in that The step of conducting sampling surveys on the ponds in the test area based on the dynamic adjustable grid sampling method, calculating the pond density, and determining the grid width includes: Divide the ponds in the test area into aquaculture ponds and natural ponds according to their types, preset the sampling ratio, and determine the total number of samples for aquaculture ponds and natural ponds as well as the overall total number of samples; Determine the width of the grid based on the density of the ponds in the test area, and allocate sample ponds to each grid; Sort the grids according to the number of sample ponds in the grids, and remove the grids with zero sample ponds; Traverse the valid grids, and sequentially extract one pond from each grid until the overall sample quantity requirement is met.

3. The remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 2, characterized in that, The calculation formula for the density of the ponds is: ； The calculation formula for the grid width is: ； In the formula, p represents the pond density in the test area; N represents the total number of ponds in the test area; S 1 represents the land area in the test area; a represents the width of the grid; represents the number of sample ponds in the grid; k represents the sampling ratio.

4. A remote sensing statistical joint estimation method for the storage capacity of pond water with classified processing according to claim 1, characterized in that, The step of calculating the normalized difference water index, determining the water body boundary through the threshold method, and performing masking processing on the survey data to extract the water surface boundary of the ponds includes the following steps: Use remote sensing images to calculate the normalized difference water index, and obtain the initial information of the water bodies in the test area; Determine the threshold of the normalized difference water index through the threshold method. If the threshold is greater than or equal to the preset value, extract the water body boundary in the test area and perform boundary smoothing processing; Based on geographic information technology, perform masking processing on the non-pond water body types in the survey data, and extract the water surface boundary of the ponds.

5. A remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 1, characterized in that, The step of using remote sensing image technology to calculate the water depth of the ponds with retrievable water depth, and calculating the water storage volume of the ponds with retrievable water depth in combination with the area of the ponds with retrievable water depth includes: Obtain multi-spectral remote sensing images, and use a custom geographic transformation to convert the universal transverse mercator projection coordinates of the multi-spectral remote sensing images into Gauss-Kruger projection coordinates; Use the multi-spectral remote sensing images to calculate the normalized difference vegetation index and the normalized water turbidity, eliminate redundant points, thin out the measured points, and make the pixel grids and the measured points correspond one by one; Extract the water body reflectance, generate band combination inversion factors through band calculation, and calculate the characteristic importance of each inversion factor in combination with the measured point data; Divide the measured point data into a training set and a validation set, construct a water depth inversion model to invert the water depth of the ponds with retrievable water depth, and calculate the evaluation indexes of the coefficient of determination and the root mean square error by comparing the inverted water depth values with the actually measured water depths. According to the inversion results, extract the water depth data of each invertible pond area, calculate the average water depth value of each invertible pond, and calculate the water storage volume of the invertible pond by combining the water surface area multiplied by the average water depth.

6. The remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 5, characterized in that, The calculation formula for the coefficient of determination of the evaluation index is: ； The calculation formula for the root mean square error is: ； The calculation formula for the root mean square error is: In the formula, y i represents the i th true value; represents the i th estimated value; represents the average value of the true values; represents the total number of true values.

7. A remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 5, characterized in that, The formula for calculating the average water depth value of each invertible pond is: ； In the formula, represents the average water depth value of the i th invertible pond; represents the measured water depth value of the i th invertible pond at the u th measurement point; num represents the total number of measurement points.

8. A remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 5, characterized in that The formula for calculating the water storage volume of the invertible pond is: ； Wherein, V 1 represents the total water storage capacity of the invertible pond; represents the average water depth value of the i th invertible pond; s i represents the area of the i th invertible pond; m represents the total number of invertible ponds.

9. A remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 1, characterized in that The formula for calculating the water storage volume of the non-invertible pond is: ； ； In the formula, z represents the water storage; x represents the area; a , b , c all represent the fitting parameters of the quadratic polynomial function; V 2 represents the total water storage of the non-invertible ponds; z j represents the j th water storage of the non-invertible ponds; n represents the total number of non-invertible ponds.

10. A remote sensing statistical joint estimation method for the storage volume of pond water with classified processing according to claim 1, characterized in that The steps of fusing the water storage volumes of the invertible and non-invertible ponds, calculating the total regional water storage volume, and generating a spatial distribution map of the water storage volume include: Use the average value method and the statistical model method to fuse the calculation results of the water storage volumes of the invertible and non-invertible ponds to obtain the total water storage volume in the test area; Based on geographic information technology and the pond water surface boundary, add a new average water depth field, assign the average water depth value of each pond to the vector pond surface, and generate a visual regional pond water storage volume distribution map.

Images