A method and system for authenticity inspection of high-resolution satellite snow cover products

Abstract

The present application relates to the technical field of quantitative remote sensing inversion, and particularly relates to a realness inspection method for high-resolution satellite snow cover product, obtaining a first snow cover product of a first spatial resolution to be inspected; obtaining an initial second snow cover product and / or first ground snow depth observation data; performing spatial aggregation processing on the second snow cover product, and performing quality inspection and snow depth determination on the first ground snow depth observation data to obtain an inspection data set for final realness inspection; the inspection data set comprises a third snow cover product and / or third ground snow depth observation data; the third spatial resolution of the third snow cover product is equal to the first spatial resolution; according to the inspection data set, a binary evaluation index and a continuous value evaluation index of the first snow cover product are respectively calculated; and according to the binary evaluation index and the continuous value evaluation index and a preset threshold, a realness inspection report is generated. The inspection result obtained by the method has higher accuracy.

Description

Technical Field

[0001] This invention relates to the field of quantitative remote sensing inversion technology, and in particular to a method and system for verifying the authenticity of snow cover products from high-resolution satellites. Background Technology

[0002] The amount of snow cover affects the Earth's radiative energy balance and, as a vast water reservoir, influences various climate and hydrological processes. With the development of domestically produced high-resolution satellite technology, high spatial resolution optical sensor band information can provide accurate snow cover information and enable large-scale observations.

[0003] Currently, research on snow cover products based on optical satellites has matured. However, for high spatial resolution optical imagery, the accuracy of snow cover products remains to be examined due to the complex spatial structure of the Earth's surface, the unique optical characteristics of snow, and the combined influence of factors such as topography, illumination, and geological features. Taking domestic high-resolution satellites such as GF-1 / 2 / 6 / WFV optical data as an example: current snow cover identification is hampered at the application level by the lack of short-wave infrared channel information, which is crucial for monitoring snow cover; secondly, due to the limited number of bands available for high-resolution satellites, it is difficult to effectively distinguish between clouds and snow; and thirdly, the optical characteristics of surface objects exhibiting similar spectra are frequently observed.

[0004] Therefore, it is necessary to conduct authenticity verification for high-resolution snow cover products. Currently, there are numerous methods for evaluating the authenticity of remote sensing snow cover products. Evaluation work can be broadly categorized into two types based on the different verification data: one is verification using higher-resolution relative true value data; the other is verification using ground-based measured data. However, for high-resolution satellite snow cover products, a relatively objective and reasonable verification method has not yet been established. Existing verification methods mostly rely on limited observations to assess the presence or absence of snow, which has certain limitations and may lead to inaccurate authenticity verification results. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method and system for verifying the authenticity of high-resolution snow cover products.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0009] In a first aspect, embodiments of the present invention provide a method for verifying the authenticity of snow cover products from high-resolution satellites, comprising:

[0010] S10. Obtain the first snow cover product to be inspected;

[0011] The first snow cover product was obtained using a high-resolution satellite sensor with a first spatial resolution.

[0012] S20. Obtain the initial first verification dataset for verifying the authenticity of the first snow-covered product;

[0013] The first test dataset includes a second snow cover product and / or first ground snow depth observation data; the second snow cover product was obtained by a high-resolution satellite sensor with a second spatial resolution; the second spatial resolution is higher than the first spatial resolution;

[0014] S30. Spatial aggregation processing is performed on the second snow cover product, and quality checks and snow depth determination are performed on the first ground snow depth observation data to obtain the second test dataset for verifying the authenticity of the first snow cover product.

[0015] The second test dataset includes a third snow cover product and / or third ground snow depth observation data; the third spatial resolution of the third snow cover product is equal to the first spatial resolution;

[0016] S40. Based on the second test dataset, calculate the binary evaluation index and continuous value evaluation index of the first snow cover product respectively.

[0017] S50. Generate an authenticity verification report based on the binarized evaluation index, the continuous value evaluation index, and the preset threshold.

[0018] Optionally, S30 includes:

[0019] S31. Spatial aggregation is performed on the second snow cover product to obtain a third snow cover product with the same spatial resolution as the first snow cover product.

[0020] S32. Perform a data quality check on the first ground snow depth observation data to obtain second ground snow depth observation data that meets the preset quality standards. Then, according to the preset judgment standards, determine whether there is snow at each position in the second ground snow depth observation data to obtain the judgment result and the third ground snow depth observation data marked with the judgment result.

[0021] S33. Obtain the second verification dataset for verifying the authenticity of the first snow-covered product.

[0022] Optionally, S32 includes:

[0023] S321. Check the climatological equipment specifications, logic, climate extremes, internal consistency and temporal consistency of the first ground snow depth observation data to obtain the second ground snow depth observation data that meets the preset quality standards.

[0024] S322. For any location in the second ground snow depth observation data, if the snow depth value is less than s, it is determined that there is no snow; if the snow depth value is greater than or equal to s, it is determined that there is snow. The determination result is marked on the corresponding location of the second ground snow depth observation data to obtain the third ground snow depth observation data.

[0025] Optionally, obtaining the binarized evaluation index in step S40 includes:

[0026] Based on the second test dataset, the binary evaluation index of the first snow cover product is calculated using the binary evaluation index expression.

[0027] The binarized evaluation metrics include: precision, recall, specificity, F-score, and accuracy.

[0028] The expression for the binarized evaluation index is:

[0029]

[0030]

[0031]

[0032]

[0033]

[0034] Wherein, Precision represents the proportion of pixels classified as having snow that are actually having snow; Recall represents the proportion of pixels correctly classified as having snow; Specificity represents the proportion of pixels correctly classified as having no snow; F represents the F-score, i.e., the accuracy score; Accuracy represents the probability that a pixel is correctly classified; TP represents the number of samples that are actually having snow that are correctly predicted as having snow; TN represents the number of samples that are actually not having snow that are correctly predicted as not having snow; FP represents the number of samples that are actually not having snow that are incorrectly predicted as having snow; and FN represents the number of samples that are actually having snow that are incorrectly predicted as not having snow.

[0035] Optionally, obtaining the continuous value evaluation index in step S40 includes:

[0036] Based on the second test dataset, the continuous value evaluation index of the first snow cover product is calculated using the continuous value evaluation index expression.

[0037] The evaluation indicators for the continued value include: root mean square error and correlation coefficient;

[0038] The expression for the continuous value evaluation index is:

[0039]

[0040]

[0041] Where RMSE is the root mean square error; R 2 The correlation coefficient is N; the total number of pixels is FSC. est This indicates the ratio of snow cover area to total area in the first snow cover product; FSC ref This indicates the ratio of snow cover area to total area in the third snow cover product and / or third ground snow depth observation data.

[0042] Optionally, S50 includes:

[0043] S51. Based on the relationship between the calculated binary evaluation index and the corresponding preset threshold, the first evaluation result is obtained;

[0044] S52. Based on the relationship between the calculated continuous value evaluation index and the corresponding preset threshold, a second evaluation result is obtained.

[0045] S53. Combine the results of the first evaluation and the second evaluation to generate an authenticity verification report.

[0046] Optionally, S51 includes:

[0047] S511. If the precision is less than 80%, it is evaluated as an over-classification error of snow-covered pixels; if the recall is less than 80%, it is evaluated as an under-classification error of snow-covered pixels; if the specificity is less than 80%, it is evaluated as an under-classification error of snow-free pixels; if the accuracy is less than 85%, it is evaluated as poor accuracy, otherwise it is evaluated as good accuracy.

[0048] S512. Based on the evaluation in S511, the first evaluation result is obtained.

[0049] Optionally, S52 includes:

[0050] S521. If the root mean square error is less than 0.15 and the correlation coefficient is higher than 0.8, the continuous value test effect of the snow cover product is evaluated as excellent; otherwise, it is considered poor.

[0051] S522. Based on the evaluation in S521, the second evaluation result is obtained.

[0052] Optionally, the high-resolution optical satellite sensor in S10 can be any one of the wide-field camera of Gaofen-1 satellite, the panchromatic multispectral camera of Gaofen-2 satellite, and the wide-field camera of Gaofen-6 satellite.

[0053] Secondly, embodiments of the present invention provide an authenticity verification system for snow cover products from high-resolution satellites, comprising:

[0054] The first snow cover product acquisition module is used to acquire the first snow cover product to be inspected.

[0055] The first snow cover product was obtained using a high-resolution satellite sensor with a first spatial resolution.

[0056] The first test dataset acquisition module is used to acquire the initial first test dataset for verifying the authenticity of the first snow-covered product.

[0057] The first test dataset includes a second snow cover product and / or first ground snow depth observation data; the second snow cover product was obtained by a high-resolution satellite sensor with a second spatial resolution; the second spatial resolution is higher than the first spatial resolution;

[0058] The second verification dataset construction module is used to perform spatial aggregation processing on the second snow cover product and to perform quality checks and snow depth determination on the first ground snow depth observation data, so as to obtain the final second verification dataset used to verify the authenticity of the first snow cover product.

[0059] The second test dataset includes a third snow cover product and / or third ground snow depth observation data; the third spatial resolution of the third snow cover product is equal to the first spatial resolution;

[0060] The evaluation index calculation module is used to calculate the binary evaluation index and continuous value evaluation index of the first snow cover product based on the second test dataset.

[0061] The authenticity verification report generation module is used to generate authenticity verification reports based on binary evaluation indicators, continuous value evaluation indicators, and preset thresholds.

[0062] (III) Beneficial Effects

[0063] The beneficial effects of this invention are as follows: The method and system for verifying the authenticity of snow cover products from high-resolution satellites, by using snow cover products with higher resolution than the snow cover product to be verified and ground snow depth observation data as data for verifying authenticity, can make the verification results more accurate compared to the prior art. By combining binarized evaluation indicators and continuous value evaluation indicators to verify the authenticity of high-resolution satellite snow cover products, the verification process can be more efficient, and the verification results can be more accurate, comprehensive, and credible. Attached Figure Description

[0064] Figure 1This is a flowchart illustrating a method for verifying the authenticity of snow cover products based on high-resolution satellite imagery, as provided in an embodiment of the present invention.

[0065] Figure 2(a) is a schematic diagram of a calculated binary evaluation index provided in an embodiment of the present invention;

[0066] Figure 2(b) is a schematic diagram of a calculated continuous value evaluation index provided by an embodiment of the present invention;

[0067] Figure 3 This is a schematic diagram of a system for verifying the authenticity of snow cover products for high-resolution satellites, provided as another embodiment of the present invention. Detailed Implementation

[0068] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0069] This invention proposes a method for verifying the authenticity of snow cover products from high-resolution satellites. First, a first snow cover product with a first spatial resolution to be verified is acquired. Then, a verification dataset is constructed to test the authenticity of the first snow cover product. The verification dataset includes a third snow cover product with a third spatial resolution and / or third ground snow depth observation data. The third snow cover product is obtained by spatially aggregating a second snow cover product with a second spatial resolution higher than the first spatial resolution, and the third spatial resolution is equal to the first spatial resolution. Then, based on the verification dataset, a binarized evaluation index and a continuous value evaluation index for the first snow cover product are calculated. Finally, based on the binarized evaluation index, the continuous value evaluation index, and a preset threshold, a final authenticity verification report is generated. This method yields higher accuracy in the verification results.

[0070] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0071] Example 1

[0072] like Figure 1 As shown in the figure, this embodiment provides a method for verifying the authenticity of snow cover products based on high-resolution satellite imagery, which may include:

[0073] S10. Obtain the first snow-covered product to be inspected.

[0074] The first snow cover product was obtained using a high-resolution satellite sensor with a first spatial resolution.

[0075] Specifically, the resolution of the first snow cover product to be tested is 16m; the high-resolution satellite sensor can be the wide-field camera of Gaofen-1 satellite, the panchromatic multispectral camera of Gaofen-2 satellite and / or the wide-field camera of Gaofen-6 satellite, i.e., the wide-field camera (WFV) and / or the high-resolution camera (PMS) L1 level standardized product.

[0076] S20. Obtain the initial first verification dataset for verifying the authenticity of the first snow-covered product.

[0077] The first test dataset includes a second snow cover product and / or first ground snow depth observation data; the second snow cover product is obtained by a high-resolution satellite sensor with a second spatial resolution; the second spatial resolution is higher than the first spatial resolution.

[0078] S30. Spatial aggregation processing is performed on the second snow cover product, and quality checks and snow depth determination are performed on the first ground snow depth observation data to obtain the second verification dataset used to verify the authenticity of the first snow cover product.

[0079] The second test dataset includes a third snow cover product and / or third ground snow depth observation data; the third spatial resolution of the third snow cover product is equal to the first spatial resolution, and the spatial resolution of the third snow cover product is also 16m.

[0080] Specifically, a second snow cover product is obtained and spatially aggregated to obtain a third snow cover product with the same spatial resolution as the first snow cover product;

[0081] Acquire first ground snow depth observation data, and check the climatological equipment specifications, logic, climate extremes, internal consistency and temporal consistency of the first ground snow depth observation data to obtain high-quality second ground snow depth observation data that meets the preset quality standards.

[0082] For any location in the second ground snow depth observation data, if the snow depth value is less than 1 cm, it is determined that there is no snow; if the snow depth value is greater than or equal to 1 cm, it is determined that there is snow. The determination result is marked on the corresponding location of the second ground snow depth observation data to obtain the third ground snow depth observation data.

[0083] Thus, the second verification dataset, which is used to verify the authenticity of the first snow-covered product, is obtained.

[0084] More preferably, in order to reduce the spatial registration error between ground stations and high-resolution satellite snow cover products, the mode sampling method can be used to first perform 7*7 window spatial aggregation on the high-resolution satellite snow cover product (16m spatial resolution) to be tested. This processing can effectively reduce the positioning error of the high-resolution satellite image itself and the error caused by point-area matching.

[0085] S40. Based on the second test dataset, calculate the binary evaluation index and continuous value evaluation index of the first snow cover product.

[0086] As shown in Figure 2(a), the binarized evaluation metrics include: Precision, Recall, Specificity, F (F-score), and Accuracy; as shown in Figure 2(b), the evaluation metrics include: RMSE (Root Mean Square Error) and R... 2 (Correlation coefficient).

[0087] Specifically, based on the second test dataset, the binary evaluation index of the first snow cover product is calculated using the binary evaluation index expression.

[0088] The expression for the binary evaluation index is:

[0089]

[0090]

[0091]

[0092]

[0093]

[0094] Wherein, Precision represents the proportion of pixels classified as having snow that are actually having snow; Recall represents the proportion of pixels correctly classified as having snow; Specificity represents the proportion of pixels correctly classified as having no snow; F represents the F-score, i.e., the accuracy score; Accuracy represents the probability that a pixel is correctly classified; TP represents the number of samples that are actually having snow that are correctly predicted as having snow; TN represents the number of samples that are actually not having snow that are correctly predicted as not having snow; FP represents the number of samples that are actually not having snow that are incorrectly predicted as having snow; and FN represents the number of samples that are actually having snow that are incorrectly predicted as not having snow.

[0095] Based on the second test dataset, the continuous value evaluation index of the first snow cover product is calculated using the continuous value evaluation index expression.

[0096] The expression for the continuous value evaluation index is:

[0097]

[0098]

[0099] Where RMSE is the root mean square error; R 2 The correlation coefficient is denoted as N; N is the total number of pixels; FSC is the correlation coefficient. est This indicates the ratio of snow cover area to total area in the first snow cover product; FSC ref This indicates the ratio of snow cover area to total area in the third snow cover product and / or third ground snow depth observation data.

[0100] S50. Generate an authenticity verification report based on the binarized evaluation index, the continuous value evaluation index, and the preset threshold.

[0101] Specifically, the first evaluation result is obtained based on the relationship between the calculated binary evaluation index and the corresponding preset threshold.

[0102] Based on the relationship between the calculated continuous value evaluation index and the corresponding preset threshold, a second evaluation result is obtained;

[0103] A authenticity verification report is generated by combining the results of the first and second evaluations.

[0104] For example, if the precision is below 80%, it is evaluated as having an over-classification error for snow-covered pixels; if the recall is below 80%, it is evaluated as having an under-classification error for snow-covered pixels; if the specificity is below 80%, it is evaluated as having an under-classification error for snow-free pixels; if the accuracy is below 85%, it is evaluated as having poor accuracy, and vice versa, resulting in the first evaluation result. If the root mean square error is less than 0.15 and the correlation coefficient is higher than 0.8, it is evaluated as having excellent continuous value test results for snow cover products, and vice versa, resulting in the second evaluation result. Then, by combining the first evaluation result and the second evaluation result, an authenticity test report is generated.

[0105] In summary, the authenticity verification method for high-resolution snow cover products provided in this embodiment is applicable to domestic high-resolution satellite imagery, including GF-1 / 6WFV / PMS snow cover products, and has good scalability. By combining binarized identification indicators to evaluate the precision, recall, specificity, F-score, and accuracy of snow cover products, it can efficiently and accurately verify the accuracy and comparative analysis results of snow cover products. It performs authenticity verification on snow cover products extracted by high-resolution satellite snow cover algorithms and provides real-time feedback on product accuracy, improving the snow cover identification capability of high-resolution satellites. Furthermore, the algorithm has high computational efficiency and strong operational capabilities. This embodiment's authenticity verification method for high-resolution satellite snow cover products supports the use of higher spatial resolution snow cover products and / or quality-checked ground-measured snow depth data as reference datasets for authenticity verification, making the verification results more accurate, comprehensive, and credible.

[0106] Example 2

[0107] like Figure 3 As shown, this embodiment provides an authenticity verification system for snow cover products from high-resolution satellites, which may include:

[0108] The first snow cover product acquisition module is used to acquire the first snow cover product to be inspected.

[0109] The first snow cover product was obtained using a high-resolution satellite sensor with a first spatial resolution.

[0110] The first test dataset acquisition module is used to acquire the initial first test dataset for verifying the authenticity of the first snow-covered product.

[0111] The first test dataset includes a second snow cover product and / or first ground snow depth observation data; the second snow cover product was obtained by a high-resolution satellite sensor with a second spatial resolution higher than the first spatial resolution;

[0112] The second verification dataset construction module is used to perform spatial aggregation processing on the second snow cover product and to perform quality checks and snow depth determination on the first ground snow depth observation data, so as to obtain the final second verification dataset used to verify the authenticity of the first snow cover product.

[0113] The second test dataset includes a third snow cover product and / or third ground snow depth observation data; the third spatial resolution of the third snow cover product is equal to the first spatial resolution;

[0114] The evaluation index calculation module is used to calculate the binary evaluation index and continuous value evaluation index of the first snow cover product based on the second test dataset.

[0115] The authenticity verification report generation module is used to generate authenticity verification reports based on binary evaluation indicators, continuous value evaluation indicators, and preset thresholds.

[0116] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0117] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0118] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first and second features are in direct contact, or that they are in indirect contact through an intermediate medium. Furthermore, "above," "over," or "on top" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," or "beneath" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0119] In the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0120] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make modifications, alterations, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for verifying the authenticity of snow cover products based on high-resolution satellite imagery, characterized in that, include: S10. Obtain the first snow cover product to be inspected; The first snow cover product was obtained using a high-resolution satellite sensor with a first spatial resolution. S20. Obtain the initial first verification dataset for verifying the authenticity of the first snow-covered product; The first test dataset includes the second snow cover product and / or the first ground snow depth observation data; The second snow cover product was obtained using a high-resolution satellite sensor with a second spatial resolution, which is higher than the first spatial resolution. S30. Spatial aggregation processing is performed on the second snow cover product, and quality checks and snow depth determination are performed on the first ground snow depth observation data to obtain the second test dataset for verifying the authenticity of the first snow cover product. The second test dataset includes third snow cover products and / or third ground snow depth observation data; The third spatial resolution of the third snow cover product is equal to the first spatial resolution; S30 includes: S31. Spatial aggregation is performed on the second snow cover product to obtain a third snow cover product with the same spatial resolution as the first snow cover product. S32. Perform a data quality check on the first ground snow depth observation data to obtain second ground snow depth observation data that meets the preset quality standards. Then, according to the preset judgment standards, determine whether there is snow at each position in the second ground snow depth observation data to obtain the judgment result and the third ground snow depth observation data marked with the judgment result. S33. Obtain the final second verification dataset used to verify the authenticity of the first snow-covered product; S32 includes: S321. Check the climatological equipment specifications, logic, climate extremes, internal consistency and temporal consistency of the first ground snow depth observation data to obtain the second ground snow depth observation data that meets the preset quality standards. S322. For any location in the second ground snow depth observation data, if the snow depth value is less than s, it is determined that there is no snow; if the snow depth value is greater than or equal to s, it is determined that there is snow. The determination result is marked on the corresponding location of the second ground snow depth observation data to obtain the third ground snow depth observation data. S40. Based on the second test dataset, calculate the binary evaluation index and continuous value evaluation index of the first snow cover product respectively. Obtaining the continuous value evaluation index in S40 includes: Based on the second test dataset, the continuous value evaluation index of the first snow cover product is calculated using the continuous value evaluation index expression. The evaluation indicators for the continued value include: root mean square error and correlation coefficient; The expression for the continuous value evaluation index is: ， ； in, This is the root mean square error; The correlation coefficient; Total number of pixels; This indicates the ratio of the snow-covered area in the first snow-covered product to the total area; This indicates the ratio of snow cover area to total area in the third snow cover product and / or third ground snow depth observation data; S50. Generate an authenticity verification report based on the binarized evaluation index, the continuous value evaluation index, and the preset threshold.

2. The method for verifying the authenticity of snow cover products for high-resolution satellites according to claim 1, characterized in that, The acquisition of the binarized evaluation index in S40 includes: Based on the second test dataset, the binary evaluation index of the first snow cover product is calculated using the binary evaluation index expression. The binarized evaluation metrics include: precision, recall, specificity, F-score, and accuracy. The expression for the binarized evaluation index is: ， ， ， ， ； in, It represents the accuracy rate, which is the proportion of pixels that are actually snow out of the pixels classified as snow. Recall rate, which is the proportion of pixels that are correctly identified from those that actually contain snow. It represents the specificity, that is, the proportion of real, snow-free pixels that are correctly divided. This represents the F-score, or accuracy score. TP represents the accuracy, which is the probability that a pixel is correctly classified; TN represents the number of samples that are actually snowy but are correctly predicted as snowy; FP represents the number of samples that are actually snowless but are incorrectly predicted as snowy; and FN represents the number of samples that are actually snowy but are incorrectly predicted as snowless.

3. The method for verifying the authenticity of snow cover products for high-resolution satellites according to claim 1, characterized in that, The S50 includes: S51. Based on the relationship between the calculated binary evaluation index and the corresponding preset threshold, the first evaluation result is obtained; S52. Based on the relationship between the calculated continuous value evaluation index and the corresponding preset threshold, a second evaluation result is obtained. S53. Combine the results of the first evaluation and the second evaluation to generate an authenticity verification report.

4. The method for verifying the authenticity of snow cover products for high-resolution satellites according to claim 3, characterized in that, S51 includes: S511. If the precision is less than 80%, it is evaluated as an over-classification error of snow-covered pixels; if the recall is less than 80%, it is evaluated as an under-classification error of snow-covered pixels; if the specificity is less than 80%, it is evaluated as an under-classification error of snow-free pixels; if the accuracy is less than 85%, it is evaluated as poor accuracy, otherwise it is evaluated as good accuracy. S512. Based on the evaluation in S511, the first evaluation result is obtained.

5. The method for verifying the authenticity of snow cover products for high-resolution satellites according to claim 3, characterized in that, S52 includes: S521. If the root mean square error is less than 0.15 and the correlation coefficient is higher than 0.8, the continuous value test effect of the snow cover product is evaluated as excellent; otherwise, it is considered poor. S522. Based on the evaluation in S521, the second evaluation result is obtained.

6. The method for verifying the authenticity of snow cover products for high-resolution satellites according to claim 1, characterized in that, The high-resolution optical satellite sensor in S10 is any one of the following: the wide-field camera of Gaofen-1 satellite, the panchromatic multispectral camera of Gaofen-2 satellite, and the wide-field camera of Gaofen-6 satellite.

7. A system for verifying the authenticity of snow cover products for high-resolution satellite imaging, characterized in that, include: The first snow cover product acquisition module is used to acquire the first snow cover product to be inspected. The first snow cover product was obtained using a high-resolution satellite sensor with a first spatial resolution. The first test dataset acquisition module is used to acquire the initial first test dataset for verifying the authenticity of the first snow-covered product. The first test dataset includes the second snow cover product and / or the first ground snow depth observation data; The second snow cover product was obtained using a high-resolution satellite sensor with a second spatial resolution. The second spatial resolution is higher than the first spatial resolution; The second verification dataset construction module is used to perform spatial aggregation processing on the second snow cover product and to perform quality checks and snow depth determination on the first ground snow depth observation data, so as to obtain the final second verification dataset used to verify the authenticity of the first snow cover product. The second test dataset includes third snow cover products and / or third ground snow depth observation data; The third spatial resolution of the third snow cover product is equal to the first spatial resolution; spatial aggregation is performed on the second snow cover product to obtain a third snow cover product with the same spatial resolution as the first snow cover product; data quality is checked on the first ground snow depth observation data to obtain second ground snow depth observation data that meets the preset quality standards; then, according to the preset judgment criteria, it is determined whether there is snow at each location in the second ground snow depth observation data to obtain the judgment result and the third ground snow depth observation data marked with the judgment result; finally, a second verification dataset is obtained to verify the authenticity of the first snow cover product. The climatological equipment specifications, logic, climatological extremes, internal consistency, and temporal consistency of the first ground snow depth observation data are checked to obtain the second ground snow depth observation data that meets the preset quality standards. For any position in the second ground snow depth observation data, if the snow depth value is less than s, it is determined that there is no snow; if the snow depth value is greater than or equal to s, it is determined that there is snow. The determination result is marked on the corresponding position of the second ground snow depth observation data to obtain the third ground snow depth observation data. The evaluation index calculation module is used to calculate the binary evaluation index and continuous value evaluation index of the first snow cover product based on the second test dataset. The acquisition of the continuous value evaluation index includes: Based on the second test dataset, the continuous value evaluation index of the first snow cover product is calculated using the continuous value evaluation index expression. The evaluation indicators for the continued value include: root mean square error and correlation coefficient; The expression for the continuous value evaluation index is: ， ； in, This is the root mean square error; The correlation coefficient; Total number of pixels; This indicates the ratio of the snow-covered area in the first snow-covered product to the total area; This indicates the ratio of snow cover area to total area in the third snow cover product and / or third ground snow depth observation data; The authenticity verification report generation module is used to generate authenticity verification reports based on binary evaluation indicators, continuous value evaluation indicators, and preset thresholds.

Images