A desert remote sensing image lake extraction method based on fusion of SSI and water body index

Abstract

The application discloses a kind of desert remote sensing image lake extraction methods based on SSI and water body index fusion, comprising the following steps: based on the remote sensing image data obtained by GEE platform, calculate suspended sediment index (SSI) and water body index;Suspending the fusion processing of silt index and water body index, obtain fusion image, to enhance the distinguish degree of lake area and background area;Proposed classification method is segmented by single index threshold value;Based on the proposed classification method, the fusion image is classified, and the lake area is accurately extracted. It can effectively improve the accuracy of lake extraction in desert environment, especially in the lake area containing high concentration of silt and the desert area with strong surface reflection. Through the fusion of the two technologies, the advantages of different spectral indexes can be fully utilized to achieve more accurate water body identification in complex environment.

Description

Technical Field

[0001] This invention relates to a lake extraction method, and more particularly to a lake extraction method based on the fusion of SSI and water index in desert remote sensing images. Background Technology

[0002] In the field of remote sensing image processing, the extraction and identification of lakes is an important research direction in GIS, environmental monitoring, and water resource management.

[0003] Currently, most common lake extraction methods are based on water body indices (such as Normalized Difference Water Index (NDWI) and Modified Normalized Difference Water Index (MNDWI), which enhance the spectral characteristics of water bodies to identify lakes. However, in desert regions, due to their unique surface reflectance characteristics and complex vegetation-water mixing issues, conventional water body index extraction methods perform poorly in this environment.

[0004] In desert regions, lakes often contain large amounts of suspended sediment, causing the water to exhibit spectral reflectance characteristics different from those of traditional water bodies. Especially in water bodies with high suspended sediment content, traditional methods struggle to distinguish the suspended sediment from the surrounding arid environment, leading to blurred lake boundaries or incorrect extraction.

[0005] Therefore, an innovative method is needed that can combine the spectral characteristics of suspended sediment with the spectral features of water bodies to improve the accuracy of lake extraction in desert environments.

[0006] In view of this, the present invention is hereby proposed. Summary of the Invention

[0007] The purpose of this invention is to provide a method for extracting lakes from desert remote sensing images based on the fusion of SSI and water index, aiming to overcome the problems of insufficient accuracy and false detection faced by existing technologies when extracting lakes in desert environments.

[0008] The objective of this invention is achieved through the following technical solution:

[0009] The present invention provides a method for extracting lakes from desert remote sensing images based on the fusion of SSI and water index, comprising the following steps:

[0010] 1) Calculate the suspended sediment index and water body index based on remote sensing image data acquired by the GEE platform;

[0011] The Suspended Sediment Index (SSI) refers to the ratio of the cumulative dry weight of suspended sediment particles of all sizes in a section of a river to the total weight of all sediment particles of all sizes. It is usually used to describe the suspension state and distribution characteristics of sediment in a river.

[0012] 2) The suspended sediment index and water body index are fused to obtain a fused image, thereby enhancing the distinction between the lake area and the background area;

[0013] 3) A classification method is proposed using single-exponential threshold segmentation;

[0014] 4) Based on the proposed classification method, the fused images are classified to accurately extract lake areas.

[0015] Compared with existing technologies, the lake extraction method based on the fusion of SSI and water body indexes in desert remote sensing images provided by this invention can effectively improve the accuracy of lake extraction in desert environments, especially in lake areas with high concentrations of sediment and desert areas with strong surface reflectivity. By combining these two technologies, the advantages of different spectral indices can be fully utilized to achieve more accurate water body identification in complex environments. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the Google Earth Engine (GEE) platform interface and the construction process of the suspended sediment index (SSI) calculation function in an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of suspended sediment (SSI) data extraction in an embodiment of the present invention;

[0018] Figure 3 This is a schematic diagram illustrating the multi-index collaborative method for extracting water body data in an embodiment of the present invention;

[0019] Figure 4 This is a schematic diagram illustrating the combination of suspended sediment data and water body extraction data in an embodiment of the present invention;

[0020] Figure 5 This is a schematic diagram comparing the details of JRC water data (a global water cover dataset provided by the European Joint Research Centre) with the embodiments of the present invention.

[0021] in, Figure 1 The interface represents the applicant's free disclosure of technology to the public and does not constitute a technical limitation on this application. Any unclear parts in the diagram can be considered as undisclosed. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them, and do not constitute a limitation on the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0023] First, the following explanations are provided for the terms that may be used in this article:

[0024] The term "and / or" means that either or both can be achieved simultaneously. For example, X and / or Y means that it includes both "X" or "Y" as well as the three cases of "X and Y".

[0025] The terms "comprising," "including," "containing," "having," or other similar semantic descriptions should be interpreted as non-exclusive inclusion. For example, including a technical feature element (such as raw material, component, ingredient, carrier, dosage form, material, size, part, component, mechanism, device, step, process, method, reaction conditions, processing conditions, parameter, algorithm, signal, data, product or article of manufacture, etc.) should be interpreted as including not only the expressly listed technical feature element, but also other technical feature elements that are not expressly listed and are well-known in the art.

[0026] The term "composed of" excludes any technical features not expressly listed. When used in a claim, it closes the claim to exclude all technical features other than those expressly listed, except for associated conventional impurities. If the term appears only in a clause of a claim, it limits the claim to the elements expressly listed in that clause; elements recited in other clauses are not excluded from the overall claim.

[0027] Unless otherwise explicitly specified or limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this document according to the specific circumstances.

[0028] The terms “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “back,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” and “counterclockwise” indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience and simplification of description and do not imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this document.

[0029] The contents not described in detail in the embodiments of this invention are prior art known to those skilled in the art. Where specific conditions are not specified in the embodiments of this invention, they shall be performed according to conventional conditions in the art or conditions recommended by the manufacturer. Where the manufacturers of the reagents or instruments used in the embodiments of this invention are not specified, they are all conventional products that can be purchased commercially.

[0030] The present invention provides a method for extracting lakes from desert remote sensing images based on the fusion of SSI and water index, comprising the following steps:

[0031] 1) Calculate the suspended sediment index and water body index based on remote sensing image data acquired by the GEE platform;

[0032] The Suspended Sediment Index (SSI) refers to the ratio of the cumulative dry weight of suspended sediment particles of all sizes in a section of a river to the total weight of all sediment particles of all sizes. It is usually used to describe the suspension state and distribution characteristics of sediment in a river.

[0033] 2) The suspended sediment index and water body index are fused to obtain a fused image, thereby enhancing the distinction between the lake area and the background area;

[0034] 3) A classification method is proposed using single-exponential threshold segmentation;

[0035] 4) Based on the proposed classification method, the fused images are classified to accurately extract lake areas.

[0036] The remote sensing image data includes multispectral or hyperspectral image data, and the data source is remote sensing satellites or UAV equipment.

[0037] The suspended sediment index is calculated using a formula.

[0038] The fusion process uses a weighted average method to balance the contributions of suspended sediment index and water body index in lake extraction.

[0039] The weights in the weighted average method are dynamically adjusted based on the reflectivity of deserts and lakes to improve the accuracy of lake extraction.

[0040] The water body index is the normalized differential water body index or the modified normalized differential water body index;

[0041] MNDWI>NDVI or MNDWI>EVI, and EVI<0.1;

[0042] NDWI is the Normalized Difference Water Index.

[0043] MNDWI is the corrected normalized difference water index.

[0044] NDVI is the Normalized Difference Vegetation Index.

[0045] EVI stands for Enhanced Vegetation Index;

[0046] Based on the relationship between NDVI and MNDWI mentioned above, a water body extraction function is defined. Based on the results obtained from the water body extraction function, the water body frequency is calculated:

[0047] ;

[0048] The water extraction function determines whether a pixel belongs to a water body based on the following conditions:

[0049] Water body frequency represents the proportion of water body pixels in the total number of pixels. Water bodies are classified according to their frequency.

[0050] Pixels with a water frequency greater than or equal to 0.75 are classified as permanent water bodies, pixels with a water frequency less than or equal to 0.25 are classified as non-water bodies, and pixels with a water frequency greater than 0.25 and less than 0.75 are classified as seasonal water bodies.

[0051] The suspended sediment index is calculated using the following formula:

[0052]

[0053] in:

[0054] It is the reflectivity in the near-infrared band;

[0055] It is the reflectivity of the red band;

[0056] This index is used to identify the concentration of suspended sediment in lakes, helping to distinguish water areas with high sediment content from non-water areas on the desert surface.

[0057] The normalized differential water index is calculated using the following formula:

[0058]

[0059] in:

[0060] It is the reflectivity in the near-infrared band.

[0061] It is the reflectivity of the green band.

[0062] The index, short for Normalized Difference Water Index, is an index that uses specific bands of remote sensing images to perform normalized difference processing, thereby highlighting water information in the images. This index enhances the contrast between water bodies and vegetation and is suitable for water body extraction, especially in densely vegetated areas.

[0063] The corrected normalized differential water index is calculated using the following formula:

[0064]

[0065] in:

[0066] It is the reflectivity of the shortwave infrared band.

[0067] It is the reflectivity of the green band.

[0068] The index, officially known as the Modified Normalized Difference Water Index, is calculated using the reflectance values ​​of the green band (GREEN) and shortwave infrared band (SWIR) in remote sensing imagery to more accurately reflect water body information. This index enhances the contrast between water bodies and exposed surfaces, making it suitable for complex areas containing buildings or desert surfaces.

[0069] The enhanced vegetation index is calculated using the following formula:

[0070]

[0071] in:

[0072] It is the reflectivity in the near-infrared band;

[0073] It is the reflectivity of the red band;

[0074] It is the reflectivity of the blue band;

[0075] G is the gain factor, set to 2.5;

[0076] and The coefficients used for atmospheric correction are 6 and 7.5;

[0077] L represents the influence of soil background, set to 1;

[0078] The index, short for Enhanced Vegetation Index, is a vegetation index obtained by combining data from multiple remote sensing bands, especially the red, near-infrared, and blue bands, through specific mathematical calculations. It aims to overcome the shortcomings of the Normalized Difference Vegetation Index (NDVI) in certain situations, such as saturation and susceptibility to soil moisture interference, thereby more accurately reflecting the growth status and coverage of vegetation.

[0079] In summary, the lake extraction method based on the fusion of Suspended Sediment Index (SSI) and water body indices in this invention significantly improves the accuracy of lake identification by analyzing remote sensing images and employing multiple water body indices to comprehensively utilize the spectral differences between water bodies and surface materials. Experimental results show that this method exhibits superior identification performance compared to traditional methods in lake extraction in desert areas, especially in lakes with high sediment content. It is particularly suitable for lake identification in desert environments.

[0080] This invention can effectively distinguish lakes containing sediment from the surrounding desert vegetation and surface. It is suitable for extracting lakes from complex desert remote sensing images and can significantly improve the accuracy of lake identification, especially for lake areas with high sediment content. It solves the problem that the existing technology has unsatisfactory identification results in desert environments.

[0081] This invention combines the unique surface features of deserts with water spectral information to improve the accuracy and reliability of desert lake extraction, effectively addressing the technical challenges in lake identification in desert regions.

[0082] Compared to existing lake extraction techniques that typically rely on traditional water indices such as the Normalized Difference Water Index (NDWI) and the Modified Normalized Difference Water Index (MNDWI), these methods suffer from limitations in extraction accuracy in desert regions due to the complex mixing of surface reflectance characteristics and water bodies. This is especially true for water bodies with high suspended sediment concentrations, whose spectral characteristics are similar to the surrounding arid environment, blurring lake boundaries. The present invention combines suspended sediment indices with water body indices to effectively distinguish between sediment and water in desert lakes, thereby improving extraction accuracy.

[0083] To more clearly demonstrate the technical solution and its effects provided by the present invention, the embodiments of the present invention will be described in detail below with reference to specific examples.

[0084] The present invention provides a method for extracting lakes from desert remote sensing images based on the fusion of suspended sediment index (SSI) and water body index, including suspended sediment index extraction, water body index extraction, and fusion of the two indices;

[0085] The Suspended Sediment Index (SSI) is a method for estimating the suspended sediment content in water bodies by utilizing the characteristics of the water reflectance spectrum in remote sensing imagery. Suspended sediment has a significant impact on light scattering characteristics, especially in the visible and near-infrared bands; the higher the sediment concentration in the water, the greater its reflectance. By using specific band combinations, the distribution of suspended sediment in water bodies can be accurately extracted.

[0086] The water body index fusion method combines multiple water body indices to accurately identify water areas by utilizing the spectral differences between water bodies and other surface materials in remote sensing imagery. Common water body indices include NDWI (Normalized Difference Water Index) and MNDWI (Modified Normalized Difference Water Index). By fusing multiple water body indices, the accuracy of the extraction results can be improved, especially in complex environments (such as desert regions).

[0087] like Figures 1 to 5 As shown:

[0088] The specific implementation includes the following steps:

[0089] Including SSI, MNDVI, NDVI, EVI, etc.;

[0090] The Suspended Sediment Index (SSI) is calculated using the following formula:

[0091]

[0092] in:

[0093] It is the reflectivity in the near-infrared band.

[0094] It is the reflectivity of the red band.

[0095] This index is used to identify the concentration of suspended sediment in lakes, helping to distinguish water areas with high sediment content from non-water areas on the desert surface.

[0096] The Normalized Difference Water Index (NDWI) is calculated using the following formula:

[0097]

[0098] in:

[0099] It is the reflectivity in the near-infrared band.

[0100] It is the reflectivity of the green band.

[0101] This index enhances the contrast between water and vegetation, making it suitable for water extraction, especially in densely vegetated areas.

[0102] The Modified Normalized Difference Water Index (MNDWI) is calculated using the following formula:

[0103]

[0104] in:

[0105] It is the reflectivity of the shortwave infrared band.

[0106] It is the reflectivity of the green band.

[0107] This index enhances the contrast between water bodies and bare surfaces, making it suitable for complex areas containing buildings or desert surfaces.

[0108] The Enhanced Vegetation Index (EVI) is calculated using the following formula:

[0109]

[0110] in:

[0111] It is the reflectivity in the near-infrared band.

[0112] It is the reflectivity of the red band.

[0113] It is the reflectivity of the blue band.

[0114] G is the gain factor (usually set to 2.5).

[0115] and Factors used for atmospheric correction (common values ​​are 6 and 7.5).

[0116] L represents the influence of soil background (usually set to 1).

[0117] A water extraction function is defined based on the relationship between NDVI and mNDWI. The water extraction function determines whether a pixel belongs to a water body based on the following conditions:

[0118] MNDWI > EVI or mNDWI > NDVI

[0119] EVI < 0.1

[0120] Based on the results obtained from the water extraction function, the water body frequency was calculated. The water body frequency represents the proportion of water body pixels in the total number of pixels. Next, water bodies were categorized according to their frequency: pixels with a water body frequency greater than or equal to 0.75 were classified as permanent water bodies; pixels with a water body frequency less than or equal to 0.25 were classified as non-water bodies; and pixels with a water body frequency greater than 0.25 and less than 0.75 were classified as seasonal water bodies. The calculation formula is as follows:

[0121]

[0122] This invention overlays the SSI (Suspended Sediment Intake) frequency distribution map with the frequency distribution map of the water body itself to form a comprehensive image. On this comprehensive image, specific threshold standards are set to identify and filter areas with high sediment content, thus classifying them as non-water bodies. To more accurately delineate the boundaries between water and non-water bodies, a weighting factor for water body boundaries is also considered. When determining whether a region belongs to a water body, in addition to the sediment content, we also consider the region's proximity to known water body boundaries or other relevant characteristics. Through these steps, the actual boundaries of water bodies can be extracted more accurately, providing a reliable foundation for subsequent analysis or applications.

[0123] Specific implementation example (taking a desert region as an example):

[0124] 1. For example Figure 1 As shown, the specific steps for obtaining the Suspended Sediment Index (SSI) in Google Earth Engine (GEE) typically involve processing and analyzing satellite imagery data using the GEE platform. Below is an overview of the steps for obtaining SSI using the GEE platform; these steps may need to be tailored to specific imagery data and requirements:

[0125] To obtain the Suspended Sediment Index (SSI) on the GEE platform, you need to log in to the GEE platform and browse the datasets to select suitable Landsat data, such as the Landsat 8 or 9 atmospheric top reflectivity dataset. Select appropriate satellite imagery based on conditions such as the study area, time range, and cloud cover, and perform necessary preprocessing, such as cloud removal, to improve data quality. Use the GEE JavaScript API to build an SSI calculation function, which is based on the SSI calculation formula and typically involves mathematical operations on different bands of the image. Apply the calculation function to the selected image data to generate the SSI image. View the generated SSI image on the GEE map to ensure it meets expectations, and you can choose to download the results locally. Throughout the process, attention should be paid to data quality and accuracy, the correctness of the calculation formula, and the resource limitations of the GEE platform.

[0126] 2. For example Figure 2 As shown, satellite images of the study area were acquired using the GEE platform. Relevant algorithms were used on the GEE platform to obtain water volume data of a desert lake. The data was downloaded to the local machine and processed using ArcGIS to obtain the area data of a desert lake in 2023.

[0127] A multi-index collaborative method was used to process the images, resulting in relatively high-quality water body extraction data. The correlation index relationships are as follows: (MNDWI > NDVI or MNDWI > EVI) and EVI < 0.1

[0128] In the formula, MNDWI is the improved normalized water index, NDVI is the normalized vegetation index, and EVI (Enhanced Vegetation Index) is the enhanced vegetation index. The main purpose of this method is to eliminate the interference of vegetation on water extraction. Through actual operation, it was found that the lake area data extracted by this method in a desert is of better quality than traditional single indices such as MNDWI and DLWI.

[0129] Compared to single-index methods, the multi-index collaborative method does not require the Otsu algorithm and can directly extract water bodies by utilizing the magnitude relationships between multiple indices, thus eliminating the need for manual delineation of lake boundaries. Regarding image data, since there are no image limitations imposed by the Otsu algorithm, the multi-index collaborative method can utilize a wider range of images. After image selection, preliminary work for lake water body extraction is performed on the GEE platform. Formulas for calculating MNDWI, NDNI, and EVI water indices, as well as a multi-index collaborative water extraction formula, are constructed. For each selected image, water body identification and extraction are performed using the multi-index collaborative method, and the water ratio is calculated. The Normalized Difference Water Index (NDWI) and Modified Normalized Difference Water Index (MNDWI) are calculated using the acquired image data. The calculation results for these two indices range from -1 to 1, with negative values ​​representing non-water features and positive values ​​representing water features.

[0130] A water extraction function is defined based on the relationship between NDVI and MNDWI. The water extraction function determines whether a pixel belongs to a water body based on the following conditions:

[0131] mNDWI > EVI or mNDWI > NDVI EVI < 0.1

[0132] Here, EVI is the calculated Enhanced Vegetation Index. Pixels that meet the above conditions are considered water bodies; otherwise, they are considered non-water bodies.

[0133] 3. For example Figure 3 , Figure 4As shown, the obtained SSI data and water body data extracted through multi-index collaborative extraction are combined, and a threshold of 0.332 is set. Data above this threshold is classified as solid sediment, and data below this threshold is classified as suspended sediment. Suspended sediment exists in the water, so it is classified as water, thus improving the accuracy of water body extraction. The water body data is visually interpreted, and each lake area is marked to obtain a more accurate threshold. Further processing of the primary water body data is performed in ArcGIS software. The raster-to-vector tool is used to vectorize the lake water body identification results, and visual interpretation removes non-water body parts such as shadows, resulting in lake water body vector data. The area calculation tool is used to obtain the area of ​​all lakes, and lakes in individual maps are assigned corresponding names. The spatial connection tool is used to associate names with lakes in all atlases.

[0134] 4. As shown in Tables 1 and 2 and Figure 5 (a, b) and Figure 5 As shown in (c) and (b), data accuracy verification was performed. A confusion matrix was constructed, and the Kappa coefficient was calculated to verify the accuracy of the obtained lake area dataset. The data was obtained through visual interpretation of Google high-resolution imagery and Jilin-1 dry-resolution imagery. To ensure the accuracy of the verification data, non-water body verification points were selected within a 100m buffer zone of the lake shoreline, while water body verification points were randomly distributed within the lake water, resulting in a total of 200 verification points. 100 verification points were obtained from Google high-resolution imagery (100 non-water body verification points and 100 water body verification points). The obtained verification points were checked using historical Google high-resolution imagery to ensure the accuracy of the verification point data.

[0135] (1) Single-exponential threshold segmentation combined with Otsu's algorithm was used to upload the validation point data to the GEE platform. The "sampleRegions" function was used to count the attributes of the validation points in the extracted lake water dataset. This function can add the attributes of the result data to the validation point data, thereby distinguishing the attributes of the validation points in the result data, counting the number of validation points, constructing a confusion matrix, and calculating the Kappa coefficient. The results are as follows:

[0136]

[0137] (2) The multi-exponential collaborative method was used to construct a confusion matrix using validation point data and lake area data, and the Kappa coefficient was calculated to verify the accuracy of a desert lake area dataset obtained by the multi-exponential collaborative method. The results are as follows:

[0138]

[0139] Comparison of local details in the extraction results of the two water bodies ( Figure 5Compared to the finished JRC water body data, the water body extracted using the hybrid index algorithm has a boundary that better matches the water body boundary in the actual synthesized remote sensing image. The JRC dataset has the problem that the extracted water body area is smaller than the actual water body area, which causes errors in water body extraction.

[0140] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims. The information disclosed in the background section is intended only to enhance the understanding of the overall background technology of the present invention and should not be construed as an admission or implication in any way that such information constitutes prior art known to those skilled in the art.

Claims

1.A method for extracting lakes from a desert remote sensing image based on fusion of SSI and water body index, characterized in that, The method comprises the following steps: 1) calculating a suspended sediment index and a water body index based on remote sensing image data obtained from a GEE platform; The suspended sediment index, abbreviated as SSI, refers to the proportion of the cumulative dry weight of suspended sediment particles of all sizes in a river to the total weight of all size levels of sediment particles, and is usually used to describe the suspended state and distribution characteristics of sediment in a river; 2) fusing the suspended sediment index and the water body index to obtain a fused image to enhance the distinction between the lake area and the background area; 3) using a single index threshold segmentation method; 4) classifying the fused image based on the proposed classification method to accurately extract the lake area; The remote sensing image data includes multispectral or hyperspectral image data, and the data source is a remote sensing satellite or a drone device; The suspended sediment index is calculated by a formula; The fusion processing uses a weighted average method to balance the contribution of the suspended sediment index and the water body index in lake extraction; The weights in the weighted average method are dynamically adjusted according to the reflection characteristics of deserts and lakes to improve the accuracy of lake extraction; The water body index is a normalized difference water index or a modified normalized difference water index; MNDWI>NDVI or MNDWI>EVI, and EVI<0.1; NDWI is a normalized difference water index; MNDWI is a modified normalized difference water index; NDVI is a normalized vegetation index; EVI is an enhanced vegetation index; According to the relationship between the above-mentioned NDVI and MNDWI, a water body extraction function is defined, and the water body frequency is calculated based on the result obtained by the water body extraction function: ； The water body extraction function determines whether a pixel belongs to a water body according to the following conditions: The water body frequency represents the proportion of water body pixels in the total pixels, and the water body categories are divided according to the water body frequency: Pixels with a water body frequency greater than or equal to 0.75 are classified as permanent water bodies, pixels with a water body frequency less than or equal to 0.25 are classified as non-water bodies, and pixels with a water body frequency greater than 0.25 and less than 0.75 are classified as seasonal water bodies; The suspended sediment index is calculated by the following formula: ； wherein: R NIR is the reflectivity in the near infrared band; R RED is the reflectivity of the red band; This index is used to identify the concentration of suspended sediment in a lake, and helps to distinguish between water body areas with high sediment content and non-water body areas on the surface of deserts; The normalized difference water index is calculated by the following formula: ； wherein: R NIR is the reflectivity in the near infrared R GREEN is the reflectivity of the green waveband The modified normalized difference water index is calculated by the following formula: ； wherein: R SWIR is the reflectivity in the short-wave infrared band R GREEN is the reflectivity of the green waveband The method further comprises: combining the obtained SSI data and the water body data extracted by the multi-index collaborative method, setting a threshold, determining solid sediment as greater than the threshold and determining suspended sediment as less than the threshold; visually interpreting the water body data to mark each lake area; vectorizing the lake water body recognition result, visually interpreting to remove the non-water body part, obtaining the lake water body vector data, and determining the area of all the lakes; giving the corresponding name to the lake in each map, and using a spatial connection tool to associate the names of the lakes in all the map sets; and the multi-index collaborative method further comprises using the verification point data and the lake area data to construct a confusion matrix, calculating a kappa coefficient, and verifying the accuracy of the desert lake area data set extracted by the multi-index collaborative method. 2.The method for lake extraction from desert remote sensing image based on fusion of SSI and water body index according to claim 1, characterized in that, The enhanced vegetation index is calculated by the following formula: ； wherein: R NIR is the reflectivity in the near infrared band; R RED is the reflectivity of the red band; R BLUE is the reflectivity in the blue band; G is a gain factor, and is set as 2.5; C1 and C2 are coefficients for atmospheric correction, and the values are 6 and 7.5; L is the influence of soil background, and is set as 1.

Images