A soybean remote sensing extraction method fusing vegetation index and cascaded K-means clustering

Abstract

The present application belongs to the technical field of remote sensing extraction, and particularly relates to a soybean remote sensing extraction method fusing a vegetation index and a cascade K-means clustering. The method comprises the following steps: S1, constructing a soybean extraction original feature set; S2, extracting a farmland region based on the soybean extraction original feature set, and generating a dry farmland mask in the farmland region; S3, performing unsupervised classification on a soybean extraction optimized feature set by using a cascade K-means clustering algorithm to obtain an initial clustering category in the dry farmland mask limited region; S4, constructing a greenness and structure comprehensive index, and obtaining a soybean reference region by combining the greenness and structure comprehensive index and a natural break method; and S5, constructing a soybean consistency scoring formula, and obtaining a soybean remote sensing extraction result based on the soybean consistency scoring formula. The present application does not depend on ground samples or experience thresholds, and can realize high-precision, scalable and automatic extraction of large-scale soybean planting distribution.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of remote sensing extraction, and particularly relates to a soybean remote sensing extraction method fusing a vegetation index and cascade K-means clustering. BACKGROUND

[0002] Soybean is an important oil and protein crop in the world, and plays an irreplaceable role in ensuring food security, providing livestock feed and producing vegetable oil. With the growth of population and the increasing demand for sustainable agriculture, accurately grasping the distribution and yield information of soybean has become a key link for agricultural management, policy making, international trade and scientific research.

[0003] Traditional acquisition of soybean planting information relies on artificial census and statistics, which has certain accuracy, but has problems of low efficiency, high cost, long cycle, etc., especially cannot adapt to crop identification and area assessment in large-scale regions, which restricts the informatization and fine management of modern agriculture. The rapid development of remote sensing technology provides a new path for soybean planting information extraction. By using the spatial, spectral and temporal characteristics of remote sensing images, crop monitoring and identification can be realized in a large range, quickly and automatically. This non-contact and efficient means has become an important direction of agricultural remote sensing research and application.

[0004] However, the current mainstream soybean remote sensing extraction method still faces many challenges. Supervised classification-based algorithms, such as random forest and support vector machine, usually rely on a large number of ground samples for training, which not only has high sample collection cost and long time consumption, but also has poor model generalization ability due to regional differences in samples, and needs to be frequently updated to adapt to different regions or years of extraction tasks. Unsupervised classification methods such as K-means and ISODATA are not supported by samples, but are highly sensitive to initial parameters and noise, and lack semantic labels, which need to be determined by artificial judgment, and are prone to classification errors and unstable clustering problems.

[0005] In addition, the method of using vegetation index (such as NDVI) for soybean identification usually relies on empirical or statistical threshold, and extracts soybean area by binaryzation segmentation, but this method is sensitive to regional differences and seasonal changes, and lacks adaptability and universality. Even on the Google Earth Engine (GEE) platform, by calling time-series remote sensing data and classification algorithms, the processing efficiency can be improved, but it still relies on ground samples or manual threshold setting, and still needs human intervention in key steps, which makes it difficult to realize truly end-to-end automatic extraction, and restricts its stability and consistency in large-scale, multi-region and long-term continuous mapping.

[0006] In summary, the existing soybean remote sensing extraction method is difficult to achieve effective balance among cost, precision and automation degree, and a new method of soybean remote sensing extraction is needed, which can realize high precision, automation and generalization of large-scale soybean planting area extraction on the GEE platform without manual sample selection and threshold setting, so as to break through the current technical bottleneck and promote the intelligent development of agricultural remote sensing. SUMMARY

[0007] Therefore, the present application aims to provide a soybean remote sensing extraction method combining vegetation index and cascade K-means clustering to solve the problem that the existing technology is difficult to achieve balance among cost, precision and automation degree. The present application does not rely on ground samples or empirical thresholds and can realize high-precision, scalable and automated extraction of large-scale soybean planting distribution.

[0008] To achieve the above-mentioned purpose, the technical scheme of the present application is as follows:

[0009] A soybean remote sensing extraction method combining vegetation index and cascade K-means clustering, specifically comprising the following steps:

[0010] S1: Constructing a soybean extraction original feature set based on Sentinel-2 multispectral images, Sentinel-1 radar images and elevation model data;

[0011] S2: Extracting farmland areas based on the soybean extraction original feature set and generating a dry farmland mask in the farmland areas;

[0012] S3: Cropping the soybean extraction original feature set based on the dry farmland mask to obtain a soybean extraction optimized feature set, and using a cascade K-means clustering algorithm to perform unsupervised classification on the soybean extraction optimized feature set to obtain initial clustering categories in the dry farmland mask limited area;

[0013] S4: Constructing a greenness and structure comprehensive index and performing index calculation in the dry farmland mask limited area using the greenness and structure comprehensive index, and using the natural discontinuity method to perform hierarchical processing on the index calculation results to obtain a soybean reference area;

[0014] S5: Constructing a soybean consistency scoring formula and inputting the initial clustering categories in the dry farmland mask limited area and the soybean reference area into the soybean consistency scoring formula for discrimination to obtain a soybean remote sensing extraction result.

[0015] Further, in step S1, the soybean remote sensing extraction features included in the soybean extraction original feature set include chlorophyll vegetation index, land surface moisture index, enhanced vegetation index, vertical emission-vertical reception, vertical emission-horizontal reception, near-infrared mean value and slope direction.

[0016] Further, the chlorophyll vegetation index, the land surface water index, and the enhanced vegetation index are preprocessed based on the Sentinel-2 multispectral image; the vertical emission-vertical reception and the vertical emission-horizontal reception are preprocessed based on the Sentinel-1 radar image; the near-infrared mean value is preprocessed based on the Sentinel-2 multispectral image; and the slope direction is preprocessed based on the elevation model data.

[0017] The preprocessed results of the chlorophyll vegetation index, the land surface water index, the enhanced vegetation index, the vertical emission-vertical reception, the vertical emission-horizontal reception, the near-infrared mean value, and the slope direction are synthesized by using the cat function to obtain a soybean extraction original feature set.

[0018] Further, in step S2, the soybean extraction original feature set is masked by using the farmland grid of the WorldCover v200 dataset to remove the non-farmland area, and the farmland area extraction is completed.

[0019] A threshold value is set, and in the farmland area, the B11 band mean value of different areas in the Sentinel-2 multispectral image is calculated, and the area with a B11 band mean value greater than the threshold value is regarded as a dry field area to generate a dry field mask.

[0020] Further, the pixel value of the farmland grid is 40, and the threshold value is 0.15.

[0021] Further, the specific method of unsupervised classification of the soybean extraction optimized feature set by using the cascade K-means clustering algorithm includes:

[0022] In the ee.Clusterer.wekaCascadeKMeans function built in the GEE platform, the scale parameter is set to 20, the numPixels parameter is set to 3000, the seed parameter is set to 42, and the geometries parameter is set to true.

[0023] The cascade K-means clustering classifier is realized by calling the ee.Clusterer.wekaCascadeKMeans function built in the GEE platform, the input of the cascade K-means clustering classifier is the soybean extraction optimized feature set, and the output of the cascade K-means clustering classifier is the initial clustering class in the dry field mask limited area.

[0024] Further, the calculation formula of the greenness and structure integrated index GSCI is:

[0025] ;

[0026] wherein, represents the reflectivity value of the near-infrared band, represents the reflectivity value of the red edge second band.

[0027] Further, the highest level region obtained by hierarchical processing using the natural break method is taken as the soybean reference region.

[0028] Further, the soybean consistency score formula is:

[0029] ;

[0030] wherein, is the soybean consistency score of the i-th category, is the number of overlapping pixels of the i-th category and the soybean reference region, is the total number of pixels of the soybean reference region.

[0031] Compared with the prior art, the present invention can achieve the following beneficial effects:

[0032] (1) The soybean remote sensing extraction method fusing vegetation index and cascade K-means clustering of the present invention realizes an end-to-end automated process from feature extraction to classification determination by integrating unsupervised cascade K-means clustering, greenness and structure comprehensive index (GSCI) and consistency score, which eliminates human intervention, saves time-consuming sample collection and tedious threshold parameter adjustment, significantly improves the automation level, and greatly enhances the objectivity of the method.

[0033] (2) The soybean remote sensing extraction method fusing vegetation index and cascade K-means clustering of the present invention is completely executed in the GEE cloud, realizes automatic collection of source region samples through GSCI grading, has strong cross-regional application ability, and eliminates the model migration problem caused by data deviation in different regions through the automatic sampling mechanism based on image features, so that the efficient extraction of large-scale soybean planting areas can be completed in a short time.

[0034] (3) The soybean remote sensing extraction method fusing vegetation index and cascade K-means clustering of the present invention, compared with the commonly used unsupervised classification algorithm (such as K-means clustering and farthest priority clustering) in GEE, can effectively alleviate the problems of initial value sensitivity and noise interference through the multi-level progressive clustering and dynamic center updating mechanism of cascade K-means clustering, and significantly improve the stability and classification accuracy of clustering. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings, which form a part of the present invention, are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the present invention and together with the description serve to explain the present invention. In the drawings:

[0036] Figure 1A flowchart of a soybean remote sensing extraction method combining a fusion vegetation index and cascade K-means clustering according to an embodiment of the present application is shown in the figure;

[0037] Figure 2 A structural block diagram of a soybean remote sensing extraction method combining a fusion vegetation index and cascade K-means clustering according to an embodiment of the present application is shown in the figure;

[0038] Figure 3 A time series curve diagram of a greenness and structure comprehensive index according to an embodiment of the present application is shown in the figure;

[0039] Figure 4 A fitting diagram of a soybean remote sensing extraction area and a statistical area according to an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and do not constitute a limitation on the present application.

[0041] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0042] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" and the like are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited by "first", "second" and the like can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0043] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "linking" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through intermediate medium, or internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0044] Google Earth Engine (GEE) is a cloud computing-based remote sensing and geospatial analysis platform developed by Google, mainly used for large-scale environmental monitoring, geospatial modeling and spatio-temporal change analysis. The platform integrates dozens of mainstream remote sensing data such as Landsat, MODIS and Sentinel, which can be called by users at any time; GEE uses Google cloud server to process data, supporting large-scale spatio-temporal analysis tasks without local image download. The related operations of the present application are realized based on the GEE platform.

[0045] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0046] As Figure 1 shown, the present application proposes a soybean remote sensing extraction method combining vegetation index and cascade K-means clustering, which specifically includes the following steps: S1: constructing a soybean extraction original feature set based on Sentinel-2 multispectral image, Sentinel-1 radar image and elevation model data; S2: extracting farmland area based on the soybean extraction original feature set, and generating a dry farmland mask in the farmland area; S3: cropping the soybean extraction original feature set based on the dry farmland mask, eliminating non-target area feature information, obtaining a soybean extraction optimized feature set, and using a cascade K-means clustering algorithm to perform unsupervised classification on the soybean extraction optimized feature set, obtaining an initial clustering class in the dry farmland mask limited area; S4: constructing a greenness and structure comprehensive index, and using the greenness and structure comprehensive index to perform index calculation in the dry farmland mask limited area, and using the natural discontinuity method to perform hierarchical processing on the index calculation result, obtaining a soybean reference area; S5: constructing a soybean consistency scoring formula, and inputting the initial clustering class in the dry farmland mask limited area and the soybean reference area into the soybean consistency scoring formula for discrimination, obtaining a soybean remote sensing extraction result.

[0047] As Figure 2As shown, the present application firstly acquires Sentinel-2 multispectral images, Sentinel-1 radar images and elevation data, and after preprocessing, constructs a soybean extraction original feature set containing vegetation index, polarization, texture and terrain, and based on auxiliary data and threshold method, successively extracts farmland area and generates farmland mask; then two parallel processes are executed, one is to perform farmland mask cutting on the soybean extraction original feature set based on the farmland mask, to eliminate non-target area feature information, to construct a soybean extraction optimized feature set, and to use a cascade K-means clustering algorithm to perform unsupervised clustering on the multi-source feature set to obtain an initial cluster class of ground objects, and the other is to construct a greenness and structure comprehensive index (GSCI) based on near-infrared and red edge bands, and to divide it into five levels using the natural discontinuity method, and to select the highest value level as the soybean reference area; by consistency scoring on the initial cluster class and the soybean reference area, the cluster class with the highest score is identified as soybean, and a soybean distribution map is extracted, and statistical analysis and classification accuracy evaluation are performed, and finally high-precision and low-sample-dependent automatic remote sensing extraction of soybean planting area is realized.

[0048] Further, the natural discontinuity method is a grading method for dividing continuous data into several discrete levels, which is widely used in remote sensing image grading and mapping. The core idea is to minimize intra-class difference and maximize inter-class difference, so as to obtain the most reasonable data grouping.

[0049] In some embodiments, in step S1, the soybean remote sensing extraction features contained in the soybean extraction original feature set include chlorophyll vegetation index, land surface moisture index, enhanced vegetation index, vertical emission-vertical reception, vertical emission-horizontal reception, near-infrared mean value, and slope direction.

[0050] It should be noted that the chlorophyll vegetation index, the land surface moisture index, the enhanced vegetation index, the vertical emission-vertical reception, the vertical emission-horizontal reception, the near-infrared mean value, and the slope direction are originally numerical indicators representing the physical or vegetation state of the target area under a specific remote sensing band or polarization mode, but in remote sensing data processing, they are usually expressed and applied in the form of raster images with geographical spatial resolution. The present application uniformly inputs the above parameters in the form of images to facilitate subsequent image processing and feature extraction operations.

[0051] In some embodiments, the chlorophyll vegetation index, the land surface moisture index, and the enhanced vegetation index are preprocessed based on Sentinel-2 multispectral images; the vertical emission-vertical reception and the vertical emission-horizontal reception are preprocessed based on Sentinel-1 radar images; the near-infrared mean value is preprocessed based on Sentinel-2 multispectral images; and the slope direction is preprocessed based on elevation model data.

[0052] The preprocessed results of chlorophyll vegetation index, land surface water index, enhanced vegetation index, vertical transmission-vertical reception, vertical transmission-horizontal reception, near-infrared mean value and slope direction are synthesized by using the cat function to obtain the original feature set of soybean extraction.

[0053] The soybean remote sensing extraction feature refers to: in remote sensing image classification, multi-dimensional input information of soybean planting area distribution is extracted, and the band information in multi-source remote sensing data and the derived index layer are spliced to form a multi-dimensional classification feature layer, which is convenient for subsequent clustering processing.

[0054] The vegetation index (including chlorophyll vegetation index (GCVI), land surface water index (LSWI) and enhanced vegetation index (EVI)) is calculated using the Sentinel-2 image data set of the GEE platform. The calculation formulas of the chlorophyll vegetation index (GCVI), land surface water index (LSWI) and enhanced vegetation index (EVI) are as follows:

[0055] ;

[0056] ; ;

[0057] Among them, 、 、 、 、 respectively represent the reflectivity values of near-infrared (usually corresponding to B8 of Sentinel-2), red (usually corresponding to B4 of Sentinel-2), green (usually corresponding to B3 of Sentinel-2), blue (usually corresponding to B2 of Sentinel-2) and short wave 1 band (usually corresponding to B11 of Sentinel-2) in the remote sensing image.

[0058] The specific process of preprocessing the vegetation index is: based on the growth period of soybean, the time window of Sentinel-2 image synthesis is limited to July 1 to September 30, and 10% is used as the cloud threshold for preliminary filtering, and then the maskS2clouds function is used to further remove the cloud interference pixels, so as to ensure the stability of the features; finally, the median function is used to synthesize single-scene data according to the time sequence, which effectively enhances the representativeness of the data.

[0059] Polarization features: polarization features include vertical transmission-vertical reception (VV) and vertical transmission-horizontal reception (VH). VV means that the radar transmits and receives the echo signal in the vertical polarization mode. VH means that the radar transmits vertically and receives horizontally.

[0060] The specific process of preprocessing the polarization features is: the two polarization features VV and VH are calculated using the Sentinel-1 image dataset of the GEE platform. Based on the soybean growth period, the time window of July 1 to September 30 is set as the Sentinel-1 image synthesis time window. First, the threshold masking is used to remove the edge or low signal-to-noise ratio area (less than -30 dB) to improve the stability of the radar features. Then, the max function is used to calculate the maximum value of the time series dataset of the Sentinel-1 image (the Sentinel-1 image dataset arranged in time sequence) to synthesize single-scene polarization feature data and enhance the structural expression capability.

[0061] Texture features: A 3x3 moving window is used in GEE to select the near-infrared band to calculate the gray matrix, and the near-infrared mean (B8_savg) feature is selected as the texture feature for soybean classification.

[0062] The specific process of preprocessing the texture features is: the dataset of the Sentinel-2 image from July 1 to September 30 is extracted, and the near-infrared band B8 of the Sentinel-2 image dataset is multiplied by 1000 to convert it to an integer type for texture calculation. The glcmTexture function (gray level co-occurrence matrix texture analysis) is used to extract the savg texture feature of the near-infrared band B8. In order to better reflect the complexity of the spatial structure of vegetation, the median function is used to calculate the B8_savg dataset between July 1 and September 30, and then synthesize single-scene data.

[0063] Terrain features: The slope direction (elevation) information calculated from the elevation (DEM) data of the study area is used as the terrain feature.

[0064] The global SRTM digital elevation model data (USGS / SRTMGL1_003) is used to calculate the slope factor, and the single-scene elevation data is obtained as the terrain feature to reflect the influence of terrain changes on the planting area.

[0065] The above steps respectively represent the integration of full-range remote sensing features from spectrum, structure, radar reflectivity, spatial texture, and terrain factors. The cat function is used to synthesize a multi-dimensional single-scene classification image, and a multi-source remote sensing feature set is constructed, i.e., the soybean extraction original feature set, which provides sufficient feature input for the subsequent cascade K-means clustering.

[0066] In some embodiments, in step S2, the soybean extraction original feature set is masked using the farmland raster of the WorldCover v200 dataset to remove non-farmland areas and complete farmland area extraction;

[0067] A threshold is set, the B11 band mean value of different regions in the Sentinel-2 multispectral image in the farmland area is calculated, and the region with a B11 band mean value greater than the threshold is regarded as a dry farmland region to generate a dry farmland mask.

[0068] It should be noted that the pixel value of the grid data of 40 in the 2020 global land cover data set (WorldCover v200) published by the European Space Agency (ESA) is used to mask the multi-source remote sensing feature set of the research area, to remove non-farmland areas such as forests, water areas, built-up areas, etc. and complete farmland coverage extraction; then, using the threshold method, the region less than 0.15 is regarded as a rice planting area based on the mean value synthesis data of short-wave infrared 1 (B11 of Sentinel-2) from April to June, and the region with a B11 band mean value greater than 0.15 is regarded as a dry farmland crop planting area containing soybeans within the farmland coverage range, to complete the dry farmland mask.

[0069] In some embodiments, the updateMask function is used to crop the soybean extraction original feature set, and the non-target area feature information is removed to obtain a soybean extraction optimized feature set. The specific method of unsupervised classification of the soybean extraction optimized feature set by using the cascade K-means clustering algorithm includes: in the ee.Clusterer.wekaCascadeKMeans function built in the GEE platform, the scale parameter is set to 20, the numPixels parameter is set to 3000, the seed parameter is set to 42, and the geometries parameter is set to true.

[0070] The cascade K-means clustering classifier is realized by calling the ee.Clusterer.wekaCascadeKMeans function built in the GEE platform. The input of the cascade K-means clustering classifier is the soybean extraction optimized feature set, and the output of the cascade K-means clustering classifier is the initial clustering class in the limited area of the dry farmland mask.

[0071] It should be noted that the scale parameter is set to 20, that is, the pixel is collected at a resolution of 20 meters; the numPixels parameter is set to 3000, which specifies that the maximum number of sampled pixels is 3000; the seed parameter is set to 42, which specifies the random number seed 42 to ensure that the sampling is reproducible; the geometries parameter is set to true to retain the geometric spatial information of each sampled pixel. The parameters are input into the ee.Clusterer.wekaCascadeKMeans function and are waiting for calling.

[0072] The ee.Clusterer.wekaCascadeKMeans function is used to call the cascade K-means clustering classifier of the GEE platform, and then the optimal clustering structure is automatically explored in the range of 4 to 8 clusters, that is, the minimum cluster number (minClusters) is set to 4, and the maximum cluster number (maxClusters) is set to 8.

[0073] Further, the cascade K-means clustering is a multi-level unsupervised clustering algorithm, which is improved on the basis of the traditional K-means algorithm. The clustering result is refined layer by layer through cascade iteration to enhance the stability of classification and the ability to maintain local structure. The ee.Clusterer.wekaCascadeKMeans built-in in Google Earth Engine is the specific implementation function of the algorithm, which has the characteristics of automatic optimization of initial center and enhancement of clustering diversity, and is suitable for scenes with high intra-class heterogeneity and similar spectra between pixels in remote sensing data. The basic principle is: initially, the K-means clustering algorithm is used for data clustering, and then the original clustering result is re-clustered (i.e., the clustering center or intra-cluster data is re-clustered) at each level to form a "hierarchical subdivision", and finally a clustering result with more hierarchical structure and separation ability is generated.

[0074] In some embodiments, the formula for calculating the greenness and structure integrated index GSCI is:

[0075] ;

[0076] wherein, represents the reflectance value of the near-infrared band, represents the reflectance value of the red edge second band.

[0077] It should be noted that the greenness and structure composite index (Greenness and Structure Composite Index, GSCI) proposed in the present application is a new type of remote sensing vegetation index specially constructed for extracting soybean planting areas. The original intention of the index is to optimize the remote sensing extraction task of soybean planting areas. Its construction logic is derived from two key features of soybean in remote sensing spectrum: 1. Significant greenness performance, which is characterized by high reflectivity in the near-infrared band; 2. Relatively complex vertical crown structure, which has a clear response in the red edge band. By combining the reflectivity of NIR and VRE2 bands in a simple product form, GSCI gives soybean crops unique spectral response characteristics. This composite index not only improves the spectral separability of soybean and other vegetation or background objects, but also enhances its temporal recognition stability at different time nodes. Therefore, GSCI can reflect the leaf green level and crown structure complexity of crops, and has good adaptability and potential for promotion in soybean remote sensing classification, growth period dynamic monitoring, and vigor analysis.

[0078] As shown in Figure 3 , the time series curve of the greenness and structure composite index of soybean, corn, rice, water, grassland and built-up area is shown, which shows that the GSCI index has good soybean separation in the main growth period of soybean.

[0079] Next, in order to facilitate subsequent automatic extraction of typical soybean planting area samples from the source area and to build an automated classification process, in order to realize automatic hierarchical processing based on remote sensing index image, the present application takes GSCI (Greenness and Structure Composite Index) image as input data source, and programs Natural Breaks Method on Google Earth Engine (GEE) platform to perform unsupervised optimal segmentation according to the natural distribution characteristics of image values, automatically determine the segmentation threshold, and divide continuous numerical values into five non-overlapping numerical intervals. Specifically, the following steps are included:

[0080] 1. Image to array processing

[0081] First, extract all valid pixel values in the GSCI index image, eliminate invalid values (such as cloud mask, boundary null), and convert them into a one-dimensional numerical array, denoted as:

[0082] ;

[0083] Wherein, represents the index value of the th valid pixel, is the number of valid pixels.

[0084] 2. Natural Breaks Method modeling calculation

[0085] The dataset D is inputted and the natural break method is used to perform optimal classification on the dataset D. The basic principle of this classification method is:

[0086] Under the premise of a given number of categories k, a set of split points is found to minimize the difference within each category (i.e., the minimum within-group variance) while maximizing the difference between categories (i.e., the maximum between-group variance). The optimization objective is to minimize the within-class variance (WCV):

[0087] ;

[0088] Where WCV (Within-Class Variance) is the total sum of within-class variance (i.e., total error sum of squares); is the j th category, containing several data points ; is a data value in the j th category; is the average value of all data in the th category; j is the category index, taking values 1, 2, 3, 4, 5.

[0089] At the same time, the total variance (TSS) of the whole set is defined as follows:

[0090] ;

[0091] ;

[0092] Under the optimal grouping condition, the "Goodness of Variance Fit" (GVF) index can be further calculated:

[0093] ;

[0094] Where GVF is closer to 1, the better the grouping effect.

[0095] 3. Threshold extraction and classification mapping

[0096] Through the dynamic programming algorithm, all possible combinations of split positions are calculated to obtain a set of optimal classification thresholds :

[0097] Where , , where is the optimal breakpoint obtained by calculation, and each category interval is defined as , a total of 5 intervals.

[0098] 4. Image automatic hierarchical classification

[0099] Finally, according to the above threshold, the original index image is classified pixel by pixel:

[0100] Where f(x) is the class number of each pixel, and the output is a hierarchical index image, and the pixel value represents the classification to which it belongs.

[0101] Subsequently, according to the order of GSCI value from high to low, the above five hierarchical intervals are labeled as "very high, high, medium, low, and very low" five probability levels, to represent the strength of the possibility of the region as a soybean target object. The interval corresponding to the "very high" level is selected as the high confidence soybean reference sample area.

[0102] This classification method does not need to rely on artificial experience to set thresholds, and can automatically divide the optimal classification interval according to the numerical distribution of the image itself, which not only retains the physical meaning of the GSCI index, but also improves the accuracy and stability of the class division in subsequent unsupervised classification, and is suitable for remote sensing automatic recognition and classification modeling tasks of regional scale crop planting areas.

[0103] In some embodiments, the soybean consistency score formula is:

[0104]

[0105] Where, is the soybean consistency score of the i-th class, is the number of overlapping pixels of the i-th class and the soybean reference area, is the total number of pixels in the soybean reference area.

[0106] The soybean consistency score formula is used to judge the pixel consistency between the supervised clustering classes and the reference map, and the soybean coincidence degree of each class and the reference area is calculated respectively, and the class with the highest soybean coincidence degree obtained by comparison is the soybean.

[0107] Taking the main soybean planting areas in Heilongjiang Province in 2021 as an example, the soybean remote sensing extraction of 9 cities in Heilongjiang Province is carried out respectively, the soybean planting area of each city is calculated according to the remote sensing extraction result, and the determination coefficient (R 2 ) of the soybean planting area obtained by remote sensing extraction and the soybean planting area in the statistical data is calculated, as shown in Figure 4 In the fitting results of the two kinds of data, the determination coefficient (R²) reaches 0.86, indicating that the present application has good fitting ability and classification accuracy in the soybean remote sensing identification task, verifying the effectiveness and practical value of the present application in large-scale crop identification.

[0108] ​​It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the present disclosure are achieved, which is not limited herein.

[0109] The specific embodiments described above are not to be taken as limiting the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives of the specific embodiments described above can be made without departing from the spirit and scope of the application. Any such modifications, equivalents, alternatives and combinations, therefore, are expressly included within the scope of the application.

Claims

1. A remote sensing extraction method for soybeans that integrates vegetation indices and cascaded K-means clustering, characterized in that: Specifically, the steps include the following: S1: Construct the original feature set for soybean extraction based on Sentinel-2 multispectral imagery, Sentinel-1 radar imagery, and elevation model data; S2: Extract farmland areas based on the original feature set extracted from soybeans, and generate dryland masks within the farmland areas; S3: Based on the dryland mask, the original feature set of soybean extraction is cropped to obtain the optimized feature set of soybean extraction. The cascaded K-means clustering algorithm is used to perform unsupervised classification on the optimized feature set of soybean extraction to obtain the initial cluster category within the area limited by the dryland mask. S4: Construct a comprehensive index of greenness and structure, and use the comprehensive index of greenness and structure to calculate the index within the area defined by the dryland mulch. The natural discontinuity method is used to classify the index calculation results to obtain the soybean reference area. The formula for calculating the Greenness and Structure Composite Index (GSCI) is as follows: ； in, This represents the reflectivity value in the near-infrared band. This represents the reflectance value of the second band of the red edge; S5: Construct a soybean consistency scoring formula, and input the initial cluster category within the dryland mask-defined area and the soybean reference area into the soybean consistency scoring formula for discrimination to obtain soybean remote sensing extraction results.

2. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering as described in claim 1, characterized in that: In step S1, the soybean remote sensing extracted features included in the original feature set of soybean extraction include: chlorophyll vegetation index, land surface moisture index, enhanced vegetation index, vertical transmission-vertical reception, vertical transmission-horizontal reception, near-infrared mean, and slope aspect.

3. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering as described in claim 2, characterized in that: Chlorophyll vegetation index, land surface moisture index, and enhanced vegetation index were preprocessed based on Sentinel-2 multispectral imagery; vertical transmission-vertical reception and vertical transmission-horizontal reception were preprocessed based on Sentinel-1 radar imagery; near-infrared mean was preprocessed based on Sentinel-2 multispectral imagery; and slope aspect was preprocessed based on elevation model data. The cat function was used to synthesize the preprocessed results of chlorophyll vegetation index, land surface moisture index, enhanced vegetation index, vertical emission-vertical reception, vertical emission-horizontal reception, near-infrared mean, and slope aspect to obtain the original feature set extracted from soybean.

4. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering as described in claim 1, characterized in that: In step S2, the original feature set of soybeans is extracted using the farmland raster of the WorldCover v200 dataset, and non-farmland areas are removed to complete the farmland area extraction. Set a threshold, calculate the mean value of B11 band in different regions of Sentinel-2 multispectral image within the farmland area, and take the region with the mean value of B11 band greater than the threshold as the dryland area to generate a dryland mask.

5. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering according to claim 4, characterized in that: The pixel value of the farmland grid is 40; the threshold is 0.

15.

6. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering according to claim 1, characterized in that: Specific methods for unsupervised classification of soybeans using the cascaded K-means clustering algorithm to extract optimized feature sets include: Within the built-in ee.Clusterer.wekaCascadeKMeans function of the GEE platform, set the scale parameter to 20, the numPixels parameter to 3000, the seed parameter to 42, and the geometries parameter to true; The cascaded K-means clustering classifier is implemented by calling the built-in ee.Clusterer.wekaCascadeKMeans function of the GEE platform. The input of the cascaded K-means clustering classifier is the optimized feature set extracted from soybeans, and the output of the cascaded K-means clustering classifier is the initial cluster category within the area defined by the dryland mask.

7. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering according to claim 1, characterized in that: The region with the highest grade obtained by grading using the natural discontinuity method will be used as the soybean reference area.

8. The soybean remote sensing extraction method based on the fusion of vegetation index and cascaded K-means clustering according to claim 1, characterized in that: The formula for soybean consistency scoring is: ； in, This is the consistency score of soybeans in category i. Let be the number of pixels in category i that overlap with the soybean reference area. This represents the total number of pixels in the soybean reference area.

Images