Mapping method of multi-source and multi-temporal spectral indices of soil salinity at regional scale

Abstract

The embodiment of the present disclosure provides a regional scale multi-source multi-temporal cultivated land soil salinity spectral index mapping method, which is applied to the technical field of remote sensing data processing and comprises the following steps: pre-processing obtained multi-source hyperspectral data to obtain multi-source reflectivity data, calculating a plurality of groups of spectral indexes, calculating the correlation coefficient of the spectral indexes and soil salinity, screening the spectral indexes by using an image quality evaluation algorithm, selecting the retained spectral indexes by using a stepwise correlation analysis algorithm, performing optimal central wavelength analysis on the selected spectral indexes, obtaining the optimal spectral index type of soil salinity, calculating the optimal spectral index of soil salinity and the bare soil index under the type based on multi-temporal images, extracting the bare soil distribution information according to the bare soil index, synthesizing the optimal spectral index of soil salinity in the bare soil pixels, determining the classification breakpoints of the optimal spectral index of soil salinity according to the soil salinity grading standard, and obtaining the regional scale soil salinity grading map.

Description

Technical Field

[0001] This disclosure relates to the field of remote sensing data processing technology, and in particular to a method for mapping the spectral index of soil salinity in cultivated land at a regional scale using multiple sources and multiple time phases. Background Technology

[0002] Soil salinity is one of the physicochemical properties of soil quality and an important indicator for measuring soil fertility and salinization. Excessive soil salinity leads to soil salinization, reducing soil fertility and crop yield. Therefore, accurate monitoring of soil salinity is a crucial foundation for agricultural production management and soil salinization control.

[0003] Currently, the main methods for monitoring soil salinity are traditional field sampling and testing and remote sensing. While field sampling and testing is accurate and reliable, it is time-consuming and labor-intensive, making it difficult to achieve rapid monitoring of soil salinity over large areas. Remote sensing, on the other hand, has advantages such as speed, efficiency, and wide coverage, and has been widely used in recent years.

[0004] Multispectral data provides spectral information across multiple bands and can be acquired in various ways, such as via satellite, aircraft, and drones. Studies using multispectral data for soil salinity monitoring have indirectly monitored soil salinity by calculating vegetation indices based on the correlation between vegetation growth and soil salinity; other studies have constructed spectral indices using soil salinity-sensitive bands. However, soil salinity monitoring is influenced by multiple factors, such as soil moisture and vegetation cover. Multispectral data contains limited information and is easily affected by atmospheric influences and data noise, thus impacting the accuracy of soil salinity monitoring. Therefore, some studies utilize hyperspectral data for soil salinity monitoring to improve accuracy.

[0005] Hyperspectral data, covering a spectral range of 400–2500 nm, offers higher spectral resolution and more accurately reflects the spectral characteristics of soil, thus improving the precision of soil salinity monitoring. By performing mathematical operations on spectral reflectance data across multiple bands, a soil salinity spectral index is obtained to reflect the distribution of soil salinity. Furthermore, with the continuous development of machine learning technology, soil salinity monitoring methods have been expanded. Combining hyperspectral data with machine learning techniques can fully utilize the rich information in hyperspectral data to further improve the accuracy of soil salinity monitoring. Despite these advantages, hyperspectral data also has certain disadvantages. The data volume is typically large, posing challenges for data storage and processing. Additionally, spectral indices constructed based on different hyperspectral datasets can vary. Therefore, a single data source cannot meet the needs of regional-scale soil salinity monitoring.

[0006] Therefore, it is necessary to combine multi-source data for soil salinity monitoring. By integrating remote sensing data from different platforms, a spectral index reflecting soil salinity information can be constructed to achieve regional-scale monitoring of soil salinity levels. This invention focuses on multi-source, multi-platform data and proposes a regional-scale multi-source, multi-temporal method for mapping spectral indices of cultivated land soil salinity. Spectral indices are calculated using multi-source reflectance data. Correlation coefficients and image quality assessments are used to analyze the spectral indices of different datasets. Then, stepwise correlation analysis and optimal center wavelength analysis are used to determine the optimal spectral index within the intersection. The spectral indices within bare soil pixels are synthesized to achieve regional-scale mapping of cultivated land soil salinity levels. This method can fully explore the potential information of multi-source data, overcome the limitations of single-platform data, expand the scope and frequency of soil salinity monitoring, and further improve the prediction accuracy of soil salinity pairs. It has good application prospects in fields such as natural resource element surveys and monitoring. Summary of the Invention

[0007] In a first aspect, embodiments of this disclosure provide a method for mapping the spectral index of soil salinity in cultivated land at a regional scale using multiple sources and time phases, the method comprising: The acquired multi-source hyperspectral data are preprocessed to obtain multi-source reflectance data; Calculate several sets of spectral indices based on multi-source reflectance data; The correlation coefficients between spectral indices and soil salinity were calculated, and spectral indices were screened using image quality assessment algorithms. The retained spectral indices were selected using a stepwise correlation analysis algorithm; Optimal center wavelength analysis was performed on the selected spectral indices to obtain the optimal spectral index type for soil salinity; Based on multi-temporal images, the optimal spectral index of soil salinity and the bare soil index are calculated. The distribution information of bare soil is extracted based on the bare soil index. The optimal spectral index of soil salinity in the bare soil pixels is synthesized. The classification discontinuity of the optimal spectral index of soil salinity is determined according to the soil salinity classification standard, and a regional scale soil salinity classification map is obtained.

[0008] In some possible implementations of the first aspect, the acquired multi-source hyperspectral data is preprocessed to obtain multi-source reflectance data, including: The acquired multi-source hyperspectral data is preprocessed to remove bands whose radiation quality does not meet the preset requirements and whose atmospheric absorption does not meet the preset requirements, in order to obtain multi-source reflectance data. Preprocessing includes: radiation coefficient correction, atmospheric correction, orthorectification correction, topographic and solar photometric correction.

[0009] In some possible implementations of the first aspect, several sets of spectral indices are calculated based on multi-source reflectance data, including: Standardize the multi-source reflectivity data; Perform spectral transformation on the standardized multi-source reflectance data; Several sets of spectral indices are calculated based on the multi-source reflectance data after spectral transformation.

[0010] In some feasible ways of implementing the first aspect, the correlation coefficient between spectral indices and soil salinity is calculated, and spectral indices are screened using image quality assessment algorithms, including: The correlation coefficient between spectral indices and soil salinity was calculated using the Pearson correlation coefficient formula, and the spectral indices were evaluated for image quality using an image quality assessment algorithm. Spectral indices were then selected based on the evaluation results. The evaluation results included image stripe noise evaluation results and relative radiometric error evaluation results.

[0011] Among the possible implementations of the first aspect, the selection of retained spectral indices utilizes a stepwise correlation analysis algorithm, including: Sort the retained spectral indices according to the correlation coefficient, select a specified number of spectral indices from the multi-source data, and perform an intersection check. If the intersection is empty, it is determined that the spectral indices of the multi-source data do not overlap. Then, the number of spectral indices is gradually increased in step size of a specified number, and an intersection check is performed until the intersection is not equal to 0. The spectral indices in the intersection are then selected.

[0012] In some feasible ways of implementing the first aspect, optimal center wavelength analysis is performed on the selected spectral index to obtain the optimal spectral index for soil salinity, including: The wavelength range is determined based on the selected spectral index. Within the wavelength range, wavelengths are set sequentially at specified intervals to obtain multiple specific bands. Combining the selected spectral index type, specific spectral indices of the same type under specific bands are calculated. By comparing the correlation between specific spectral indices and soil salinity, the optimal spectral index type for soil salinity is determined.

[0013] In some feasible methods of the first aspect, the optimal soil salinity spectral index and bare soil index are calculated based on multi-temporal images. Bare soil distribution information is extracted based on the bare soil index. The optimal soil salinity spectral indices within the bare soil pixels are synthesized. The grading discontinuities of the optimal soil salinity spectral index are determined according to the soil salinity grading standard to obtain a regional-scale soil salinity grading map, including: Based on multi-temporal imagery, the optimal spectral index of soil salinity and the bare soil index were calculated. The numerical distribution of the bare soil index in cultivated land pixels was statistically analyzed. Using the Otsu's method with human-computer interaction, the threshold for distinguishing between bare soil pixels and non-bare soil pixels was determined. Bare soil pixels were assigned a value of 1, and non-bare soil pixels were assigned a value of 0, resulting in a bare soil distribution map. By statistically analyzing the median of the optimal spectral index of soil salinity in bare soil pixels, a grayscale map of the optimal spectral index of soil salinity was obtained. Based on this, by fitting the linear relationship between soil salinity and the optimal spectral index of soil salinity, the grading discontinuity points of the optimal spectral index of soil salinity were determined, resulting in a regional-scale soil salinity grading map.

[0014] Secondly, embodiments of this disclosure provide a regional-scale multi-source, multi-temporal cultivated land soil salinity spectral index mapping device, the device comprising: The preprocessing module is used to preprocess the acquired multi-source hyperspectral data to obtain multi-source reflectance data; The calculation module is used to calculate several sets of spectral indices based on multi-source reflectance data; The calculation module is also used to calculate the correlation coefficient between spectral indices and soil salinity, and to screen spectral indices using image quality assessment algorithms; The selection module is used to select the spectral indices to be retained using a stepwise correlation analysis algorithm; The analysis module is used to perform optimal center wavelength analysis on the selected spectral index to obtain the optimal spectral index type for soil salinity. The mapping module is used to calculate the optimal spectral index of soil salinity and the bare soil index under the optimal spectral index type of soil salinity based on multi-temporal images. It extracts the distribution information of bare soil based on the bare soil index, synthesizes the optimal spectral index of soil salinity in the bare soil pixels, and determines the grading discontinuity of the optimal spectral index of soil salinity according to the soil salinity grading standard to obtain a regional scale soil salinity grading map.

[0015] Thirdly, embodiments of this disclosure provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0016] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above.

[0017] In the embodiments of this disclosure, the characteristics of hyperspectral data from different sources are fully considered, including spatial resolution, spectral resolution, and revisit period. Multi-source data are coupled based on a stepwise correlation analysis algorithm, fully utilizing the wavelength information of the multi-source data, reducing inconsistencies commonly found in practical applications, and improving the accuracy of soil salinity monitoring results. Synthesis of multi-temporal data avoids discontinuities caused by changes in surface features and environmental factors. Furthermore, a spectral index is constructed based on soil salinity content, which is sensitive to soil salinity, has a simple calculation process, and has a wide range of applications.

[0018] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0019] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A flowchart illustrating a method for mapping the spectral index of soil salinity at a regional scale across multiple sources and time phases in cultivated land, provided as an embodiment of this disclosure; Figure 2 A high-resolution image of a typical area of ​​soil salinity provided for embodiments of this disclosure; Figure 3 A soil salinity classification map of a typical region provided for embodiments of this disclosure; Figure 4 A scatter plot of spectral indices versus soil salinity is provided for embodiments of this disclosure; Figure 5 A structural diagram of a regional-scale multi-source, multi-temporal cultivated land soil salinity spectral index mapping device provided by an embodiment of the present disclosure is shown. Figure 6 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0021] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0022] To address the problems in the background art, embodiments of this disclosure provide a method for mapping the spectral index of soil salinity in cultivated land at a regional scale using multiple sources and multiple temporal phases. Specifically, the acquired multi-source hyperspectral data is preprocessed to obtain multi-source reflectance data, and several sets of spectral indices are calculated based on this data. The correlation coefficient between the spectral indices and soil salinity is calculated, and spectral indices are screened using an image quality evaluation algorithm. A stepwise correlation analysis algorithm is used to select the retained spectral indices, and optimal center wavelength analysis is performed on the selected spectral indices to obtain the optimal spectral index type for soil salinity. Based on multi-temporal images, the optimal spectral index for soil salinity and the bare soil index under this type are calculated. The bare soil distribution information is extracted based on the bare soil index, and the optimal spectral index for soil salinity within the bare soil pixels is synthesized. The grading discontinuities of the optimal spectral index for soil salinity are determined according to the soil salinity grading standard to obtain a regional scale soil salinity grading map.

[0023] This approach fully considers the characteristics of hyperspectral data from different sources, including spatial resolution, spectral resolution, and revisit periods. By coupling data from different sources using a stepwise correlation analysis algorithm, it fully leverages the wavelength information of multi-source data, reducing inconsistencies commonly found in practical applications and improving the accuracy of soil salinity monitoring results. Synthesizing multi-temporal data avoids discontinuities caused by changes in surface features and environmental factors. Furthermore, constructing a spectral index based on soil salinity content is sensitive to soil salinity, has a simple calculation process, and broad application prospects.

[0024] The following detailed description, in conjunction with the accompanying drawings, of a method for mapping the spectral index of soil salinity at a regional scale across multiple sources and time phases provided by the present disclosure, will illustrate in detail the specific embodiments.

[0025] Figure 1 The flowchart illustrates a method for mapping the spectral index of soil salinity at a regional scale using multiple sources and time phases in cultivated land, as provided in an embodiment of this disclosure. Figure 1 As shown, method 100 may include the following steps: S110 preprocesses the acquired multi-source hyperspectral data to obtain multi-source reflectance data.

[0026] In some embodiments, the acquired multi-source hyperspectral data is preprocessed to remove bands whose radiation quality does not meet preset requirements and bands whose atmospheric absorption does not meet preset requirements, thereby obtaining multi-source reflectance data.

[0027] For example, L1A-level hyperspectral data of the ZY1-02D ​​satellite in the study area can be acquired, and then preprocessed using ENVI software in sequence, including radiometric coefficient correction, FLAASH model atmospheric correction, orthorectification correction, topographic and solar photometric correction. Through visual analysis, bands with serious radiation quality problems such as low signal-to-noise ratio, strip noise, CCD inconsistency, and bad lines, as well as bands with serious atmospheric absorption effects, are removed. Finally, multi-source reflectance data including the 438~1290nm, 1492~1745nm, and 2081~2450nm bands are obtained.

[0028] S120 calculates several sets of spectral indices based on multi-source reflectance data.

[0029] In some embodiments, multi-source reflectivity data are standardized to eliminate spatial heterogeneity caused by factors such as different resolutions and projection systems, making the data easier to compare.

[0030] For example, spectral resampling methods can be used to adjust multi-source reflectance data to the same spectral resolution. For instance, spectral resampling methods can be used to sample laboratory data to match the band range of the ZY1-02D ​​image.

[0031] Spectral transformation was performed on the standardized multi-source reflectance data to enhance the correlation between band reflectance data and soil salinity.

[0032] For example, as shown in Table 1, spectral transformation can include the original spectrum (OR), reciprocal spectrum (RR), square root spectrum (SRR), logarithmic spectrum (LOGRR), first-order differential spectrum (FDR), second-order differential spectrum (SDR), and envelope spectrum (CR). For instance, based on ZY1-02D ​​hyperspectral satellite data extracted from field sampling points, spectral transformation is calculated using reflectance data from both satellite and laboratory datasets. The correlation between spectral reflectance data and soil salinity is analyzed, and soil salinity-sensitive wavelengths are extracted.

[0033] Table 1

[0034] Several sets of spectral indices are calculated based on the multi-source reflectance data after spectral transformation, which are then used to extract soil salinity-sensitive spectral indices.

[0035] For example, several sets of spectral indices can be calculated using multi-source reflectance data after spectral transformation. These include the difference index (DI), ratio index (RI), square root difference index (DSI), normalized difference index (NDI), and seven three-band indices. It is worth noting that leave-one-out cross-validation is used to train the dataset when constructing these spectral indices, improving their stability and generalization ability. The calculation method is shown in Table 2. Table 2

[0036] S130, calculate the correlation coefficient between spectral indices and soil salinity, and use image quality assessment algorithms to screen spectral indices.

[0037] In some embodiments, the correlation coefficient between spectral indices and soil salinity is calculated using the Pearson correlation coefficient formula, and the spectral indices are evaluated for image quality using an image quality assessment algorithm. Spectral indices are then selected based on the evaluation results. The evaluation results include image stripe noise evaluation results and relative radiometric error evaluation results.

[0038] For example, the formula for calculating the Pearson correlation coefficient R can be: (1) Image quality assessment can include image stripe noise assessment and relative radiometric error assessment, as shown below: Image stripe noise evaluation compares all pixels in adjacent columns of the data. If the proportion of pixels in the current column whose values ​​are greater or less than those in the next column exceeds a preset threshold, the current column is identified as a stripe column.

[0039] Relative radiation error evaluation includes issues such as inconsistencies between CCD wafers, bad lines, and abnormal bright spots.

[0040] It is worth noting that when the number of problematic pixels accounts for less than 10% of the total number of pixels, the image is considered to have no quality problems or minor quality problems; otherwise, the image is considered to have serious quality problems.

[0041] S140 uses a stepwise correlation analysis algorithm to select the retained spectral indices.

[0042] In some embodiments, the retained spectral indices are sorted according to the correlation coefficient. A specified number (e.g., 0.1%) of the spectral indices from the multi-source data are selected, and an intersection judgment is performed. If the intersection is empty, it is determined that the spectral indices of the multi-source data do not overlap. Then, the number of spectral indices is gradually increased in steps of a specified number (e.g., 0.1%), and an intersection judgment is performed until the intersection is not equal to 0, indicating that the spectral indices of the multi-source data overlap. At this time, the spectral indices in the intersection are selected to obtain a set of better spectral indices.

[0043] S150, perform optimal center wavelength analysis on the selected spectral index to obtain the optimal spectral index type for soil salinity.

[0044] In some embodiments, a wavelength range is determined based on a selected spectral index. Within the wavelength range, wavelengths are sequentially set at intervals of a specified length (e.g., 5 nm) to obtain multiple specific bands. In combination with the type of the selected spectral index, a specific spectral index of the same type under the specific band is calculated. By comparing the correlation between the specific spectral index and soil salinity, the optimal spectral index type for soil salinity is determined.

[0045] S160 calculates the optimal spectral index of soil salinity and the bare soil index under the optimal spectral index type of soil salinity based on multi-temporal images. The distribution information of bare soil is extracted based on the bare soil index. The optimal spectral index of soil salinity in the bare soil pixels is synthesized. The classification discontinuity of the optimal spectral index of soil salinity is determined according to the soil salinity classification standard to obtain a regional scale soil salinity classification map.

[0046] In some embodiments, the optimal soil salinity spectral index and bare soil index under the optimal soil salinity spectral index type are calculated based on multi-temporal images. The numerical distribution of bare soil index in cultivated land pixels is statistically analyzed. The maximum inter-class variance method is used to assist human-computer interaction to determine the threshold for distinguishing bare soil pixels from non-bare soil pixels. Bare soil pixels are assigned a value of 1, and non-bare soil pixels are assigned a value of 0 to obtain a bare soil distribution map. By statistically analyzing the median of the optimal soil salinity spectral index of bare soil pixels, a grayscale map of the optimal soil salinity spectral index is obtained. Based on this, by fitting the linear relationship between soil salinity and the optimal soil salinity spectral index, the graded discontinuity points of the optimal soil salinity spectral index are determined to obtain a regional-scale soil salinity graded map.

[0047] For example, the formula for calculating the bare soil index can be: (2) The soil salinity classification standards are shown in Table 3: Table 3

[0048] It is worth noting that method 100 can be verified here, such as... Figures 2-4 As shown, the method 100 provided in the embodiments of this disclosure can effectively generate a regional-scale soil salinity classification map.

[0049] According to the above embodiments, at least the following technical effects are achieved: The method 100 provided by this invention is characterized by its simple operation and high degree of automation. It can combine multi-source and multi-temporal data to achieve high-precision identification of soil salinity in arable land. It can be widely applied to multi-source satellite data such as ZY-1 02D, Gaofen-5 02, Landsat, and Sentinel to achieve high-frequency regional monitoring and obtain dynamic changes in soil salinity. It provides important technical support in fields such as natural resource element investigation and monitoring, and arable land resource management.

[0050] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0051] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0052] Figure 5 A structural diagram of a regional-scale multi-source, multi-temporal cultivated land soil salinity spectral index mapping device provided by an embodiment of this disclosure is shown, as follows: Figure 5 As shown, the device 500 may include: The preprocessing module 510 is used to preprocess the acquired multi-source hyperspectral data to obtain multi-source reflectance data.

[0053] The calculation module 520 is used to calculate several sets of spectral indices based on multi-source reflectance data.

[0054] The calculation module 520 is also used to calculate the correlation coefficient between spectral indices and soil salinity, and to screen spectral indices using image quality assessment algorithms.

[0055] Selection module 530 is used to select the retained spectral indices using a stepwise correlation analysis algorithm.

[0056] Analysis module 540 is used to perform optimal center wavelength analysis on the selected spectral index to obtain the optimal spectral index type for soil salinity.

[0057] The mapping module 550 is used to calculate the optimal spectral index of soil salinity and the bare soil index under the optimal spectral index type of soil salinity based on multi-temporal images. It extracts the bare soil distribution information based on the bare soil index, synthesizes the optimal spectral index of soil salinity in the bare soil pixels, and determines the classification discontinuity of the optimal spectral index of soil salinity according to the soil salinity classification standard to obtain a regional scale soil salinity classification map.

[0058] In some embodiments, the preprocessing module 510 is specifically used for: The acquired multi-source hyperspectral data is preprocessed to remove bands whose radiation quality does not meet the preset requirements and whose atmospheric absorption does not meet the preset requirements, in order to obtain multi-source reflectance data.

[0059] Preprocessing includes: radiation coefficient correction, atmospheric correction, orthorectification correction, topographic and solar photometric correction.

[0060] In some embodiments, the calculation module 520 is specifically used for: Standardize the multi-source reflectivity data; Perform spectral transformation on the standardized multi-source reflectance data; Several sets of spectral indices are calculated based on the multi-source reflectance data after spectral transformation.

[0061] In some embodiments, the calculation module 520 is specifically used for: The correlation coefficient between spectral indices and soil salinity was calculated using the Pearson correlation coefficient formula, and the spectral indices were evaluated for image quality using an image quality assessment algorithm. Spectral indices were then selected based on the evaluation results. The evaluation results included image stripe noise evaluation results and relative radiometric error evaluation results.

[0062] In some embodiments, the selection module 530 is specifically used for: Sort the retained spectral indices according to the correlation coefficient, select a specified number of spectral indices from the multi-source data, and perform an intersection check. If the intersection is empty, it is determined that the spectral indices of the multi-source data do not overlap. Then, the number of spectral indices is gradually increased in step size of a specified number, and an intersection check is performed until the intersection is not equal to 0. The spectral indices in the intersection are then selected.

[0063] In some embodiments, the analysis module 540 is specifically used for: The wavelength range is determined based on the selected spectral index. Within the wavelength range, wavelengths are set sequentially at specified intervals to obtain multiple specific bands. Combining the selected spectral index type, specific spectral indices of the same type under specific bands are calculated. By comparing the correlation between specific spectral indices and soil salinity, the optimal spectral index type for soil salinity is determined.

[0064] In some embodiments, the drafting module 550 is specifically used for: Based on multi-temporal imagery, the optimal spectral index of soil salinity and the bare soil index were calculated. The numerical distribution of the bare soil index in cultivated land pixels was statistically analyzed. Using the Otsu's method with human-computer interaction, the threshold for distinguishing between bare soil pixels and non-bare soil pixels was determined. Bare soil pixels were assigned a value of 1, and non-bare soil pixels were assigned a value of 0, resulting in a bare soil distribution map. By statistically analyzing the median of the optimal spectral index of soil salinity in bare soil pixels, a grayscale map of the optimal spectral index of soil salinity was obtained. Based on this, by fitting the linear relationship between soil salinity and the optimal spectral index of soil salinity, the grading discontinuity points of the optimal spectral index of soil salinity were determined, resulting in a regional-scale soil salinity grading map.

[0065] Understandable, Figure 5 Each module / unit in the illustrated device 500 has the ability to implement Figure 1 The functions of each step in method 100 shown, and their corresponding technical effects, will not be elaborated here for the sake of brevity.

[0066] Figure 6 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Electronic device 600 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 600 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0067] like Figure 6 As shown, the electronic device 600 may include a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0068] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0069] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer program product, including a computer program tangibly contained in a computer-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform method 100 by any other suitable means (e.g., by means of firmware).

[0070] The various embodiments described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), payload programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0071] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0072] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0073] It should be noted that this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute method 100 and achieve the corresponding technical effects achieved by the embodiments of this disclosure in executing the method. For the sake of brevity, these will not be elaborated here.

[0074] In addition, this disclosure also provides a computer program product including a computer program that implements method 100 when executed by a processor.

[0075] To provide interaction with a user, the embodiments described above can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0076] The embodiments described above can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0077] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0078] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0079] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for mapping the spectral index of soil salinity in cultivated land at a regional scale using multiple sources and multiple time phases, characterized in that, The method includes: The acquired multi-source hyperspectral data are preprocessed to obtain multi-source reflectance data; Calculate several sets of spectral indices based on multi-source reflectance data; The correlation coefficients between spectral indices and soil salinity were calculated, and spectral indices were screened using image quality assessment algorithms. The retained spectral indices were selected using a stepwise correlation analysis algorithm; Optimal center wavelength analysis was performed on the selected spectral indices to obtain the optimal spectral index type for soil salinity; Based on multi-temporal images, the optimal spectral index of soil salinity and the bare soil index are calculated. The distribution information of bare soil is extracted based on the bare soil index. The optimal spectral index of soil salinity in the bare soil pixels is synthesized. The classification discontinuity of the optimal spectral index of soil salinity is determined according to the soil salinity classification standard, and a regional scale soil salinity classification map is obtained. The selection of retained spectral indices using a stepwise correlation analysis algorithm includes: Sort the retained spectral indices according to the correlation coefficient, select a specified number of spectral indices from the multi-source data, and perform an intersection check. If the intersection is empty, it is determined that the spectral indices of the multi-source data do not overlap. Then, the number of spectral indices is gradually increased in step size of a specified number, and an intersection check is performed again until the number of indices in the intersection is not equal to 0. Select the spectral indices in the intersection. The method involves calculating the optimal soil salinity spectral index and bare soil index based on multi-temporal imagery, extracting bare soil distribution information based on the bare soil index, synthesizing the optimal soil salinity spectral index within bare soil pixels, determining the grading discontinuities of the optimal soil salinity spectral index according to soil salinity grading standards, and obtaining a regional-scale soil salinity grading map, including: Based on multi-temporal imagery, the optimal spectral index of soil salinity and the bare soil index were calculated. The numerical distribution of the bare soil index in cultivated land pixels was statistically analyzed. Using the Otsu's method with human-computer interaction, the threshold for distinguishing between bare soil pixels and non-bare soil pixels was determined. Bare soil pixels were assigned a value of 1, and non-bare soil pixels were assigned a value of 0, resulting in a bare soil distribution map. By statistically analyzing the median of the optimal spectral index of soil salinity in bare soil pixels, a grayscale map of the optimal spectral index of soil salinity was obtained. Based on this, by fitting the linear relationship between soil salinity and the optimal spectral index of soil salinity, the grading discontinuity points of the optimal spectral index of soil salinity were determined, resulting in a regional-scale soil salinity grading map.

2. The method according to claim 1, characterized in that, The preprocessing of the acquired multi-source hyperspectral data to obtain multi-source reflectance data includes: The acquired multi-source hyperspectral data is preprocessed to remove bands whose radiation quality does not meet the preset requirements and bands whose atmospheric absorption does not meet the preset requirements, in order to obtain multi-source reflectance data. The preprocessing includes: radiation coefficient correction, atmospheric correction, orthorectification correction, topographic and solar photometric correction.

3. The method according to claim 1, characterized in that, The calculation of several sets of spectral indices based on multi-source reflectance data includes: Standardize the multi-source reflectivity data; Perform spectral transformation on the standardized multi-source reflectance data; Several sets of spectral indices are calculated based on the multi-source reflectance data after spectral transformation.

4. The method according to claim 1, characterized in that, The calculation of the correlation coefficient between spectral indices and soil salinity, and the screening of spectral indices using image quality assessment algorithms, includes: The correlation coefficient between spectral indices and soil salinity was calculated using the Pearson correlation coefficient formula, and the spectral indices were evaluated for image quality using an image quality assessment algorithm. Spectral indices were then selected based on the evaluation results. The evaluation results included image stripe noise evaluation results and relative radiometric error evaluation results.

5. The method according to claim 1, characterized in that, The process of performing optimal center wavelength analysis on the selected spectral index to obtain the optimal spectral index for soil salinity includes: The wavelength range is determined based on the selected spectral index. Within the wavelength range, wavelengths are set sequentially at specified intervals to obtain multiple specific bands. Combining the selected spectral index type, specific spectral indices of the same type under specific bands are calculated. By comparing the correlation between specific spectral indices and soil salinity, the optimal spectral index type for soil salinity is determined.

6. A regional-scale, multi-source, multi-temporal-phase cultivated land soil salinity spectral index mapping device, characterized in that, The apparatus is used to perform the method according to any one of claims 1-5, comprising: The preprocessing module is used to preprocess the acquired multi-source hyperspectral data to obtain multi-source reflectance data; The calculation module is used to calculate several sets of spectral indices based on multi-source reflectance data; The calculation module is also used to calculate the correlation coefficient between spectral indices and soil salinity, and to screen spectral indices using an image quality assessment algorithm. The selection module is used to select the spectral indices to be retained using a stepwise correlation analysis algorithm; The analysis module is used to perform optimal center wavelength analysis on the selected spectral index to obtain the optimal spectral index type for soil salinity. The mapping module is used to calculate the optimal spectral index of soil salinity and the bare soil index under the optimal spectral index type of soil salinity based on multi-temporal images. It extracts the distribution information of bare soil based on the bare soil index, synthesizes the optimal spectral index of soil salinity in the bare soil pixels, and determines the grading discontinuity of the optimal spectral index of soil salinity according to the soil salinity grading standard to obtain a regional scale soil salinity grading map.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

Images