Method and device for determining thickness of black soil layer and medium

Abstract

The invention discloses a method and device for determining the thickness of a black soil layer and a medium, and relates to the technical field of soil layer thickness determination, and the method for determining the thickness of the black soil layer comprises the steps: carrying out the absorbance conversion and smoothing processing of the reflectivity of any pixel point in a preprocessed target image under each wavelength in an effective wave band, obtaining the processed absorbance of the current pixel point under each wavelength in the effective wave band, and inputting the absorbance into a soil organic matter content prediction model to obtain a predicted value of the soil organic matter content of the current pixel point; determining a soil organic matter content pixel-level vertical distribution diagram based on the predicted value and the space coordinate of the soil organic matter content of each pixel point in the preprocessed target image; based on the soil organic matter content pixel-level vertical distribution diagram, determining a black soil layer identification result; and determining the thickness of the black soil layer based on the identification result of the black soil layer and the pixel-level vertical distribution diagram of the soil organic matter content. The determination precision of the thickness of the black soil layer is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of soil layer thickness determination, in particular to a black soil layer thickness determination method, device and medium. BACKGROUND

[0002] The black soil layer, as one of the important ploughing layers, has rich organic matter content and good physicochemical properties. The thickness of the black soil layer not only reflects the maturity of the soil development, but also plays a key reference role in outdoor rapid identification of soil fertility. At the same time, the change of the black soil layer is also of important guiding value for evaluating the degree of black soil degradation. Accurate monitoring of the thickness of the black soil layer helps to comprehensively understand and master the distribution and characteristics of regional land resources, and provides scientific basis and technical support for agricultural production and land use planning.

[0003] The traditional black soil layer identification method mainly relies on manual visual inspection and color card comparison. This method is greatly affected by subjective judgment and is difficult to achieve high-precision and standardized identification, especially in areas where the soil layer is transitional and fuzzy or human disturbance is strong, which is prone to misjudgment. In addition, the traditional identification method cannot quantify the continuous change of the black soil layer in the soil profile, and it is difficult to meet the needs of high-precision research. SUMMARY

[0004] The purpose of the present application is to provide a black soil layer thickness determination method, device and medium to solve the problem of low accuracy of black soil layer thickness determination.

[0005] To achieve the above-mentioned purpose, the present application provides the following solutions.

[0006] In a first aspect, the present application provides a black soil layer thickness determination method, comprising: obtaining a target image; the target image is a hyperspectral image containing a target soil column undisturbed profile; the spectral values of each pixel point in the hyperspectral image include reflectivity of the pixel point at multiple wavelengths in a preset waveband and spatial coordinates; performing image preprocessing on the target image to obtain a preprocessed target image; determining any pixel point in the preprocessed target image as a current pixel point, and determining the reflectivity of the current pixel point at each wavelength in the effective waveband; sequentially performing absorbance conversion and smoothing processing on the reflectivity of the current pixel point at each wavelength in the effective waveband to obtain the processed absorbance of the current pixel point at each wavelength in the effective waveband; inputting the processed absorbance of the current pixel point at each wavelength in the effective waveband into a soil organic matter content prediction model to obtain a predicted value of the soil organic matter content of the current pixel point; the soil organic matter content prediction model is determined based on a spectral learning machine model; determine a pixel-level vertical distribution map of soil organic matter content of the target soil column undisturbed profile based on the predicted value and spatial coordinates of each pixel point in the pre-processed target image; determine a pixel-level black soil distribution map of the target soil column undisturbed profile based on the pixel-level vertical distribution map of soil organic matter content of the target soil column undisturbed profile; determine a black soil layer identification result of the target soil column undisturbed profile based on the pixel-level black soil distribution map of the target soil column undisturbed profile; determine a black soil layer thickness of the target soil column undisturbed profile based on the black soil layer identification result and the pixel-level black soil distribution map of the target soil column undisturbed profile.

[0007] In an embodiment, the target image is subjected to image preprocessing to obtain a pre-processed target image, including: the target image is subjected to whiteboard correction to obtain a whiteboard-corrected target image; the non-target soil column undisturbed profile part in the whiteboard-corrected target image is cropped to obtain a cropped target image; the reflectance of each pixel point in the cropped target image at multiple wavelengths in a preset waveband is input into a soil classification model to obtain a soil classification result of each pixel point in the cropped target image; the soil classification result is soil or non-soil; all reflectances corresponding to each pixel point with a non-soil soil classification result in the cropped target image are set to null to obtain the pre-processed target image.

[0008] In an embodiment, the reflectance of the current pixel point at each wavelength in the effective waveband is subjected to absorbance conversion and smoothing processing in sequence to obtain the processed absorbance of the current pixel point at each wavelength in the effective waveband, including: the reflectance of the current pixel point at each wavelength in the effective waveband is subjected to absorbance conversion to obtain the absorbance of the current pixel point at each wavelength in the effective waveband; the absorbance of the current pixel point at each wavelength in the effective waveband is subjected to smoothing processing using SG smoothing filtering and first derivative transformation to obtain the processed absorbance of the current pixel point at each wavelength in the effective waveband.

[0009] In an embodiment, the determination process of the soil organic matter content prediction model includes: obtain the reflectance of each pixel point in the hyperspectral image of each sample soil column undisturbed profile in the soil imaging hyperspectral library at each wavelength in the effective waveband; any layer of the hyperspectral image of any sample soil column undisturbed profile is determined as a layer to be screened, and any layer in the pre-processed target image is determined as a target layer; Based on the reflectivity of all pixels in the layer to be screened at each wavelength in the effective band, the average reflectivity of the layer to be screened at each wavelength in the effective band is determined; based on the reflectivity of all pixels in the target layer at each wavelength in the effective band, the average reflectivity of the target layer at each wavelength in the effective band is determined; Based on the average reflectivity of the to-be-screened layer at each wavelength in the effective band and the average reflectivity of the target layer at each wavelength in the effective band, a spectral similarity coefficient between the to-be-screened layer and the target layer is determined, and the spectral similarity coefficient between the to-be-screened layer and all layers in the preprocessed target image is determined as judgment data for the to-be-screened layer; Each layer to be screened whose judgment data is greater than a preset threshold is determined as a training sample layer; Determine the mean absorbance of the corresponding training sample layer based on the processed absorbance of all pixels in each training sample layer; Obtain the actual value of soil organic matter content in each training sample layer from the soil imaging hyperspectral library; Initialize the spectral learning machine model; The absorbance mean of each training sample layer is input, and the actual value of the soil organic matter content of the corresponding training sample layer is output, and the spectral learning machine model is trained to obtain the soil organic matter content prediction model.

[0010] In one embodiment, determining a pixel-level vertical distribution map of soil organic matter content in an undisturbed cross-section of a target soil column based on the predicted value and spatial coordinates of the soil organic matter content of each pixel in the preprocessed target image includes: The predicted value of soil organic matter content at each pixel in each preprocessed target image is mapped to the corresponding spatial coordinate to generate a two-dimensional rasterized image, and the pixel-level vertical distribution map of soil organic matter content in the undisturbed section of the target soil column is obtained.

[0011] In one embodiment, determining a pixel-level black soil distribution map of the undisturbed cross-section of the target soil column based on the pixel-level vertical distribution map of soil organic matter content of the undisturbed cross-section of the target soil column includes: The pixels with predicted values ​​of 0 or missing values ​​in the pixel-level vertical distribution map of soil organic matter content in the original section of the target soil column are determined as non-soil pixels, and the other pixels are determined as soil pixels; Soil pixels whose predicted values ​​of soil organic matter content are greater than the soil organic matter content threshold are determined as black soil pixels, and soil pixels whose predicted values ​​of soil organic matter content are less than the soil organic matter content threshold are determined as non-black soil pixels, thereby obtaining a pixel-level black soil distribution map of the undisturbed profile of the target soil column.

[0012] In one embodiment, determining a black soil layer identification result of the undisturbed cross section of the target soil column based on a pixel-level black soil distribution map of the undisturbed cross section of the target soil column includes: determining a relative proportion of the number of black soil pixel points and the number of soil pixel points in each layer in the pixel-level black soil distribution map respectively; one layer corresponds to one row of pixel points in the pixel-level black soil distribution map; determining the layer as a black soil layer if the relative proportion is greater than or equal to a preset proportion, and determining the layer as a non-black soil layer if the relative proportion is less than the preset proportion, thereby obtaining the black soil layer identification result of the target soil column undisturbed profile.

[0013] In an embodiment, based on the black soil layer identification result of the target soil column undisturbed profile and the pixel-level black soil distribution map, the thickness of the black soil layer of the target soil column undisturbed profile is determined, including: starting from the surface layer in the order from the surface layer downwards, the first layer in which a continuous preset number of non-black soil layers first appears is determined as a termination layer; the number of layers contained from the surface layer to the last layer is determined as the number of black soil layers of the target soil column undisturbed profile; a proportion between the number of black soil layers of the target soil column undisturbed profile and the total number of layers of the pixel-level black soil distribution map is calculated to obtain the black soil layer proportion of the target soil column undisturbed profile; the black soil layer proportion of the target soil column undisturbed profile is multiplied by the actual thickness of the target soil column undisturbed profile to obtain the thickness of the black soil layer of the target soil column undisturbed profile.

[0014] In a second aspect, the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the black soil layer thickness determination method described above.

[0015] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the black soil layer thickness determination method described above.

[0016] According to the specific embodiments provided by the present application, the following technical effects are disclosed: This application discloses a method, device, and medium for determining the thickness of black soil layers, which significantly improves the accuracy and efficiency of identifying the thickness of black soil layers in black soil areas. First, the soil column profile is quickly and continuously scanned using imaging hyperspectral technology to obtain hyperspectral images with submillimeter pixels. After removing the non-soil portion of the image, a high-precision mapping of the pixel-level vertical distribution of organic matter content in the original soil profile is achieved based on a soil imaging hyperspectral library combined with spectral similarity analysis and a spectral learning machine algorithm. This not only greatly improves the efficiency and accuracy of soil information acquisition, but also provides high-quality data support for in-depth revelation of the spatial variability and evolution of profile soil properties, making it possible to achieve high-precision determination of the thickness of the black soil layer. Secondly, soil pixels whose predicted soil organic matter content is greater than the soil organic matter content threshold (1%) are determined as black soil pixels, and soil pixels whose predicted soil organic matter content is less than the soil organic matter content threshold are determined as non-black soil pixels. This results in a pixel-level black soil distribution map of the original profile of the target soil column, which enables quantitative identification of black soil areas in the soil profile. This overcomes the subjectivity and reliance on expert experience of traditional manual colorimetric card interpretation, and avoids the long cycle and high cost of traditional laboratory soil organic matter determination methods. Thirdly, by statistically analyzing whether the proportion of black soil pixels in the vertical profile exceeds the set threshold, the black soil layer interface is scientifically determined, and the thickness of the black soil layer is accurately calculated, which significantly improves the accuracy, objectivity, and repeatability of the black soil layer thickness measurement results, providing an efficient and reliable technical means for black soil resource survey and monitoring. This application not only circumvents the problems of low efficiency and strong subjectivity of the traditional colorimetric card determination method in measuring the thickness of the black soil layer, but also achieves rapid and accurate measurement of the black soil layer thickness, improves the efficiency and accuracy of black soil layer thickness measurement, and provides high-quality data support for in-depth revelation of the spatial variability and evolution of profile soil properties. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a flow chart of a method for determining the thickness of a black soil layer provided in one embodiment of the present application.

[0019] Figure 2 This is the pixel-level vertical distribution map of soil organic matter content.

[0020] Figure 3 This is the first example diagram of the black soil layer thickness identification results.

[0021] Figure 4 This is the second example schematic diagram of the black soil layer thickness identification results.

[0022] Figure 5 A third example schematic diagram for black soil layer thickness identification results.

[0023] Figure 6 A fourth example schematic diagram for black soil layer thickness identification results.

[0024] Figure 7 A structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0026] The purpose of the present application is to provide a black soil layer thickness determination method, device and medium, aiming to improve the determination accuracy of black soil layer thickness.

[0027] In order to make the above-mentioned purposes, characteristics and advantages of the present application more apparent and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0028] In an exemplary embodiment, as shown in Figure 1 A black soil layer thickness determination method is provided, including the following steps.

[0029] Step 1: Obtain a target image.

[0030] The target image is a hyperspectral image containing a target soil column undisturbed profile; the spectral values of each pixel point in the hyperspectral image include the reflectivity of the pixel point at multiple wavelengths in a preset wavelength band and spatial coordinates.

[0031] Specifically, a soil drill is used to collect a 0-100cm soil column at a target sampling point set in a study area to obtain a target soil column. The collected target soil column is placed in a polyvinyl chloride pipe and sealed with plastic film to prevent water evaporation and external interference, so as to maintain the original state of the soil. The collected target soil column is vertically divided into two halves along the vertical direction from the center of the top layer port to the bottom layer. A hyperspectral push-broom polarization analyzer (Hyperimager Plant Phenomics Analysis, HPPA) is used to scan the undisturbed profile of the cut target soil column in a darkroom environment to obtain hyperspectral image data (i.e. the target image) of the target soil column undisturbed profile in the 375.5nm-1017.3nm wavelength band (i.e. the preset wavelength band).

[0032] Step 2: image preprocessing is performed on the target image to obtain a preprocessed target image.

[0033] As an optional implementation, step 2 includes steps 21-24.

[0034] Step 21: whiteboard correction is performed on the target image to obtain a whiteboard-corrected target image.

[0035] Step 22: the non-target soil column undisturbed section in the whiteboard-corrected target image is cropped to obtain a cropped target image.

[0036] Specifically, when collecting the target image, not only the target soil column undisturbed section, but also the non-target soil column undisturbed section such as the light absorption experiment table, the correction whiteboard, and the polyvinyl chloride pipe may be included. Therefore, the non-target soil column undisturbed section in the whiteboard-corrected target image is cropped to obtain the cropped target image, so that the cropped target image only contains the target soil column undisturbed section.

[0037] Step 23: the reflectance of each pixel point in the cropped target image at multiple wavelengths in the preset waveband is input into a soil classification model to obtain the soil classification result of each pixel point in the cropped target image; the soil classification result is soil or non-soil.

[0038] Specifically, the soil classification model is obtained by training a random forest model, and the determination process of the soil classification model includes: 1) obtaining multiple hyperspectral images containing soil; 2) selecting multiple regions of interest from each hyperspectral image containing soil; 3) using the actual soil zoning result of each region of interest as a training sample to train the random forest model to obtain the soil classification model.

[0039] Step 24: all reflectances corresponding to each pixel point with a non-soil soil classification result in the cropped target image are set to null to obtain the preprocessed target image.

[0040] Step 3: any pixel point in the preprocessed target image is determined as a current pixel point, and the reflectance of the current pixel point at each wavelength in the effective waveband is determined.

[0041] Step 4: the reflectance of the current pixel point at each wavelength in the effective waveband is sequentially converted into absorbance and smoothed to obtain the processed absorbance of the current pixel point at each wavelength in the effective waveband.

[0042] As an optional implementation, the effective waveband is obtained by screening the preset waveband.

[0043] Specifically, the effective waveband is 434 nm-927 nm.

[0044] As an optional implementation, step 4 comprises steps 41-42.

[0045] Step 41: Absorbance conversion is performed on the reflectivity of the current pixel point at each wavelength in the effective waveband to obtain the absorbance of the current pixel point at each wavelength in the effective waveband.

[0046] Step 42: The absorbance of the current pixel point at each wavelength in the effective waveband is smoothed by using SG smoothing filtering and first derivative transformation to obtain the processed absorbance of the current pixel point at each wavelength in the effective waveband.

[0047] Specifically, the smoothing processing of the absorbance effectively eliminates the baseline drift and background noise, and enhances the stability and recognizability of the absorbance.

[0048] Step 5: The processed absorbance of the current pixel point at each wavelength in the effective waveband is input into the soil organic matter content prediction model to obtain the predicted value of the soil organic matter content of the current pixel point.

[0049] The soil organic matter content prediction model is determined based on a spectrum learning machine model.

[0050] As an optional implementation, in step 5, the determination process of the soil organic matter content prediction model comprises steps 51-59.

[0051] Step 51: The reflectivity of each pixel point at each wavelength in the effective waveband in the high-spectrum image of each sample soil column undisturbed profile in the soil imaging hyperspectral library is obtained.

[0052] Step 52: Any layer of the high-spectrum image of any sample soil column undisturbed profile is determined as a layer to be screened, and any layer in the preprocessed target image is determined as a target layer.

[0053] Step 53: Based on the reflectivity of all pixel points in the effective waveband in the layer to be screened, the average reflectivity of the layer to be screened in the effective waveband is determined, and based on the reflectivity of all pixel points in the effective waveband in the target layer, the average reflectivity of the target layer in the effective waveband is determined.

[0054] Step 54: Based on the average reflectivity of the layer to be screened in the effective waveband and the average reflectivity of the target layer in the effective waveband, the spectral similarity coefficient between the layer to be screened and the target layer is determined, and the spectral similarity coefficient between the layer to be screened and all layers in the preprocessed target image is determined as the judgment data of the layer to be screened.

[0055] Step 55: Each layer to be screened with judgment data greater than a preset threshold is determined as a training sample layer.

[0056] wherein the preset threshold value is 0.8.

[0057] Step 56: determining the mean absorbance of each training sample layer based on the processed absorbance of all pixel points in the training sample layer.

[0058] Step 57: obtaining the actual value of soil organic matter content of each training sample layer from the soil imaging hyperspectral library.

[0059] Step 58: initializing the spectral learning machine model.

[0060] Step 59: training the spectral learning machine model by taking the mean absorbance of each training sample layer as input and the actual value of soil organic matter content of the corresponding training sample layer as output, to obtain the soil organic matter content prediction model.

[0061] The determination coefficient is calculated for the modeling set and the validation set respectively The root mean square error And the relative percentage difference as a model precision evaluation index, the specific formula is as follows.

[0062] .

[0063] .

[0064] .

[0065] wherein, represents the actual value of soil organic matter content of the i-th training sample layer in the validation set, represents the predicted value of soil organic matter content of the i-th training sample layer in the validation set, represents the average value of the actual value of soil organic matter content of all training sample layers in the validation set, represents the number of training sample layers in the validation set.

[0066] Step 6: determining the pixel-level vertical distribution map of soil organic matter content of the target soil column undisturbed profile based on the predicted value of soil organic matter content and the spatial coordinates of each pixel point in the preprocessed target image.

[0067] As an optional implementation, step 6 includes: mapping the predicted value of soil organic matter content of each pixel point in each preprocessed target image to the corresponding spatial coordinates to generate a two-dimensional raster image, to obtain the pixel-level vertical distribution map of soil organic matter content of the target soil column undisturbed profile.

[0068] Specifically, the pixel-level vertical distribution map of soil organic matter content is as followsFigure 2 SOM represents the soil organic matter content. Figure 2

[0069] Step 7: determining the pixel-level black soil distribution map of the target soil column undisturbed profile based on the pixel-level vertical distribution map of the soil organic matter content of the target soil column undisturbed profile.

[0070] As an optional implementation, step 7 comprises steps 71-72.

[0071] Step 71: determining the non-soil pixel points as the pixel points with the predicted value of the soil organic matter content being 0 or missing value in the pixel-level vertical distribution map of the soil organic matter content of the target soil column undisturbed profile, and determining the other pixel points as soil pixel points.

[0072] Specifically, in step 24, all reflectances corresponding to the pixel points with the soil area division result being non-soil in the cropped target image are emptied (only the spatial coordinates of the pixel points are reserved), and the predicted value of the soil organic matter content of the pixel points with the soil area division result being non-soil is assigned as 0 or missing value when the soil organic matter content prediction model is used for prediction.

[0073] Step 72: determining the black soil pixel points as the soil pixel points with the predicted value of the soil organic matter content being greater than the soil organic matter content threshold value, and determining the non-black soil pixel points as the soil pixel points with the predicted value of the soil organic matter content being less than the soil organic matter content threshold value, thereby obtaining the pixel-level black soil distribution map of the target soil column undisturbed profile.

[0074] Specifically, the soil organic matter content threshold value is 1%.

[0075] Step 8: determining the black soil layer identification result of the target soil column undisturbed profile based on the pixel-level black soil distribution map of the target soil column undisturbed profile.

[0076] As an optional implementation, step 8 comprises steps 81-82.

[0077] Step 81: respectively determining the relative proportions of the number of black soil pixel points and the number of soil pixel points in each layer in the pixel-level black soil distribution map; one layer corresponds to one row of pixel points in the pixel-level black soil distribution map.

[0078] Step 82: determining the black soil layer as the layer with the relative proportion being greater than or equal to the preset proportion, and determining the non-black soil layer as the layer with the relative proportion being less than the preset proportion, thereby obtaining the black soil layer identification result of the target soil column undisturbed profile.

[0079] ​Specifically, the preset ratio is 90%. The black soil layer identification result determined by the relative ratio can effectively reduce the misjudgment caused by a single abnormal pixel and improve the stability and spatial continuity of the profile layer identification. The black soil layer identification results of the soil column profiles of multiple examples are shown in FIGS. 8A-8D, respectively. Figures 3-6 Figures 3-6 The dashed line indicates the position of the fault tail.

[0080] Step 9: Based on the black soil layer identification result of the target soil column undisturbed profile and the pixel-level black soil distribution map, the black soil layer thickness of the target soil column undisturbed profile is determined.

[0081] As an optional implementation, step 9 includes steps 91-94.

[0082] Step 91: In the order from the surface layer downward, starting from the surface layer, the first layer that first appears continuously in a preset number of non-black soil layers is determined as the termination layer.

[0083] Step 92: The number of layers contained from the surface layer to the upper layer of the termination layer is determined as the number of black soil layers of the target soil column undisturbed profile.

[0084] Specifically, for example, when 30 layers from the 41st layer to the 70th layer are all "non-black soil layers" for the first time, the 41st layer is regarded as the termination layer, and the number of black soil layers is 40.

[0085] Step 93: The ratio between the number of black soil layers of the target soil column undisturbed profile and the total number of layers of the pixel-level black soil distribution map is calculated to obtain the black soil layer ratio of the target soil column undisturbed profile.

[0086] Step 94: The black soil layer ratio of the target soil column undisturbed profile is multiplied by the actual thickness of the target soil column undisturbed profile to obtain the black soil layer thickness of the target soil column undisturbed profile.

[0087] Further, in order to verify the determination accuracy of the black soil layer thickness method of the present application, the black soil layer thickness of each pixel point is determined based on the reflectivity of multiple pixel points using the method of the present application, and the determination coefficient R2 between the black soil layer thickness obtained by the method of the present application and the black soil layer thickness identified by the color card is calculated as the reference. The results are shown in Table 1.

[0088] Table 1 Determination coefficient and root mean square error table

[0089] The results show that the determination accuracy of the method of the present application for the black soil layer thickness is high, which provides important technical support for the digital characterization of the profile properties of the black soil area and the development of protection strategies.​​

[0090] In an exemplary embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the method for determining thickness of black soil layer.

[0091] In an exemplary embodiment, a computer readable storage medium is provided, having stored thereon a computer program, the computer program being executed by a processor to implement the method for determining thickness of black soil layer.

[0092] In an exemplary embodiment, a computer device is provided, which can be a server or a terminal, and its internal structure diagram can be as shown in Figure 7 The computer device comprises a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a method for determining thickness of black soil layer.

[0093] Those skilled in the art can understand that Figure 7 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of each method can be included. Any reference to memory, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

[0095] The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0096] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0097] Each technical feature of the above embodiments can be combined arbitrarily. In order to make the description simple, not all possible combinations of each technical feature in the above embodiments are described, but as long as the combination of these technical features does not exist contradictory, it should be considered as the scope of the present application.

[0098] The principles and implementations of the present application are described in detail with specific examples in this paper, and the above examples are only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed. Therefore, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for determining the thickness of a black soil layer, characterized in that: The method for determining the thickness of the black soil layer comprises: Acquire a target image; the target image is a hyperspectral image containing an undisturbed cross-section of the target soil column; the spectral value of each pixel in the hyperspectral image includes the reflectivity and spatial coordinates of the pixel at multiple wavelengths in a preset band; performing image preprocessing on the target image to obtain a preprocessed target image; Determine any pixel point in the preprocessed target image as the current pixel point, and determine the reflectivity of the current pixel point at each wavelength in the effective band; The reflectivity of the current pixel at each wavelength in the effective band is sequentially converted to absorbance and smoothed to obtain the processed absorbance of the current pixel at each wavelength in the effective band; Inputting the processed absorbance of the current pixel at each wavelength in the effective band into a soil organic matter content prediction model to obtain a predicted value of the soil organic matter content of the current pixel; the soil organic matter content prediction model is determined based on a spectral learning machine model; Based on the predicted value and spatial coordinates of the soil organic matter content of each pixel in the preprocessed target image, the pixel-level vertical distribution map of the soil organic matter content of the undisturbed section of the target soil column is determined; Based on the pixel-level vertical distribution map of soil organic matter content in the original section of the target soil column, determine the pixel-level black soil distribution map of the original section of the target soil column; Based on the pixel-level black soil distribution map of the original section of the target soil column, the black soil layer identification result of the original section of the target soil column is determined; Based on the black soil layer identification results and pixel-level black soil distribution map of the undisturbed section of the target soil column, the thickness of the black soil layer of the undisturbed section of the target soil column is determined.

2. The method for determining the thickness of the black soil layer according to claim 1, wherein: Performing image preprocessing on the target image to obtain a preprocessed target image includes: Performing whiteboard correction on the target image to obtain a whiteboard-corrected target image; The non-target soil column original cross-section part in the target image after whiteboard correction is cropped to obtain a cropped target image; The reflectance of each pixel point in the cropped target image at multiple wavelengths in the preset band is input into the soil differentiation model to obtain the soil differentiation result of each pixel point in the cropped target image; the soil differentiation result is soil or non-soil; All reflectances corresponding to pixels whose soil classification results are non-soil in the cropped target image are set to blank to obtain the preprocessed target image.

3. The method for determining the thickness of the black soil layer according to claim 1, wherein: The reflectivity of the current pixel at each wavelength in the effective band is sequentially converted to absorbance and smoothed to obtain the processed absorbance of the current pixel at each wavelength in the effective band, including: Perform absorbance conversion on the reflectance of the current pixel at each wavelength in the effective band to obtain the absorbance of the current pixel at each wavelength in the effective band; The absorbance of the current pixel at each wavelength in the effective band is smoothed by using SG smoothing filtering and first-order derivative transformation to obtain the processed absorbance of the current pixel at each wavelength in the effective band.

4. The method for determining the thickness of the black soil layer according to claim 1, wherein: The process of determining the soil organic matter content prediction model includes: Obtain the reflectivity of each pixel point at each wavelength in the effective band in the hyperspectral image of the original cross-section of each sample soil column in the soil imaging hyperspectral library; Determine any layer in the hyperspectral image of any original section of the native column as a layer to be screened, and determine any layer in the pre-processed target image as a target layer; Based on the reflectivity of all pixels in the layer to be screened at each wavelength in the effective band, the average reflectivity of the layer to be screened at each wavelength in the effective band is determined; based on the reflectivity of all pixels in the target layer at each wavelength in the effective band, the average reflectivity of the target layer at each wavelength in the effective band is determined; Based on the average reflectivity of the to-be-screened layer at each wavelength in the effective band and the average reflectivity of the target layer at each wavelength in the effective band, a spectral similarity coefficient between the to-be-screened layer and the target layer is determined, and the spectral similarity coefficient between the to-be-screened layer and all layers in the preprocessed target image is determined as judgment data for the to-be-screened layer; Each layer to be screened whose judgment data is greater than a preset threshold is determined as a training sample layer; Determine the mean absorbance of the corresponding training sample layer based on the processed absorbance of all pixels in each training sample layer; Obtain the actual value of soil organic matter content in each training sample layer from the soil imaging hyperspectral library; Initialize the spectral learning machine model; The absorbance mean of each training sample layer is input, and the actual value of the soil organic matter content of the corresponding training sample layer is output, and the spectral learning machine model is trained to obtain the soil organic matter content prediction model.

5. The method for determining the thickness of the black soil layer according to claim 1, wherein: Based on the predicted value and spatial coordinates of the soil organic matter content of each pixel in the preprocessed target image, the pixel-level vertical distribution map of the soil organic matter content of the undisturbed profile of the target soil column is determined, including: The predicted value of soil organic matter content at each pixel in each preprocessed target image is mapped to the corresponding spatial coordinate to generate a two-dimensional rasterized image, and the pixel-level vertical distribution map of soil organic matter content in the undisturbed section of the target soil column is obtained.

6. The method for determining the thickness of the black soil layer according to claim 1, wherein: Based on the pixel-level vertical distribution map of soil organic matter content in the original profile of the target soil column, the pixel-level black soil distribution map of the original profile of the target soil column is determined, including: The pixels with predicted values ​​of 0 or missing values ​​in the pixel-level vertical distribution map of soil organic matter content in the original section of the target soil column are determined as non-soil pixels, and the other pixels are determined as soil pixels; Soil pixels whose predicted values ​​of soil organic matter content are greater than the soil organic matter content threshold are determined as black soil pixels, and soil pixels whose predicted values ​​of soil organic matter content are less than the soil organic matter content threshold are determined as non-black soil pixels, thereby obtaining a pixel-level black soil distribution map of the undisturbed profile of the target soil column.

7. The method for determining the thickness of the black soil layer according to claim 1, wherein: Based on the pixel-level black soil distribution map of the original profile of the target soil column, the black soil layer identification results of the original profile of the target soil column are determined, including: Determine the relative ratio of the number of black soil pixels to the number of soil pixels in each layer of the pixel-level black soil distribution map; one layer corresponds to a row of pixels in the pixel-level black soil distribution map; The layer with a relative proportion greater than or equal to the preset proportion is determined as the black soil layer, and the layer with a relative proportion less than the preset proportion is determined as the non-black soil layer, thereby obtaining the black soil layer identification result of the original profile of the target soil column.

8. The method for determining the thickness of the black soil layer according to claim 1, wherein: Based on the black soil layer identification results and pixel-level black soil distribution map of the target soil column's undisturbed profile, the thickness of the black soil layer of the target soil column's undisturbed profile is determined, including: In order from the surface layer downward, starting from the surface layer, the first layer among the preset number of consecutive non-black soil layers that appear for the first time is determined as the end layer; Determine the number of layers from the surface layer to the layer above the termination layer as the number of black soil layers in the original profile of the target soil column; Calculate the ratio between the number of black soil layers in the original section of the target soil column and the total number of layers in the pixel-level black soil distribution map to obtain the black soil layer ratio in the original section of the target soil column; The thickness of the black soil layer in the undisturbed cross section of the target soil column is obtained by multiplying the proportion of the black soil layer in the undisturbed cross section of the target soil column by the actual thickness of the undisturbed cross section of the target soil column.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for determining the thickness of the black soil layer according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the thickness of the black soil layer according to any one of claims 1 to 8 is implemented.

Images