A dynamic programming method for phosphorus-rich biochar mulch

Through multi-spectral camera acquisition and image processing technology, the application of phosphorus-rich biochar is dynamically planned, which solves the problems of excessive phosphorus content and pollution in soil, improves the reliability and stability of the application, and promotes the sustainability of agricultural production and ecology. .

CN118552858BActive Publication Date: 2024-11-19INST OF AGRI RESOURCES & ENVIRONMENT GUANGDONG ACADEMY OF AGRI SCI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411025192.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-19
Estimated Expiration
2044-07-30

AI Technical Summary

Technical Problem

In the prior art, the application method of phosphorus-rich biochar in agricultural production fails to combine the soil's adaptive properties to phosphorus, which easily leads to excessive phosphorus content and pollution. Especially when using animal feces to compose compost, the risk is greater, and the lack of dynamic programming methods is Optimize the casting effect and reduce the risk of excessive casting.

Method used

Data acquisition is collected from the covered area by using a multi-spectral camera, low conversion risk is calculated through image preprocessing and analysis, combined with superpixel segmentation algorithm and quantization processing, risk areas are divided and early warning is provided, and dynamic programming methods are provided to optimize the application of phosphorus-rich biochar. .

Benefits of technology

Effectively quantify the inefficient conversion of phosphorus-rich biochar in selected areas, provide a real basis for assessment data, improve the reliability and stability of the deployment, reduce pollution risks, and sustainability for agricultural production and ecology. Development is of great significance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118552858B_ABST
    Figure CN118552858B_ABST
Patent Text Reader

Abstract

The present invention belongs to the technical field of data acquisition and machine vision analysis, and proposes a dynamic planning method for covering phosphorus-rich biochar, specifically: data is collected from the area to be covered by phosphorus-rich biochar through a multispectral camera to obtain a collection image sequence; the collection image sequence is then preprocessed to obtain a processed spectral image; the low conversion risk of applying phosphorus-rich biochar is analyzed and calculated based on the processed spectral image; finally, an early warning is given to the risk area in the area to be covered based on the obtained low conversion risk. By quantifying the relative risk of low-efficiency conversion of phosphorus-rich biochar in a selected area; providing a real and effective assessment data basis for the dynamic application of phosphorus-rich biochar in a selected area, the reliability and stability of phosphorus-rich biochar in actual agricultural production applications are improved; at the same time, the method has the characteristics of high efficiency, and the difficulty and complexity of operation are reduced, making its application efficiency higher.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of data acquisition and machine vision analysis, and specifically relates to a dynamic programming method for covering phosphorus-rich biochar. Background Art

[0002] Phosphorus-rich biochar has the advantage of being rich in phosphorus in improving soil, providing nutrition and promoting plant growth. The porous structure of ordinary biochar helps to improve the aeration and water retention capacity of the soil, while phosphorus-rich biochar can be directly used as a source of nutrition for plants because it is rich in available phosphorus, especially for those soils that are deficient in phosphorus. It can significantly improve the fertility of the soil. Especially in the production of sustainable agriculture and organic agriculture, it can effectively reduce the use of chemical fertilizers. However, excessive application of phosphorus-rich biochar has the risk of causing excessive phosphorus content in the soil, which will not only affect the absorption and utilization of other nutrients by plants, but may also cause phosphorus to accumulate in the soil, eventually flowing into the water body through surface runoff, causing eutrophication problems in nearby water bodies.

[0003] At present, in the actual agricultural production application of phosphorus-rich biochar, the application method of phosphorus-rich biochar usually adopts a uniform covering mode. This method fails to combine the soil's own adaptive characteristics to available phosphorus, including the amount of loss and conversion, and can easily cause excessive phosphorus content to lead to pollution; and this risk is particularly prominent in the case of animal manure-type compost. Therefore, a dynamic programming method for covering phosphorus-rich biochar is urgently needed to optimize the application effect of phosphorus-rich biochar in agricultural production applications, improve the sustainability of application, and reduce the risk caused by excessive application. Summary of the invention

[0004] The purpose of the present invention is to propose a dynamic programming method for phosphorus-rich biochar coverage to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0005] In order to achieve the above object, according to one aspect of the present invention, a dynamic programming method for covering phosphorus-rich biochar is provided, the method comprising the following steps:

[0006] S100, collecting data on the area to be covered by phosphorus-rich biochar using a multispectral camera to obtain a collection image sequence;

[0007] S200, preprocessing the acquired image sequence to obtain a processed spectral image;

[0008] S300, analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image;

[0009] S400: Based on the obtained low conversion risk, an early warning is issued for the risk area in the area to be covered.

[0010] Furthermore, in step S100, data is collected on the area to be covered by the phosphorus-rich biochar by a multispectral camera, and a method for obtaining a collected image sequence is as follows: the area to be covered by the phosphorus-rich biochar is the soil area where the phosphorus-rich biochar is planned to be applied; the multispectral camera is carried by a drone or an airplane, and a multispectral scan is performed on the area to be covered to obtain spectral graphs in different wavelength ranges, and the obtained spectral graphs constitute a collected image sequence.

[0011] Furthermore, in step S200, the collected image sequence is preprocessed to obtain a processed spectral image by:

[0012] Each spectral graph in the image sequence has a phase classification, and the classification content includes a high phase graph, a low phase graph and a base phase graph; the image sequence is denoised, and the spectral values ​​calculated from the high phase graph by a linear spectral unmixing algorithm are recorded as high phase values, the spectral values ​​calculated from the low phase graph are recorded as low phase values, and the spectral values ​​calculated from the base phase graph are recorded as base phase values; the tuple composed of the high phase value, the low phase value and the base phase value is recorded as an acquisition group; an image constructed from the acquisition group of all pixels is used as a processed spectral image.

[0013] Further, in step S300, the method of analyzing and calculating the low conversion risk of applying phosphorus-rich biochar according to the processed spectral image is: calculating the phase deficiency ratio GDRt of any pixel through the high phase value GV and the low phase value SV: GDRt = (GV-SV) / max{GV,SV};

[0014] All phase deficiency ratios obtained by processing the spectrum image are normalized to form a phase deficiency standard value, and the processed spectrum image is divided into regions according to the phase deficiency standard value. The obtained regions are recorded as soil regions, and the region division method is a superpixel segmentation algorithm;

[0015] If the lack ratio of a pixel is negative, it is defined as a strong focus point, otherwise it is defined as a weak focus point. The ratio of the number of strong focus points to the number of weak focus points in the region is calculated, and the ratio is defined as the focus weight of the region.

[0016] The calibration offset weight LO_LQS is calculated according to the phase deficiency ratio and the base phase value of each strong focus point in the soil area: LO_LQS = (exp(rg.GDRt / st.GDRt)×rg.BV) / ds.BV; wherein exp() is an exponential function with the natural constant e as the base; rg.GDRt is the average value of the phase deficiency ratio of each strong focus point in the soil area, and st.GDRt is a preset reference value of the phase deficiency ratio value; rg.BV represents the average value of the base phase value of each strong focus point in the soil area, and ds.BV represents the extreme value of each base phase value in the soil area;

[0017] The attention weight of the soil area and the calibration offset weight are combined into a tuple and recorded as a risk array. After obtaining each risk array in the image, the corresponding standard score of each risk array is calculated by calling the numpy library, and the standard score calculated for the soil area is defined as its corresponding low conversion risk.

[0018] Since there is a lack of reference to the base phase value in the soil area division in the process of calculating the low conversion risk by the phase deficiency ratio, it will lead to the problem of insufficient sensitivity in the process of the base phase value participating in the quantitative calculation, especially in the case of large distribution differences in the base phase value under the same image, which is more likely to reduce the sensitivity of the quantitative calculation. However, the existing technology cannot solve the underfitting problem here. In order to make the calculation method better and solve the problem and eliminate the phenomenon of insufficient sensitivity, the present invention proposes a more preferred solution as follows:

[0019] Preferably, in step S300, the method for analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image is: performing min-max normalization processing on the high phase value, low phase value and base phase value in the processed spectral image respectively, and any pixel uses the average value of each element after normalization processing in the collection group as the pixel information degree;

[0020] According to the pixel information, the processed spectral image is divided into regions using superpixel segmentation algorithm, and the divided regions are recorded as soil regions;

[0021] For any pixel, the ratio of the low phase value to the high phase value corresponding to the pixel is recorded as the pixel point comparison, and the sequence of the corresponding point comparisons of each pixel in any area is defined as RVLs, then the comparison index StIdx of the area is: StIdx=ln(1+(mx.RVLs-mn.RVLs) / st.RVLs); where mn.RVLs and mx.RVLs are the average and maximum values ​​of RVLs respectively, and st.RVLs is the standard deviation of the sequence RVLs; the average value of the matrix phase value of each pixel in an area is recorded as the matrix level; the median value of the comparison index of all soil areas is the comparison median value;

[0022] For any soil area, if its comparison index is greater than the lower quartile value of the comparison index of all soil areas, it meets the first inhibition condition; if its substrate level is less than the upper quartile value of the substrate level of all soil areas, it meets the second inhibition condition; the soil area that meets both the first inhibition condition and the second inhibition condition is recorded as the inhibition mark area;

[0023] Take any inhibition mark area as the current inhibition mark area, take the center of the current inhibition mark area as the center, draw the circumscribed circle of the current inhibition mark area, and the obtained circumscribed circle is the mark growth area, and its radius is RG pixels;

[0024] The first overflow condition is set as follows: the marked growth area completely contains another inhibited marked area; the second overflow condition is set as follows: the comparison index of the marked growth area is less than or equal to the comparison median;

[0025] The first overflow condition or the second overflow condition is used as the iteration termination rule. Each iteration increases the radius by 1 pixel and updates the marked growth area, and recalculates the comparison index of the marked growth area. The comparison indexes obtained in each iteration are sequentially written into a sequence and recorded as the index iteration sequence of the current suppressed marked area.

[0026] In the indicator iteration sequence, if an element is larger than the previous element, the difference between the two is recorded as the iteration growth value of the element, and the sequence value of the element in the indicator iteration sequence and the iteration growth value are constructed into a tuple and recorded as a growth array; the slope value is calculated by the polyfit function in combination with all growth arrays under the indicator iteration sequence and recorded as the iteration growth coefficient erIdx;

[0027] The correlation quantity K is preset, K is a positive integer greater than 2, and any pixel is taken as the current pixel; the K inhibition mark areas with the smallest Euclidean distance to the current pixel are selected as its enhancement area, and the low conversion sub-value VE_OLINBI of the current pixel is calculated according to the enhancement area:

[0028] ;

[0029] Where i is the accumulated variable, exp() is an exponential function with the natural constant e as the base, RZ_K represents the number of times the current pixel appears within the boundary of the corresponding marked growth zone in each growth zone of the current pixel; dis(i) is the Euclidean distance between the i-th growth zone and the current pixel; erIdx i and StIdx i They represent the iterative growth coefficient and the comparison index of the i-th potential enhancement zone respectively; min_K_er represents the minimum value of the iterative growth coefficients of each potential enhancement zone;

[0030] Calculate the low conversion sub-value of each pixel, select the pixel whose low conversion sub-value is not the maximum value in the eight neighborhoods as the first selection pixel, exclude all pixels corresponding to the center of the inhibition mark area from the first selection pixels, and calculate the average low conversion sub-value of all first selection pixels in the soil area as its low conversion risk.

[0031] Since the low conversion risk is obtained by step-by-step calculation based on the quantitative positioning of substances based on spectral images, the relative risk of inefficient conversion of phosphorus-rich biochar in the selected area is effectively quantified; it provides a real and effective assessment data basis for the dynamic release of phosphorus-rich biochar in the selected area, and improves the reliability and stability of phosphorus-rich biochar in actual agricultural production. It is of great significance to the sustainable development of agricultural production and ecology.

[0032] Further, in step S400, a method for providing an early warning for a risk area in the area to be covered in combination with the obtained low conversion risk is:

[0033] Send each low conversion risk to the server for storage;

[0034] The lower quartile value of each low conversion risk obtained is recorded as the first threshold; if the low conversion risk is greater than the lower quartile value, the soil area corresponding to the low conversion risk is defined as having a low conversion risk, and the location of each soil area with a low conversion risk and the low conversion risk are sent to the client and an early warning is issued.

[0035] Furthermore, in step S400, a method for issuing an early warning to the risk area in the area to be covered in combination with the obtained low conversion risk is as follows: the first threshold value can be replaced with a preset value.

[0036] Preferably, all undefined variables in the present invention, if not clearly defined, can be manually set thresholds.

[0037] The present invention also provides a dynamic planning system for covering phosphorus-rich biochar, the dynamic planning system for covering phosphorus-rich biochar comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the dynamic planning method for covering phosphorus-rich biochar when executing the computer program, the dynamic planning system for covering phosphorus-rich biochar can be run in computing devices such as desktop computers, notebook computers, PDAs, and cloud data centers, the executable system may include, but is not limited to, a processor, a memory, and a server cluster, the processor executing the computer program runs in the following system units:

[0038] A spectral acquisition unit is used to acquire data of the phosphorus-rich biochar to be covered area through a multispectral camera to obtain an acquired image sequence;

[0039] An image preprocessing unit, used for preprocessing the acquired image sequence to obtain a processed spectral image;

[0040] A spectral analysis unit, used for analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image;

[0041] The result feedback unit is used to give early warning to the risk area in the area to be covered based on the obtained low conversion risk.

[0042] The beneficial effects of the present invention are as follows: the present invention provides a dynamic programming method for phosphorus-rich biochar coverage, which effectively quantifies the relative risk of low-efficiency conversion of phosphorus-rich biochar in a selected area by quantifying the spectral image hierarchical processing; provides a real and effective evaluation data basis for the dynamic application of phosphorus-rich biochar in the selected area, improves the reliability and stability of phosphorus-rich biochar in the application of actual agricultural production; and is of great significance to the sustainable development of agricultural production and ecology. At the same time, the method has the characteristics of high efficiency, which is a huge improvement compared with the traditional method of analyzing separately through field sampling, and the difficulty and complexity of operation are reduced, making its application efficiency high. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings:

[0044] Figure 1 Shown is a flow chart of a dynamic programming method for phosphorus-rich biochar coverage;

[0045] Figure 2 Shown is a structural diagram of a dynamic programming system for phosphorus-rich biochar coverage. DETAILED DESCRIPTION

[0046] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0047] like Figure 1 The following is a flow chart of a dynamic programming method for phosphorus-rich biochar coverage. Figure 1 A dynamic programming method for covering phosphorus-rich biochar according to an embodiment of the present invention is described, the method comprising the following steps:

[0048] S100, collecting data on the area to be covered by phosphorus-rich biochar using a multispectral camera to obtain a collection image sequence;

[0049] S200, preprocessing the acquired image sequence to obtain a processed spectral image;

[0050] S300, analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image;

[0051] S400: Based on the obtained low conversion risk, an early warning is issued for the risk area in the area to be covered.

[0052] Furthermore, in step S100, data is collected on the area to be covered by the phosphorus-rich biochar by a multispectral camera, and a method for obtaining a collected image sequence is as follows: the area to be covered by the phosphorus-rich biochar is the soil area where the phosphorus-rich biochar is planned to be applied; the multispectral camera is carried by a drone or an airplane, and a multispectral scan is performed on the area to be covered to obtain spectral graphs in different wavelength ranges, and the obtained spectral graphs constitute a collected image sequence.

[0053] Furthermore, in step S200, the collected image sequence is preprocessed to obtain a processed spectral image by:

[0054] Each spectrum in the image sequence has a phase classification, which includes high phase diagram, low phase diagram and base phase diagram;

[0055] One of the spectral graphs has only one phase classification, which is pre-set in combination with the substances to be tested, including organic matter, sand and soil phosphorus in the soil; the spectral graph corresponding to organic matter is a high phase graph, the spectral graph corresponding to sand is a low phase graph, and the spectral graph corresponding to soil phosphorus is a base phase graph.

[0056] The image sequence is denoised, and the spectral values ​​calculated from the high phase map by the linear spectral unmixing algorithm are recorded as high phase values, the spectral values ​​calculated from the low phase map are recorded as low phase values, and the spectral values ​​calculated from the matrix phase map are recorded as matrix phase values; the tuple consisting of the high phase value, the low phase value and the matrix phase value is recorded as an acquisition group; the image constructed by the acquisition group of all pixels is used as the processed spectral image.

[0057] That is, any pixel in the processed spectral image contains a collection group, and any collection group is composed of a high phase value, a low phase value, and a base phase value;

[0058] The calculation method of high phase value, low phase value or base phase value is: define high phase value, low phase value or base phase value as processing phase value, wherein the calculation method of any processing phase value is, each spectrum image corresponding to the phase classification of the processing phase value is used as the phase image sequence, Sbj_P is the processing spectrum image,

[0059] Sbj x,y,pcss = ∑ z=1 k Sb _O(x,y,z)arf(z) / k ; z∈[1,k] ;

[0060] Where Sbj_P(x,y,pcss) represents the current processing phase value with coordinates (x,y), z is the image sequence number, and k is the number of images in the current phase image sequence; Sbj_O(x,y,z) represents the spectral value of the zth image in the current phase image sequence at coordinates (x,y), and arf(z) is the weight of the corresponding band of the zth image in the current phase image sequence, and its default value is 1.

[0061] Further, in step S300, the method of analyzing and calculating the low conversion risk of applying phosphorus-rich biochar according to the processed spectral image is: calculating the phase deficiency ratio GDRt of any pixel through the high phase value GV and the low phase value SV: GDRt = (GV-SV) / max{GV,SV};

[0062] All phase deficiency ratios obtained by processing the spectrum image are normalized to form a phase deficiency standard value, and the processed spectrum image is divided into regions according to the phase deficiency standard value. The obtained regions are recorded as soil regions, and the region division method is a superpixel segmentation algorithm;

[0063] If the lack ratio of a pixel is negative, it is defined as a strong focus point, otherwise it is defined as a weak focus point. The ratio of the number of strong focus points to the number of weak focus points in the region is calculated, and the ratio is defined as the focus weight of the region.

[0064] The calibration offset weight LO_LQS is calculated according to the phase deficiency ratio and the base phase value of each strong focus point in the soil area: LO_LQS = (exp(rg.GDRt / st.GDRt)×rg.BV) / ds.BV; wherein exp() is an exponential function with the natural constant e as the base; rg.GDRt is the average value of the phase deficiency ratio of each strong focus point in the soil area, and st.GDRt is a preset reference value of the phase deficiency ratio value; rg.BV represents the average value of the base phase value of each strong focus point in the soil area, and ds.BV represents the extreme value of each base phase value in the soil area;

[0065] The attention weight of the soil area and the calibration offset weight are combined into a tuple and recorded as a risk array. After obtaining each risk array in the image, the corresponding standard score of each risk array is calculated by calling the numpy library, and the standard score calculated for the soil area is defined as its corresponding low conversion risk.

[0066] Among them, max{} is the maximum value function, which returns the maximum value in the set;

[0067] Preferably, in step S300, the method for analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image is: performing min-max normalization processing on the high phase value, low phase value and base phase value in the processed spectral image respectively, and any pixel uses the average value of each element after normalization processing in the collection group as the pixel information degree;

[0068] According to the pixel information, the processed spectral image is divided into regions using superpixel segmentation algorithm, and the divided regions are recorded as soil regions;

[0069] For any pixel, the ratio of the low phase value to the high phase value corresponding to the pixel is recorded as the pixel point comparison, and the sequence of the corresponding point comparisons of each pixel in any area is defined as RVLs, then the comparison index StIdx of the area is: StIdx=ln(1+(mx.RVLs-mn.RVLs) / st.RVLs); where mn.RVLs and mx.RVLs are the average and maximum values ​​of RVLs respectively, and st.RVLs is the standard deviation of the sequence RVLs; the average value of the matrix phase value of each pixel in an area is recorded as the matrix level; the median value of the comparison index of all soil areas is the comparison median value;

[0070] For any soil area, if its comparison index is greater than the lower quartile value of the comparison index of all soil areas, it meets the first inhibition condition; if its substrate level is less than the upper quartile value of the substrate level of all soil areas, it meets the second inhibition condition; the soil area that meets both the first inhibition condition and the second inhibition condition is recorded as the inhibition mark area, and the rest is the empty mark area;

[0071] Take any inhibition mark area as the current inhibition mark area, take the center of the current inhibition mark area as the center, draw the circumscribed circle of the current inhibition mark area, and the obtained circumscribed circle is the mark growth area, and its radius is RG pixels;

[0072] The first overflow condition is set as follows: the marked growth area completely contains another inhibited marked area; the second overflow condition is set as follows: the comparison index of the marked growth area is less than or equal to the comparison median;

[0073] The first overflow condition or the second overflow condition is used as the iteration termination rule. Each iteration increases the radius by 1 pixel and updates the marked growth area, and recalculates the comparison index of the marked growth area. The comparison indexes obtained in each iteration are sequentially written into a sequence and recorded as the index iteration sequence of the current suppressed marked area.

[0074] In the indicator iteration sequence, if an element is larger than the previous element, the difference between the two is recorded as the iteration growth value of the element, and the sequence value of the element in the indicator iteration sequence and the iteration growth value are constructed into a tuple and recorded as a growth array; the slope value is calculated by the polyfit function in combination with all growth arrays under the indicator iteration sequence and recorded as the iteration growth coefficient erIdx;

[0075] The correlation quantity K is preset, K is a positive integer greater than 2, and any pixel is taken as the current pixel;

[0076] Select the K inhibition mark areas with the smallest Euclidean distance to the current pixel as its growth potential area.

[0077] Calculate the low conversion value VE_OLINBI of the current pixel based on the potential area:

[0078] ;

[0079] Where i is the accumulated variable, exp() is an exponential function with the natural constant e as the base, RZ_K represents the number of times the current pixel appears within the boundary of the corresponding marked growth zone in each growth zone of the current pixel; dis(i) is the Euclidean distance between the i-th growth zone and the current pixel; erIdx i and StIdx i They represent the iterative growth coefficient and the comparison index of the i-th potential enhancement zone respectively; min_K_er represents the minimum value of the iterative growth coefficients of each potential enhancement zone;

[0080] Calculate the low conversion sub-value of each pixel, select the pixel whose low conversion sub-value is not the maximum value in the eight neighborhoods as the first selection pixel, exclude all pixels corresponding to the center of the inhibition mark area from the first selection pixels, and calculate the average low conversion sub-value of all first selection pixels in the soil area as its low conversion risk.

[0081] ln() is a logarithmic function with the natural constant e as the base.

[0082] The center of the current suppression mark area refers to the coordinate point formed by the average value of the horizontal coordinate and the average value of the vertical coordinate of each pixel in the area;

[0083] The mark growth region completely contains another suppression mark region means that, in addition to the current suppression mark region, there is another suppression mark region in the mark growth region, and all pixels in the other suppression mark region are in the mark growth region.

[0084] Taking the radius increasing by 1 pixel as the iteration content means that each iteration increases the radius by 1 pixel, thereby defining a new marker growth area;

[0085] The Euclidean distance between the current pixel and the suppression mark area refers to the Euclidean distance between the current pixel and the center of the suppression mark area.

[0086] Further, in step S400, a method of issuing an early warning to a risk area in the area to be covered in combination with the obtained low conversion risk is: sending each low conversion risk to a server for storage;

[0087] The lower quartile value of each low conversion risk obtained is recorded as the first threshold; if the low conversion risk is greater than the lower quartile value, the soil area corresponding to the low conversion risk is defined as having a low conversion risk, and the location of each soil area with a low conversion risk and the low conversion risk are sent to the client and an early warning is issued.

[0088] Furthermore, in step S400, a method for issuing an early warning to the risk area in the area to be covered in combination with the obtained low conversion risk is as follows: the first threshold value can be replaced with a preset value.

[0089] An embodiment of the present invention provides a dynamic planning system for phosphorus-rich biochar coverage, such as Figure 2 Shown is a structural diagram of a dynamic planning system for covering phosphorus-rich biochar according to the present invention. The dynamic planning system for covering phosphorus-rich biochar in this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiment of a dynamic planning method for covering phosphorus-rich biochar are implemented.

[0090] The system comprises: 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 run in the following units of the system:

[0091] A spectral acquisition unit is used to acquire data of the phosphorus-rich biochar to be covered area through a multispectral camera to obtain an acquired image sequence;

[0092] An image preprocessing unit, used for preprocessing the acquired image sequence to obtain a processed spectral image;

[0093] A spectral analysis unit, used for analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image;

[0094] The result feedback unit is used to give early warning to the risk area in the area to be covered based on the obtained low conversion risk.

[0095] The dynamic programming system for covering phosphorus-rich biochar can be run on computing devices such as desktop computers, laptops, PDAs, and cloud servers. The dynamic programming system for covering phosphorus-rich biochar can be operated on systems including, but not limited to, processors and memories. Those skilled in the art will appreciate that the example is merely an example of a dynamic programming system for covering phosphorus-rich biochar, and does not constitute a limitation on a dynamic programming system for covering phosphorus-rich biochar. It can include more or fewer components than the example, or a combination of certain components, or different components. For example, the dynamic programming system for covering phosphorus-rich biochar can also include input and output devices, network access devices, buses, and the like.

[0096] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the dynamic programming system for covering phosphorus-rich biochar, and uses various interfaces and lines to connect the various parts of the dynamic programming system for covering phosphorus-rich biochar.

[0097] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the dynamic programming system for covering phosphorus-rich biochar by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0098] Although the description of the present invention has been quite detailed and has been described in particular with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present invention. In addition, the present invention is described above with the embodiments foreseeable by the inventors, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes of the present invention.

Claims

1. A dynamic programming method for covering phosphorus-rich biochar, characterized in that: The method comprises the following steps: S100, collecting data on the area to be covered by phosphorus-rich biochar using a multispectral camera to obtain a collection image sequence; S200, preprocessing the acquired image sequence to obtain a processed spectral image; S300, analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image; S400, issuing an early warning for a risk area in the to-be-covered area based on the obtained low conversion risk; In step S200, the collected image sequence is preprocessed to obtain a processed spectral image in the following manner: each spectral graph in the image sequence has a phase classification, and the classification content includes a high phase graph, a low phase graph and a base phase graph; One of the spectra has only one phase classification, which is pre-set in combination with the substance to be tested, and the substance to be tested includes organic matter, sand and soil phosphorus in the soil; the spectrum corresponding to organic matter is a high phase diagram, the spectrum corresponding to sand is a low phase diagram, and the spectrum corresponding to soil phosphorus is a base phase diagram; The image sequence is denoised, and the spectral value calculated from the high phase map by the linear spectral unmixing algorithm is recorded as the high phase value, the spectral value calculated from the low phase map is recorded as the low phase value, and the spectral value calculated from the base phase map is recorded as the base phase value; the tuple consisting of the high phase value, the low phase value and the base phase value is recorded as the acquisition group; the acquisition group of all pixels constructs an image as the processed spectral image That is, any pixel in the processed spectral image contains a collection group, and any collection group is composed of a high phase value, a low phase value, and a base phase value; The calculation method of high phase value, low phase value or base phase value is: define high phase value, low phase value or base phase value as processing phase value, wherein the calculation method of any processing phase value is, each spectrum image corresponding to the phase classification of the processing phase value is used as the phase image sequence, Sbj_P is the processing spectrum image, ; Where Sbj_P(x,y,pcss) represents the current processing phase value at coordinates (x,y), z is the image number, and k is the number of images in the current phase image sequence; Sbj_O(x,y,z) represents the spectral value of the zth image in the current phase image sequence at coordinates (x,y), and arf(z) is the weight of the corresponding band of the zth image in the current phase image sequence, and its default value is 1; In step S300, the method for analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image is: calculating the phase deficiency ratio GDRt of any pixel through the high phase value GV and the low phase value SV: GDRt = (GV-SV) / max{GV,SV}; normalizing all phase deficiency ratios obtained from the processed spectral image to form a phase deficiency standard value, dividing the processed spectral image into regions according to the phase deficiency standard value, and recording the obtained regions as soil regions, and the method of regional division is a superpixel segmentation algorithm; If the phase lack ratio of a pixel is negative, it is defined as a strong focus point, otherwise it is defined as a weak focus point. The ratio of the number of strong focus points to the number of weak focus points in the soil area is calculated, and the ratio is defined as the focus weight of the soil area; the calibration offset weight LO_LQS is calculated according to the phase lack ratio of each strong focus point in the soil area and the base phase value: LO_LQS=(exp(rg.GDRt / st.GDRt)×rg.BV) / ds.BV; where rg.GDRt is the average value of the phase lack ratio of each strong focus point in the soil area, and st.GDRt is the reference value of the preset phase lack ratio value; rg.BV represents the average value of the base phase value of each strong focus point in the soil area, and ds.BV represents the extreme difference value of each base phase value in the soil area; The attention weight of the soil area and the calibration offset weight are combined into a tuple and recorded as a risk array. After obtaining each risk array in the image, the corresponding standard score of each risk array is calculated by calling the numpy library, and the standard score calculated for the soil area is defined as its corresponding low conversion risk.

2. A dynamic programming method for covering phosphorus-rich biochar according to claim 1, characterized in that: In step S100, data is collected on the area to be covered by the phosphorus-rich biochar by a multispectral camera, and a method for obtaining a collection image sequence is as follows: the area to be covered by the phosphorus-rich biochar is the soil area where the phosphorus-rich biochar is planned to be applied; the multispectral camera is carried by a drone or an airplane, and a multispectral scan is performed on the area to be covered to obtain spectral graphs in different wavelength ranges, and the obtained spectral graphs constitute a collection image sequence.

3. A dynamic programming method for covering phosphorus-rich biochar according to claim 1, characterized in that: In step S300, the method of analyzing and calculating the low conversion risk of applying phosphorus-rich biochar based on the processed spectral image can be replaced by: performing min-max normalization processing on the high phase value, low phase value and base phase value in the processed spectral image respectively, and any pixel uses the average value of each element after normalization processing in the collection group as the pixel information degree; According to the pixel information, the processed spectral image is divided into regions using superpixel segmentation algorithm, and the divided regions are recorded as soil regions; For any pixel, the ratio of the low phase value to the high phase value corresponding to the pixel is recorded as the pixel point comparison, and the sequence of the corresponding point comparisons of each pixel in any area is defined as RVLs, then the comparison index StIdx of the area is: StIdx=ln(1+(mx.RVLs-mn.RVLs) / st.RVLs)); where mn.RVLs and mx.RVLs are the average and maximum values ​​of RVLs respectively, and st.RVLs is the standard deviation of the sequence RVLs; the average value of the matrix phase value of each pixel in an area is recorded as the matrix level; the median value of the comparison index of all soil areas is the comparison median value; For any soil area, if its comparison index is greater than the lower quartile value of the comparison index of all soil areas, it meets the first inhibition condition; if its substrate level is less than the upper quartile value of the substrate level of all soil areas, it meets the second inhibition condition; the soil area that meets both the first inhibition condition and the second inhibition condition is recorded as the inhibition mark area; Take any inhibition mark area as the current inhibition mark area, take the center of the current inhibition mark area as the center, draw the circumscribed circle of the current inhibition mark area, and the obtained circumscribed circle is the mark growth area, and its radius is RG pixels; The first overflow condition is set as follows: the marked growth area completely contains another inhibited marked area; the second overflow condition is set as follows: the comparison index of the marked growth area is less than or equal to the comparison median; The first overflow condition or the second overflow condition is used as the iteration termination rule. Each iteration increases the radius by 1 pixel and updates the marked growth area, and recalculates the comparison index of the marked growth area. The comparison indexes obtained in each iteration are sequentially written into a sequence and recorded as the index iteration sequence of the current suppressed marked area. In the indicator iteration sequence, if an element is larger than the previous element, the difference between the two is recorded as the iteration growth value of the element, and the sequence value of the element in the indicator iteration sequence and the iteration growth value are constructed into a tuple and recorded as a growth array; the slope value is calculated by the polyfit function in combination with all growth arrays under the indicator iteration sequence and recorded as the iteration growth coefficient erIdx; Preset the correlation quantity K, K is a positive integer greater than 2, and take any pixel as the current pixel; select K inhibition mark areas with the smallest Euclidean distance to the current pixel as its enhancement area, and calculate the low conversion sub-value VE_OLINBI of the current pixel according to the enhancement area; Calculate the low conversion sub-value of each pixel, select the pixel whose low conversion sub-value is not the maximum value in the eight neighborhoods as the first selection pixel, exclude all pixels corresponding to the center of the inhibition mark area from the first selection pixels, and calculate the average low conversion sub-value of all first selection pixels in the soil area as its low conversion risk.

4. A dynamic programming method for covering phosphorus-rich biochar according to claim 1, characterized in that: In step S400, the method of issuing an early warning to the risk area in the area to be covered in combination with the obtained low conversion risk is: sending each low conversion risk to the server for storage; The lower quartile value of each low conversion risk obtained is recorded as the first threshold; If the low conversion risk is greater than the lower quartile value, the area corresponding to the low conversion risk is defined as having a low conversion risk, and the location of each area with a low conversion risk and the low conversion risk are sent to the client and an early warning is issued.

5. A dynamic programming method for covering phosphorus-rich biochar according to claim 4, characterized in that: In step S400, the first threshold is replaced with a preset value.

6. A dynamic programming system for phosphorus-rich biochar coverage, characterized in that: The dynamic planning system for phosphorus-rich biochar covering includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the dynamic planning method for phosphorus-rich biochar covering described in any one of claims 1 to 5 are implemented. The dynamic planning system for phosphorus-rich biochar covering runs on desktop computers, laptop computers, PDAs, and computing devices in cloud data centers.