Soil element spectrum detection and analysis method and system based on machine learning

Abstract

The present application discloses a soil element spectral detection and analysis method and system based on machine learning, which belongs to the field of smart agricultural technology. The present application obtains field soil element data, plant growth data and environmental data, constructs an element mineralization release model, an element loss model, a plant absorption model and a pollution element impact model, evaluates the element mineralization release amount, the plant absorption amount of elements and the impact of harmful elements on plant absorption, constructs a soil element content prediction model, imports the mineralization release amount, element loss amount, plant absorption amount and pollution element impact into the soil element content prediction model to calculate the future soil element content, constructs a fertilization time prediction model, imports the future soil element content into the fertilization time prediction model to evaluate the fertilization time, and the present application predicts the fertilization time by coupling the dynamic evolution of soil elements with plant growth and absorption, combined with the nutrient demand characteristics of plants under different growth states, thereby improving the efficiency of plant planting and fertilization.

Description

Technical Field

[0001] This application belongs to the field of smart agricultural technology, specifically a soil element spectral detection and analysis method and system based on machine learning. Background Art

[0002] In current agricultural production, fertilization management mainly relies on regular manual sampling and soil testing, combined with agronomic experience to determine the time for fertilization. However, this method has significant problems such as information lag, weak prediction ability, and disconnection from the actual fertilizer demand of crops. Traditional fertilization plans are often based on static soil data and plant growth status, lacking the trend of soil nutrient changes over time during the planting cycle, and failing to consider the impact of environmental factors such as temperature, humidity, and soil type on soil element migration, mineralization, leaching and other processes. The element absorption patterns of plants at various growth stages are not quantified, and the precise matching between soil element supply capacity and crop fertilizer demand dynamics is not achieved, resulting in a misalignment between fertilization timing and actual fertilizer demand peak, low fertilizer utilization rate, and even resource waste and environmental pollution.

[0003] This application couples the dynamic evolution of soil elements with plant growth and absorption to achieve dynamic prediction of the concentration change trend of key elements in the soil over a period of time in the future. Combined with the nutrient demand characteristics of plants under different growth states, the most suitable time for fertilization is predicted, fertilization is achieved on demand and on time, the efficiency of plant planting and fertilization is improved, and green, efficient and sustainable agricultural development is achieved. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, this application proposes a soil element spectral detection and analysis method and system based on machine learning.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] The soil element spectral detection and analysis method and system based on machine learning includes the following specific steps:

[0007] Obtain field soil element data, plant growth data and environmental data;

[0008] Construct an element mineralization release model, import soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount;

[0009] Construct an element loss model and import rainfall intensity, vegetation coverage and soil structure parameters into the element loss model to evaluate the element loss amount;

[0010] Construct a plant absorption model, import the soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of elements;

[0011] Construct a pollution element impact model, import the harmful element content into the pollution element impact model to evaluate the impact of harmful elements on plant absorption;

[0012] Construct a soil element content prediction model, and import the mineralization release, element loss, plant absorption and the impact of polluting elements into the soil element content prediction model to calculate the future soil element content;

[0013] A fertilization time prediction model was constructed, and the future soil element content was imported into the fertilization time prediction model to evaluate the fertilization time.

[0014] Preferably, the acquisition of field soil element data, plant growth data and environmental data includes the following specific steps:

[0015] S11. Use spectrometers deployed in the field to collect spectral signals of soil elements in real time, preprocess spectral data using partial least squares regression, extract characteristic wavelength intervals, identify spectral characteristic bands related to soil element content, and obtain soil element content and organic matter content;

[0016] S12. Use sensors to monitor plant growth in real time to obtain environmental data, use drones to capture plant surface images, and obtain basic information about plant cultivation.

[0017] Preferably, the step of constructing the element mineralization release model and importing the soil environment data and soil element data into the element mineralization release model to evaluate the element mineralization release amount comprises the following specific steps:

[0018] Substitute the current soil temperature, soil moisture, soil type and organic matter content information of the target area obtained through monitoring into the mineralization release calculation formula of the element to calculate the mineralization release of the element. The mineralization release calculation formula of the i-th element is: ,in, is the potential release amount of the i-th element in organic matter, is the temperature adjustment factor, is the soil moisture adjustment factor, is the soil type adjustment factor, where the calculation formula for the potential release of the i-th element in organic matter is: ,in, is the soil organic matter content, is the proportion of the i-th element in organic matter, is the release rate of the i-th element in organic matter, where the temperature adjustment factor is calculated as follows: ,in, The mineralization rate increases by a multiple of 10°C when the temperature rises. is the reference temperature, T is the current soil temperature, and the calculation formula of the soil moisture adjustment factor is: , where H is the current soil moisture, The lowest mineralizable humidity, For the optimum humidity, is the over-wet suppression value, where soil type adjustment factor Through querying the soil classification database, it was found that different soil types affect the mineralization rate.

[0019] Preferably, the step of constructing an element loss model and importing rainfall intensity, vegetation coverage, and soil structure parameters into the element loss model to evaluate element loss comprises the following specific steps:

[0020] Substitute rainfall intensity, vegetation coverage and soil structure parameters into the element loss calculation formula to calculate the element loss. The element loss calculation formula is: ,in, is the element loss coefficient, is the rainfall intensity, is the vegetation coverage rate, is the soil compaction degree, is the adsorption factor, is the content of the i-th element in the soil.

[0021] Preferably, the step of constructing a plant absorption model and importing the soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of the element comprises the following specific steps:

[0022] Substitute the plant growth status and element absorption kinetic parameters into the calculation formula of plant absorption to calculate the absorption of soil elements by plants. The calculation formula of plant absorption is: ,in, is the growth state of the plant at time t, is the relationship between soil element content and absorption amount, where the element absorption kinetic parameter formula is: ,in, is the maximum absorption rate of the i-th element, is the half-saturation constant of the absorption rate, where the growth state of the plant at time t is calculated as: ,in, It is the basic absorption amount of elements in the healthy state of the plant at the current growth stage. is the area of ​​lesions on the surface of plant leaves, is the surface area of ​​plant leaves, is the adjustment factor.

[0023] Preferably, the construction of the pollutant element impact model and the introduction of the harmful element content into the pollutant element impact model to evaluate the impact of the harmful elements on plant absorption include the following specific steps:

[0024] S51. Substitute the content of elements in the soil that are detrimental to plant growth into the pollution evolution calculation formula to calculate the impact of the detrimental elements on plant absorption. The pollution evolution calculation formula is: ,in, is the jth harmful element content, Enter the rate for the pollutant source, is the natural decay rate of pollutants, where , is the source strength, is the deposition rate, , is the pollutant decay constant;

[0025] S52. Substitute the pollution evolution into the inhibition function calculation formula to calculate the impact of harmful elements on plant absorption, wherein the inhibition function calculation formula is: ,in, is the antagonistic sensitivity coefficient between the i-th element and the j-th harmful element, and m is the number of harmful elements.

[0026] Preferably, the construction of a soil element content prediction model, importing the mineralization release, element loss, plant absorption and the impact of polluting elements into the soil element content prediction model to calculate the future soil element content includes the following specific steps:

[0027] S61. Substitute the mineralization release, element loss, plant absorption, and inhibition function of the i-th element into the soil element evolution formula to calculate the soil element evolution content, wherein the soil element evolution formula is: ;

[0028] S62. Integrate the soil element evolution formula to calculate the soil element content at a future time, wherein the future soil element content calculation formula is: ,in, for The content of the i-th element in the soil at time is the interval duration.

[0029] Preferably, the step of constructing a fertilization time prediction model and importing future soil element contents into the fertilization time prediction model to estimate the fertilization time comprises the following specific steps:

[0030] S71. Obtain the soil element requirements of the plant at different growth stages based on the plant's historical growth data, wherein the soil element requirements at different growth stages are: ,in, is the minimum requirement of the plant for the i-th element during its growth stage at time t, is the maximum demand of the plant for the i-th element during the growth stage at time t. The time point when the content first falls below the lower limit is obtained by the calculation formula of the future soil element content. The calculation formula for the time point when the content first falls below the lower limit is: , where N is all soil nutrient elements;

[0031] S72. Substitute the time point when the content first falls below the lower limit into the fertilization time calculation formula to calculate the fertilization time, wherein the fertilization time calculation formula is: ,in, It is the lag time of fertilizer absorption.

[0032] The soil element spectrum detection and analysis system based on machine learning is implemented based on the soil element spectrum detection and analysis method based on machine learning, and specifically includes:

[0033] Data acquisition module, used to obtain field soil element data, plant growth data and environmental data;

[0034] Element mineralization release module, used to evaluate element mineralization release based on soil environmental data and soil element data;

[0035] Element loss module, used to evaluate element loss through rainfall intensity, vegetation cover and soil structure parameters;

[0036] Plant absorption module, used to evaluate the absorption of elements by plants based on soil element content and plant growth status;

[0037] Pollution element impact module, used to evaluate the impact of harmful elements on plant absorption through the content of harmful elements;

[0038] Soil element content prediction module, used to calculate future soil element content through mineralization release, element loss, plant absorption and the impact of pollution elements;

[0039] The fertilization time prediction module is used to predict the fertilization time based on the future soil element content.

[0040] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0041] The processor executes the above-mentioned soil element spectral detection and analysis method based on machine learning by calling the computer program stored in the memory.

[0042] A computer-readable storage medium, characterized in that it stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned soil element spectral detection and analysis method based on machine learning.

[0043] Compared with the prior art, the present invention has the following advantages:

[0044] This application obtains field soil element data, plant growth data and environmental data, constructs an element mineralization release model, imports soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount, constructs an element loss model, imports rainfall intensity, vegetation coverage and soil structure parameters into the element loss model to evaluate the element loss amount, constructs a plant absorption model, imports soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of elements, constructs a pollution element impact model, imports harmful element content into the pollution element impact model to evaluate the impact of harmful elements on plant absorption, constructs a soil element content prediction model, imports mineralization release, element loss, plant absorption and pollution element impact into the soil element content prediction model to calculate future soil element content, constructs a fertilization time prediction model, imports future soil element content into the fertilization time prediction model to evaluate the fertilization time. This application couples the dynamic evolution of soil elements with plant growth and absorption, combines the nutrient demand characteristics of plants under different growth states, predicts fertilization time, and improves the efficiency of plant planting and fertilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a schematic diagram of the overall process of the soil element spectral detection and analysis method based on machine learning in this application;

[0046] Figure 2 This is a flow chart for calculating the element mineralization release amount for this application;

[0047] Figure 3 Flowchart for calculating element loss for this application;

[0048] Figure 4 Flowchart for calculating the evolution of soil element content for this application;

[0049] Figure 5 This is a schematic diagram of the overall framework of the soil element spectral detection and analysis system based on machine learning in this application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with 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.

[0051] Example 1

[0052] See also Figure 1-4 , this application provides an embodiment: a soil element spectral detection and analysis method based on machine learning, which includes the following specific steps:

[0053] Obtain field soil element data, plant growth data and environmental data;

[0054] Construct an element mineralization release model, import soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount;

[0055] Construct an element loss model and import rainfall intensity, vegetation coverage and soil structure parameters into the element loss model to evaluate the element loss amount;

[0056] Construct a plant absorption model, import the soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of elements;

[0057] Construct a pollution element impact model, import the harmful element content into the pollution element impact model to evaluate the impact of harmful elements on plant absorption;

[0058] Construct a soil element content prediction model, and import the mineralization release, element loss, plant absorption and the impact of polluting elements into the soil element content prediction model to calculate the future soil element content;

[0059] A fertilization time prediction model was constructed, and the future soil element content was imported into the fertilization time prediction model to evaluate the fertilization time.

[0060] In this embodiment, it should be specifically explained that obtaining field soil element data, plant growth data, and environmental data includes the following specific steps:

[0061] S11. Use spectrometers deployed in the field to collect spectral signals of soil elements in real time, preprocess spectral data using partial least squares regression, extract characteristic wavelength intervals, identify spectral characteristic bands related to soil element content, and obtain soil element content and organic matter content;

[0062] It should be noted that the spectral range covers visible light, near-infrared and mid-infrared regions, capturing the complete spectral characteristics of soil elements. Spectrometers deployed in the field are used to continuously and in real time collect spectral data of the target farmland area. The collected spectral signals are first subjected to noise reduction and normalization through a standard preprocessing process, including spectral smoothing and removal of interference bands. The preprocessed spectral data are modeled using a partial least squares regression algorithm. By comparing the correspondence between the spectral signals and the element contents in the measured soil samples, characteristic wavelength intervals that are highly correlated with the target elements are extracted from the full band. By combining the spectral characteristics with the training model, the content of each major nutrient element in the soil can be quickly inverted and estimated.

[0063] S12. Real-time monitoring of plant growth to obtain environmental data using sensors, including obtaining soil moisture using a soil moisture sensor, obtaining soil temperature using a temperature sensor, and taking plant surface images using a drone;

[0064] S13. Obtain basic information on plant planting, including plant varieties, planting density, and plant growth stages.

[0065] In this embodiment, it should be specifically explained that constructing an element mineralization release model and importing soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount includes the following specific steps:

[0066] Substitute the current soil temperature, soil moisture, soil type and organic matter content information of the target area obtained through monitoring into the mineralization release calculation formula of the element to calculate the mineralization release of the element. The mineralization release calculation formula of the i-th element is: ,in, is the potential release amount of the i-th element in organic matter, is the temperature adjustment factor, is the soil moisture adjustment factor, is the soil type adjustment factor, where the calculation formula for the potential release of the i-th element in organic matter is: ,in, is the soil organic matter content, is the proportion of the i-th element in organic matter, is the release rate of the i-th element in organic matter, where the temperature adjustment factor is calculated as follows: ,in, The mineralization rate increases by a multiple of 10°C when the temperature rises. is the reference temperature, T is the current soil temperature measured by the temperature sensor, and the temperature adjustment factor is used to reflect the effect of the current temperature on the element mineralization rate relative to the reference temperature. The calculation formula of the soil moisture adjustment factor is: , where H is the current soil moisture, The lowest mineralizable humidity, For the optimum humidity, is the over-humidity inhibition value. The humidity adjustment factor is used to characterize the nonlinear effect of humidity on microbial activity and mineralization rate. It reaches its maximum value near the optimum humidity. The mineralization rate is affected by different soil types, as determined by querying a soil classification database. The potential release rate of the target element in the organic matter is calculated based on the organic matter content. The potential release rate is multiplied by the temperature adjustment factor, the humidity adjustment factor, and the soil type adjustment factor to obtain the mineralization release rate of the element at the current moment.

[0067] For example, in this embodiment, in the calculation formula of the temperature adjustment factor, The mineralization rate increases by a multiple of 10°C when the temperature rises. The default value is 2.3, the default reference temperature is 20℃, the calculation formula of the soil moisture adjustment factor is that the minimum mineralizable humidity is 10% field moisture content, the optimum humidity is 60% field moisture content, the over-humidity inhibition value is 90% field moisture content, and the soil type adjustment factor is set according to different soil types. The default value for sandy soil is 1.2, the default value for loam is 1.0, the default value for clay is 0.8, and the default value for peat soil is 1.1.

[0068] In this embodiment, it should be specifically explained that constructing an element loss model and importing rainfall intensity, vegetation coverage, and soil structure parameters into the element loss model to evaluate element loss includes the following specific steps:

[0069] Substitute rainfall intensity, vegetation coverage and soil structure parameters into the element loss calculation formula to calculate the element loss. The element loss calculation formula is: ,in, is the element loss coefficient obtained by fitting agronomic data and experiments, is the rainfall intensity, is the vegetation coverage rate, The soil compaction degree is obtained through field measurement. is the adsorption factor, which is the adsorption capacity of soil type to elements, obtained through agronomic data and experimental fitting. is the content of the i-th element in the soil.

[0070] In this embodiment, it should be specifically explained that constructing a plant absorption model and importing the soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of the element includes the following specific steps:

[0071] Substitute the plant growth status and element absorption kinetic parameters into the calculation formula of plant absorption to calculate the absorption of soil elements by plants. The calculation formula of plant absorption is: ,in, is the growth state of the plant at time t, is the relationship between soil element content and absorption amount, where the element absorption kinetic parameter formula is: ,in, is the maximum absorption rate of the i-th element, is the upper limit of absorption per unit time, is the half-saturation constant of the absorption rate, where the growth state of the plant at time t is calculated as: ,in, It is the basic absorption amount of elements in the healthy state of the plant at the current growth stage. is the area of ​​lesions on the surface of plant leaves, is the surface area of ​​plant leaves, is the adjustment coefficient (1.3), where plant absorption increases with the increase of element content in the soil and tends to saturation at high content. The calculation formula of plant absorption includes the ratio of element content to the set half-saturation constant and multiplying it by the growth status of the crop at the current growth stage, reflecting the influence of the current plant status on the actual absorption of the element;

[0072] It should be specifically noted here that in the actual plant absorption process, the plant's absorption rate of nutrients such as nitrogen and phosphorus does not increase linearly. When the element content is very low, the absorption rate is close to zero. When the content increases, the absorption rate increases rapidly. However, when the content continues to rise, the absorption capacity reaches the physiological upper limit and tends to saturation.

[0073] In this embodiment, it should be specifically explained that constructing a pollutant element impact model and importing the harmful element content into the pollutant element impact model to evaluate the impact of the harmful element on plant absorption includes the following specific steps:

[0074] S51. Substitute the content of elements in the soil that are detrimental to plant growth into the pollution evolution calculation formula to calculate the impact of the detrimental elements on plant absorption. The pollution evolution calculation formula is: ,in, is the jth harmful element content, Enter rates for pollutant sources, including external discharges of industrial wastewater, pesticide residues, and soil releases, is the natural attenuation rate of pollutants, including rain dilution, microbial degradation and phytoremediation, where , is the source intensity, including the discharge of neighboring industries, the amount of pesticides applied, etc. is the deposition rate, , is the pollutant decay constant, which was obtained by consulting the literature;

[0075] S52. Substitute the pollution evolution into the inhibition function calculation formula to calculate the impact of harmful elements on plant absorption, wherein the inhibition function calculation formula is: ,in, is the antagonistic sensitivity coefficient between the ith element and the jth harmful element, obtained through experiments and literature fitting, and m is the number of harmful elements.

[0076] In this embodiment, it should be specifically explained that the construction of a soil element content prediction model, importing the mineralization release, element loss, plant absorption, and the impact of polluting elements into the soil element content prediction model to calculate the future soil element content includes the following specific steps:

[0077] S61. Substitute the mineralization release, element loss, plant absorption, and inhibition function of the i-th element into the soil element evolution formula to calculate the soil element evolution content, wherein the soil element evolution formula is: ;

[0078] S62. Integrate the soil element evolution formula to calculate the soil element content at a future time, wherein the future soil element content calculation formula is: ,in, for The content of the i-th element in the soil at time is the interval duration.

[0079] In this embodiment, it should be specifically explained that constructing a fertilization time prediction model and importing future soil element contents into the fertilization time prediction model to estimate the fertilization time includes the following specific steps:

[0080] S71. Obtain the soil element requirements of the plant at different growth stages based on the plant's historical growth data, wherein the soil element requirements at different growth stages are: ,in, is the minimum requirement of the plant for the i-th element during its growth stage at time t, is the maximum demand of the plant for the i-th element during the growth stage at time t. The time point when the content first falls below the lower limit is obtained by the calculation formula of the future soil element content. The calculation formula for the time point when the content first falls below the lower limit is: , where N is all soil nutrient elements;

[0081] S72. Substitute the time point when the content first falls below the lower limit into the fertilization time calculation formula to calculate the fertilization time, wherein the fertilization time calculation formula is: ,in, In order to calculate the lag time of fertilizer absorption, the target element content at multiple time points in the future is predicted based on the constructed soil element evolution model, and compared with the dynamic threshold of the demand of the crops, the time point when the content first falls below the lower limit of the demand is found. Combined with the lag period of fertilizer effect, the recommended fertilization time window is generated in advance, and the effective content of the elements is corrected considering the polluting elements in the soil to avoid the output being used as a basis for decision-making on fertilization time by farmers, drones or intelligent fertilization devices due to sufficient content.

[0082] The advantages of this embodiment over the prior art are as follows: this application obtains field soil element data, plant growth data and environmental data, constructs an element mineralization release model, imports soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount, constructs an element loss model, imports rainfall intensity, vegetation coverage and soil structure parameters into the element loss model to evaluate the element loss amount, constructs a plant absorption model, imports soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of elements, constructs a pollution element impact model, imports harmful element content into the pollution element impact model to evaluate the impact of harmful elements on plant absorption, constructs a soil element content prediction model, imports mineralization release, element loss, plant absorption and pollution element impact into the soil element content prediction model to calculate future soil element content, constructs a fertilization time prediction model, imports future soil element content into the fertilization time prediction model to evaluate the fertilization time, this application couples the dynamic evolution of soil elements with plant growth and absorption, combines the nutrient demand characteristics of plants under different growth states, predicts fertilization time, and improves the efficiency of plant planting and fertilization.

[0083] Example 2

[0084] like Figure 5 As shown, a soil element spectral detection and analysis system based on machine learning is implemented based on the above-mentioned soil element spectral detection and analysis method based on machine learning, and specifically includes a data acquisition module, an element mineralization release module, an element loss module, a plant absorption module, a pollution element impact module, a soil element content prediction module and a fertilization time prediction module. The data acquisition module is used to obtain field soil element data, plant growth data and environmental data; the element mineralization release module is used to evaluate the element mineralization release amount through soil environmental data and soil element data; the element loss module is used to evaluate the element loss amount through rainfall intensity, vegetation coverage and soil structure parameters; the plant absorption module is used to evaluate the element absorption amount of plants through soil element content and plant growth status; the pollution element impact module is used to evaluate the impact of harmful elements on plant absorption through harmful element content; the soil element content prediction module is used to calculate the future soil element content through mineralization release, element loss, plant absorption and pollution element impact; the fertilization time prediction module is used to predict the fertilization time through future soil element content.

[0085] Example 3

[0086] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0087] The processor executes the above-mentioned soil element spectral detection and analysis method based on machine learning by calling the computer program stored in the memory.

[0088] This electronic device can vary significantly depending on its configuration or performance. It can include one or more processors (Central Processing Units, CPUs) and one or more memories, wherein the memories store at least one computer program, which is loaded and executed by the processor to implement the machine learning-based soil element spectral detection and analysis method provided in the above-mentioned method embodiment. The electronic device can also include other components for implementing the device's functions. For example, the electronic device can also include components such as wired or wireless network interfaces and input / output interfaces for data input and output. This embodiment is not described in detail here.

[0089] Example 4

[0090] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0091] When the computer program runs on a computer device, the computer device executes the above-mentioned soil element spectrum detection and analysis method based on machine learning.

[0092] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0093] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

Claims

1. A soil element spectral detection and analysis method based on machine learning, characterized in that: It includes the following specific steps: Obtain field soil element data, plant growth data and environmental data; Construct an element mineralization release model, import soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount; Construct an element loss model and import rainfall intensity, vegetation coverage and soil structure parameters into the element loss model to evaluate the element loss amount; Construct a plant absorption model, import the soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of elements; Construct a pollution element impact model, import the harmful element content into the pollution element impact model to evaluate the impact of harmful elements on plant absorption; Construct a soil element content prediction model, and import the mineralization release, element loss, plant absorption and the impact of polluting elements into the soil element content prediction model to calculate the future soil element content; A fertilization time prediction model was constructed, and the future soil element content was imported into the fertilization time prediction model to evaluate the fertilization time.

2. The soil element spectral detection and analysis method based on machine learning according to claim 1, characterized in that: The acquisition of field soil element data, plant growth data and environmental data includes the following specific steps: Spectral signals of soil elements are collected in real time through spectrometers deployed in the field. Spectral data are preprocessed using partial least squares regression to extract characteristic wavelength intervals, identify spectral characteristic bands related to soil element content, and obtain soil element content and organic matter content. Sensors are used to monitor plant growth in real time to obtain environmental data, and drones are used to capture plant surface images and obtain basic information on plant cultivation.

3. The soil element spectrum detection and analysis method based on machine learning according to claim 2, characterized in that: The construction of the element mineralization release model and the importation of soil environmental data and soil element data into the element mineralization release model to evaluate the element mineralization release amount include the following specific steps: Substitute the current soil temperature, soil moisture, soil type, and organic matter content information of the target area obtained through monitoring into the calculation formula for the mineralization release of the element. Multiply the potential release rate by the temperature adjustment factor, the moisture adjustment factor, and the soil type adjustment factor to obtain the mineralization release of the element at the current moment. Calculate the potential release amount of the target element in the organic matter based on the organic matter content, the proportion of the element in the organic matter, and the release rate; Calculating a temperature adjustment factor based on the soil temperature increase multiple based on the mineralization rate; Calculating a humidity adjustment factor based on the soil moisture, minimum mineralizable humidity, optimum humidity, and over-humidity inhibition value; A soil type adjustment factor is determined based on the soil type.

4. The soil element spectrum detection and analysis method based on machine learning according to claim 3 is characterized in that: The construction of the element loss model and the introduction of rainfall intensity, vegetation coverage and soil structure parameters into the element loss model to evaluate the element loss amount include the following specific steps: The amount of element loss is determined by rainfall intensity, vegetation cover, soil structure parameters and migration characteristics of target elements. Among them, the loss amount is positively correlated with rainfall intensity, and is inhibited by the degree of crop cover and the buffering effect of soil compaction on loss. The loss amount of target elements is obtained by combining rainfall intensity, cover ratio and soil buffering factor.

5. The soil element spectrum detection and analysis method based on machine learning according to claim 4 is characterized in that: The construction of the plant absorption model and the introduction of the soil element content and plant growth status into the plant absorption model to evaluate the plant's absorption of the element include the following specific steps: The amount of plant uptake is determined based on the current content of the target element in the soil, the plant growth status, and the element uptake kinetic parameters; The plant growth status is calculated by the basic absorption amount of elements in the healthy state of the plant at the current growth stage and the area of ​​lesions on the surface of the plant leaves; The element absorption kinetic parameter is the product of the maximum absorption capacity and the current element content, divided by the sum of the current content and the set half-saturation content constant, and adjusted in combination with the exponential factor of the current growth stage of the crop to calculate the difference in plant absorption at different growth stages.

6. The soil element spectrum detection and analysis method based on machine learning according to claim 5, characterized in that: The construction of the pollution element impact model and the introduction of the harmful element content into the pollution element impact model to evaluate the impact of the harmful elements on plant absorption include the following specific steps: Substitute the content of elements in the soil that are unfavorable to plant growth into the pollution evolution calculation formula to calculate the impact of the unfavorable elements on plant absorption. The pollution evolution calculation formula is: ,in, is the jth harmful element content, Enter the rate for the pollutant source, is the natural decay rate of pollutants, where , is the source strength, is the conversion or deposition rate, , is the pollutant decay constant; Substitute the pollution evolution into the inhibition function calculation formula to calculate the impact of harmful elements on plant absorption. The inhibition function calculation formula is: ,in, is the antagonistic sensitivity coefficient between the i-th element and the j-th harmful element, is the content of the i-th element in the soil, and m is the number of harmful elements.

7. The soil element spectrum detection and analysis method based on machine learning according to claim 6, characterized in that: The construction of the soil element content prediction model and the introduction of mineralization release, element loss, plant absorption and the impact of polluting elements into the soil element content prediction model to calculate the future soil element content include the following specific steps: Substitute the mineralization release, element loss, plant absorption and inhibition function of the i-th element into the soil element evolution formula to calculate the soil element evolution content, where the soil element evolution formula is: ,in, is the mineralization release of the i-th element at time t, is the amount of plant absorption of the i-th element at time t, is the amount of element loss of the i-th element at time t; The soil element evolution formula is integrated to calculate the soil element content in the future. The calculation formula for the future soil element content is: ,in, for The content of the i-th element in the soil at time is the interval duration.

8. The soil element spectrum detection and analysis method based on machine learning according to claim 7, characterized in that: The construction of the fertilization time prediction model and the importation of future soil element contents into the fertilization time prediction model to estimate the fertilization time include the following specific steps: The requirements of plants for soil elements at different growth stages are obtained based on the historical growth data of plants. The requirements for soil elements at different growth stages are as follows: ,in, is the minimum requirement of the plant for the i-th element during its growth stage at time t, is the maximum demand of the plant for the i-th element during the growth stage at time t. The time point when the content first falls below the lower limit is obtained by the calculation formula of the future soil element content. The calculation formula for the time point when the content first falls below the lower limit is: , where N is all soil nutrient elements; Substitute the time point when the content first falls below the lower limit into the fertilization time calculation formula to calculate the fertilization time, where the fertilization time calculation formula is: ,in, It is the lag time of fertilizer absorption.

9. A soil element spectrum detection and analysis system based on machine learning, which is implemented based on the soil element spectrum detection and analysis method based on machine learning according to any one of claims 1 to 8, characterized in that: Specifically include: Data acquisition module, used to obtain field soil element data, plant growth data and environmental data; Element mineralization release module, used to evaluate element mineralization release based on soil environmental data and soil element data; Element loss module, used to evaluate element loss through rainfall intensity, vegetation cover and soil structure parameters; Plant absorption module, used to evaluate the absorption of elements by plants based on soil element content and plant growth status; Pollution element impact module, used to evaluate the impact of harmful elements on plant absorption through the content of harmful elements; Soil element content prediction module, used to calculate future soil element content through mineralization release, element loss, plant absorption and the impact of pollution elements; The fertilization time prediction module is used to predict the fertilization time based on the future soil element content.

10. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the soil element spectral detection and analysis method based on machine learning as described in any one of claims 1 to 8 by calling the computer program stored in the memory.

Images