Soil nitrogen content dynamic estimation method and device, terminal and storage medium

Abstract

The invention provides a soil nitrogen content dynamic estimation method and device, a terminal and a storage medium, and relates to the technical field of soil content analysis. The method comprises the following steps: acquiring a hyperspectral remote sensing image of crops in a to-be-detected area, and calculating spectral characteristic parameters and vegetation indexes according to the hyperspectral remote sensing image; inputting the spectral characteristic parameters and the vegetation indexes into a crop spectrum-nitrogen content inversion model, and outputting the plant nitrogen content in the to-be-detected area; calculating the soil nitrogen variable quantity of the to-be-detected area by utilizing the plant nitrogen content, and dynamically estimating the soil nitrogen content of the to-be-detected area by utilizing the soil nitrogen variable quantity. According to the invention, the efficiency and accuracy of soil nitrogen content estimation can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of soil content analysis, and particularly relates to a soil nitrogen content dynamic estimation method and device, a terminal and a storage medium. BACKGROUND

[0002] In traditional agriculture, the nitrogen content information in soil is mainly obtained by manual destructive field sampling combined with indoor manual measurement and chemical analysis, which has the advantages of high measurement accuracy and strong accuracy, but the monitoring method is difficult to apply to large-scale and continuous soil monitoring, and has large workload and high cost. SUMMARY

[0003] The present application provides a soil nitrogen content dynamic estimation method, device, terminal and storage medium to solve the problems of low detection efficiency and inability to realize real-time dynamic monitoring in the prior art.

[0004] In a first aspect, the present application provides a soil nitrogen content dynamic estimation method, comprising: obtaining a hyperspectral remote sensing image of crops in a to-be-measured region, and calculating spectral feature parameters and vegetation indices according to the hyperspectral remote sensing image; inputting the spectral feature parameters and the vegetation indices into a crop spectrum-nitrogen content inversion model to output plant nitrogen content in the to-be-measured region; calculating a soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content, and dynamically estimating soil nitrogen content of the to-be-measured region by using the soil nitrogen change amount.

[0005] In a second aspect, the present application provides a soil nitrogen content dynamic estimation device, comprising: a data calculation module configured to obtain a hyperspectral remote sensing image of crops in a to-be-measured region, and calculate spectral feature parameters and vegetation indices according to the hyperspectral remote sensing image; a plant nitrogen content determination module configured to input the spectral feature parameters and the vegetation indices into a crop spectrum-nitrogen content inversion model to output plant nitrogen content in the to-be-measured region; a nitrogen content estimation module configured to calculate a soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content, and dynamically estimate soil nitrogen content of the to-be-measured region by using the soil nitrogen change amount.

[0006] In a third aspect, the present application provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.

[0007] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect.

[0008] The present application provides a soil nitrogen content dynamic estimation method, device, terminal and storage medium. The soil nitrogen content dynamic estimation method comprises the following steps: acquiring a hyperspectral remote sensing image of crops in a to-be-measured region; calculating spectral characteristic parameters and vegetation indexes according to the hyperspectral remote sensing image; inputting the spectral characteristic parameters and the vegetation indexes into a crop spectrum-nitrogen content inversion model to output plant nitrogen content in the to-be-measured region; calculating a soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content; and dynamically estimating soil nitrogen content of the to-be-measured region by using the soil nitrogen change amount. The present application acquires the hyperspectral remote sensing image of crops by means of the hyperspectral remote sensing technology, can quickly cover a large area of the to-be-measured region, greatly shortens the time for data acquisition and processing compared with the traditional method of collecting a large number of samples on site and analyzing in a laboratory, realizes rapid estimation of the soil nitrogen content, and does not cause physical damage to the crops and the soil. Moreover, the present application correlates the crop spectrum characteristics and the plant nitrogen content by using the crop spectrum-nitrogen content inversion model, and further deduces the soil nitrogen content, fully utilizes the close nutrient relationship between the crops and the soil nitrogen, reduces the influence of the complex physicochemical properties of the soil itself on direct estimation of the soil nitrogen, and improves the accuracy of the estimation result. Meanwhile, the dynamically estimated soil nitrogen content data can provide a scientific basis for precise fertilization of the crops, reasonably adjusts the nitrogen fertilizer application amount according to the actual situation of the soil nitrogen in different regions, avoids excessive or insufficient nitrogen fertilizer, improves the nitrogen fertilizer utilization efficiency, and reduces the risk of agricultural non-point source pollution. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0010] Figure 1 is an implementation flowchart of the soil nitrogen content dynamic estimation method provided by the present application; Figure 2 is a structural schematic diagram of the soil nitrogen content dynamic estimation device provided by the present application; Figure 3 is a schematic diagram of the terminal provided by the present application. DETAILED DESCRIPTION

[0011] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, technologies, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0012] In order to make the purpose, technical scheme and advantages of the present application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0013] Since the nitrogen content of soil is closely related to the nitrogen content of crop plants, the amount of fertilization, etc., in order to solve the problem of low detection efficiency and inability to realize real-time dynamic monitoring in the prior art for detecting soil nitrogen, a dynamic estimation method for soil nitrogen content is proposed, which uses a UAV to carry a hyperspectral remote sensing device to obtain crop spectral information, and inversely obtains the nitrogen content of plants, and then estimates the soil nitrogen content in combination with information such as the amount of fertilization and fertilizer utilization rate.

[0014] Among them, hyperspectral remote sensing refers to a technology that obtains a lot of narrow and continuous spectral data in the visible light and infrared band range. At the same time, UAVs are widely used in various fields of agricultural monitoring in China, and the use of airborne hyperspectral remote sensing means can obtain fine spectral information of ground objects, and has incomparable advantages over traditional methods such as non-destructive, large-scale rapid monitoring, high spatial and temporal resolution, and flexible operation.

[0015] Figure 1 The implementation flowchart of the dynamic estimation method for soil nitrogen content provided by the embodiments of the present application is described in detail as follows: In step 101, the hyperspectral remote sensing image of the crops in the to-be-detected area is obtained, and the spectral feature parameters and vegetation index are calculated according to the hyperspectral remote sensing image.

[0016] Among them, the to-be-detected area can be a farmland.

[0017] In the embodiments of the present application, the UAV carries the hyperspectral remote sensing device to collect the hyperspectral remote sensing image of the crops in the to-be-detected area according to the flight path and height of the UAV reasonably planned. Then, after collecting the hyperspectral remote sensing image, the spectral feature parameters and vegetation index are calculated according to the data extracted from the hyperspectral remote sensing image.

[0018] Among them, the preparation and setting of the UAV carrying the hyperspectral remote sensing device are as follows: 1) Equipment preparation: the embodiments of the present application use a UAV with stable flight performance and sufficient load capacity to carry a hyperspectral remote sensing device for flight operation. At the same time, auxiliary equipment such as GPS positioning equipment and data transmission module is prepared.

[0019] 2) Flight parameter setting: according to the area of the region to be detected, the terrain and the growth conditions of the crops, the flight route and height of the unmanned aerial vehicle are reasonably planned. Generally, the flight height can be set between 50-150 meters to ensure that the hyperspectral remote sensing image obtained has appropriate spatial resolution and coverage. The flight speed is controlled at 5-15 meters / second to ensure the stability and accuracy of image acquisition. At the same time, the acquisition parameters of the hyperspectral remote sensing equipment are set, such as the spectral acquisition range, acquisition frequency, etc. A gray cloth, white board and black board acquisition correction is performed once per flight.

[0020] After the hyperspectral remote sensing equipment is set on the unmanned aerial vehicle, the embodiment of the present application controls the unmanned aerial vehicle to fly according to the flight route and parameters of the equipment under suitable weather conditions (such as sunny and windless day) to obtain the hyperspectral remote sensing image of the crops in the region to be detected. During the flight, the geographic position information, flight time and other auxiliary data are recorded in real time.

[0021] After the flight is completed, the collected data is transmitted to the data processing platform (such as a terminal device) through the data transmission module. At the same time, the hyperspectral remote sensing equipment carried by the unmanned aerial vehicle can monitor crops of different growth periods according to actual needs. The embodiment of the present application can flexibly perform multiple spectral information acquisition according to different growth stages of crops, realize dynamic monitoring of the nitrogen status of crops during the growth process, and timely grasp the change trend of the nitrogen content of the soil.

[0022] Compared with the traditional method which usually needs to collect soil samples and bring them back to the laboratory for analysis, the process is complicated and time-consuming. The embodiment of the present application uses the hyperspectral remote sensing equipment carried by the unmanned aerial vehicle to perform non-contact spectral information acquisition in the air on a large area of the detection region, which can quickly obtain the spectral data of the crops, greatly improves the detection efficiency, and does not cause physical damage to the crops and the soil.

[0023] In one possible implementation, after obtaining the hyperspectral remote sensing image of the crops in the region to be detected, the method can further include: preprocessing the hyperspectral remote sensing image, the preprocessing including radiation correction, geometric correction and atmospheric correction; Correspondingly, calculating the spectral feature parameters and the vegetation index according to the hyperspectral remote sensing image can include: calculating the spectral feature parameters and the vegetation index according to the preprocessed hyperspectral remote sensing image.

[0024] Optionally, after obtaining the hyperspectral remote sensing image of the crops in the region to be detected, the embodiment of the present application needs to preprocess the image, including but not limited to radiation correction, geometric correction and atmospheric correction, to eliminate the influence of external factors on the spectral data and improve the accuracy and reliability of the data.

[0025] In a possible implementation, the calculating the spectral characteristic parameters and the vegetation index according to the hyperspectral remote sensing image can include: extracting characteristic bands of the crops in the target region and spectral reflectance of the corresponding bands from the hyperspectral remote sensing image; calculating the spectral characteristic parameters and the vegetation index by using the characteristic bands of the crops in the target region and the spectral reflectance of the corresponding bands.

[0026] Optionally, the characteristic bands of the crops in the target region and the spectral reflectance of the corresponding bands are extracted from the acquired hyperspectral remote sensing image. Then, the spectral characteristic parameters and the vegetation index of the corresponding bands are calculated by using each characteristic band of the crops in the target region and the spectral reflectance of the corresponding band.

[0027] For the vegetation index in the prior art, the normalized difference vegetation index (NDVI), the relative vegetation index (RVI), the difference vegetation index (DVI), or the like can be used.

[0028] For example, the calculation formula of the partial vegetation index of the summer corn is used as an example, and the corresponding vegetation index is as follows:

[0029] For the spectral characteristic parameters in the prior art, the index is used to describe and quantify the characteristics of the hyperspectral data, and is mainly used to analyze the spectral characteristics of the material.

[0030] In a possible implementation, the calculating the spectral characteristic parameters by using the characteristic bands of the crops in the target region and the spectral reflectance of the corresponding bands can include: calculating the spectral characteristic parameters of each characteristic band by using the first-order differential spectral analysis method.

[0031] Optionally, the first-order differential spectral analysis method is used to calculate the spectral characteristic parameters of each characteristic band, and the specific process is as follows: the ratio of the difference between the spectral reflectance of the target characteristic band and the spectral reflectance of the adjacent two characteristic bands before and after the target characteristic band to the difference between the corresponding wavelengths is used as the derivative spectrum of the target characteristic band, where the target characteristic band is any one of all the characteristic bands in the target region. The specific calculation formula is as follows:

[0032] wherein, is a derivative spectrum, is a characteristic wavelength band corresponding spectral reflectance at the wavelength, is a characteristic wavelength band corresponding spectral reflectance at the wavelength, is a characteristic wavelength band corresponding wavelength at the wavelength, is a characteristic wavelength band corresponding wavelength at the wavelength.

[0033] In the embodiments of the present application, the spectral feature parameters mainly include spectral position-based feature parameters, spectral area-based feature parameters and spectral vegetation index-based feature parameters. The specific spectral feature parameters and the corresponding calculation processes are shown in Table 1: Table 1: Hyperspectral feature parameters

[0034] In step 102, the spectral feature parameters and the vegetation index are input into the crop spectral-nitrogen content inversion model to output the plant nitrogen content in the to-be-measured region.

[0035] In the embodiments of the present application, the spectral feature parameters and the vegetation index extracted from the hyperspectral remote sensing image of the crop in the to-be-measured region obtained in step 101 are input into the established crop spectral-nitrogen content inversion model to output the plant nitrogen content of the crop in the to-be-measured region.

[0036] In the embodiments of the present application, the spectral feature parameters and the vegetation index are input into the crop spectral-nitrogen content inversion model, which is trained and verified by a large amount of data and can accurately establish the quantitative relationship between the spectral feature parameters, the vegetation index and the plant nitrogen content. Through this scientific inversion process, the output plant nitrogen content has high accuracy and provides reliable basic data for subsequent soil nitrogen content estimation.

[0037] In a possible implementation manner, the construction process of the crop spectral-nitrogen content inversion model can be as follows: Obtain historical spectral feature parameters, historical vegetation indexes and corresponding historical plant nitrogen contents of crops in a target region, the target region being any region; Construct the crop spectral-nitrogen content inversion model by using a statistical regression method; Train the crop spectral-nitrogen content inversion model by taking the historical spectral feature parameters and the historical vegetation indexes as inputs and taking the historical plant nitrogen contents as outputs.

[0038] Optionally, there is a close relationship between the nitrogen content and the hyperspectral data. By analyzing the hyperspectral data of crops and combining the sample data measured on the ground, the spectral features related to the nitrogen content can be extracted, and a crop spectral-nitrogen content inversion model can be constructed to realize quantitative evaluation and monitoring of the nitrogen content.

[0039] The process of obtaining the historical spectral feature parameters, the historical vegetation index, and the corresponding historical plant nitrogen content is as follows: The hyperspectral remote sensing equipment carried by the unmanned aerial vehicle obtains multiple historical hyperspectral remote sensing images of crops in the target region according to the set flight route and height, and splices the multiple historical hyperspectral remote sensing images according to the shooting order to obtain a complete historical hyperspectral remote sensing image of the target region.

[0040] The complete historical hyperspectral remote sensing image is preprocessed, including radiation correction, geometric correction, and atmospheric correction, to eliminate the influence of external factors on the spectral data and improve the accuracy and reliability of the data.

[0041] The historical characteristic bands of crops in the target region and the historical spectral reflectance of the corresponding bands are extracted from the preprocessed complete historical hyperspectral remote sensing image, wherein the historical spectral reflectance is the average of the spectral reflectance of all historical hyperspectral remote sensing images.

[0042] The historical plant nitrogen content of crops in the target region is obtained accordingly.

[0043] The construction process of the crop spectral-nitrogen content inversion model is as follows: Optionally, the spectral feature parameters and vegetation indices that are significantly correlated with the plant nitrogen content are selected based on the correlation coefficient method, and not less than three spectral feature parameters and vegetation indices with high correlation (such as the normalized difference vegetation index, the ratio vegetation index, and the difference vegetation index mentioned above) are selected. The data set is divided into a training set and a validation set according to a ratio of 7:3, and a crop nitrogen content estimation model is constructed using a statistical regression method. The statistical regression method can include linear regression (y=a+bx), logarithmic regression (y=a+blnx), quadratic regression (y=a+bx+cx 2 ), and exponential regression (y=ae bx ), wherein y is the physiological and ecological parameter fitting value, x is the vegetation index, and a, b, and c are constants.

[0044] The process of obtaining the data set is as follows: 20-30 sampling points are selected in the flight area using a grid random sampling method to collect crop samples and soil samples. The soil samples are collected from the 0-50 cm soil layer. Then the plant total nitrogen content and the soil total nitrogen content are measured in the laboratory.

[0045] After the construction of the multiple crop nitrogen content estimation models, in order to further screen the best model, that is, the crop spectrum-nitrogen content inversion model required in the embodiments of the present application, one regression equation with high determination coefficient R 2 and variance test quantity (i.e., F value) is selected from each spectrum characteristic parameter and vegetation index. The experimental measured data are used to test and verify the accuracy of each model. Through the test of root mean square error (RMSE) and relative error (RE), the crop nitrogen content estimation model corresponding to the spectrum characteristic parameter or vegetation index with the minimum RMSE and RE is selected as the crop spectrum-nitrogen content inversion model.

[0046] In step 103, the soil nitrogen change amount of the to-be-measured region is calculated by using the plant nitrogen content, and the soil nitrogen content of the to-be-measured region is dynamically estimated by using the soil nitrogen change amount.

[0047] In the embodiments of the present application, the soil nitrogen change amount of the to-be-measured region is calculated by using the plant nitrogen content calculated in step 102, and then the soil nitrogen content of the to-be-measured region is dynamically estimated by using the soil nitrogen change amount.

[0048] The embodiments of the present application calculate the soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content, and further dynamically estimate the soil nitrogen content, fully considering the dynamic change characteristics of the soil nitrogen in time and space. The soil nitrogen content is not fixed and unchangeable, and it is affected by various factors such as crop growth, fertilization, rainfall, etc. This method can reflect the influence of these factors on the soil nitrogen content in real time, so that the estimation result is more in line with the actual situation, and provides a scientific basis for precision agriculture management.

[0049] In one possible implementation, calculating the soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content can include: obtaining the fertilization amount and the fertilizer utilization rate of the to-be-measured region; calculating the nitrogen loss amount of the to-be-measured region; multiplying the fertilization amount and the fertilizer utilization rate to obtain a first product, and subtracting the nitrogen loss amount and the plant nitrogen content from the first product to obtain the soil nitrogen change amount.

[0050] Optionally, the soil nitrogen change amount calculated in the embodiments of the present application needs to be combined with the data such as the fertilization amount, the fertilizer utilization rate, and the plant nitrogen content of the to-be-measured region, etc. Among them, the fertilizer utilization rate is determined according to factors such as fertilizer type, soil type, and climate conditions. Therefore, firstly, the fertilization amount and the fertilizer utilization rate of the to-be-measured region need to be obtained, and then the nitrogen loss amount of the to-be-measured region needs to be calculated. Finally, the soil nitrogen change amount is calculated by using the soil nitrogen dynamic balance equation, that is:

[0051] wherein, is the soil nitrogen variation, in kg / ha; is the fertilization amount, in kg / ha, is the fertilizer utilization rate, in %, is the first product; is the plant nitrogen content, in kg / ha; is the nitrogen loss, which can be estimated by a leaching model, in kg / ha.

[0052] The fertilization amount and the fertilizer utilization rate of the to-be-measured region are obtained as follows: In the process of collecting the hyperspectral remote sensing image, the embodiment of the application collects the ground crop and soil sample data of the to-be-measured region, and records the fertilization amount, the fertilizer type (such as urea, organic fertilizer, etc.), the fertilization time, the fertilizer utilization rate, and the like.

[0053] In a possible implementation, the nitrogen loss of the to-be-measured region can be calculated as follows: The rainfall of the to-be-measured region is obtained; The nitrogen loss of the to-be-measured region is calculated by using the rainfall of the to-be-measured region and the preset soil depth.

[0054] Optionally, the nitrogen loss calculated in the embodiment of the application needs to be corrected in combination with environmental parameters such as soil texture (such as sandy soil and clay), rainfall, and temperature. First, the rainfall, the temperature, and the soil texture type of the to-be-measured region are obtained, and then the nitrogen loss is calculated by using the formula , wherein is the nitrogen loss, is the leaching coefficient, is the rainfall, is the nitrogen loss rate parameter, is the soil depth.

[0055] In a possible implementation, the soil nitrogen content of the to-be-measured region is dynamically estimated by using the soil nitrogen variation, which can include: The initial soil nitrogen content of the to-be-measured region is obtained; The soil nitrogen content of the to-be-measured region is dynamically estimated by using the initial soil nitrogen content and the sum of the soil nitrogen variations of each time period in the to-be-measured region.

[0056] Optionally, the soil nitrogen content of the to-be-measured region is dynamically estimated by using the following calculation formula in the embodiment of the application, that is,

[0057] , wherein is the soil nitrogen content at time , and is the initial soil nitrogen content, which is determined by a traditional method. is a soil nitrogen change amount in a first time period, is a soil nitrogen change amount in a first time period, is a time.

[0058] In a possible implementation, after the soil nitrogen content of the to-be-measured region is dynamically estimated by using the soil nitrogen change amount, the method can further include: visualizing the soil nitrogen content of the to-be-measured region.

[0059] Optionally, the soil nitrogen content dynamically estimated is visualized to generate a spatial distribution map of the soil nitrogen content, and combined with a geographic information system (GIS) technology, the distribution map is superimposed and displayed with information such as the topography and crop planting area of the to-be-measured region, to provide the user with intuitive soil nitrogen status information of the to-be-measured region. Meanwhile, according to the distribution of the soil nitrogen content, the growth demand of the crop and the fertilization standard, personalized fertilization suggestions are provided for the user to guide precision fertilization operations. The embodiments of the present application utilize the hyperspectral equipment carried by the unmanned aerial vehicle to record the spatial position information while obtaining the spectral information, to generate the spatial distribution map of the soil nitrogen content, which can intuitively show the distribution difference of the soil nitrogen content in different regions of the farmland, to realize precision agriculture.

[0060] The present application provides a soil nitrogen content dynamic estimation method, which obtains a hyperspectral remote sensing image of crops in a to-be-measured region, and calculates spectral characteristic parameters and vegetation indices according to the hyperspectral remote sensing image; inputs the spectral characteristic parameters and the vegetation indices into a crop spectrum-nitrogen content inversion model to output plant nitrogen content in the to-be-measured region; calculates a soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content, and dynamically estimates the soil nitrogen content of the to-be-measured region by using the soil nitrogen change amount. The present application obtains the hyperspectral remote sensing image of crops by means of the hyperspectral remote sensing technology, which can quickly cover a large area of the to-be-measured region, greatly shortens the time for data acquisition and processing compared with the traditional method of collecting a large number of samples in the field and analyzing in the laboratory, realizes rapid estimation of the soil nitrogen content, and does not cause physical damage to the crops and the soil; and by the crop spectrum-nitrogen content inversion model, the crop spectrum characteristics are associated with the plant nitrogen content, and the soil nitrogen content is further deduced, which fully utilizes the close nutrient relationship between the crops and the soil nitrogen, reduces the influence of the interference of the complex physicochemical properties of the soil itself on the direct estimation of the soil nitrogen, and improves the accuracy of the estimation result; meanwhile, the dynamically estimated soil nitrogen content data can provide a scientific basis for precision fertilization of crops, reasonably adjust the nitrogen fertilizer application amount according to the actual situation of the soil nitrogen in different regions, avoid excessive or insufficient nitrogen fertilizer, improve the nitrogen fertilizer utilization efficiency, and reduce the risk of agricultural non-point source pollution.

[0061] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0062] The following is the device embodiment of the present application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0063] Figure 2 The structure diagram of the soil nitrogen content dynamic estimation device provided by the embodiment of the present application is shown. For the convenience of description, only the part related to the embodiment of the present application is shown, and the details are as follows: As Figure 2 The soil nitrogen content dynamic estimation device 2 includes: The data calculation module 21 is configured to acquire a hyperspectral remote sensing image of crops in a to-be-measured region, and calculate spectral characteristic parameters and vegetation indices according to the hyperspectral remote sensing image. The plant nitrogen content determination module 22 is configured to input the spectral characteristic parameters and the vegetation indices into a crop spectrum-nitrogen content inversion model, and output plant nitrogen content in the to-be-measured region. The nitrogen content estimation module 23 is configured to calculate a soil nitrogen change amount of the to-be-measured region by using the plant nitrogen content, and dynamically estimate the soil nitrogen content of the to-be-measured region by using the soil nitrogen change amount.

[0064] The application provides a soil nitrogen content dynamic estimation device. The device obtains a hyperspectral remote sensing image of crops in a to-be-measured region, calculates spectral characteristic parameters and vegetation indexes according to the hyperspectral remote sensing image, inputs the spectral characteristic parameters and the vegetation indexes into a crop spectrum-nitrogen content inversion model, outputs plant nitrogen content in the to-be-measured region, calculates soil nitrogen variation in the to-be-measured region by using the plant nitrogen content, and dynamically estimates soil nitrogen content in the to-be-measured region by using the soil nitrogen variation. The device obtains the hyperspectral remote sensing image of crops by means of the hyperspectral remote sensing technology, can quickly cover a large area of the to-be-measured region, greatly shortens the time for data acquisition and processing compared with a traditional method of collecting a large number of samples on site and analyzing in a laboratory, realizes rapid estimation of soil nitrogen content, and does not cause physical damage to crops and soil. Moreover, the device correlates crop spectrum characteristics and plant nitrogen content by using the crop spectrum-nitrogen content inversion model, and further deduces soil nitrogen content, fully utilizes the close nutrient relationship between crops and soil nitrogen, reduces the influence of interference of complex physicochemical properties of soil itself on direct estimation of soil nitrogen, and improves the accuracy of estimation results. Meanwhile, the dynamically estimated soil nitrogen content data can provide a scientific basis for precise fertilization of crops, reasonably adjusts the amount of nitrogen fertilizer according to the actual situation of soil nitrogen in different regions, avoids excessive or insufficient nitrogen fertilizer, improves nitrogen fertilizer utilization efficiency, and reduces the risk of agricultural non-point source pollution.

[0065] In a possible implementation, the nitrogen content estimation module can be configured to: obtain the amount of fertilization and the fertilizer utilization rate of the to-be-measured region; calculate the nitrogen loss amount of the to-be-measured region; multiply the amount of fertilization and the fertilizer utilization rate to obtain a first product, and subtract the nitrogen loss amount and the plant nitrogen content from the first product to obtain the soil nitrogen variation amount.

[0066] In a possible implementation, the nitrogen content estimation module can be further configured to: calculate the nitrogen loss amount of the to-be-measured region by using the rainfall amount of the to-be-measured region and a preset soil depth.

[0067] In a possible implementation, the nitrogen content estimation module can be further configured to: obtain the initial soil nitrogen content of the to-be-measured region; dynamically estimate the soil nitrogen content of the to-be-measured region by using the initial soil nitrogen content and the sum of the soil nitrogen variation amounts of each time period in the to-be-measured region.

[0068] In a possible implementation, the data calculation module can be configured to: extract a characteristic band of crops in a target region and spectral reflectivity of the corresponding band from the hyperspectral remote sensing image; The spectral characteristic parameters and the vegetation indexes are calculated by using the characteristic wave bands of the crops in the target area and the spectral reflectivity of the corresponding wave bands.

[0069] In a possible implementation, the data calculation module can be further configured to: The spectral characteristic parameters corresponding to each characteristic wave band are obtained by using a first-order differential spectral analysis method to calculate the spectral reflectivity of the characteristic wave bands of the crops in the target area and the corresponding wave bands.

[0070] In a possible implementation, the construction process of the crop spectral-nitrogen content inversion model is as follows: The historical spectral characteristic parameters, the historical vegetation indexes, and the corresponding historical plant nitrogen contents of the crops in the target area are obtained, and the target area is any area; The crop spectral-nitrogen content inversion model is constructed by using a statistical regression method; The historical spectral characteristic parameters and the historical vegetation indexes are taken as inputs, and the historical plant nitrogen contents are taken as outputs, so as to train the crop spectral-nitrogen content inversion model.

[0071] Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present application. As shown in Figure 3 the terminal 3 of this embodiment includes a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. The processor 30 implements the steps in each of the soil nitrogen content dynamic estimation method embodiments described above when executing the computer program 32, such as Figure 1 steps 101 to 103 shown in the drawings. Alternatively, the processor 30 implements the functions of each module / unit in each of the device embodiments described above when executing the computer program 32, such as Figure 2 the functions of each module shown in the drawings.

[0072] For example, the computer program 32 can be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 32 in the terminal 3. For example, the computer program 32 can be divided into Figure 2 the modules shown in the drawings.

[0073] The terminal 3 can be a desktop computer, a notebook, a palm computer, and a cloud server, etc. The terminal 3 can include, but is not limited to, the processor 30 and the memory 31. Those skilled in the art can understand that Figure 3The example of the terminal 3 is merely illustrative and does not limit the terminal 3, which can include more or fewer components than shown, or combine some components, or have different components, such as the terminal can also include an input / output device, a network access device, a bus, etc.

[0074] The processor 30 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0075] The memory 31 can be an internal storage unit of the terminal 3, such as a hard disk or a memory of the terminal 3. The memory 31 can also be an external storage device of the terminal 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 3. Further, the memory 31 can also include both the internal storage unit and the external storage device of the terminal 3. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0077] In the above embodiments, the description of each embodiment is focused on, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0078] Those skilled in the art can appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0079] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other ways. For example, the apparatus / terminal embodiments described above are only schematic, and the division of the modules or units is only a logical function division, and there can be another division in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0080] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0081] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0082] The integrated module / unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiments can also be implemented by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various soil nitrogen content dynamic estimation method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0083] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for dynamically estimating soil nitrogen content, characterized in that: include: Acquire a hyperspectral remote sensing image of crops in the area to be measured, and calculate spectral characteristic parameters and vegetation index based on the hyperspectral remote sensing image; Inputting the spectral characteristic parameters and the vegetation index into a crop spectrum-nitrogen content inversion model, and outputting the plant nitrogen content in the area to be measured; The plant nitrogen content is used to calculate the soil nitrogen change in the area to be measured, and the soil nitrogen content in the area to be measured is dynamically estimated using the soil nitrogen change.

2. The method for dynamic estimation of soil nitrogen content according to claim 1, characterized in that: The method of calculating the change in soil nitrogen in the measured area by using the plant nitrogen content includes: Obtaining the amount of fertilizer applied and the fertilizer utilization rate in the area to be measured; Calculating the nitrogen loss in the measured area; The product of the fertilizer application amount and the fertilizer utilization rate is taken as a first product, and the nitrogen loss amount and the plant nitrogen content are subtracted from the first product to obtain the soil nitrogen change amount.

3. The method for dynamic estimation of soil nitrogen content according to claim 2, wherein: The calculating of the nitrogen loss in the measured area includes: Obtaining the rainfall in the area to be measured; The nitrogen loss in the area to be measured is calculated using the rainfall in the area to be measured and the preset soil depth.

4. The method for dynamic estimation of soil nitrogen content according to claim 1, wherein: The dynamically estimating the soil nitrogen content of the measured area by utilizing the soil nitrogen change includes: Obtaining the initial soil nitrogen content of the area to be tested; The soil nitrogen content of the area to be measured is dynamically estimated by using the sum of the initial soil nitrogen content and the soil nitrogen change in each time period in the area to be measured.

5. The method for dynamic estimation of soil nitrogen content according to claim 1, wherein: Calculating spectral characteristic parameters and vegetation index based on the hyperspectral remote sensing image includes: Extracting characteristic bands of crops in the target area and spectral reflectance of corresponding bands from the hyperspectral remote sensing image; The spectral characteristic parameters and the vegetation index are calculated using the characteristic wavebands of the crops in the target area and the spectral reflectance of the corresponding wavebands.

6. The method for dynamic estimation of soil nitrogen content according to claim 5, characterized in that: The calculating of the spectral characteristic parameters by using the characteristic wavebands of the crops in the target area and the spectral reflectance of the corresponding wavebands includes: The characteristic bands of the crops in the target area and the spectral reflectance of the corresponding bands are calculated using a first-order differential spectral analysis method to obtain spectral characteristic parameters corresponding to each characteristic band.

7. The method for dynamic estimation of soil nitrogen content according to claim 1, wherein: The construction process of the crop spectrum-nitrogen content inversion model is as follows: Obtaining historical spectral characteristic parameters, historical vegetation index, and corresponding historical plant nitrogen content of crops in a target area, wherein the target area is any area; Statistical regression method was used to construct crop spectrum-nitrogen content inversion model; The crop spectrum-nitrogen content inversion model is trained by taking the historical spectral characteristic parameters and the historical vegetation index as input and the historical plant nitrogen content as output.

8. A device for dynamically estimating soil nitrogen content, characterized in that: include: A data calculation module is used to obtain hyperspectral remote sensing images of crops in the area to be measured, and calculate spectral characteristic parameters and vegetation index based on the hyperspectral remote sensing images; a plant nitrogen content determination module, configured to input the spectral characteristic parameters and the vegetation index into a crop spectrum-nitrogen content inversion model, and output the plant nitrogen content in the area to be measured; The nitrogen content estimation module is used to calculate the soil nitrogen change in the test area using the plant nitrogen content, and dynamically estimate the soil nitrogen content in the test area using the soil nitrogen change.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for dynamically estimating soil nitrogen content as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for dynamically estimating soil nitrogen content as described in any one of claims 1 to 7 are implemented.

Images