Fertilizer proportion management method and system combined with remote sensing data analysis

Abstract

The invention provides a remote sensing data analysis-combined fertilizer proportion management method and system, and relates to the technical field of remote sensing data, the method comprises the following steps: using an unmanned aerial vehicle to shoot an original data set of crops in a key growth period of a target field, and preprocessing the original data set to obtain a remote sensing image set; calculating a vegetation index according to the remote sensing image set, and generating a vegetation index map in combination with GIS software; obtaining a soil nutrient content data set and a crop nutrient content data set; performing correlation modeling on the crop nutrient content data set and the vegetation index map by using a random forest regression algorithm, and performing nutrient inversion calculation on the target field by using the model to obtain a nutrient spatial distribution map; generating a fertilizer ratio decision; spatial expression is carried out on the decision result through GIS software, and a digital fertilization prescription map is obtained. The technical problems of low efficiency, large error, incomplete coverage and slow response in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of remote sensing data, in particular to a fertilizer ratio management method and system combined with remote sensing data analysis. BACKGROUND

[0002] In modern agricultural production, scientific and reasonable fertilizer ratio not only directly affects the yield and quality of crops, but also relates to soil health and sustainable development of agriculture. Excessive fertilization is easy to cause resource waste and environmental pollution, while insufficient fertilization will lead to crop nutrient deficiency and reduce yield potential. Therefore, how to dynamically adjust the fertilizer ratio according to the actual growth status of crops and the soil nutrient supply capacity has become a key problem to improve the efficiency and ecological benefits of agricultural production.

[0003] The traditional fertilizer ratio method is based on manual sampling and laboratory analysis, and its limitations are increasingly prominent. Manual sampling is limited by time and cost, and usually only a few points of farmland can be covered, which is difficult to fully reflect the spatial heterogeneity of soil nutrients in the field, resulting in significant deviation of the fertilization scheme. The limitations of traditional methods make it difficult for existing technologies to meet the needs of precision agriculture for efficient, real-time and full-coverage fertilization management.

[0004] In summary, the traditional fertilizer ratio method has the problems of low efficiency, large error, incomplete coverage and slow response, and it is difficult to realize precise, efficient and dynamic fertilization management, so there is an urgent need for a method to solve the above problems. SUMMARY

[0005] The present disclosure provides a fertilizer ratio management method and system combined with remote sensing data analysis to solve the technical problems of low efficiency, large error, incomplete coverage and slow response in the prior art.

[0006] According to a first aspect of the present disclosure, a fertilizer ratio management method combined with remote sensing data analysis is provided, comprising: An unmanned aerial vehicle is used to shoot an original data set of crops in a target field during a key growth period, the original data set is preprocessed to obtain a remote sensing image set, and the preprocessing includes radiation calibration, atmospheric correction, geometric correction and cloud mask; A vegetation index is calculated according to the remote sensing image set, and a vegetation index map is generated in combination with GIS software; Based on the soil type of the target field, historical yield data and the vegetation index map, representative points of the target field are selected, soil and crop samples are collected, and key nutrient content analysis is performed on the samples to obtain a soil nutrient content data set and a crop nutrient content data set; A random forest regression algorithm is applied to correlate and model the crop nutrient content data set and the vegetation index map, and the model is used to calculate the nutrient inversion of the target field to obtain a nutrient spatial distribution map; The vegetation index map, the soil nutrient content dataset, the nutrient spatial distribution map and historical yield data are comprehensively used, a clustering analysis algorithm is applied to spatial partition, the target field plot is divided into M management units, the fertilizer application amount and element abundance and deficiency index required by each management unit are determined, and a fertilizer ratio decision is generated; The decision result is spatialized by using GIS software, and a digital fertilization prescription map is obtained.

[0007] According to a second aspect of the present disclosure, a fertilizer ratio management system combined with remote sensing data analysis is provided, comprising: A remote sensing image acquisition module is configured to use a UAV to shoot an original dataset of crops in a target field plot during a key growth period, pre-process the original dataset to obtain a remote sensing image set, and the pre-processing includes radiation calibration, atmospheric correction, geometric correction and cloud mask; A vegetation index calculation module is configured to calculate a vegetation index according to the remote sensing image set, and generate a vegetation index map in combination with GIS software; A soil and crop nutrient analysis module is configured to select a representative point of a target field plot based on the soil type, historical yield data and vegetation index map of the target field plot, collect soil and crop samples, analyze the key nutrient content of the samples, and obtain a soil nutrient content dataset and a crop nutrient content dataset; A nutrient inversion modeling module is configured to use a random forest regression algorithm to correlate and model the crop nutrient content dataset and the vegetation index map, use the model to calculate the nutrient inversion of the target field plot, and obtain a nutrient spatial distribution map; A precise partition and fertilization decision module is configured to comprehensively use the vegetation index map, the soil nutrient content dataset, the nutrient spatial distribution map and the historical yield data, apply a clustering analysis algorithm to spatial partition, divide the target field plot into M management units, determine the fertilizer application amount and element abundance and deficiency index required by each management unit, and generate a fertilizer ratio decision; A digital fertilization prescription generation module is configured to use GIS software to spatialize the decision result, and obtain a digital fertilization prescription map.

[0008] The one or more technical solutions provided in the disclosure have at least the following technical effects or advantages: original data sets of crops in a key growth period of a target field are photographed by using a drone, the original data sets are preprocessed to obtain a remote sensing image set, the preprocessing includes radiation calibration, atmospheric correction, geometric correction and a cloud mask; a vegetation index is calculated according to the remote sensing image set, and a vegetation index map is generated in combination with GIS software; representative points of the target field are selected based on a soil type of the target field, historical yield data and the vegetation index map, soil and crop samples are collected, key nutrient content analysis is performed on the samples, and a soil nutrient content data set and a crop nutrient content data set are obtained; a random forest regression algorithm is applied to associate modeling of the crop nutrient content data set and the vegetation index map, and nutrient inversion calculation is performed on the target field by using the model to obtain a nutrient spatial distribution map; the vegetation index map, the soil nutrient content data set, the nutrient spatial distribution map and the historical yield data are comprehensively used, a spatial partitioning is performed by using a clustering analysis algorithm, the target field is divided into M management units, required fertilizer application amounts and element abundance deficiency indexes of each management unit are determined, and a fertilizer ratio decision is generated; and the decision result is spatialized and expressed by using GIS software to obtain a digital fertilization prescription map. The technical problems of low efficiency, large error, incomplete coverage and slow response in the prior art are solved. The technical effects of improving the calculation precision, coverage range and decision efficiency of the fertilizer ratio are achieved.

[0009] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the following specific embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application will be described. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present disclosure or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creating laborious work on the basis of the provided drawings.

[0011] Figure 1 The flowchart of the fertilizer ratio management method combined with remote sensing data analysis provided in the embodiments of the present application; Figure 2 The structural diagram of the fertilizer ratio management system combined with remote sensing data analysis provided in the embodiments of the present application.

[0012] Explanation of reference signs: remote sensing image acquisition module 11, vegetation index calculation module 12, soil and crop nutrient analysis module 13, nutrient inversion modeling module 14, precise partitioning and fertilization decision module 15, digital fertilization prescription generation module 16. DETAILED DESCRIPTION

[0013] The following description of exemplary embodiments of the present disclosure is provided in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0014] Example 1: The fertilizer ratio management method combined with remote sensing data analysis provided by the embodiment of the present disclosure is referred to Figure 1 For illustration, the methods include: S1: Use drones to capture the original dataset of crops in the target field during the critical growth period, and preprocess the original dataset to obtain a remote sensing image set. The preprocessing includes radiometric calibration, atmospheric correction, geometric correction, and cloud masking. Furthermore, this step S1 also includes: Evenly select N ground control points in the target field, spray L-shaped marks and record the coordinate positions simultaneously; The flight parameters of the drone are set based on the geographical conditions of the target field, and the original data set of the target field is collected during the key crop growth period. The drone is equipped with a multispectral sensor, and the original data set includes the original DN image set and the flight parameter log. Obtain the original data set, perform radiometric calibration, and convert the original DN value into apparent reflectance by combining the sensor calibration file and the flight parameter log to obtain the apparent reflectance image set; Based on the apparent reflectance image set, the empirical linear method assisted by the ground calibration plate is used to convert the apparent reflectance into the surface reflectance to obtain the surface reflectance image set; The surface reflectance image set is roughly stitched using POS data and SIFT feature points to generate an initial orthophoto image set. A second-order polynomial transformation is performed on the coordinates of the ground control points, and bilinear interpolation resampling is used to output an orthophoto reflectance image set in a projected coordinate system. Cloud mask processing is performed based on the spectral characteristics of the orthoreflectance image set to remove invalid areas and finally generate a remote sensing image set.

[0015] Specifically, N ground control points are evenly selected in the target field plot, and no less than 5 points are arranged per 10 mu. Each point is sprayed with a permanent L-shaped mark, and the high-precision coordinates of the mark center point are recorded by an RTK measuring instrument. Based on GIS software and field surveying and mapping, the boundary of the target field plot is determined, and the flight parameters of the unmanned aerial vehicle are planned accordingly: the flight height is set to 80 to 100 meters, the ground resolution is guaranteed to be 3 to 5 cm, the heading overlap rate is greater than or equal to 80%, the lateral overlap rate is greater than or equal to 70%, and the flight direction is parallel to the long side of the field plot to optimize the coverage efficiency. Select the key growth period of the crop, and perform the flight task in sunny and cloudless weather conditions with a wind speed less than 5 m / s at 10:00 to 14:00 every day when the sun height is greater than 45 degrees. The unmanned aerial vehicle automatically cruises with a multi-spectral sensor and synchronously collects the original data set of the target field plot, specifically including the original DN image set and the flight parameter log, wherein the original DN image set includes the DN value data of the blue, green, red, red edge, and near-infrared bands, and the flight parameter log includes the GPS timestamp, the sensor attitude angle, the sun zenith angle, and the real-time irradiance.

[0016] The DN value is converted into apparent reflectance by radiometric calibration. The gain coefficient K band and the offset value Offset band of each band are obtained based on the calibration file provided by the sensor manufacturer, and the real-time irradiance in the flight parameter log is combined to perform radiometric calibration. The original DN value is converted into radiance L λ , and the specific formula is: , wherein L λ is the radiance at the entrance pupil of the sensor, is the DN value data in the original data set, Offset band is the offset value, and K band is the gain coefficient of each band. The day-earth distance correction factor d is calculated according to the GPS timestamp, the exoatmospheric solar irradiance Esun corresponding to the center wavelength of the band is queried, such as about 1530 Wm -2 μm -1 , and the apparent reflectance is calculated in combination with the sun zenith angle θ in the flight parameter log, and the specific formula is: , wherein R represents the apparent reflectance, is a constant, is the radiance, d is the day-earth distance correction factor, Esun is the exoatmospheric solar irradiance, is the cosine function of the sun zenith angle. All apparent reflectance data are integrated, and the output result is a floating-point apparent reflectance image set, and whether the values of each band meet the expected range is verified by a histogram.

[0017] The apparent reflectance image set is acquired and is subjected to atmospheric correction. An experience linear method assisted by a ground calibration board is used to eliminate the influence of atmospheric scattering. Three groups of reflectance calibration boards with standard reflectance of 10%, 30% and 50% are laid in a field before flight, and the real reflectance of the calibration boards is measured by using a handheld spectrometer The mean value of the image element in the calibration board region is extracted from the apparent reflectance image set A linear equation is independently fitted for each waveband: wherein a represents a slope, b represents an intercept, and the coefficients of specific wavebands are different, for example, the typical coefficients of the near-infrared waveband are a = 1.12 and b = -0.03. The regression model is applied to the panoramic image to generate the ground surface reflectance data with clear physical meaning, all the ground surface reflectance data are integrated, and the ground surface reflectance image set is obtained.

[0018] The spatial precision is improved by combining the previously set N ground control points and the POS data, the geometric correction and image splicing are performed on the ground surface reflectance influence set. The POS data of the unmanned aerial vehicle and the SIFT feature matching algorithm are used to perform initial splicing on the single-scene ground surface reflectance image to generate an initial orthographic image set with residual error of 5-10 pixels. The measured ground control point coordinates are imported, and a second-order polynomial geometric transformation is performed: , wherein and are the corrected map coordinates, x and y represent the original image element coordinates, a0 to a5 represent the X-direction transformation coefficients, and b0 to b5 represent the Y-direction transformation coefficients. The bilinear interpolation resampling is used to ensure that the RMS of all GCP residual errors is less than or equal to 0.5 pixels, and the high-resolution GIS base map such as the ridge vector line is superimposed, the alignment accuracy of the ground objects is visually checked, and the edge registration error is required to be less than 1 pixel element. The final output result is the orthographic reflectance image set in the projection coordinate system, and the edge registration error is less than 1 pixel element.

[0019] The orthographic reflectance image set is subjected to cloud mask processing, and invalid regions are identified and removed based on spectral characteristics. Specifically, the cloud detection standard is that the near-infrared waveband and the ratio of the blue light waveband to the red light waveband The shadow detection standard is that the near-infrared waveband and the red light waveband A dilation operation using a 3×3 pixel rectangular structuring element is performed on the identified area to eliminate small patches of debris. Finally, manual review is performed and erroneous areas are corrected by comparing them against the RGB true color preview image. For example, if white plastic film is mistakenly identified as cloud, a binary mask file is generated, with valid farmland = 1 and cloud or shadow = 0. The resulting mask is applied to the orthoreflectance image set, with invalid areas assigned a NaN value, retaining the pure farmland observation data, and generating a remote sensing image set. The remote sensing image set stores reflectance data for each band in GeoTIFF format, with metadata files attached. All images are aligned to the same coordinate system and resolution.

[0020] S2: Calculate vegetation index based on remote sensing image sets and generate vegetation index maps using GIS software; Furthermore, this step S2 also includes: The vegetation index is calculated based on the remote sensing image set and the crop growth stage. If the crop is in the early to mid-growth stage, the vegetation index uses the normalized difference vegetation index. If the crop is in the mid-to-late growth stage, the vegetation index uses the red edge normalized index. The specific calculation formula of the normalized difference vegetation index is: ; in, represents the Normalized Difference Vegetation Index, represents the surface reflectance in the near-infrared band, Represents the surface reflectance in the red light band; The specific calculation formula of the red edge normalization index is: ; Where NDRE stands for Normalized Red Edge Index, represents the surface reflectance in the near-infrared band, Represents the surface reflectance in the red edge band; Performing spatial optimization on the calculated vegetation index, wherein the spatial optimization includes spatial relationship matching and clipping operations; Statistical features are obtained based on the spatially optimized vegetation index. Grading thresholds are set according to the statistical features. Different threshold areas are mapped into asymptotic color bands using the HSV color space model to generate a vegetation index map. The statistical features include minimum value, maximum value and quartiles.

[0021] Specifically, a remote sensing image set is obtained and data standardization is performed to ensure computational reliability. First, spatial consistency verification is performed to check the geographic coordinates, projection system, resolution, and pixel alignment of each band image. GIS software is used to confirm that the spatial offset of near-infrared, red light, red edge, and other bands does not exceed 0.5 pixels. If there is a deviation, a resampling operation is performed to force alignment. Then, a value range validity screening is performed, and the near-infrared reflectance of the vegetation coverage area is calculated. Should be in the range of 0.1-0.9, red light reflectivity In the interval of 0.02-0.25. The pixels out of the range are marked as invalid values.

[0022] Based on the normalized reflectance data and the crop growth stage, the vegetation index is calculated. If the crop is in the early to middle growth stage, the normalized difference vegetation index is selected, and if the crop is in the middle to late growth stage, the red edge normalized index is selected. The specific calculation formula of the normalized difference vegetation index is: ; Wherein, represents the normalized difference vegetation index, represents the near-infrared band surface reflectance, which is derived from multiple scattering of plant cell walls, represents the red band surface reflectance, which is usually <0.1 in the vegetation area due to strong absorption by chlorophyll. The molecule represents the photosynthetic capacity of vegetation. Healthy plants have strong chlorophyll absorption in the red light, and the cell structure has high reflectivity in the near-infrared. The higher the value, the stronger the chlorophyll activity. The denominator indicates the standardization process, which normalizes the light conditions and eliminates the influence of the solar elevation angle, so that the output value is limited to [-1, 1].

[0023] The specific calculation formula of the red edge normalized index is: ; Wherein, NDRE represents the red edge normalized index, which is mainly used to describe the state of crops in the middle to late growth stage, represents the near-infrared band surface reflectance, represents the red edge band surface reflectance, which is sensitive to chlorophyll concentration and can penetrate high-density canopy. Its calculation process is the same as that of NDVI, but the band input needs to be replaced.

[0024] The vegetation index obtained by calculation is spatially optimized. The boundary points are collected in the field along the target field plot by RTK measuring instrument, and a coordinate point is recorded every 10 meters for straight boundary. The point interval is encrypted to 3 meters at corners. Avoid crop shading when collecting. After importing the data into GIS software, generate farmland boundary vector file, and the attribute table contains field number and area field. Use ArcGIS topology verification tool to check the topology of farmland boundary vector, ensure that the polygon is completely closed, there is no hanging line, and there is no overlap or gap between adjacent fields. At the same time, the coordinate of farmland boundary vector is corrected. If the vector coordinate system is inconsistent with the remote sensing image, use seven-parameter affine transformation to unify to the target coordinate system. Load the vegetation index data and farmland boundary vector into the GIS platform at the same time, check the consistency of the coordinate system, and match the spatial relationship. If deviation is found, use the projection tool ProjectRaster to convert the raster coordinate system, and apply spatial correction Spatial Adjustment to translate the vector boundary. Use the vector polygon as a mold to extract the raster data within its coverage range, and perform clipping operation. The clipping parameters are set as follows: the clipping mode is selected as accurate clipping, all pixels within the boundary are retained; the area outside the boundary is filled with invalid values; the resampling method is set to bilinear interpolation to avoid jagged edges. Finally, the spatially optimized vegetation index data is output, and the error between the data raster area and the vector area is less than or equal to 0.5%, and the visual image boundary of the target field plot can be aligned without error and loss.

[0025] The vegetation index after spatial optimization is obtained, and the vegetation index data at this time is a GeoTIFF file of floating point type, each pixel stores a vegetation index value between -1.0 and 1.0, contains accurate geographic coordinate information, and has completed spatial optimization steps such as farmland boundary clipping. In order to realize the intuitive expression of crop information, the continuous vegetation index value is converted into a graded color with clear agronomic significance. The specific steps include: statistical characteristic analysis, calculation of the histogram distribution of the vegetation index, determination of the key demarcation points, including the minimum value, the maximum value and the quartiles, specifically the minimum value Min is the actual minimum value after removing bare soil and water, the maximum value Max is the crop saturation point after removing 5% of the highest value, the quartiles are 25% Q1, 50% Median and 75% Q3; analyze the statistical characteristics of the vegetation index of the target field block to determine the grading threshold, set Min to Q1 as the low-fertilizer area, representing the 25% area with the worst growth, Q1 to Median as the medium-fertilizer area, representing the 25% area with medium growth, Median to Q3 as the balance area, representing the 25% area with medium growth, Q3 to Max as the high-fertilizer area, representing the 25% area with the best growth, and simultaneously adjust the grading threshold according to the actual situation of crop growth to ensure that the threshold interval is flexible and variable, for example, if it is a drought year, the overall threshold interval can be lowered by 0.1 to adapt to the changes in crop physiological state; design a color mapping scheme, use the HSV color space model to realize the scientific conversion from numerical value to color, specifically, the hue is gradually changed from red to green, corresponding to the growth from poor to good, among which the red color corresponds to the low-fertilizer area, indicating the stress state of chlorophyll deficiency, the yellow color corresponds to the medium-fertilizer area, indicating normal growth but not up to standard, the green color corresponds to the balance area, indicating normal crop growth, and the dark green color corresponds to the high-fertilizer area, indicating saturated biomass and potential lodging risk, and the color saturation is set to remain above 85% to ensure bright colors, and the high-value area reduces the lightness to enhance the visual hierarchy; finally, generate a vegetation index map according to the above settings, the index map contains spatial information and agronomic interpretation, the vegetation index rendering map occupies 70% of the map area, and the scale length corresponds to 100 meters in the field.

[0026] S3: Based on the target field block soil type, historical yield data and vegetation index map, select representative points of the target field block, collect soil and crop samples, and analyze the key nutrient content of the samples to obtain soil nutrient content dataset and crop nutrient content dataset; Specifically, to achieve precision agriculture nutrient management, first of all, based on the target field soil type, historical yield data and vegetation index map for multi-source spatial overlay analysis. In the GIS platform, the three types of data are unified to the same coordinate system, and the variation weight value of each position is calculated by weighted fusion algorithm: the difference of soil type gives the basic weight, the historical yield fluctuation reflects the long-term fertility trend, and the vegetation index indicates the real-time crop growth. The three are fused according to the weight ratio of 3:4:3 to generate a field comprehensive variation grid map with a value range of 0-1. According to the grid value, the field is divided into high, medium and low variation levels, and the weight greater than 0.7 is determined as a high variation area, 8 sampling points per hectare, the weight between 0.4 and 0.7 is determined as a medium variation area, 5 sampling points per hectare, and the weight less than 0.4 is determined as a low variation area, 3 sampling points per hectare. When distributing points, strictly follow the principle of spatial uniformity, each point represents a 15-meter radius circular area, avoid 10 meters away from the ridge and far away from the ditch road, and finally generate a sampling point distribution map containing accurate GPS coordinates.

[0027] The professional sampling team carries stainless steel soil drill and liquid nitrogen insulation box for field sampling operation. Soil sampling adopts five-point method: taking 5 drills of 0-20 cm plough layer soil samples within a radius of 5 meters with point as center, mixing 1 sample after removing stones and roots on site, and recording sampling depth error within ±2 cm. Crop sampling strictly follows the organ standard, such as taking the latest fully expanded leaves of corn and the third leaf of the main stem of wheat, and collecting 10 leaves of the same part per point. After natural drying for 7 days, the soil samples are ground through 2 mm nylon screen, sealed and packed according to the standard of 200 grams per bag, and the leaf samples are immediately frozen in liquid nitrogen tank and transferred to-80℃ ultra-low temperature refrigerator for storage, to ensure that the nutrients are not degraded. In the laboratory analysis stage, samples are detected according to industry standard, each batch of samples is inserted into standard material calibration, and 15% parallel sample error control is set to ensure that the relative deviation is less than or equal to 5%.

[0028] After obtaining the original analysis data, two structured data sets were constructed. The crop nutrient content data set retained the sampling point scale characteristics and stored the spatial coordinates and nitrogen, phosphorus, and potassium contents of each point in CSV format. This data set was directly associated with the vegetation index modeling and did not perform spatial extrapolation. The fields included point, coordinates, total nitrogen, total phosphorus, total potassium content, and sampling date. The soil nutrient content data set needed to cover the entire field. The discrete sampling point data was spatialized using the Kriging interpolation method. Based on the digital elevation model as the covariate, the autocorrelation weight was calculated based on the semi-variation function model to generate a 1-meter resolution raster layer. The alkali-hydrolyzable nitrogen, available phosphorus, and available potassium were stored as independent bands, respectively, and the fourth band recorded the interpolation standard deviation. After 20% of the reserved points were verified, the interpolation error of alkali-hydrolyzable nitrogen was less than or equal to 8 mg / kg, and the available phosphorus was less than or equal to 2 mg / kg, forming a GeoTIFF file that could fully reflect the spatial heterogeneity of soil fertility. The final output results included the crop nutrient content data set and the soil nutrient content data set, which were spatially related through a unified coordinate system. The crop data set provided true value calibration for vegetation index inversion, and the soil data set directly drove the zoning fertilization decision, together constituting the basic data chain of precision agriculture nutrient management. All data were accompanied by metadata documents, which detailed the sampling specifications, detection methods, and accuracy verification reports, ensuring that the results were traceable and reusable.

[0029] S4: Apply random forest regression algorithm to correlate the crop nutrient content data set and the vegetation index map to model, and use the model to calculate the nutrient content of the target field to obtain the nutrient spatial distribution map; Further, the step S4 further comprises: Obtain the crop nutrient content data set and the vegetation index map, and perform spatial matching through GIS software to extract the sampling point number, coordinates, average value of vegetation index pixels, band ratio, texture features, and measured nutrient data to construct the modeling data set; Select the random forest regression algorithm for correlation modeling, and the model expression is: ; Wherein, represents the predicted nutrient content, T represents the number of decision trees, t represents the index value, represents the single decision tree prediction function, and x represents the data column in the modeling data set; Extract 70% of the data in the modeling data set as the training set to train the model, and determine the optimal hyperparameters through grid search with the minimum mean square error as the criterion; Based on the trained model, the nutrient content of the target field is inverted to generate an initial nutrient spatial distribution map; The other 30% of the independent samples in the modeling data set are used as a validation set. The model accuracy is verified by statistical verification indicators and residual space diagnosis. The statistical verification indicators include the determination coefficient and the root mean square error. The residual space diagnosis uses the Moran index. The specific formulas are as follows: Determination coefficient: ; Root mean square error: ; Wherein, represents the determination coefficient, the root mean square error, and the remaining parameters in the two formulas have the same physical meaning, is the measured nutrient content of the ith validation point, represents the nutrient content predicted by the model at the corresponding point, which is obtained from the initial nutrient space distribution map, represents the average of all nutrient content data in the validation set, and n represents the number of samples in the validation set; Moran index: ; Wherein, I is the Moran index, n represents the total number of residual points, i and j are two adjacent points, represents the residual value of the ith point, and the specific value is , represents the residual value of the jth point, and the calculation formula is the same as , represents the global average of the residual, and the specific value is , is the spatial weight matrix, which is generated by the distance decay function, and the specific value is , wherein dij is the Euclidean distance between points i and j; Based on the determination coefficient, the root mean square error and the Moran index, the predicted data calculated by the model is judged. If there is an aggregation deviation in the judgment result, the high estimation area is corrected. The specific correction formula is as follows: ; Wherein, represents the corrected predicted nutrient content, represents the original predicted nutrient content, is the local residual mean value, is the maximum measured nutrient content in the region; Finally, the initial nutrient space distribution map after correction is rendered into a color picture through the HSV color space model to obtain the nutrient space distribution map.

[0030] Specifically, the crop nutrient content dataset and the vegetation index map are obtained, wherein the crop nutrient content dataset contains the accurate coordinate positions of each sampling point and the corresponding nutrient data, and the vegetation index map contains the multi-band GeoTIFF file of NDVI or NDRE index. The crop nutrient content dataset and the vegetation index map are imported into the GIS software for spatial matching, and the point sampling tool is used to create a circular buffer area with a radius of 5 meters centered on the sampling point coordinates, and the average value of all vegetation index pixels in the buffer area is extracted, and the derived features are added to improve the sensitivity of the model, and the derived features include the band ratio and the texture feature, and the specific formula is as follows: Vegetation index pixel average value: wherein, represents the vegetation index pixel average value, n represents the number of vegetation index pixels, and i is an index value, represents the specific value of the i th vegetation index pixel; Band ratio: wherein, BD represents the band ratio, represents the near-infrared band surface reflectivity, represents the red band surface reflectivity.

[0031] Texture feature: wherein, represents the texture feature, represents the contrast of the near-infrared band gray level co-occurrence matrix, i represents the gray value of the reference pixel, j represents the gray value of the adjacent pixel, p(i,j) is the pixel gray level joint probability, represents the frequency of the gray combination (i,j) appearing, and represents the crown layer structure roughness.

[0032] The sampling point number, coordinates, vegetation index pixel average value, band ratio, texture feature and measured nutrient data are integrated to form a modeling dataset.

[0033] The random forest regression algorithm is selected for correlation modeling, and the model expression is as follows: wherein, represents the predicted nutrient content, T represents the number of decision trees, t represents an index value, and the specific value is 500, represents the single decision tree prediction function, and x represents the data column in the modeling dataset.

[0034] ​​​​Training was performed based on the pre-defined model. 70% of the samples in the modeling dataset were extracted by soil type as the training set. A grid search was performed to determine the optimal hyperparameters using the minimum mean squared error (MSE) criterion. The resulting tree depth was optimized to range from 3 to 15, with a minimum leaf node sample size of 1 to 10. The trained model was applied to pixel-level predictions for target fields. Vegetation indices were reorganized into a three-dimensional feature array with dimensions including rows, columns, and features. Predictions were input pixel by pixel into the model, generating an initial floating-point nutrient spatial distribution map. To eliminate random fluctuations in the model, a 5×5 pixel mean filter was applied, and non-arable land areas were removed using a cropland boundary vector mask.

[0035] 30% of the independent samples reserved in the modeling data set are used as the validation set to verify the model accuracy and calculate the coefficient of determination and root mean square error. The specific formulas are: Coefficient of determination: ; Root mean square error: ; in, represents the coefficient of determination, Root mean square error, the other parameters in the two formulas have the same physical meaning, is the measured nutrient content at the i-th verification point, Represents the nutrient content predicted by the corresponding point model, which is extracted from the initial nutrient spatial distribution map. represents the mean of all nutrient content data in the validation set, n represents the number of samples in the validation set, and when R² ≥ 0.75 and RMSE ≤ 0.35%, it indicates that the predicted data obtained by the model is accurate.

[0036] Since the coefficient of determination and root mean square error can only reflect the overall accuracy and cannot capture the spatial heterogeneity of the error, the residual space diagnosis is introduced to further verify the model. For the spatial residual distribution, the Moran index is used to test the spatial autocorrelation. The specific formula is: ; Among them, I is the Moran index, n represents the total number of residual points, i and j are two adjacent points, Represents the residual value of point i, the specific value is , Represents the residual value of point j, and the formula is obtained. same, Represents the global mean of the residual, reflecting the direction of system deviation, and the specific value is , is the spatial weight matrix, generated by the distance decay function, and the specific value is , where d ij is the Euclidean distance between point i and point j.

[0037] If I > 0.3 is detected, it is judged as an aggregation deviation, and correction needs to be implemented on the overestimation area. The determination criterion of the overestimation area is the area with a residual value less than -2σ, wherein σ is the global residual standard deviation. The specific correction formula is: ; wherein, represents the corrected predicted nutrient content, represents the original predicted nutrient content, is the local residual mean, is the maximum measured nutrient content in the area.

[0038] The final initial nutrient spatial distribution map after verification and correction is in the floating-point GeoTIFF format. Finally, the mapping of agronomic significance is realized through the HSV color space model. The area with a nutrient content less than 2.5% is rendered as red, indicating the nitrogen stress area. The area with a nutrient content of 2.5% to 3.2% is rendered as yellow, indicating the potential deficiency area. The area with a nutrient content greater than 3.2% is rendered as dark green, indicating the sufficient area. Finally, the complete nutrient spatial distribution map is obtained.

[0039] S5: Integrating the vegetation index map, the soil nutrient content dataset, the nutrient spatial distribution map and the historical yield data, applying the clustering analysis algorithm for spatial partitioning, dividing the target field block into M management units, determining the required fertilizer application amount and element abundance and deficiency index of each management unit, and generating the fertilizer ratio decision; Further, the step S5 further comprises: Integrating the vegetation index map, the soil nutrient content dataset, the nutrient spatial distribution map and the historical yield data, performing spatial registration, unifying the coordinate system and data standardization; Using the K-means++ clustering algorithm to realize the division of the management unit, and obtaining M homogeneous management units; Obtaining the target yield of each management unit based on the vegetation index map and the historical yield data, and the specific formula is: ; wherein, represents the target yield of the k unit, represents the average yield of the k unit in the past three years, and S represents the yield increase coefficient, represents the vegetation index of the unit, represents the health threshold of the vegetation index; Obtaining the soil available nutrient supply based on the soil nutrient content dataset, and the specific formula is: ; wherein, represents the soil available nutrient supply of the k unit e nutrient element, a soil nutrient content representing the kth unit e nutrient element, an available coefficient representing the e nutrient element, and G represents a conversion factor, indicating conversion from mg / kg units to kg / acre units; The soil available coefficient correction factor is obtained based on the soil nutrient content dataset and the nutrient spatial distribution map, and the specific formula is: ; wherein a soil crop nutrient transfer efficiency ratio representing the e nutrient element, and the specific value is , wherein a crop nutrient content representing the e nutrient element, a soil nutrient content representing the e nutrient element; The target yield, soil available nutrient supply, and soil available coefficient correction factor are obtained, and the fertilizer application amount is calculated by using the nutrient balance method, and the specific formula is: ; wherein a fertilizer application amount representing the kth unit e element, k represents the unit number, a total of M, e represents the nutrient element type, U e ×C k is the target fertilizer requirement, wherein U e represents the nutrient demand per unit yield of crops, C k represents the target yield of the kth unit, a soil available nutrient supply representing the kth unit e nutrient element, is a soil available coefficient correction factor, a fertilizer utilization rate representing the kth unit e nutrient element, represents a fertilizer efficiency adjustment coefficient, which is determined based on the soil leaf nutrient transfer efficiency ratio, represents the unit area; The fertilizer application amount is obtained, and the abundance and deficiency index of each element in each management unit is calculated, and the specific calculation formula is: ; wherein represents the fertilizer application amount, Line e represents the critical value of each element; Finally, the fertilizer ratio decision is generated based on the minimum nutrient law according to the fertilizer application amount and the element abundance and deficiency index.

[0040] Specifically, vegetation index maps, soil nutrient content datasets, nutrient spatial distribution maps, and historical yield data were obtained. The vegetation index map represents real-time crop growth and is generated from drone remote sensing imagery. The soil nutrient content dataset, generated through laboratory analysis combined with spatial interpolation, includes data on nitrogen, phosphorus, and potassium. The nutrient spatial distribution map, generated through inversion using a random forest model, includes crop nutrient content data. Historical yield data comes from a combine harvester yield monitoring system. Four key datasets with explicit spatial representation were integrated and uniformly input into GIS software for rigorous spatial registration. Using ground control point constraints, the coordinate system was moved to the EPSG:32650 projection system, and the pixel size was resampled to 1×1 meter to ensure accurate spatial alignment. Z-score normalization was used to address data dimensionality differences. Ultimately, a multi-source spatial data cube was generated, containing eight feature layers in depth: vegetation index, soil nitrogen, soil phosphorus, soil potassium, leaf nitrogen, leaf phosphorus, leaf potassium, and three-year average yield.

[0041] Based on the standardized multi-source spatial data cube, the K-means++ clustering algorithm is applied to achieve fine-grained field zoning. This method first avoids the random bias of traditional K-means by intelligently initializing the centroid selection, ensuring stable and reliable zoning results. In feature space, the algorithm measures the similarity between each pixel and the centroid based on the Euclidean distance, and performs an allocation and update cycle through multiple rounds of iteration: spatial pixels are dynamically classified into the nearest centroid cluster, and then the geometric center position within the cluster is recalculated. The iterative process continues until the centroid movement distance is less than a preset threshold, which is set to 0.001 units. At this point, the spatial pattern tends to be stable, and a zoning grid map is output. This map divides the target field into M homogeneous management units. The spectral, soil, nutrient, and yield characteristics within each unit are highly uniform, and the coefficient of variation is strictly controlled within 15%, which is significantly lower than the spatial fluctuation level of more than 35% in the original field.

[0042] For each management unit, the nutrient balance formula is used to calculate the fertilizer application amount and develop a personalized fertilization plan: ; in, represents the fertilizer application rate of the kth unit e nutrient element, k represents the unit number, a total of M, e represents the nutrient element type, determined by agronomic diagnosis as nitrogen, phosphorus, potassium, U e ×C k is the target fertilizer requirement, where U e Represents the nutrient requirement per unit crop yield, derived from variety trial data, C k represents the target output of the kth unit, represents the effective nutrient supply of the soil for the kth unit e nutrient element, a soil available coefficient correction factor, representing the fertilizer utilization rate of the kth unit e nutrient element, and the specific values are 40% for urea, 20% for phosphorus fertilizer, and 50% for potassium fertilizer, representing the fertilizer efficiency adjustment coefficient, when less than 0.8, the value is 1.2, and the value is 1 in other cases, representing the unit area; wherein the target yield C k is obtained according to the formula wherein representing the average yield of the kth unit in the past three years, and S represents the yield increase coefficient, and the specific value is 1.1-1.3, representing the vegetation index of the unit, representing the health threshold of the vegetation index; wherein the soil available nutrient supply amount is obtained according to the formula wherein representing the soil nutrient content of the kth unit e nutrient element, representing the available coefficient of the e nutrient element, and the specific values are 0.3 for nitrogen, 0.4 for phosphorus, and 0.5 for potassium, and G represents the conversion factor, indicating the conversion from mg / kg to kg / acre unit; wherein the soil available coefficient correction factor is obtained according to the formula wherein representing the soil crop nutrient transfer efficiency ratio of the e nutrient element, and the specific value is wherein, representing the crop nutrient content of the e nutrient element, representing the soil nutrient content of the e nutrient element.

[0043] After obtaining the fertilizer application amount, the fertilizer ratio decision is generated based on the minimum nutrient law, and the element abundance index of each management unit is calculated, and the specific calculation formula is wherein representing the fertilizer application amount, Line e representing the critical value of each element, and the critical value of nitrogen is 90 mg / kg, the critical value of phosphorus is 15 mg / kg, and the critical value of potassium is 100 mg / kg. For elements with Ie<80%, priority is given to supplementing. For example, when the element abundance index of nitrogen in unit k is 65% and the element abundance index of phosphorus is 110%, only nitrogen fertilizer needs to be supplemented.

[0044] S6: using GIS software to spatialize the decision results to obtain a digital fertilization prescription map.

[0045] Further, the step S6 further comprises: Based on the vector boundary of M management units generated by spatial clustering, a fertilization prescription thematic layer is created by GIS software, the fertilizer decision data is connected through attribute table association function, and the universal geodetic coordinate system is used to ensure the unity of spatial reference; Multi-level visual rendering is implemented to generate a digital fertilization prescription map, which includes fertilizer type expression, application amount intensity mapping and dynamic agronomic annotation.

[0046] Specifically, the fertilizer ratio decision is obtained, and the decision result is converted into a spatial and executable digital fertilization prescription map through the GIS platform. First, based on the vector boundary of M management units obtained by spatial clustering analysis, a fertilization prescription thematic layer is created in QGIS or ArcGIS Pro. The layer inherits all the geometric properties of the management unit, and dynamically connects the fertilizer ratio decision through the attribute table association function. In order to ensure accurate identification of the agricultural machinery system, the universal geodetic coordinate system is used, and the topological checking tool is used to verify that there is no overlap or gap in the unit boundary, and the boundary positioning error is strictly controlled within 0.3 meters. Then, multi-level visual rendering is implemented, which specifically includes: fertilizer type expression, using a composite symbol system, with a 45° blue diagonal line to represent the urea application area, an orange dot matrix to represent the phosphorus fertilizer area, and a red grid to represent the potassium fertilizer area. The three symbols are displayed in actual proportion, for example, if urea and phosphorus fertilizer need to be applied in a unit, the blue and orange interlaced diagonal dot matrix hybrid texture will be displayed; application amount intensity mapping, according to the pure nitrogen per mu amount, five color gradients are divided, light green marks the ecological protection area, representing 0-5 kg / mu, yellow indicates the optimization control area, representing 5-10 kg / mu, orange represents the conventional management area, representing 10-15 kg / mu, red warns the soil fertility improvement area, representing 15-20 kg / mu, and dark red highlights the capacity breakthrough area, representing more than 20 kg / mu, and the layer is overlaid without covering the base map through semi-transparent rendering; dynamic agronomic annotation, a text box is automatically generated at the center of each unit, displaying the customized fertilization formula, such as N:8.5 kg / mu, and an operation prompt label is hung at the boundary, for example, unit 7 applies 60% urea before September 15, the font size is dynamically adjusted according to the map scale to ensure that the text is clear and identifiable when viewed on a mobile terminal.

[0047] The final prescription map converts the agronomic decision into a spatially locatable, measurable, and traceable geographical entity, realizing the precision management mode.

[0048] Embodiment two, based on the same inventive concept as the fertilizer ratio management method combined with remote sensing data analysis in the preceding embodiments, the present application also provides a fertilizer ratio management system combined with remote sensing data analysis, please refer to the attached Figure 2 , the system comprises: The remote sensing image acquisition module 11 is configured to use a UAV to shoot an original data set of crops in a key growth period of a target field, and to obtain a remote sensing image set by preprocessing the original data set, wherein the preprocessing includes radiation calibration, atmospheric correction, geometric correction, and a cloud mask; The vegetation index calculation module 12 is configured to calculate a vegetation index according to the remote sensing image set, and to generate a vegetation index map in combination with GIS software. The soil and crop nutrient analysis module 13 is configured to select representative points of the target field based on a soil type of the target field, historical yield data, and the vegetation index map, to collect soil and crop samples, to analyze key nutrient content of the samples, and to obtain a soil nutrient content data set and a crop nutrient content data set. The nutrient inversion modeling module 14 is configured to use a random forest regression algorithm to model the crop nutrient content data set and the vegetation index map, to use the model to calculate nutrient inversion of the target field, and to obtain a nutrient spatial distribution map. The precise zoning and fertilization decision module 15 is configured to comprehensively use the vegetation index map, the soil nutrient content data set, the nutrient spatial distribution map, and the historical yield data, to use a clustering analysis algorithm to perform spatial zoning, to divide the target field into M management units, to determine a required fertilizer application amount and an element abundance deficiency index of each management unit, and to generate a fertilizer ratio decision. The digital fertilization prescription generation module 16 is configured to use GIS software to spatially express the decision result, and to obtain a digital fertilization prescription map.

[0049] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not contradict each other, they should be considered as the scope of the disclosure.

[0050] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fertilizer ratio management method combined with remote sensing data analysis, characterized in that: The method comprises: Using drones to capture raw datasets of crops in target fields during their critical growth period, the raw datasets are preprocessed to obtain remote sensing image sets. The preprocessing includes radiometric calibration, atmospheric correction, geometric correction, and cloud masking. Calculate vegetation index based on remote sensing image sets and generate vegetation index maps using GIS software; Based on the soil type, historical yield data, and vegetation index map of the target field, representative points of the target field were selected, soil and crop samples were collected, and key nutrient content of the samples was analyzed to obtain soil nutrient content datasets and crop nutrient content datasets; The random forest regression algorithm was applied to establish a correlation model between the crop nutrient content dataset and the vegetation index map. The model was then used to perform nutrient inversion calculations on the target fields to obtain a nutrient spatial distribution map. By integrating vegetation index maps, soil nutrient content datasets, nutrient spatial distribution maps, and historical yield data, a cluster analysis algorithm was applied to perform spatial partitioning, dividing the target field into M management units. The fertilizer application rate and element abundance and deficiency index required for each management unit were determined to generate fertilizer ratio decisions. GIS software is used to spatially express the decision-making results and obtain a digital fertilization prescription map.

2. The fertilizer ratio management method combined with remote sensing data analysis according to claim 1, characterized in that: Access remote sensing imagery collections, including: Evenly select N ground control points in the target field, spray L-shaped marks and record the coordinate positions simultaneously; The flight parameters of the drone are set based on the geographical conditions of the target field, and the original data set of the target field is collected during the key crop growth period. The drone is equipped with a multispectral sensor, and the original data set includes the original DN image set and the flight parameter log. Obtain the original data set, perform radiometric calibration, and convert the original DN value into apparent reflectance by combining the sensor calibration file and the flight parameter log to obtain the apparent reflectance image set; Based on the apparent reflectance image set, the empirical linear method assisted by the ground calibration plate is used to convert the apparent reflectance into the surface reflectance to obtain the surface reflectance image set; The surface reflectance image set is roughly stitched using POS data and SIFT feature points to generate an initial orthophoto image set. A second-order polynomial transformation is performed on the coordinates of the ground control points, and bilinear interpolation resampling is used to output an orthophoto reflectance image set in a projected coordinate system. Cloud mask processing is performed based on the spectral characteristics of the orthoreflectance image set to remove invalid areas and finally generate a remote sensing image set.

3. The fertilizer ratio management method combined with remote sensing data analysis according to claim 1, characterized in that: Generate vegetation index maps, including: The vegetation index is calculated based on the remote sensing image set and the crop growth stage. If the crop is in the early to mid-growth stage, the vegetation index uses the normalized difference vegetation index. If the crop is in the mid-to-late growth stage, the vegetation index uses the red edge normalized index. The specific calculation formula of the normalized difference vegetation index is: ； in, represents the normalized difference vegetation index, represents the surface reflectance in the near-infrared band, Represents the surface reflectance in the red light band; The specific calculation formula of the red edge normalization index is: ； Where NDRE stands for Normalized Red Edge Index, represents the surface reflectance in the near-infrared band, Represents the surface reflectance in the red edge band; Performing spatial optimization on the calculated vegetation index, wherein the spatial optimization includes spatial relationship matching and clipping operations; Statistical features are obtained based on the spatially optimized vegetation index. Grading thresholds are set according to the statistical features. Different threshold areas are mapped into asymptotic color bands using the HSV color space model to generate a vegetation index map. The statistical features include minimum value, maximum value and quartiles.

4. The fertilizer ratio management method combined with remote sensing data analysis according to claim 1, characterized in that: Obtain spatial distribution maps of nutrients, including: Obtain crop nutrient content datasets and vegetation index maps, perform spatial matching using GIS software, extract sampling point numbers, coordinates, average values ​​of vegetation index pixels, band ratios, texture features, and measured nutrient data to construct a modeling dataset; The random forest regression algorithm is used for association modeling, and the model expression is: ； in, Represents the predicted nutrient content, T represents the number of decision trees, and t represents the index value. Represents a single decision tree prediction function, and x represents the data column in the modeling dataset; 70% of the data in the modeling dataset was extracted as the training set to train the model, and the optimal hyperparameters were determined by grid search with the minimum mean square error as the criterion; Based on the trained model, the nutrient content of the target field is inverted to generate an initial nutrient spatial distribution map; The other 30% independent samples in the modeling data set are used as the validation set. The model accuracy is verified by statistical validation indicators and residual space diagnosis. Among them, the statistical validation indicators include the coefficient of determination and the root mean square error, and the residual space diagnosis uses the Moran index. The specific formulas are: Coefficient of determination: ; Root mean square error: ; in, represents the coefficient of determination, Root mean square error, the other parameters in the two formulas have the same physical meaning, y i is the measured nutrient content at the i-th verification point, Represents the nutrient content predicted by the corresponding point model, which is extracted from the initial nutrient spatial distribution map. represents the mean of all nutrient content data in the validation set, and n represents the number of samples in the validation set; Moran Index: ; Among them, I is the Moran index, n represents the total number of residual points, i and j are two adjacent points, Represents the residual value of point i, the specific value is , Represents the residual value of point j, and the formula is obtained. same, Represents the global mean of the residual, and the specific value is , is the spatial weight matrix, generated by the distance decay function, and the specific value is , where d ij is the Euclidean distance between point i and point j; The predicted data calculated by the model are judged based on the coefficient of determination, root mean square error and Moran's index. If there is a clustering deviation in the judgment result, the overestimated area is corrected. The specific correction formula is: ； in, represents the corrected predicted nutrient content, represents the original predicted nutrient content, is the local residual mean, is the maximum measured nutrient content in the region; Finally, the corrected initial nutrient spatial distribution map was rendered into a color image using the HSV color space model to obtain the nutrient spatial distribution map.

5. The fertilizer ratio management method combined with remote sensing data analysis according to claim 1, characterized in that: Generate fertilizer ratio decisions, including: Integrate vegetation index maps, soil nutrient content datasets, nutrient spatial distribution maps, and historical yield data, perform spatial registration, unify coordinate systems, and standardize data; The K-means++ clustering algorithm is used to realize the division of management units and obtain M homogeneous management units; The target yield of each management unit is obtained based on the vegetation index map and historical yield data. The specific formula is: ； in, represents the target output of the kth unit, represents the average output of unit k in the past three years, S represents the production increase coefficient, Represents the vegetation index of the unit, represents the health threshold of vegetation index; The effective nutrient supply of soil is obtained based on the soil nutrient content dataset. The specific formula is: ； in, Represents the kth unit The effective nutrient supply of soil for various nutrient elements, Represents the kth unit Soil nutrient content of nutrient elements, represents the effective coefficient of the nutrient element e, G represents the conversion factor, which means converting the mg / kg unit into kg / mu unit; The soil effectiveness coefficient correction factor is obtained based on the soil nutrient content dataset and the nutrient spatial distribution map. The specific formula is: ； in Represents the soil-crop nutrient transfer efficiency ratio of e nutrient element, the specific value is ,in, Represents the crop nutrient content of e nutrient element, represents the soil nutrient content of e nutrient element; Obtain the target yield, effective soil nutrient supply, and soil effectiveness coefficient correction factor, and use the nutrient balance method to calculate the fertilizer application rate. The specific formula is: ； in, represents the fertilizer application amount of element e in unit k, k represents the unit number, totaling M, e represents the nutrient element type, U e ×C k is the target fertilizer requirement, where U e Represents the nutrient requirement per unit crop yield, C k represents the target output of the kth unit, represents the effective nutrient supply of the soil for the kth unit e nutrient element, is the soil effectiveness coefficient correction factor, represents the fertilizer utilization rate of the kth unit e nutrient element, represents the fertilizer efficiency adjustment coefficient, which is determined based on the soil-leaf nutrient transfer efficiency ratio. represents the unit area; Obtain the fertilizer application rate and calculate the abundance and deficiency index of each element in each management unit. The specific calculation formula is: ； in Represents the amount of fertilizer applied, Line e Represents the critical value of each element; Finally, the fertilizer ratio decision is generated based on the minimum nutrient law according to the fertilizer application amount and element abundance and deficiency index.

6. The fertilizer ratio management method combined with remote sensing data analysis according to claim 1, characterized in that: Get a digital fertilization prescription map, including: Based on the vector boundaries of M management units generated by spatial clustering, GIS software was used to create a thematic layer of fertilizer prescriptions. Fertilizer decision data was linked through the attribute table association function, and a universal geodetic coordinate system was used to ensure a unified spatial reference. Multi-level visual rendering is implemented to generate a digital fertilization prescription map, which includes fertilizer type expression, application intensity mapping and dynamic agronomic annotation.

7. The fertilizer ratio management system combined with remote sensing data analysis is characterized by: The system is used to implement the fertilizer ratio management method combined with remote sensing data analysis as described in any one of claims 1 to 6, and the system includes: A remote sensing image acquisition module is used to use a drone to capture a raw data set of crops in a target field during its critical growth period, and preprocess the raw data set to obtain a remote sensing image set. The preprocessing includes radiometric calibration, atmospheric correction, geometric correction, and cloud masking. A vegetation index calculation module is used to calculate the vegetation index based on the remote sensing image set and generate a vegetation index map in combination with GIS software; A soil and crop nutrient analysis module, which is used to select representative points in the target field based on the target field soil type, historical yield data, and vegetation index map, collect soil and crop samples, analyze the samples for key nutrient content, and obtain soil nutrient content datasets and crop nutrient content datasets; A nutrient inversion modeling module is used to apply a random forest regression algorithm to perform correlation modeling on a crop nutrient content dataset and a vegetation index map, and to perform nutrient inversion calculations on target fields using the model to obtain a nutrient spatial distribution map; A precise zoning and fertilization decision module, which integrates vegetation index maps, soil nutrient content datasets, nutrient spatial distribution maps, and historical yield data, applies a cluster analysis algorithm to perform spatial zoning, divides the target field into M management units, determines the fertilizer application rate and element abundance and deficiency index required for each management unit, and generates fertilizer ratio decisions; The digital fertilization prescription generation module is used to spatially express the decision results using GIS software to obtain a digital fertilization prescription map.

Images