Crop nitrogen nutrition monitoring and diagnosis method and device based on multispectral remote sensing image, medium and product
By using multispectral remote sensing imagery and nitrogen nutrient diagnostic models, the problem of large-scale crop nitrogen nutrient monitoring and diagnosis has been solved, enabling real-time, non-destructive, and low-cost nitrogen nutrient monitoring. This has improved crop yield and quality, reduced fertilizer use, and protected the environment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2024-11-21
- Publication Date
- 2026-05-22
AI Technical Summary
Existing technologies cannot achieve real-time, non-destructive, and low-cost monitoring and diagnosis of nitrogen nutrition in crops over a wide range of areas, resulting in inaccurate nitrogen fertilizer management and affecting crop yield and quality.
By employing multispectral remote sensing imagery technology, multispectral reflectance images of crops, soil-regulated vegetation index raster maps, and near-infrared-red edge index raster maps are obtained. Combined with a nitrogen nutrition diagnostic model, real-time monitoring and diagnosis of crop nitrogen nutrition can be achieved.
It enables real-time, non-destructive, and low-cost monitoring of crop nitrogen nutrition, providing precise fertilization management decisions, improving crop yield and quality, reducing fertilizer use, and protecting the environment.
Smart Images
Figure CN122072229A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of modern agricultural intelligent technology, and in particular to a method, device, medium and product for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing images. Background Technology
[0002] Nitrogen is a crucial limiting factor for crop yield and quality. Due to differences in crop physiological characteristics and the diversity of field soil environments, crop nitrogen requirements vary significantly in time and space throughout their growth cycle. Insufficient or absent nitrogen application can impair normal crop growth and development, leading to decreased yield and quality. However, current nitrogen fertilizer management tends to apply excessive amounts of chemical fertilizer during the basal fertilizer stage, which is not only detrimental to crop growth but also impacts the soil and water environment. Studies have shown that rationally allocating nitrogen application based on the crop's nitrogen requirements at different stages can improve nitrogen fertilizer utilization efficiency. Therefore, real-time monitoring and diagnosis of crop nitrogen nutrient status are crucial for making accurate fertilization management decisions in actual production.
[0003] Nitrogen concentration within a crop decreases as dry matter increases; this phenomenon is known as nitrogen dilution. A classic method for diagnosing crop nitrogen nutrition is using a critical nitrogen concentration dilution curve relating dry matter to nitrogen concentration. The critical nitrogen concentration is the minimum nitrogen concentration required for crop growth and dry matter formation at a specific growth stage. If the actual nitrogen concentration in the crop is below the critical nitrogen concentration, it indicates nitrogen deficiency. Studies have shown that this method is feasible for guiding precise nitrogen management. However, traditional methods for obtaining crop dry matter and actual nitrogen concentration require destructive sampling and chemical analysis, which is not only time-consuming and labor-intensive but also fails to provide spatial variability information for dry matter and actual nitrogen concentration, making them unsuitable for large-scale nitrogen nutrition monitoring and diagnosis. Summary of the Invention
[0004] The purpose of this application is to provide a method, device, medium, and product for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing images, in order to solve the problem of the inability to perform large-scale nitrogen nutrition monitoring and diagnosis.
[0005] To achieve the above objectives, this application provides the following solution:
[0006] In a first aspect, this application provides a method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery, including:
[0007] Acquire multispectral remote sensing images of the area to be measured and the target radiometric correction plate; the area to be measured is a field planted with crops, and the target radiometric correction plate is a radiometric correction plate set in the area to be measured; the multispectral remote sensing images include: grayscale images of the red band, grayscale images of the red edge band, and grayscale images of the near-infrared band.
[0008] Based on the multispectral remote sensing images of the area to be measured and the multispectral remote sensing images of the target radiometric correction plate, the multispectral reflectance image of the area to be measured is determined; the multispectral reflectance image includes: a reflectance raster map of the red band, a reflectance raster map of the red edge band, and a reflectance raster map of the near-infrared band.
[0009] Based on the multispectral reflectance image of the area to be measured, the soil-modified vegetation index raster map of the area to be measured is determined.
[0010] Based on the soil-regulated vegetation index raster map of the area to be tested, the vegetation canopy area of the area to be tested is determined.
[0011] Based on the reflectance grid map of the red-edge band and the reflectance grid map of the near-infrared band of the region to be measured, the near-infrared-red-edge index grid map of the region to be measured is determined.
[0012] The canopy coverage of the area to be tested is determined based on the number of pixels in the vegetation canopy area and the number of pixels in the multispectral remote sensing image of the area to be tested.
[0013] The canopy coverage of the area to be tested is input into the nitrogen nutrition diagnostic model to obtain the optimal near-infrared-red edge index confidence interval of the area to be tested; the nitrogen nutrition diagnostic model is obtained by fitting the average near-infrared-red edge index of the vegetation canopy area in the target area at multiple growth stages determined according to the optimal nitrogen application rate and the canopy coverage.
[0014] Based on the near-infrared-red edge index raster map of the area to be tested and the optimal near-infrared-red edge index confidence interval, the crop nitrogen nutrient deficit distribution map of the area to be tested is determined.
[0015] Optionally, the process of determining the nitrogen nutrition diagnostic model includes:
[0016] Different actual nitrogen application rates were applied to different sampling areas in the experimental field.
[0017] To obtain the cost per unit of nitrogen fertilizer and the crop yield after the actual nitrogen application rate was applied to each sampling area;
[0018] The optimal nitrogen application rate was determined based on the cost per unit of nitrogen fertilizer and the crop yield after actual nitrogen application in each sampling area.
[0019] The sampling area corresponding to the actual nitrogen application rate that has the smallest absolute value of the difference from the optimal nitrogen application rate is determined as the target area;
[0020] Acquire multispectral remote sensing images of the experimental radiation correction plate and the target area at different growth stages; the experimental radiation correction plate is a radiation correction plate set in the experimental field.
[0021] Based on the multispectral remote sensing images of the target area and the multispectral remote sensing images of the experimental radiometric correction plate, the multispectral reflectance image of the target area in the current period is determined.
[0022] Based on the multispectral reflectance image of the target area in the current period, determine the soil-modified vegetation index raster map of the target area in the current period.
[0023] Based on the soil-regulated vegetation index raster map of the target area in the current period, the vegetation canopy area of the target area in the current period is determined.
[0024] Based on the reflectance raster maps of the target area in the red-edge band and the near-infrared band in the current period, the near-infrared-red-edge index raster map of the target area in the current period is determined.
[0025] Based on the near-infrared-red edge index raster map and vegetation canopy area of the target area in the current period, determine the average near-infrared-red edge index of the vegetation canopy area in the target area in the current period;
[0026] The canopy coverage of the target area at the current time is determined based on the number of pixels in the vegetation canopy area of the target area at the current time and the number of pixels in the multispectral remote sensing image of the target area at the current time.
[0027] Based on the 95% confidence interval, the average near-infrared red edge index and canopy coverage of the vegetation canopy area in the target region at each growth stage were fitted to obtain the nitrogen nutrition diagnostic model.
[0028] Optionally, the area to be tested or the target area can be defined as the current area, and the target radiation correction plate or the test radiation correction plate can be defined as the current radiation correction plate;
[0029] Based on the multispectral remote sensing image of the current area and the multispectral remote sensing image of the current radiometrically corrected plate, determine the multispectral reflectance image of the current area, including:
[0030] The average gray value of each pixel in the grayscale image of the red band of the current radiation correction plate is determined as the average gray value of the red band.
[0031] Based on the gray values of each pixel in the grayscale image of the red band of the current region and the average gray value of the red band, the reflectance of each pixel in the grayscale image of the current region is determined, thereby obtaining the reflectance raster map of the red band of the current region.
[0032] The average gray value of each pixel in the grayscale image of the red-edge band of the current radiation correction plate is determined as the average gray value of the red-edge band.
[0033] Based on the gray values of each pixel in the grayscale image of the red-edge band of the current region and the average gray value of the red-edge band, the reflectance of each pixel in the grayscale image of the current region is determined, thereby obtaining the reflectance raster map of the red-edge band of the current region.
[0034] The average gray value of each pixel in the grayscale image of the current radiation correction plate in the near-infrared band is determined as the near-infrared band grayscale average value.
[0035] Based on the grayscale values of each pixel in the grayscale image of the near-infrared band of the current region and the average grayscale value of the near-infrared band, the reflectance of each pixel in the grayscale image of the near-infrared band of the current region is determined, thereby obtaining the reflectance raster map of the near-infrared band of the current region.
[0036] Optionally, the area to be tested or the target area can be defined as the current area;
[0037] Based on the multispectral reflectance image of the current area, determine the soil-modified vegetation index raster map of the current area, including:
[0038] Based on the reflectance of each pixel in the red band reflectance raster map and the reflectance of the corresponding pixel in the near-infrared band reflectance raster map of the current region, the soil-regulated vegetation index of each pixel is determined, thereby obtaining the soil-regulated vegetation index raster map of the current region.
[0039] Optionally, the area to be tested or the target area can be defined as the current area;
[0040] Based on the current region's soil-regulated vegetation index raster map, the vegetation canopy area of the current region is determined, including:
[0041] The soil-regulated vegetation index and index threshold of each pixel in the current region's soil-regulated vegetation index raster map are compared.
[0042] Pixels whose soil-regulated vegetation index is greater than the index threshold are identified as pixels in the vegetation canopy region of the current area.
[0043] The vegetation canopy region of the current region is determined based on all pixels of the vegetation canopy region of the current region.
[0044] Optionally, the area to be tested or the target area can be defined as the current area;
[0045] Based on the reflectance raster maps of the red-edge band and near-infrared band of the current region, the near-infrared-red-edge index raster map of the current region is determined, including:
[0046] Based on the reflectance of each pixel in the reflectance raster of the red-edge band and the reflectance of the corresponding pixel in the reflectance raster of the near-infrared band of the current region, the near-infrared-red-edge index of each pixel is determined, thereby obtaining the near-infrared-red-edge index raster of the current region.
[0047] Optionally, based on the near-infrared-red edge index raster map of the area to be tested and the optimal near-infrared-red edge index confidence interval, a crop nitrogen nutrient deficit distribution map of the area to be tested is determined, including:
[0048] Based on the near-infrared-red edge index of each pixel in the near-infrared-red edge index raster image of the area to be tested and the confidence interval of the optimal near-infrared-red edge index of the area to be tested, the nitrogen nutrient deficiency judgment result corresponding to each pixel is determined; the nitrogen nutrient deficiency judgment result is that the crop is nitrogen deficient or the crop is not nitrogen deficient.
[0049] Based on the nitrogen nutrient deficit assessment results corresponding to all pixels, a crop nitrogen nutrient deficit distribution map of the test area is drawn.
[0050] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery as described in any of the preceding claims.
[0051] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing images as described in any of the above claims.
[0052] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery as described in any of the above claims.
[0053] According to the specific embodiments provided in this application, the following technical effects are disclosed:
[0054] This application discloses a method, device, medium, and product for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery. First, multispectral remote sensing images of the area to be monitored and the target radiometrically corrected plate are acquired. Based on the multispectral remote sensing images of the area to be monitored and the target radiometrically corrected plate, the multispectral reflectance image of the area to be monitored is determined. Second, based on the multispectral reflectance image of the area to be monitored, a soil-regulated vegetation index (SVR) raster map of the area to be monitored is determined. Based on the SVR map of the area to be monitored, the vegetation canopy area of the area to be monitored is determined. Then, based on the red light intensity of the area to be monitored... The reflectance raster maps of the edge band and near-infrared band are used to determine the near-infrared-red-edge index raster map of the area to be measured. Then, based on the number of pixels in the vegetation canopy area and the number of pixels in the multispectral remote sensing image of the area, the canopy coverage of the area is determined. Next, the canopy coverage of the area is input into the nitrogen nutrient diagnostic model to obtain the optimal near-infrared-red-edge index confidence interval for the area. Finally, based on the near-infrared-red-edge index raster map and the optimal near-infrared-red-edge index confidence interval, the crop nitrogen nutrient deficiency distribution map of the area is determined. This application utilizes multispectral remote sensing imagery and a nitrogen nutrient diagnostic model to achieve real-time monitoring and diagnosis of crop nitrogen deficiency. It has the advantages of real-time operation, non-destructive nature, and low cost, providing precise fertilization management decision support for agricultural production, which is beneficial for improving crop yield and quality, reducing fertilizer use, and protecting the environment. Attached Figure Description
[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0056] Figure 1 A schematic diagram of a crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery provided in an embodiment of this application;
[0057] Figure 2 This is a schematic diagram illustrating the different actual nitrogen application rates applied to each sampling area.
[0058] Figure 3 This is a schematic diagram of the fitted curve;
[0059] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation
[0060] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0061] The purpose of this application is to provide a method, device, medium, and product for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing images, aiming to achieve large-scale monitoring and diagnosis of crop nitrogen nutrition.
[0062] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0063] In one exemplary embodiment, such as Figure 1 As shown, the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery in this embodiment includes:
[0064] Step 1: Acquire multispectral remote sensing images of the area to be measured and the target radiometric correction plate.
[0065] The area to be measured is a field where crops are grown, the target radiometric correction plate is a radiometric correction plate set in the area to be measured, and the multispectral remote sensing image includes: grayscale image of the red band, grayscale image of the red edge band and grayscale image of the near-infrared band.
[0066] Specifically, multispectral remote sensing images are acquired using multispectral cameras mounted on drones.
[0067] Step 2: Based on the multispectral remote sensing image of the area to be measured and the multispectral remote sensing image of the target radiometric correction plate, determine the multispectral reflectance image of the area to be measured.
[0068] The multispectral reflectance imagery includes: a reflectance raster in the red band, a reflectance raster in the red-edge band, and a reflectance raster in the near-infrared band.
[0069] Step 3: Based on the multispectral reflectance image of the area to be measured, determine the soil-modified vegetation index raster map of the area to be measured.
[0070] Step 4: Determine the vegetation canopy area of the test area based on the soil-adjusted vegetation index raster map of the test area.
[0071] Step 5: Based on the reflectance grid map of the red-edge band and the reflectance grid map of the area to be measured, determine the near-infrared-red-edge index grid map of the area to be measured.
[0072] Step 6: Determine the canopy coverage of the area to be tested based on the number of pixels in the vegetation canopy area and the number of pixels in the multispectral remote sensing image of the area to be tested.
[0073] Step 7: Input the canopy coverage of the area to be tested into the nitrogen nutrition diagnostic model to obtain the optimal near-infrared-red edge index confidence interval for the area to be tested.
[0074] Among them, the nitrogen nutrition diagnostic model is obtained by fitting the average near-infrared red edge index of the vegetation canopy area and the canopy coverage of the target area at multiple growth stages determined according to the optimal nitrogen application rate.
[0075] As an optional implementation, step 7, the process of determining the nitrogen nutrition diagnostic model, includes:
[0076] Step 701: Apply different actual nitrogen application rates to each sampling area in the experimental field.
[0077] Specifically, the crops in the experimental plots were the same as those in the test area. For example... Figure 2 As shown, based on the nitrogen requirement characteristics of the crop, five different actual nitrogen application rates (N0 to N4) were set for each sampling area in the experimental field, and three sampling areas were set for each actual nitrogen application rate.
[0078] The method for setting the values of the five actual nitrogen application amounts is as follows: Based on the nitrogen nutrition characteristics of the crop variety, the amount of N4 can be determined as X kg / hm by consulting literature or according to the experience of local farmers. Then, under normal circumstances, the fertilizer application amounts of N0 to N3 can be set as 0, 1 / 4×X kg / hm, 1 / 2×X kg / hm and 3 / 4×X kg / hm, respectively.
[0079] Step 702: Obtain the cost per unit of nitrogen fertilizer and the crop yield after the actual nitrogen application rate in each sampling area.
[0080] Step 703: Determine the optimal nitrogen application rate based on the cost per unit of nitrogen fertilizer and the crop yield after the actual nitrogen application rate treatment in each sampling area.
[0081] Specifically, step 703 includes:
[0082] Step 7031: Fit the crop yield and actual nitrogen application rate of each sampling area after different actual nitrogen application rates. The fitting function is as follows:
[0083] FY = -a × N 2 +b×N+c.
[0084] Where FY represents the crop yield of the sampling area; a, b, and c are constants of the fitting function; and N represents the actual nitrogen application rate.
[0085] Step 7032: Differentiate the above function to obtain the additional yield resulting from each additional unit of nitrogen fertilizer input. The calculation formula is:
[0086]
[0087] in, This is the sign for a partial derivative.
[0088] Step 7033: Based on the fact that the economic benefit generated by each additional unit of nitrogen fertilizer equals the cost of one unit of nitrogen fertilizer, the optimal nitrogen application rate is obtained. The calculation formula is as follows:
[0089]
[0090] Among them, P p The price per unit of output; The optimal nitrogen application rate corresponds to N' represents the optimal nitrogen application rate; P N Cost per unit of nitrogen fertilizer.
[0091] Step 704: The sampling area corresponding to the actual nitrogen application rate with the smallest absolute value of the difference from the optimal nitrogen application rate is determined as the target area.
[0092] Step 705: Acquire multispectral remote sensing images of the experimental radiation correction plate and the target area at different growth stages; the experimental radiation correction plate is a radiation correction plate set in the experimental field.
[0093] Step 706: Based on the multispectral remote sensing image of the target area in the current period and the multispectral remote sensing image of the experimental radiometric correction plate, determine the multispectral reflectance image of the target area in the current period.
[0094] As an optional implementation, in step 2 or step 706, the area to be tested or the target area is determined as the current area, and the target radiation correction plate or the test radiation correction plate is determined as the current radiation correction plate.
[0095] Based on the multispectral remote sensing image of the current area and the multispectral remote sensing image of the current radiometrically corrected plate, determine the multispectral reflectance image of the current area, including:
[0096] The average gray value of each pixel in the grayscale image of the red band of the current radiation correction plate is determined as the average grayscale value of the red band.
[0097] Based on the gray values of each pixel in the grayscale image of the red band of the current region and the average gray value of the red band, the reflectance of each pixel in the grayscale image of the current region is determined, thereby obtaining the reflectance raster map of the red band of the current region.
[0098] Specifically, the formula for calculating the reflectance of any pixel in the red band reflectance raster of the current region is:
[0099]
[0100] Among them, R ref R represents the reflectance of pixels in the red band reflectance raster for the current region. DN，field R represents the grayscale value of the pixels in the red band of the current region's grayscale image; DN，panel ρ is the average gray value of the red band; R This represents the inherent red band reflectivity of the current radiation correction plate.
[0101] The average gray value of each pixel in the grayscale image of the red-edge band of the current radiation correction plate is determined as the average grayscale value of the red-edge band.
[0102] Based on the gray values of each pixel in the grayscale image of the red-edge band of the current region and the average gray value of the red-edge band, the reflectance of each pixel in the grayscale image of the current region's red-edge band is determined, thereby obtaining the reflectance raster map of the current region's red-edge band.
[0103] Specifically, the formula for calculating the reflectance of any pixel in the reflectance raster of the red-edge band of the current region is:
[0104]
[0105] Among them, RE ref RE represents the reflectance of pixels in the red-edge band of the current region in the raster image; DN，field RE represents the grayscale value of the pixels in the red-edge band of the current region's grayscale image. DN，panel ρ is the average gray value of the red-edge band. RE This represents the inherent red-edge reflectivity of the current radiation correction plate.
[0106] The average gray value of each pixel in the grayscale image of the near-infrared band of the current radiation correction plate is determined as the near-infrared band grayscale average value.
[0107] Based on the grayscale values of each pixel in the grayscale image of the near-infrared band of the current region and the average grayscale value of the near-infrared band, the reflectance of each pixel in the grayscale image of the near-infrared band of the current region is determined, thereby obtaining the reflectance raster map of the near-infrared band of the current region.
[0108] Specifically, the formula for calculating the reflectance of any pixel in the near-infrared reflectance raster of the current region is:
[0109]
[0110] Among them, NIRref The reflectance of pixels in the near-infrared (NIR) band reflectance raster for the current region; DN，field The grayscale values of the pixels in the near-infrared band of the current region; NIR DN，panel The average grayscale value in the near-infrared band; ρ NIR This represents the inherent near-infrared reflectivity of the current radiation correction plate.
[0111] Step 707: Based on the multispectral reflectance image of the target area in the current period, determine the soil-modified vegetation index raster map of the target area in the current period.
[0112] As an optional implementation, in step 3 or step 707, the area to be tested or the target area is determined as the current area.
[0113] Based on the multispectral reflectance image of the current area, determine the soil-modified vegetation index raster map of the current area, including:
[0114] Based on the reflectance of each pixel in the red band reflectance raster map and the reflectance of the corresponding pixel in the near-infrared band reflectance raster map of the current region, the soil-regulated vegetation index of each pixel is determined, thereby obtaining the soil-regulated vegetation index raster map of the current region.
[0115] Specifically, the formula for calculating the soil-regulated vegetation index of any pixel in the soil-regulated vegetation index raster map is as follows:
[0116]
[0117] OSAVI represents the soil-regulated vegetation index of a pixel in the soil-regulated vegetation index raster.
[0118] Step 708: Based on the soil-regulated vegetation index raster map of the target area in the current period, determine the vegetation canopy area of the target area in the current period.
[0119] As an optional implementation, in step 4 or step 708, the area to be tested or the target area is determined as the current area.
[0120] Based on the current region's soil-regulated vegetation index raster map, the vegetation canopy area of the current region is determined, including:
[0121] The soil-regulated vegetation index and index threshold of each pixel in the current region's soil-regulated vegetation index raster are compared.
[0122] Pixels whose soil-regulated vegetation index is greater than the index threshold are identified as pixels in the vegetation canopy region of the current area.
[0123] The vegetation canopy region of the current region is determined based on all pixels of the vegetation canopy region of the current region.
[0124] Specifically, the index threshold is generally set to 0.25 to 0.45.
[0125] Step 709: Based on the reflectance raster map of the red-edge band and the reflectance raster map of the target area in the current period, determine the near-infrared-red-edge index raster map of the target area in the current period.
[0126] As an optional implementation, in step 5 or step 709, the area to be tested or the target area is determined as the current area.
[0127] Based on the reflectance raster maps of the red-edge band and near-infrared band of the current region, the near-infrared-red-edge index raster map of the current region is determined, including:
[0128] Based on the reflectance of each pixel in the reflectance raster of the red-edge band and the reflectance of the corresponding pixel in the reflectance raster of the near-infrared band of the current region, the near-infrared-red-edge index of each pixel is determined, thereby obtaining the near-infrared-red-edge index raster of the current region.
[0129] Specifically, the formula for calculating the near-infrared-red edge index of any pixel in the near-infrared-red edge index raster image is as follows:
[0130]
[0131] Wherein, RRE is the near-infrared-red edge index of a pixel in the near-infrared-red edge index raster.
[0132] Step 710: Based on the near-infrared-red edge index raster map and vegetation canopy area of the target area in the current period, determine the average near-infrared-red edge index of the vegetation canopy area in the target area in the current period.
[0133] Specifically, the average value of the near-infrared-red edge index of each pixel in the near-infrared-red edge index raster of the target area in the current period is calculated to obtain the average value of the near-infrared-red edge index of the vegetation canopy area in the target area in the current period.
[0134] Step 711: Determine the canopy coverage of the target area in the current period based on the number of pixels in the vegetation canopy area of the target area in the current period and the number of pixels in the multispectral remote sensing image of the target area in the current period.
[0135] Specifically, the formula for calculating canopy coverage is:
[0136]
[0137] Where CC represents the number of pixels in the vegetation canopy region of the target area; P c P represents the number of pixels in the vegetation canopy area of the target region. ROI The number of pixels in the multispectral remote sensing image of the target area.
[0138] Step 712: Based on the 95% confidence interval, fit the average near-infrared red edge index and canopy coverage of the vegetation canopy area in the target region at each growth stage to obtain the nitrogen nutrition diagnostic model.
[0139] Specifically, the expression for the nitrogen nutrition diagnostic model is:
[0140] RRE'=-x×CC 2 +y×CC+z.
[0141] Where RRE' is the average near-infrared red edge index of the vegetation canopy region; x, y, and z are the fitting parameters of the nitrogen nutrition diagnostic model.
[0142] A nitrogen nutrition diagnostic model with a 95% confidence interval (dashed line) (i.e., the portion within the two dashed lines) is as follows: Figure 3 As shown.
[0143] Step 8: Based on the near-infrared-red edge index raster map of the area to be tested and the optimal near-infrared-red edge index confidence interval, determine the crop nitrogen nutrient deficit distribution map of the area to be tested.
[0144] As an optional implementation, step 8 includes:
[0145] Step 81: Based on the near-infrared-red edge index of each pixel in the near-infrared-red edge index raster of the area to be tested and the confidence interval of the optimal near-infrared-red edge index of the area to be tested, determine the nitrogen nutrient deficiency judgment result corresponding to each pixel; the nitrogen nutrient deficiency judgment result is that the crop is nitrogen deficient or the crop is not nitrogen deficient.
[0146] Step 82: Based on the nitrogen nutrient deficit judgment results corresponding to all pixels, draw a crop nitrogen nutrient deficit distribution map of the area to be tested.
[0147] In one exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery.
[0148] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements a method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery.
[0149] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements a method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery.
[0150] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery.
[0151] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0153] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0154] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0156] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery, characterized in that, The crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery includes: Acquire multispectral remote sensing images of the area to be measured and the target radiometric correction plate; the area to be measured is a field planted with crops, and the target radiometric correction plate is a radiometric correction plate set in the area to be measured; the multispectral remote sensing images include: grayscale images of the red band, grayscale images of the red edge band, and grayscale images of the near-infrared band. Based on the multispectral remote sensing images of the area to be measured and the multispectral remote sensing images of the target radiometric correction plate, the multispectral reflectance image of the area to be measured is determined; the multispectral reflectance image includes: a reflectance raster map of the red band, a reflectance raster map of the red edge band, and a reflectance raster map of the near-infrared band. Based on the multispectral reflectance image of the area to be measured, the soil-modified vegetation index raster map of the area to be measured is determined. Based on the soil-regulated vegetation index raster map of the area to be tested, the vegetation canopy area of the area to be tested is determined. Based on the reflectance grid map of the red-edge band and the reflectance grid map of the near-infrared band of the region to be measured, the near-infrared-red-edge index grid map of the region to be measured is determined. The canopy coverage of the area to be tested is determined based on the number of pixels in the vegetation canopy area and the number of pixels in the multispectral remote sensing image of the area to be tested. The canopy coverage of the area to be tested is input into the nitrogen nutrition diagnostic model to obtain the optimal near-infrared-red edge index confidence interval of the area to be tested; the nitrogen nutrition diagnostic model is obtained by fitting the average near-infrared-red edge index of the vegetation canopy area in the target area at multiple growth stages determined according to the optimal nitrogen application rate and the canopy coverage. Based on the near-infrared-red edge index raster map of the area to be tested and the optimal near-infrared-red edge index confidence interval, the crop nitrogen nutrient deficit distribution map of the area to be tested is determined.
2. The method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery according to claim 1, characterized in that, The process of determining the nitrogen nutrition diagnostic model includes: Different actual nitrogen application rates were applied to different sampling areas in the experimental field. To obtain the cost per unit of nitrogen fertilizer and the crop yield after the actual nitrogen application rate was applied to each sampling area; The optimal nitrogen application rate was determined based on the cost per unit of nitrogen fertilizer and the crop yield after actual nitrogen application in each sampling area. The sampling area corresponding to the actual nitrogen application rate that has the smallest absolute value of the difference from the optimal nitrogen application rate is determined as the target area; Acquire multispectral remote sensing images of the experimental radiation correction plate and the target area at different growth stages; the experimental radiation correction plate is a radiation correction plate set in the experimental field. Define any growth stage as the current stage; Based on the multispectral remote sensing images of the target area and the multispectral remote sensing images of the experimental radiometric correction plate, the multispectral reflectance image of the target area in the current period is determined. Based on the multispectral reflectance image of the target area in the current period, determine the soil-modified vegetation index raster map of the target area in the current period. Based on the soil-regulated vegetation index raster map of the target area in the current period, the vegetation canopy area of the target area in the current period is determined. Based on the reflectance raster maps of the target area in the red-edge band and the near-infrared band in the current period, the near-infrared-red-edge index raster map of the target area in the current period is determined. Based on the near-infrared-red edge index raster map and vegetation canopy area of the target area in the current period, determine the average near-infrared-red edge index of the vegetation canopy area in the target area in the current period; The canopy coverage of the target area at the current time is determined based on the number of pixels in the vegetation canopy area of the target area at the current time and the number of pixels in the multispectral remote sensing image of the target area at the current time. Based on the 95% confidence interval, the average near-infrared red edge index and canopy coverage of the vegetation canopy area in the target region at each growth stage were fitted to obtain the nitrogen nutrition diagnostic model.
3. The method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery according to claim 2, characterized in that, The area to be tested or the target area is determined as the current area, and the target radiation correction plate or the test radiation correction plate is determined as the current radiation correction plate; Based on the multispectral remote sensing image of the current area and the multispectral remote sensing image of the current radiometrically corrected plate, determine the multispectral reflectance image of the current area, including: The average gray value of each pixel in the grayscale image of the red band of the current radiation correction plate is determined as the average gray value of the red band. Based on the gray values of each pixel in the grayscale image of the red band of the current region and the average gray value of the red band, the reflectance of each pixel in the grayscale image of the current region is determined, thereby obtaining the reflectance raster map of the red band of the current region. The average gray value of each pixel in the grayscale image of the red-edge band of the current radiation correction plate is determined as the average gray value of the red-edge band. Based on the gray values of each pixel in the grayscale image of the red-edge band of the current region and the average gray value of the red-edge band, the reflectance of each pixel in the grayscale image of the current region is determined, thereby obtaining the reflectance raster map of the red-edge band of the current region. The average gray value of each pixel in the grayscale image of the current radiation correction plate in the near-infrared band is determined as the near-infrared band grayscale average value. Based on the grayscale values of each pixel in the grayscale image of the near-infrared band of the current region and the average grayscale value of the near-infrared band, the reflectance of each pixel in the grayscale image of the near-infrared band of the current region is determined, thereby obtaining the reflectance raster map of the near-infrared band of the current region.
4. The method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery according to claim 2, characterized in that, Define the area to be tested or the target area as the current area; Based on the multispectral reflectance image of the current area, determine the soil-modified vegetation index raster map of the current area, including: Based on the reflectance of each pixel in the red band reflectance raster map and the reflectance of the corresponding pixel in the near-infrared band reflectance raster map of the current region, the soil-regulated vegetation index of each pixel is determined, thereby obtaining the soil-regulated vegetation index raster map of the current region.
5. The method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery according to claim 2, characterized in that, Define the area to be tested or the target area as the current area; Based on the current region's soil-regulated vegetation index raster map, the vegetation canopy area of the current region is determined, including: The soil-regulated vegetation index and index threshold of each pixel in the current region's soil-regulated vegetation index raster map are compared. Pixels whose soil-regulated vegetation index is greater than the index threshold are identified as pixels in the vegetation canopy region of the current area. The vegetation canopy region of the current region is determined based on all pixels of the vegetation canopy region of the current region.
6. The method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery according to claim 2, characterized in that, Define the area to be tested or the target area as the current area; Based on the reflectance raster maps of the red-edge band and near-infrared band of the current region, the near-infrared-red-edge index raster map of the current region is determined, including: Based on the reflectance of each pixel in the reflectance raster of the red-edge band and the reflectance of the corresponding pixel in the reflectance raster of the near-infrared band of the current region, the near-infrared-red-edge index of each pixel is determined, thereby obtaining the near-infrared-red-edge index raster of the current region.
7. The method for monitoring and diagnosing crop nitrogen nutrition based on multispectral remote sensing imagery according to claim 1, characterized in that, Based on the near-infrared-red edge index raster map and the optimal near-infrared-red edge index confidence interval of the test area, the crop nitrogen nutrient deficit distribution map of the test area is determined, including: Based on the near-infrared-red edge index of each pixel in the near-infrared-red edge index raster image of the area to be tested and the confidence interval of the optimal near-infrared-red edge index of the area to be tested, the nitrogen nutrient deficiency judgment result corresponding to each pixel is determined; the nitrogen nutrient deficiency judgment result is that the crop is nitrogen deficient or the crop is not nitrogen deficient. Based on the nitrogen nutrient deficit assessment results corresponding to all pixels, a crop nitrogen nutrient deficit distribution map of the test area is drawn.
8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery as described in any one of claims 1-7.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery as described in any one of claims 1-7.
10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the crop nitrogen nutrition monitoring and diagnosis method based on multispectral remote sensing imagery as described in any one of claims 1-7.