An adaptive fertilization management method and management system based on peanut growth detection

Abstract

The present invention discloses an adaptive fertilization management method and management system based on peanut growth detection, relating to the field of agricultural management technology. The method includes selecting sample plants with growth conditions that meet standards as qualified sample plants, adding the growth conditions of multiple parts of the qualified sample plants and the application rates of various types of fertilizers per unit area during the current growth phase to a comparison library; determining the application rates of various types of fertilizers per unit area for each qualified sample plant in the next growth phase; dividing the peanut planting area into a plurality of isomorphic growth zones based on the location of the sample plants at the detection point and the growth conditions of multiple parts; and screening and comparing the growth conditions of multiple parts of non-standard sample plants with the comparison library to determine the application rates of various types of fertilizers per unit area suitable for each non-standard sample plant in the next growth phase. The present invention improves peanut yield and quality while reducing management costs.

Description

Technical Field

[0001] The present invention belongs to the technical field of agricultural management, and in particular relates to an adaptive fertilization management method and management system based on peanut growth detection. Background Art

[0002] With the advancement of agricultural modernization, precision agriculture technologies are becoming an important means of improving agricultural production efficiency, reducing production costs, and mitigating environmental pollution. Fertilization management, a key component of agricultural production, directly impacts crop yield and quality. Traditional fertilization methods rely primarily on empirical judgment and lack scientific evidence, which can easily lead to over- or under-fertilization, resulting in not only wasted resources but also negative impacts on the soil and environment.

[0003] As an important oilseed and cash crop, peanuts have a phased nutrient requirement during their growth. The demand for nutrients like nitrogen, phosphorus, and potassium varies at different growth stages and is influenced by a variety of factors, including soil conditions and climate. Summary of the Invention

[0004] The purpose of the present invention is to provide an adaptive fertilization management method and management system based on peanut growth detection, which can perform adaptive and precise fertilization based on the actual growth conditions of substandard peanut plants, thereby improving peanut yield and quality while reducing management costs.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention provides an adaptive fertilization management method based on peanut growth detection, comprising:

[0007] The peanut planting area is evenly divided into multiple planting grids, and detection points are selected in each planting grid;

[0008] At the end of each growth cycle of the peanut plant, the growth status of multiple parts of the sample plant at the detection point is obtained;

[0009] Select sample plants that meet the growth standards as qualified sample plants, and add the growth status of multiple parts of the qualified sample plants and the application rate of each type of fertilizer per unit area during the current growth stage to the comparison library;

[0010] Formulate the application amount of each type of fertilizer per unit area for each qualified sample plant in the next growth stage;

[0011] Dividing the peanut planting area into a plurality of isomorphic growth zones according to the position of the sample plants at the detection point and the growth status of multiple parts;

[0012] The growth status of multiple parts of the non-standard sample plants are screened and compared with the comparison library to obtain the application amount of each type of fertilizer per unit area suitable for each non-standard sample plant in the next growth stage.

[0013] The present invention also discloses an adaptive fertilization management method based on peanut growth detection, comprising:

[0014] Obtain the location of each sample plant and the detection point where it is located, as well as the coverage of the planting grid where each detection point is located;

[0015] Receive the application rate of each type of fertilizer per unit area for the qualified sample plants in the next growth period, and the application rate of each type of fertilizer per unit area for each non-qualified sample plant in the next growth period;

[0016] For each planting grid coverage area where the qualified sample plants and non-qualified sample plants are located, fertilizer is applied according to the corresponding application amount of each type of fertilizer per unit area.

[0017] The present invention also discloses an adaptive fertilization management system based on peanut growth detection, comprising:

[0018] A detection unit, used to detect the growth status of multiple parts of the sample plant;

[0019] A fertilization management unit is used to evenly divide the peanut planting area into multiple planting grids and select detection points within each planting grid;

[0020] At the end of each growth cycle of the peanut plant, the growth status of multiple parts of the sample plant at the detection point is obtained;

[0021] Select sample plants that meet the growth standards as qualified sample plants, and add the growth status of multiple parts of the qualified sample plants and the application rate of each type of fertilizer per unit area during the current growth stage to the comparison library;

[0022] Formulate the application amount of each type of fertilizer per unit area for each qualified sample plant in the next growth stage;

[0023] Dividing the peanut planting area into a plurality of isomorphic growth zones according to the position of the sample plants at the detection point and the growth status of multiple parts;

[0024] Screening and comparing the growth status of multiple parts of the non-standard sample plants with the comparison library to obtain the application rate of each type of fertilizer per unit area suitable for each non-standard sample plant in the next growth stage;

[0025] The field management unit is used to obtain the location of each sample plant and the detection point where it is located, as well as the coverage of the planting grid where each detection point is located;

[0026] Receive the application rate of each type of fertilizer per unit area for the qualified sample plants in the next growth period, and the application rate of each type of fertilizer per unit area for each non-qualified sample plant in the next growth period;

[0027] For each planting grid coverage area where the qualified sample plants and non-qualified sample plants are located, fertilizer is applied according to the corresponding application amount of each type of fertilizer per unit area.

[0028] The present invention uses a fertilizer management unit to compare the growth status of numerous non-standard sample plants, finds the closest standard sample plant from the comparison library, and adopts its fertilizer application plan in the next growth stage. In this process, it automatically adapts to the growth status of the non-standard sample plants and completes the fertilizer application plan for the next growth cycle. The entire process only requires manual intervention by staff on a small number of standard sample plants, thereby improving peanut yield and quality while reducing manual management costs.

[0029] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 This is a schematic diagram of functional units and information flows of an adaptive fertilization management system based on peanut growth detection according to an embodiment of the present invention;

[0032] Figure 2 This is a schematic diagram of the steps of the fertilization management unit in one embodiment of the present invention;

[0033] Figure 3 This is a schematic diagram of the steps of the field management unit in one embodiment of the present invention;

[0034] Figure 4 This is a schematic diagram of the process flow of step S5 in one embodiment of the present invention;

[0035] Figure 5 This is a schematic diagram of the process flow of step S51 in one embodiment of the present invention;

[0036] Figure 6 This is a schematic diagram of the process flow of step S6 in one embodiment of the present invention;

[0037] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0038] 1-Detection unit, 2-Fertilization management unit, 3-Field management unit. DETAILED DESCRIPTION

[0039] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0040] It should be noted that the terms "first," "second," and the like in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with certain aspects of the present application as detailed in the appended claims.

[0041] See also Figures 1 to 3 As shown, the present invention provides an adaptive fertilization management system based on peanut growth detection, which is divided into functional units including a detection unit 1, a fertilization management unit 2, and a field management unit 3. The detection unit 1 in this system can be a virtual functional unit, which is operated by a field management personnel. Specifically, step S01 can be executed to detect the growth status of multiple parts of a sample plant. The growth status of a plant part can be any multiple of plant height, average stem diameter, difference between stem and root tip, average leaf area, number of leaves, average leaf color depth, average leaf thickness, degree of flower bud differentiation, number of flower buds, and average flower bud diameter.

[0042] After detection unit 1 completes the peanut detection in the planting area, fertilization management unit 2 can then execute step S1 to evenly divide the peanut planting area into multiple planting grids and select a detection point within each planting grid. The planting grid can be a square plot structure, and the detection point can be the center point of the planting grid. The fertilization management unit can then take over the detection results of detection unit 1. Because peanuts require targeted fertilization at different growth stages, it can then execute step S2 to obtain the growth status of multiple parts of the sample plants at the detection points at the end of each growth cycle of the peanut plants.

[0043] Since peanut plants need to use fertilizers of different proportions and concentrations in different growth states, it is necessary for staff to adjust the fertilization plan for the growing peanut plants. However, due to the huge number of peanut plants in the planting area, field management personnel cannot make adjustments one by one, which not only consumes a lot of time but also is economically unbearable. This solution formulates a fertilization plan for the next stage of a very small number of peanut plants with good growth, which can reduce the workload of formulating a fertilization plan. Specifically, step S3 can be performed first to select sample plants with growth conditions that meet the standards as standard sample plants, and the growth conditions of multiple parts of the standard sample plants and the application rate of each type of fertilizer per unit area in this round of growth stage are added to the comparison library. The fertilizer types include nitrogen fertilizer, phosphate fertilizer, potash fertilizer, calcium fertilizer, organic fertilizer, borax, ammonium molybdate and zinc sulfate. Next, step S4 can be performed to formulate the application rate of each type of fertilizer per unit area for each standard sample plant in the next round of growth stage for the standard sample plants. Since in this process, only a small number of qualified sample plants need to be fertilized in the next growth phase, the workload of the staff is greatly reduced.

[0044] See also Figure 2 and 4 As shown, since the staff only formulates a fertilization plan for a small number of sample plants that meet the standards, an adaptive comparison is required to find a suitable fertilization calculation for the other sample plants. That is, step S5 can be executed next to divide the peanut planting area into several isomorphic growth zones based on the location of the sample plants at the detection point and the growth status of multiple parts. Specifically, step S51 can be executed first to divide multiple sample plants with consistent growth status into the same plant group based on the differences in the growth status of each part of each sample plant.

[0045] See also Figure 5 As shown, in the process of grouping plant combinations, it is necessary to fully consider the difference in growth parameters of different parts of each sample plant, that is, to quantify the difference in plant growth status, and the cumulative value of the difference in growth status parameters of each corresponding part of two sample plants can be used as the growth status difference of the two sample plants. In view of this, when classifying the growth status of sample plants, step S511 can be first executed to select several sample plants that meet the standards and sample plants that do not meet the standards as benchmark sample plants. Next, step S512 can be executed to use the cumulative value of the difference in growth status parameters of each corresponding part of the two sample plants as the growth status difference of the two sample plants, and calculate the growth status difference between each benchmark sample plant and other sample plants. Next, step S513 can be executed for each sample plant other than the benchmark sample plant, and the benchmark sample plant with the smallest difference in growth status difference can be divided into the same plant combination.

[0046] Please continue reading Figure 5 As shown, since the growth status of the sample plants in the plant combination obtained by the above classification may not be completely and fully consistent, it is necessary to verify the consistency. Specifically, step S514 can be first executed to determine whether there are sample plants that meet the standards and sample plants that do not meet the standards mixedly classified in the same plant combination in each plant combination after division. If not, it means that the growth status of the sample plants in each plant combination is consistent, so step S515 can be executed next to determine that the growth status of the sample plants in the plant combination obtained by the current division is consistent. If so, then the plant combination with consistent growth status can be re-divided.

[0047] In the process of re-dividing the plant combinations, it is first necessary to reselect the benchmark sample plants. First, step S516 can be executed to calculate the cumulative value of the difference in growth status between each sample plant and all other sample plants in the plant combination in each plant combination. Next, step S517 can be executed to use the sample plant with the smallest cumulative value of the difference in growth status between each plant combination and all other sample plants in the plant combination as the reselected benchmark sample plant. Next, steps S512 to S514 can be executed to obtain the re-divided plant combination based on the re-selected benchmark sample plants, and to determine whether there is a situation in which qualified sample plants and substandard sample plants are mixed and classified in the same plant combination in the re-divided plant combination. The above process continuously optimizes the sample plants in the plant combination through continuous iterative updates until a plant combination with consistent growth status is obtained.

[0048] To supplement the implementation of steps S511 to S517, we provide the source code for some functional modules, with cross-references and explanations provided in the comments. To prevent the leakage of data involving commercial secrets, data that does not affect the implementation of the solution is desensitized. The same applies below.

[0049] #include <iostream>

[0050] #include <vector>

[0051] #include <map>

[0052] #include <cmath>

[0053] #include <algorithm>

[0054] / / Define the growth status structure of the peanut plant

[0055] struct PlantStatus {

[0056] double height; / / Plant height

[0057] double stemDiameter; / / Average stem diameter

[0058] double stemTipDifference; / / Stem root tip difference

[0059] double leafArea; / / average leaf area

[0060] int leafCount; / / Number of leaves

[0061] double leafColorDepth; / / Average color depth of leaves

[0062] double leafThickness; / / Average leaf thickness

[0063] double budDifferentiation; / / Flower bud differentiation degree

[0064] int budCount; / / Number of flower buds

[0065] double budDiameter; / / Average diameter of flower buds

[0066] };

[0067] / / Define the detection point structure

[0068] struct DetectionPoint {

[0069] int gridID; / / grid ID

[0070] PlantStatus status; / / Plant growth status

[0071] bool is reached; / / whether it reaches the standard

[0072] };

[0073] / / Function: Calculate the convergence rate of two plant states (the cumulative value of the difference)

[0074] double calculateConvergenceRate(const PlantStatus&a, constPlantStatus&b) {

[0075] double difference = 0.0;

[0076] difference += fabs(a.height - b.height);

[0077] difference += fabs(a.stemDiameter - b.stemDiameter);

[0078] difference += fabs(a.stemTipDifference - b.stemTipDifference);

[0079] difference += fabs(a.leafArea - b.leafArea);

[0080] difference += fabs(a.leafCount - b.leafCount);

[0081] difference += fabs(a.leafColorDepth - b.leafColorDepth);

[0082] difference += fabs(a.leafThickness - b.leafThickness);

[0083] difference += fabs(a.budDifferentiation - b.budDifferentiation);

[0084] difference += fabs(a.budCount - b.budCount);

[0085] difference += fabs(a.budDiameter - b.budDiameter);

[0086] returndifference ;

[0087] }

[0088] / / Function: Select benchmark sample plants

[0089] std::vector <detectionpoint>selectBasePlants(const std::vector <detectionpoint>&plants, int baseCount) {

[0090] std::vector <detectionpoint>basePlants;

[0091] / / Simple implementation: select the first baseCount plants as benchmark sample plants

[0092] for (int i = 0; i <baseCount&&i<plants.size(); ++i) {

[0093] basePlants.push_back(plants[i]);

[0094] }

[0095] return basePlants;

[0096] }

[0097] / / Function: Divide plant combinations

[0098] std::vector <std::vector <detectionpoint>>groupPlants(const std::vector <detectionpoint>&plants, const std::vector <detectionpoint>&basePlants) {

[0099] std::vector<std::vector <detectionpoint>>groups(basePlants.size());

[0100] / / Traverse all sample plants and assign them to the group where the benchmark sample plant with the highest convergence rate is located

[0101] for (const auto&plant : plants) {

[0102] doubleminConvergenceRate = -1.0;

[0103] int bestGroupIndex = -1;

[0104] / / Calculate the difference from each benchmark sample plant

[0105] for (size_t i = 0; i <basePlants.size(); ++i) {

[0106] double rate = calculateConvergenceRate(plant.status, basePlants[i].status);

[0107] if (rate <minConvergenceRate) {

[0108] minConvergenceRate = rate;

[0109] bestGroupIndex = i;

[0110] }

[0111] }

[0112] / / Assign sample plants to corresponding groups

[0113] if (bestGroupIndex != -1) {

[0114] groups[bestGroupIndex].push_back(plant);

[0115] }

[0116] }

[0117] return groups;

[0118] }

[0119] / / Function: Check whether the plant combination is mixed with qualified and unqualified sample plants

[0120] bool isMixedGroup(const std::vector <detectionpoint>&group) {

[0121] bool has_reached_standard = false;

[0122] bool hasNotMeeting = false;

[0123] for (const auto&plant : group) {

[0124] if (plant.is reaches the standard) has reached the standard = true;

[0125] else has not reached the target = true;

[0126] if (has reached the standard && has not reached the standard) return true;

[0127] }

[0128] return false;

[0129] }

[0130] / / Function: Reselect benchmark sample plants and re-divide groups

[0131] std::vector <std::vector <detectionpoint>>regroupPlants(const std::vector<std::vector <detectionpoint>>&groups) {

[0132] std::vector<std::vector <detectionpoint>>newGroups;

[0133] for (const auto&group : groups) {

[0134] if (isMixedGroup(group)) {

[0135] / / If the group is mixed, reselect the benchmark sample plants

[0136] std::vector <double>convergenceSums(group.size(), 0.0);

[0137] / / Calculate the cumulative difference between each sample plant and other sample plants in the group

[0138] for (size_t i = 0; i <group.size(); ++i) {

[0139] for (size_t j = 0; j <group.size(); ++j) {

[0140] if (i != j) {

[0141] convergenceSums[i] += calculateConvergenceRate(group[i].status, group[j].status);

[0142] }

[0143] }

[0144] }

[0145] / / Select the sample plant with the smallest cumulative convergence value as the new benchmark sample plant

[0146] auto minIt = std::, min_element(convergenceSums.begin(),convergenceSums.end());

[0147] int baseIndex = std::distance(convergenceSums.begin(),minIt);

[0148] auto newBasePlant = group[baseIndex];

[0149] / / Re-divide the groups

[0150] auto newGroup = groupPlants(group, {newBasePlant});

[0151] newGroups.insert(newGroups.end(), newGroup.begin(), newGroup.end());

[0152] } else {

[0153] / / If there is no mixing in the group, just keep it

[0154] newGroups.push_back(group);

[0155] }

[0156] }

[0157] return newGroups;

[0158] }

[0159] int main() {

[0160] / / Detection point data

[0161] std::vector <detectionpoint>detectionPoints = {

[0162] {1, {35.0, 5.0, 2.0, 50.0, 12, 0.8, 0.2, 0.9, 6, 1.0}, true},

[0163] {2, {34.0, 5.1, 2.1, 51.0, 13, 0.81, 0.21, 0.91, 7, 1.1}, true},

[0164] {3, {28.0, 4.0, 1.5, 40.0, 8, 0.7, 0.15, 0.8, 4, 0.8}, false},

[0165] {4, {29.0, 4.1, 1.6, 41.0, 9, 0.71, 0.16, 0.81, 5, 0.9}, false},

[0166] {5, {40.0, 6.0, 2.5, 60.0, 15, 0.9, 0.25, 1.0, 8, 1.2}, true}

[0167] };

[0168] / / Step 1: Select benchmark sample plants

[0169] int baseCount = 2; / / Select 2 benchmark sample plants

[0170] auto basePlants = selectBasePlants(detectionPoints, baseCount);

[0171] / / Step 2: Divide the plant groups

[0172] auto groups = groupPlants(detectionPoints, basePlants);

[0173] / / Step 3: Check and re-divide mixed groups

[0174] auto finalGroups = regroupPlants(groups);

[0175] / / Output the final division result

[0176] for (size_t i = 0; i <finalGroups.size(); ++i) {

[0177] std::cout<<"Plant combination"<

[0178] for (const auto&plant : finalGroups[i]) {

[0179] std::cout< <plant.gridID<<" ";

[0180] }

[0181] std::cout< <std::endl;

[0182] }

[0183] return 0;

[0184] }

[0185] This code implements the function of dividing plant combinations according to growth status differences in the adaptive fertilization management method based on peanut growth detection. First, select the benchmark sample plants from the sample plants that meet the standards and those that do not meet the standards, and calculate the difference in growth status between each sample plant and the benchmark sample plant. Then divide each sample plant into the group where the benchmark sample plant with the highest convergence rate is located. Then check whether each group is mixed with sample plants that meet the standards and those that do not meet the standards. If so, reselect the benchmark sample plants and re-divide the groups until the growth status of the sample plants in the group is consistent. Finally, output the divided plant combination to provide a basis for subsequent isomorphic growth zoning and precise fertilization.

[0186] Please continue reading Figure 2 and 4 As shown, after the plant combinations are obtained by grouping, the positions of the sample plants need to be considered. This is because only the detection points with close positions have similar soil compositions. Therefore, step S52 can be executed to divide the multiple sample plants with adjacent positions in each plant combination into the same homomorphic plant combination according to the position of each sample plant at the detection point. Finally, step S53 can be executed to treat the range of the multiple planting grids where the sample plants contained in the same homomorphic plant combination are located as a homomorphic growth partition. After the division, the peanut plants in the same homomorphic growth partition not only have the same growth state, but also have similar soils in which they grow.

[0187] See also Figure 2 and 6 ​As shown, step S6 can be executed next to screen and compare the growth status of multiple parts of the non-standard sample plants with the comparison library to obtain the application amount of each type of fertilizer per unit area suitable for each non-standard sample plant in the next growth stage. Specifically, step S61 can be executed first to calculate the difference in growth status between each non-standard sample plant and each standard sample plant in the comparison library for each non-standard sample plant. Next, step S62 can be executed to use the standard sample plant with the smallest difference in growth status with the non-standard sample plant in the comparison library as the standard sample plant. Finally, step S63 can be executed to use the application amount of each type of fertilizer per unit area of ​​the standard sample plant as the application amount of each type of fertilizer per unit area suitable for the non-standard sample plant in the next growth stage.

[0188] See also Figures 1 to 3 As shown, the field management unit 3 in this solution can be a guidance terminal held by a staff member, which is used to carry out targeted fertilization of peanut plants in different positions according to the fertilization plan. Specifically, step S031 can be first executed to obtain the position of each sample plant and the detection point where it is located, as well as the coverage of the planting grid where each detection point is located. Next, step S032 can be executed to receive the application amount of each type of fertilizer per unit area of ​​the qualified sample plants in the next round of growth stage, as well as the application amount of each type of fertilizer per unit area applicable to each non-qualified sample plant in the next round of growth stage. Finally, step S033 can be executed to fertilize the planting grid coverage area where each qualified sample plant and non-qualified sample plant is located according to the corresponding application amount of each type of fertilizer per unit area.

[0189] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and the part for the module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be performed substantially in parallel, and they can sometimes also be performed in the opposite order, depending on the function involved.

[0190] It should also be noted that each box in the block diagram and / or flowchart, and combinations of boxes in the block diagram and / or flowchart, can be implemented by hardware that performs the corresponding function or action, such as a circuit or ASIC (Application Specific Integrated Circuit), or can be implemented by a combination of hardware and software, such as firmware.

[0191] Although the present invention has been described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by examining the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. The fact that certain measures are recorded in different dependent claims does not mean that these measures cannot be combined to produce good results.

[0192] The embodiments of the present application have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.< / detectionpoint> < / double> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / detectionpoint> < / algorithm> < / cmath> < / map> < / vector> < / iostream>

Claims

1. An adaptive fertilization management method based on peanut growth detection, characterized in that: include, The peanut planting area is evenly divided into multiple planting grids, and detection points are selected in each planting grid; At the end of each growth cycle of the peanut plant, the growth status of multiple parts of the sample plant at the detection point is obtained; Select sample plants that meet the growth standards as qualified sample plants, and add the growth status of multiple parts of the qualified sample plants and the application rate of each type of fertilizer per unit area during the current growth stage to the comparison library; Formulate the application amount of each type of fertilizer per unit area for each qualified sample plant in the next growth stage; Select several sample plants that meet the standards and several sample plants that do not meet the standards as benchmark sample plants; The cumulative value of the difference in growth state parameters of each corresponding part of the two sample plants is used as the growth state difference of the two sample plants, and the growth state difference between each reference sample plant and other sample plants is calculated; For each sample plant other than the reference sample plant, grouping the sample plant with the smallest difference in growth status from the reference sample plant into the same plant combination; Determine whether there are sample plants that meet the standards and sample plants that do not meet the standards mixed and classified in the same plant combination after each plant combination has been divided; If not, it is determined that the growth status of the sample plants in the currently divided plant combination is consistent; If so, re-divide to obtain a plant combination with consistent growth status; In each plant combination, a plurality of sample plants that are adjacent to each other in the plant combination are divided into the same isomorphic plant combination according to the position of each sample plant at the detection point; The range of multiple planting grids where the sample plants contained in the same isomorphic plant combination are located is regarded as a isomorphic growth partition; The growth status of multiple parts of the non-standard sample plants are screened and compared with the comparison library to obtain the application amount of each type of fertilizer per unit area suitable for each non-standard sample plant in the next growth stage.

2. The method according to claim 1, characterized in that The growth status of plant parts includes plant height, average stem diameter, difference between stem and root tip, average leaf area, number of leaves, average leaf color depth, average leaf thickness, degree of flower bud differentiation, number of flower buds and / or average flower bud diameter; Fertilizer types include nitrogen, phosphate, potash, calcium, organic fertilizers, borax, ammonium molybdate, and / or zinc sulfate.

3. The method according to claim 1, characterized in that The step of re-dividing to obtain a plant combination with consistent growth status, include, Reselect benchmark sample plants; The re-divided plant combination is obtained according to the re-selected benchmark sample plant division; Determine whether there is a situation in which qualified sample plants and non-qualified sample plants are mixed and classified in the same plant combination after re-division.

4. The method according to claim 3, characterized in that The step of reselecting the benchmark sample plants, include, In each plant combination, the cumulative value of the difference in growth status between each sample plant and all other sample plants in the plant combination is calculated; The sample plant with the smallest cumulative difference in growth status between each plant combination and all other sample plants in the same plant combination is used as the reselected benchmark sample plant.

5. The method according to any one of claims 1 to 4, characterized in that The step of screening and comparing the growth status of multiple parts of the non-standard sample plants with the comparison library to obtain the application rate of each type of fertilizer per unit area suitable for each non-standard sample plant in the next growth stage, include, For each non-standard sample plant, calculate and obtain the difference in growth status between the non-standard sample plant and each standard sample plant in the comparison library; The qualified sample plant with the smallest difference in growth status between the sample plant that does not meet the standard and the sample plant that does not meet the standard in the comparison library is used as the target qualified sample plant; The amount of each type of fertilizer applied per unit area to the target-compliant sample plants will be used as the amount of each type of fertilizer applied per unit area to the non-compliant sample plants in the next growth stage.

6. An adaptive fertilization management method based on peanut growth detection, characterized in that: include, Obtain the location of each sample plant and the detection point where it is located, as well as the coverage of the planting grid where each detection point is located; Receive the application rate of each type of fertilizer per unit area for the qualified sample plants in the next growth stage, and the application rate of each type of fertilizer per unit area for each non-qualified sample plant in the next growth stage according to the adaptive fertilization management method based on peanut growth detection according to any one of claims 1 to 5; For each planting grid coverage area where the qualified sample plants and non-qualified sample plants are located, fertilizer is applied according to the corresponding application amount of each type of fertilizer per unit area.

7. An adaptive fertilization management system based on peanut growth detection, characterized in that: include, A detection unit, used to detect the growth status of multiple parts of the sample plant; A fertilization management unit is used to evenly divide the peanut planting area into multiple planting grids and select detection points within each planting grid; At the end of each growth cycle of the peanut plant, the growth status of multiple parts of the sample plant at the detection point is obtained; Select sample plants that meet the growth standards as qualified sample plants, and add the growth status of multiple parts of the qualified sample plants and the application rate of each type of fertilizer per unit area during the current growth stage to the comparison library; Formulate the application amount of each type of fertilizer per unit area for each qualified sample plant in the next growth stage; Select several sample plants that meet the standards and several sample plants that do not meet the standards as benchmark sample plants; The cumulative value of the difference in growth state parameters of each corresponding part of the two sample plants is used as the growth state difference of the two sample plants, and the growth state difference between each reference sample plant and other sample plants is calculated; For each sample plant other than the reference sample plant, grouping the sample plant with the smallest difference in growth status from the reference sample plant into the same plant combination; Determine whether there are sample plants that meet the standards and sample plants that do not meet the standards mixed and classified in the same plant combination after each plant combination has been divided; If not, it is determined that the growth status of the sample plants in the currently divided plant combination is consistent; If so, re-divide to obtain a plant combination with consistent growth status; In each plant combination, a plurality of sample plants that are adjacent to each other in the plant combination are divided into the same isomorphic plant combination according to the position of each sample plant at the detection point; The range of multiple planting grids where the sample plants contained in the same isomorphic plant combination are located is regarded as a isomorphic growth partition; Screening and comparing the growth status of multiple parts of the non-standard sample plants with the comparison library to obtain the application rate of each type of fertilizer per unit area suitable for each non-standard sample plant in the next growth stage; The field management unit is used to obtain the location of each sample plant and the detection point where it is located, as well as the coverage of the planting grid where each detection point is located; Receive the application rate of each type of fertilizer per unit area for the qualified sample plants in the next growth period, and the application rate of each type of fertilizer per unit area for each non-qualified sample plant in the next growth period; For each planting grid coverage area where the qualified sample plants and non-qualified sample plants are located, fertilizer is applied according to the corresponding application amount of each type of fertilizer per unit area.

Images