Crop sowing parameter control optimization method applied to multi-target precise fertilization

Abstract

The invention discloses a crop sowing parameter control optimization method applied to multi-target precise fertilization, and relates to the technical field of agricultural crop sowing, and the method comprises the following steps: collecting a soil sample, carrying out spectrum scanning and analysis, combining with known soil nutrient data, building a soil nutrient content prediction model, and calculating a soil nutrient content prediction model; and combining spectral data to predict the nutrient content in the soil. According to the invention, through accurate evaluation of soil nutrient conditions and deep analysis of crop growth demands, fertilization and sowing parameters are optimized, so that crops can obtain required nutrients in the growth process, the optimized sowing depth, row spacing and plant spacing can effectively promote the development of crop roots, the absorption ability of the crops to moisture and nutrients is enhanced, and the quality of the crops is improved. And through real-time monitoring and adjustment of the intelligent fertilization equipment, the fertilization amount can be dynamically adjusted according to actual demands of crops, and the common problem of excessive or insufficient fertilizer in a traditional fertilization method is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural crop sowing, and in particular to a crop sowing parameter control optimization method applied to multi-objective precision fertilization. Background Art

[0002] With the continuous development of intelligent and automated technologies, agricultural production is gradually moving towards intelligence and automation. In traditional agricultural production, excessive use of chemical fertilizers is a common problem, which not only leads to the decline of soil quality and the aggravation of environmental pollution, but also increases the cost of agricultural production. Precision agriculture has become an important means to improve agricultural production efficiency and resource utilization efficiency. Precision fertilization, as an important part of precision agriculture, improves the quality and growth efficiency of crop sowing through the scientific and reasonable application of fertilizers, while reducing resource waste and environmental pollution. Therefore, optimizing and controlling the crop sowing parameters of multi-target precision fertilization is one of the key technologies to realize agricultural modernization and precision agriculture.

[0003] Traditional agricultural precision fertilization requires testing of soil composition and then adjusting fertilization parameters during crop sowing based on soil nutrients. However, the overall acquisition cycle is long. Therefore, how to quickly predict soil nutrient content and evaluate the status of soil nutrients to optimize and control fertilization parameters for crop sowing is a problem we need to solve. To this end, a crop sowing parameter control optimization method for multi-objective precision fertilization is proposed. Summary of the invention

[0004] The object of the present invention is to provide a crop sowing parameter control optimization method applied to multi-objective precision fertilization to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A crop sowing parameter control optimization method for multi-objective precision fertilization includes the following steps: Step 1: Collect soil samples for spectral scanning and analysis, and establish a soil nutrient content prediction model based on known soil nutrient data. Combined with spectral data, predict the nutrient content in the soil, including nitrogen, phosphorus, potassium, etc.; Step 2: Analyze the prediction results, evaluate the nutrient status of the soil, comprehensively reflect the soil nutrient level, and classify it; Step 3: According to the assessment results of soil nutrient levels and the nutrient requirements of crops, determine the fertilization parameters for crop sowing, including the type, amount, time and method of fertilization, to ensure that the crops obtain the nutrients they need during their growth; Step 4: Based on the growth characteristics of crops and the actual conditions of the soil, optimize the sowing parameters of crops, including sowing depth, row spacing and plant spacing, through simulation and experimental verification, to ensure that crops grow under optimal conditions; Step 5. Use intelligent fertilization equipment to carry out precise fertilization and crop sowing according to fertilization parameters and optimized crop sowing parameters, and automatically adjust the amount of fertilizer based on real-time monitoring data to ensure uniform distribution and effective use of fertilizers.

[0006] A further improvement of the technical solution of the present invention is that in step 1, the prediction process of soil nutrient content is: Collect representative soil samples from farmland plots in the target area. The sampling depth is usually 0-20 cm (field crops) or 0-40 cm (orchard crops). Use the "s"-shaped method to uniformly and randomly sample to ensure the representativeness and uniformity of the samples. Use a spectrometer to perform spectral scans of the soil samples using visible-near infrared (vis-NIR) and mid-infrared (MIR) to obtain spectral reflectance data of the soil in different bands. The spectral range is usually 350-2500nm (vis-NIR) and 4000-650cm⁻¹ (MIR); Preprocessing of the acquired spectral data, including atmospheric correction, stray light correction and data normalization steps; Extract spectral features of characteristic bands related to nutrients required for crop sowing from spectral data. The spectral features are reflectance and absorptivity. Divide known soil nutrient data into training sets and test sets for model training and verification. The nutrients required for crop sowing include nitrogen, phosphorus, potassium, etc. The soil nutrient content prediction model was established using training set data combined with the support vector machine machine learning algorithm, the correlation between spectral characteristics and nutrient content was analyzed, and the model was verified using test set data to evaluate the model's prediction ability and stability. The spectral characteristics of soil samples from farmland plots in the target area are input into the established soil nutrient content prediction model to obtain the predicted content of soil nutrients.

[0007] A further improvement of the technical solution of the present invention is that in step 2, the evaluation process of soil nutrient status is: Arrange the predicted soil nutrient content data to form a soil nutrient data sequence table, where each data point has clear soil sample number, sampling location, and sampling time information; Based on crop growth requirements, soil type and regional climate factors, a comprehensive analysis is conducted to obtain a standard value data set, including standard values ​​of soil nutrient content required for sowing different crops. The abnormal values ​​and unreasonable values ​​in the soil nutrient data sequence table are preliminarily identified, such as abnormally high nutrient content or extremely low values ​​below common sense. The abnormal values ​​are reviewed to check whether there are errors in the data input, sampling and analysis process. Soil samples with obvious abnormal differences in abnormal values ​​are retested to ensure the accuracy of the data; Compare and analyze the sorted soil nutrient data with the standard values ​​of soil nutrient content for crop sowing, calculate the soil nutrient evaluation index, and quantitatively evaluate the nutrient status of the soil samples. The standard values ​​are formulated based on crop growth requirements, soil type, and regional climate factors. According to the calculation results of soil nutrient evaluation index, the ratio and relationship between different nutrients are compared, and the nutrient adequacy, balance and deficiency / excess are further analyzed to evaluate whether the content of various nutrients in the soil is sufficient and whether it can meet the needs of crop growth. The nutrient balance is analyzed, that is, whether the ratio between various nutrients is coordinated, whether there is too much or too little of a certain nutrient, and whether there is a lack or excess of nutrients in the soil; According to the assessment results of soil nutrient evaluation index and soil nutrient status, the soil nutrient level is divided into different nutrient levels, namely, rich nutrient level, medium nutrient level and deficient nutrient level, and each nutrient level is matched with a corresponding nutrient evaluation threshold. Among them, the nutrient evaluation threshold is formulated according to crop growth needs, soil type and regional climate factors, and is used to guide soil management and the implementation of nutrient regulation measures.

[0008] A further improvement of the technical solution of the present invention is that the calculation process of the soil nutrient evaluation index is: Collect the actual nutrient content of the soil samples, record the corresponding standard nutrient content, and determine the number of nutrient types. For each soil nutrient, calculate the ratio of its actual content to the standard content, and calculate the sum of the squares of the ratios. Calculate the maximum sum of squares of all nutrient ratios in multiple soil samples, and divide the sum of squares of the ratios by the maximum sum of squares of all nutrient ratios to obtain the benchmark ratio function. , analyze the minimum and maximum values ​​of the ratio of actual content to standard content, and obtain the equilibrium ratio function , combining the benchmark ratio function and the equilibrium ratio function to calculate the soil nutrient evaluation index; The calculation formula of the soil nutrient evaluation index is: ; ; ; Among them, SI is the soil nutrient evaluation index, is the benchmark ratio function, is the equilibrium ratio function, is the actual content of the ith nutrient, is the standard content of the i-th nutrient, n is the number of nutrient types, for and The minimum value of the ratio, for and The maximum value of the ratio.

[0009] A further improvement of the technical solution of the present invention is that: the multiple nutrient levels correspond to the multiple nutrient evaluation thresholds, wherein the nutrient evaluation thresholds include an upper threshold and a lower threshold; The plurality of nutrient levels and the plurality of nutrient evaluation thresholds satisfy the following relationship: Rich nutrient levels ; Medium nutrient level ; Lack of nutrient levels ; Among them, SI is the soil nutrient evaluation index, is the lower threshold corresponding to the rich nutrient level and the upper threshold corresponding to the medium nutrient level, is the lower threshold corresponding to the medium nutrient level and the upper threshold corresponding to the nutrient deficiency level, , .

[0010] A further improvement of the technical solution of the present invention is that in step 3, the process of determining the crop sowing and fertilization parameters is as follows: Based on the evaluation results of soil nutrient evaluation index and soil nutrient status, accurate soil nutrient data can be obtained through soil nutrient testing to determine the sufficiency of each nutrient in the soil, identify deficient, suitable and excessive nutrients, and identify which nutrients in the soil are insufficient, which may be excessive, and which nutrients are at an appropriate level; Analyze the type and growth stage of the crop to determine its demand for soil nutrients such as nitrogen, phosphorus, and potassium, and choose fertilizers containing the required nutrients (such as nitrogen, phosphorus, and potassium). If the nitrogen content in the soil is insufficient, nitrogen fertilizer can be selected. If the phosphorus and potassium content are insufficient, compound fertilizer or phosphorus fertilizer and potassium fertilizer can be selected; According to the soil nutrient test results and crop nutrient requirements, the recommended application amount of each nutrient is accurately calculated to ensure that the nutrient supply is sufficient but not excessive. The application time of basal fertilizer is determined according to the crop growth cycle and nutrient requirements. Usually, it is before sowing or in the early stage of crop growth. According to the crop growth situation and soil nutrient status, the best time for topdressing is determined to avoid fertilizing during the crop dormancy period or the period with low nutrient requirements; Based on the crop sowing requirements, the fertilization method is selected, which are soil fertilization, foliar spraying and irrigation fertilization.

[0011] A further improvement of the technical solution of the present invention is that in step 4, the optimization process of crop sowing parameters is: Identify the growth characteristics of crops, including seed germination conditions, root development, light requirements, water requirements, and analyze the actual soil conditions to determine the texture, pH value, organic matter content, drainage capacity, and nutrient levels of the soil in the target area; Determine the appropriate sowing depth range based on the size of crop seeds and germination requirements, and refer to historical crop sowing data to preliminarily set the row spacing and plant spacing; Using simulation software, we simulated the growth of crops at different sowing depths within a range of sowing depths according to the root distribution of crops and soil conditions, and set up test plots with different sowing depths in the farmland plots in the target area to observe the emergence rate, growth rate and yield indicators of crops. Based on the simulation and experimental results, we determined the optimal sowing depth. Using crop growth models and spatial distribution models, simulate the growth of crops under different row and plant spacings, and set up test plots with different row and plant spacings in the farmland plots in the target area to observe the growth status, light utilization, ventilation conditions and yield indicators of crops. According to the simulation and experimental results, determine the optimal row and plant spacing; Combined with the optimization results of sowing depth, row spacing and plant spacing, the comprehensive score of the optimal sowing parameters was calculated to determine the best combination of sowing parameters.

[0012] A further improvement of the technical solution of the present invention is that the calculation formula of the optimal sowing parameter comprehensive score is: ; in, is the comprehensive score of the optimal sowing parameters, D is the actual sowing depth, The optimal planting depth for the crop is determined based on the crop seed size and germination requirements. is the standard deviation of sowing depth, reflecting the variability of sowing depth under different conditions, R is the actual row spacing, The optimal row spacing for crops is determined based on crop growth model and spatial distribution model. is the standard deviation of row spacing, reflecting the variability of row spacing under different conditions, S is the actual plant spacing, The optimal spacing between crops is determined based on crop growth model and spatial distribution model. is the standard deviation of plant spacing, reflecting the variability of plant spacing under different conditions.

[0013] A further improvement of the technical solution of the present invention is that in step 5, the process of precise fertilization and crop sowing is: Based on the determined fertilizer type, application amount, fertilization time and fertilization method, as well as sowing depth, row spacing and plant spacing, calibrate intelligent fertilization equipment (such as intelligent sprinkler irrigation system, precision fertilizer applicator) to ensure the accuracy of fertilizer application amount, and input fertilization parameters and sowing parameters into the control system of the intelligent fertilization equipment; Use intelligent fertilization equipment to apply fertilizers while sowing to ensure that fertilizers are evenly distributed around the seeds, and use sensors to monitor soil moisture, temperature, and pH value, and then automatically adjust the amount of fertilizers based on real-time monitoring data to ensure even distribution and effective use of fertilizers; Record the time, location and amount of each fertilization for subsequent analysis and adjustment, and regularly evaluate the fertilization effects, including changes in crop growth conditions and soil nutrient levels, analyze fertilization data and crop growth data, and identify problems and room for improvement in fertilization strategies.

[0014] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art: The present invention provides a crop sowing parameter control optimization method for multi-target precision fertilization. Through accurate evaluation of soil nutrient status and in-depth analysis of crop growth needs, fertilization and sowing parameters are optimized to ensure that crops obtain required nutrients during the growth process, so that the optimized sowing depth, row spacing and plant spacing can effectively promote the development of crop roots and enhance their ability to absorb water and nutrients. Moreover, through real-time monitoring and adjustment of intelligent fertilization equipment, the amount of fertilizer can be dynamically adjusted according to the actual needs of the crops, avoiding the problem of excessive or insufficient fertilizer commonly seen in traditional fertilization methods.

[0015] The present invention provides a crop sowing parameter control optimization method for multi-target precision fertilization. By combining intelligent fertilization equipment with optimized crop sowing parameters, the utilization rate of fertilizers can be significantly improved. By optimizing the sowing parameters, it is helpful for crop roots to better absorb and utilize nutrients in the fertilizer, and the fertilizer utilization rate is further improved, which not only reduces agricultural production costs, but also reduces soil and water pollution caused by excessive fertilization, is beneficial to protecting the ecological environment and maintaining sustainable agricultural development, and dynamically adjusts the fertilization strategy according to the growth stage of the crop and the change in nutrient demand to ensure that the crop can obtain sufficient nutrient supply throughout the growth cycle, so that the use of fertilizers is more efficient, and the risk of crop growth stagnation and yield reduction due to insufficient or excessive nutrient supply is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 is a flow chart of the method of the present invention; Figure 2 is a flow chart for evaluating soil nutrient status of the present invention; Figure 3 This is a flow chart for optimizing crop sowing parameters of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1, as Figure 1 , Figure 2 As shown, the present invention provides a crop sowing parameter control optimization method applied to multi-objective precision fertilization, comprising the following steps: Step 1: Collect soil samples for spectral scanning and analysis. Combined with known soil nutrient data, a soil nutrient content prediction model is established. Combined with spectral data, the nutrient content in the soil, including nitrogen, phosphorus, potassium, etc., is predicted. Representative soil samples are collected from farmland plots in the target area. The sampling depth is usually 0-20 cm (field crops) or 0-40 cm (orchard crops). The "s"-shaped method is used for uniform random sampling to ensure the representativeness and uniformity of the samples. The soil samples are spectrally scanned using a spectrometer using visible-near infrared (vis-NIR) and mid-infrared (MIR) to obtain spectral reflectance data of the soil in different bands. The spectral range is usually 350-2500nm (vis-NIR) and 4000-650cm⁻¹ (MIR). The acquired spectral data is preprocessed, including atmospheric correction, stray light correction and data normalization steps. Among them, the spectral data is atmospherically corrected. To eliminate the influence of the atmosphere on the spectral data, the spectral data is corrected for stray light to improve the accuracy and reliability of the spectral data. The spectral data is standardized to make the spectral data between different samples comparable to improve the accuracy of subsequent modeling. The spectral features of the characteristic bands related to the nutrients required for crop sowing are extracted from the spectral data. The spectral features are reflectance and absorptivity. The known soil nutrient data are divided into a training set and a test set for model training and verification. The nutrients required for crop sowing include nitrogen, phosphorus, potassium, etc. The training set data is combined with the machine learning algorithm of the support vector machine to establish a soil nutrient content prediction model, analyze the correlation between the spectral features and the nutrient content, and use the test set data to verify the model to evaluate the prediction ability and stability of the model. The spectral features of the soil samples of the farmland plots in the target area are input into the established soil nutrient content prediction model to obtain the predicted content of soil nutrients. Step 2: Analyze the prediction results, evaluate the nutrient status of the soil, comprehensively reflect the soil nutrient level, and classify it. Organize the predicted soil nutrient content data to form a soil nutrient data sequence table. Each data point has a clear soil sample number, sampling location, and sampling time information. Based on crop growth requirements, soil type, and regional climate factors, a comprehensive analysis is performed to obtain a standard value data set, which includes standard values ​​of soil nutrient content required for sowing different crops. Preliminary identification is performed on abnormal values ​​and unreasonable values ​​in the soil nutrient data sequence table, such as abnormally high nutrient content or extremely low values ​​below common sense. The abnormal values ​​are reviewed to check whether there are errors in the data input, sampling, and analysis process. Soil samples with obvious abnormal value differences are retested to ensure the accuracy of the data. The sorted soil nutrient data are compared and analyzed with the standard values ​​of soil nutrient content for crop sowing, and the soil nutrient evaluation index is calculated to quantitatively evaluate the soil samples. Nutrient status, where the standard value is formulated based on the crop growth requirements, soil type and regional climate factors. According to the calculation results of the soil nutrient evaluation index, the ratio and relationship between different nutrients are compared, and the nutrient adequacy, balance and deficiency / excess are further analyzed to evaluate whether the content of various nutrients in the soil is sufficient and whether it can meet the needs of crop growth. The nutrient balance is analyzed, that is, whether the ratio between various nutrients is coordinated, whether there is too much or too little of a certain nutrient, and whether there is a lack or excess of nutrients in the soil. According to the evaluation results of the soil nutrient evaluation index and the soil nutrient status, the soil nutrient level is divided into different nutrient levels, namely, rich nutrient level, medium nutrient level and deficient nutrient level, and the corresponding nutrient evaluation threshold is matched for each nutrient level. Among them, the nutrient evaluation threshold is formulated according to the crop growth requirements, soil type and regional climate factors, and is used to guide the implementation of soil management and nutrient regulation measures; Furthermore, the calculation process of soil nutrient evaluation index is: Collect the actual nutrient content of the soil samples, record the corresponding standard nutrient content, and determine the number of nutrient types. For each soil nutrient, calculate the ratio of its actual content to the standard content, and calculate the sum of the squares of the ratios. Calculate the maximum sum of squares of all nutrient ratios in multiple soil samples, and divide the sum of squares of the ratios by the maximum sum of squares of all nutrient ratios to obtain the benchmark ratio function. , analyze the minimum and maximum values ​​of the ratio of actual content to standard content, and obtain the equilibrium ratio function , combining the benchmark ratio function and the equilibrium ratio function to calculate the soil nutrient evaluation index; The calculation formula of soil nutrient evaluation index is: ; ; ; Among them, SI is the soil nutrient evaluation index, is the benchmark ratio function, is the equilibrium ratio function, is the actual content of the ith nutrient, is the standard content of the i-th nutrient, n is the number of nutrient types, for and The minimum value of the ratio, for and The maximum value of the ratio, Calculating the sum of the squares of the ratios of the actual content to the standard content of all nutrient types helps capture the overall deviation of all nutrients. Divide the sum by the maximum possible sum to ensure that the result is between 0 and 1. The overall score is adjusted by adding 1 to the denominator and the inverse of the summed ratio to ensure that when all nutrients meet the standards, the SI is close to 1. By considering the minimum and maximum values ​​of the ratio of actual content to standard content, the score is adjusted to reflect the balance of nutrients. The SI value range is between 0 and 1. When the ratio of the actual content of all nutrients to the standard content is close to 1, the SI is close to 1, indicating that the soil nutrient status is good. When the minimum and maximum values ​​of the ratio are very different, or the actual content of some nutrients is far lower than the standard content, the SI value decreases, indicating that the soil nutrient status is poor. Furthermore, the plurality of nutrient levels correspond to a plurality of nutrient evaluation thresholds, wherein the nutrient evaluation thresholds include an upper threshold and a lower threshold; Multiple nutrient levels and multiple nutrient evaluation thresholds satisfy the following relationship: Rich nutrient levels ; The soil nutrient content is sufficient to meet or exceed the needs of crop growth, maintain the current nutrient level, and pay attention to avoid environmental problems caused by excessive fertilization; Medium nutrient level ; The soil nutrient content basically meets the needs of crop growth, but there is still room for improvement. Targeted fertilization should be carried out according to the specific nutrients lacking to improve soil fertility; Lack of nutrient levels ; The soil nutrient content is insufficient to support optimal crop growth, and additional nutrient supplementation, soil improvement and fertilization are needed, especially to increase the lack of nutrients to improve crop yield and quality; Among them, SI is the soil nutrient evaluation index, is the lower threshold corresponding to the rich nutrient level and the upper threshold corresponding to the medium nutrient level, is the lower threshold corresponding to the medium nutrient level and the upper threshold corresponding to the nutrient deficiency level, , ; Step 3. According to the assessment results of soil nutrient levels and the nutrient requirements of crop sowing, determine the fertilization parameters for crop sowing, including the type of fertilizer, application amount, fertilization time and fertilization method, to ensure that crops obtain the nutrients they need during the growth process. According to the soil nutrient evaluation index and the assessment results of soil nutrient status, obtain accurate soil nutrient data through soil nutrient testing, determine the sufficiency of each nutrient in the soil, identify deficient, suitable and excessive nutrients, identify which nutrients in the soil are insufficient, which may be excessive and which nutrients are at an appropriate level. Analyze the type and growth stage of the crop, determine its demand for soil nutrients such as nitrogen, phosphorus and potassium, and select fertilizers containing the required nutrients (such as nitrogen, phosphorus and potassium). If the nitrogen content in the soil is insufficient, nitrogen fertilizer can be selected. If the phosphorus and potassium content are insufficient, compound fertilizer can be selected. Or phosphorus fertilizer, potassium fertilizer, according to the soil nutrient test results and crop nutrient requirements, accurately calculate the recommended application amount of each nutrient to ensure that the nutrient supply is sufficient but not excessive, and determine the application time of basal fertilizer according to the crop growth cycle and nutrient requirements, usually before sowing or in the early stage of crop growth, according to the crop growth and soil nutrient conditions, determine the best time for topdressing, avoid fertilizing during the crop dormancy period or when the nutrient demand is low, based on the crop sowing needs, select the fertilization method, which are soil fertilization, foliar spraying and irrigation fertilization, among which soil fertilization includes broadcasting, strip application, spot application, etc., which is selected according to the crop root distribution and soil conditions. For some nutrients, such as trace elements, foliar spraying is used to directly supply crops, and irrigation fertilization is combined with irrigation systems, such as drip irrigation, to improve the utilization rate of fertilizers; Step 4: Based on the growth characteristics of crops and the actual conditions of the soil, optimize the sowing parameters of crops, including sowing depth, row spacing and plant spacing, through simulation and experimental verification, to ensure that crops grow under optimal conditions; Step 5. Use intelligent fertilization equipment to carry out precise fertilization and crop sowing according to fertilization parameters and optimized crop sowing parameters, and automatically adjust the amount of fertilizer based on real-time monitoring data to ensure uniform distribution and effective use of fertilizers.

[0020] Embodiment 2, as Figure 3 As shown, based on Example 1, the present invention provides a technical solution: Preferably, in step 4, the optimization process of crop sowing parameters is: Clarify the growth characteristics of crops, including seed germination conditions, root development, light requirements, and water requirements, and analyze the actual soil conditions to determine the soil texture, pH value, organic matter content, drainage capacity, and nutrient level of the farmland plots in the target area. According to the size of crop seeds and germination requirements, determine the appropriate sowing depth range, and refer to the historical data of crop sowing to preliminarily set the row spacing and plant spacing. Use simulation software to simulate the growth of crops at different sowing depths within the sowing depth range based on the root distribution of crops and soil conditions, and set different sowing depths in the farmland plots in the target area. The optimal sowing depth is determined based on the simulation and experimental results. The crop growth under different row spacing and plant spacing is simulated using the crop growth model and spatial distribution model. The test blocks with different row spacing and plant spacing are set up in the farmland plots in the target area to observe the crop growth, light utilization, ventilation conditions and yield indicators. The optimal row spacing and plant spacing are determined based on the simulation and experimental results. Combined with the optimization results of sowing depth, row spacing and plant spacing, the comprehensive score of the optimal sowing parameters is calculated, and then the optimal sowing parameter combination is determined. Furthermore, the calculation formula for the optimal seeding parameter comprehensive score is: ; in, is the comprehensive score of the optimal sowing parameters, D is the actual sowing depth, The optimal planting depth for the crop is determined based on the crop seed size and germination requirements. is the standard deviation of sowing depth, reflecting the variability of sowing depth under different conditions, R is the actual row spacing, The optimal row spacing for crops is determined based on crop growth model and spatial distribution model. is the standard deviation of row spacing, reflecting the variability of row spacing under different conditions, S is the actual plant spacing, The optimal spacing between crops is determined based on crop growth model and spatial distribution model. is the standard deviation of plant spacing, reflecting the variability of plant spacing under different conditions. The value range is between 0 and 1. The closer the value is to 1, the better the sowing parameters are. When the sowing depth D, row spacing R and plant spacing S are close to their optimal values , and hour, Close to 1, it means that the seeding parameters are optimal. If any parameter deviates from its optimal value, will decrease, indicating that the seeding parameters need to be adjusted; In step 5, the process of precision fertilization and crop sowing is as follows: Based on the determined fertilizer type, application amount, fertilization time and method, as well as sowing depth, row spacing and plant spacing, calibrate intelligent fertilization equipment (such as intelligent sprinkler system, precision fertilizer applicator) to ensure the accuracy of fertilizer application amount, and input fertilization parameters and sowing parameters into the control system of intelligent fertilization equipment. Use intelligent fertilization equipment to apply fertilizer while sowing to ensure that the fertilizer is evenly distributed around the seeds. Use sensors to monitor soil moisture, temperature, and pH value, and then automatically adjust the amount of fertilizer based on real-time monitoring data to ensure uniform distribution and effective use of fertilizers. Record the time, location and amount of each fertilization for subsequent analysis and adjustment, and regularly evaluate the fertilization effect, including changes in crop growth conditions and soil nutrient levels, analyze fertilization data and crop growth data, and identify problems and room for improvement in fertilization strategies.

[0021] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A crop sowing parameter control optimization method for multi-objective precision fertilization, characterized in that: The following steps are involved: Step 1: Collect soil samples for spectral scanning and analysis, establish a soil nutrient content prediction model based on known soil nutrient data, and predict the nutrient content in the soil based on spectral data; Step 2: Analyze the prediction results, evaluate the nutrient status of the soil, comprehensively reflect the soil nutrient level, and classify it; Step 3: Determine the fertilization parameters for crop sowing based on the evaluation results of soil nutrient levels and the nutrient requirements of crop sowing; Step 4: Combine the growth characteristics of crops and the actual conditions of the soil, and optimize the sowing parameters of crops, including sowing depth, row spacing, and plant spacing, through simulation and experimental verification; Step 5: Use intelligent fertilization equipment to carry out precise fertilization and crop sowing according to fertilization parameters and optimized crop sowing parameters.

2. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 1 is characterized in that: In step 1, the prediction process of soil nutrient content is: Soil samples are collected from farmland plots in the target area, and a spectrometer is used to perform spectral scans on the soil samples using visible-near infrared and mid-infrared to obtain spectral reflectance data of the soil in different bands; Preprocessing the acquired spectral data includes atmospheric correction, stray light correction and data normalization steps; Extract spectral features of characteristic bands related to nutrients required for crop sowing from spectral data. The spectral features are reflectance and absorption rate. Divide the known soil nutrient data into training set and test set. The soil nutrient content prediction model was established using the training set data combined with the support vector machine machine learning algorithm, the correlation between spectral characteristics and nutrient content was analyzed, and the model was verified using the test set data; The spectral characteristics of soil samples from farmland plots in the target area are input into the established soil nutrient content prediction model to obtain the predicted content of soil nutrients.

3. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 2 is characterized in that: In step 2, the evaluation process of soil nutrient status is as follows: Arrange the predicted soil nutrient content data to form a soil nutrient data sequence table, where each data point has clear soil sample number, sampling location, and sampling time information; Based on crop growth requirements, soil type and regional climate factors, a standard value data set is obtained through comprehensive analysis, including standard values ​​of soil nutrient content required for sowing different crops; Compare and analyze the sorted soil nutrient data with the standard values ​​of soil nutrient content for crop sowing, calculate the soil nutrient evaluation index, and quantitatively evaluate the nutrient status of the soil samples; According to the calculation results of soil nutrient evaluation index, the proportion and relationship between different nutrients are compared to further analyze the nutrient adequacy, balance and deficiency / excess; According to the evaluation results of soil nutrient evaluation index and soil nutrient status, the soil nutrient level is divided into different nutrient levels, namely, rich nutrient level, medium nutrient level and lack of nutrient level, and the corresponding nutrient evaluation threshold is matched for each nutrient level.

4. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 3 is characterized in that: The calculation process of the soil nutrient evaluation index is: Collect the actual nutrient content of the soil samples, record the corresponding standard nutrient content, and determine the number of nutrient types. For each soil nutrient, calculate the ratio of its actual content to the standard content, and calculate the sum of the squares of the ratios. Calculate the maximum sum of squares of all nutrient ratios in multiple soil samples, and divide the sum of squares of the ratios by the maximum sum of squares of all nutrient ratios to obtain the benchmark ratio function. , analyze the minimum and maximum values ​​of the ratio of actual content to standard content, and obtain the equilibrium ratio function , combining the benchmark ratio function and the equilibrium ratio function to calculate the soil nutrient evaluation index; The calculation formula of the soil nutrient evaluation index is: ； ； ； Among them, SI is the soil nutrient evaluation index, is the benchmark ratio function, is the equilibrium ratio function, is the actual content of the ith nutrient, is the standard content of the i-th nutrient, n is the number of nutrient types, for and The minimum value of the ratio, for and The maximum value of the ratio. The SI value range is between 0 and 1.

5. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 4 is characterized in that: The plurality of nutrient levels correspond to the plurality of nutrient evaluation thresholds, wherein the nutrient evaluation thresholds include an upper threshold and a lower threshold; The plurality of nutrient levels and the plurality of nutrient evaluation thresholds satisfy the following relationship: Rich nutrient levels ; Medium nutrient level ; Lack of nutrient levels ; Among them, SI is the soil nutrient evaluation index, is the lower threshold corresponding to the rich nutrient level and the upper threshold corresponding to the medium nutrient level, is the lower threshold corresponding to the medium nutrient level and the upper threshold corresponding to the nutrient deficiency level, , .

6. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 5 is characterized in that: In step 3, the process of determining the crop sowing and fertilization parameters is as follows: Based on the evaluation results of soil nutrient evaluation index and soil nutrient status, soil nutrient data can be obtained through soil nutrient testing to determine the sufficiency of each nutrient in the soil and identify deficient, suitable and excessive nutrients; Analyze crop types and growth stages to determine their soil nutrient requirements and select fertilizers containing the required nutrients; According to the soil nutrient test results and crop nutrient requirements, accurately calculate the recommended application amount of each nutrient, and determine the application time of base fertilizer according to the crop growth cycle and nutrient requirements; Based on the crop sowing requirements, the fertilization method is selected, which are soil fertilization, foliar spraying and irrigation fertilization.

7. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 6 is characterized in that: In step 4, the optimization process of crop sowing parameters is as follows: Identify the growth characteristics of crops, including seed germination conditions, root development, light requirements, water requirements, and analyze the actual soil conditions to determine the texture, pH value, organic matter content, drainage capacity, and nutrient levels of the soil in the target area; Determine the appropriate sowing depth range based on the size of crop seeds and germination requirements, and refer to historical crop sowing data to preliminarily set the row spacing and plant spacing; Using simulation software, we simulated the growth of crops at different sowing depths within a range of sowing depths according to the root distribution of crops and soil conditions, and set up test plots with different sowing depths in the farmland plots in the target area to observe the emergence rate, growth rate and yield indicators of crops. Based on the simulation and experimental results, we determined the optimal sowing depth. Using crop growth models and spatial distribution models, simulate the growth of crops under different row and plant spacings, and set up test plots with different row and plant spacings in the farmland plots in the target area to observe the growth status, light utilization, ventilation conditions and yield indicators of crops. According to the simulation and experimental results, determine the optimal row and plant spacing; Combined with the optimization results of sowing depth, row spacing and plant spacing, the comprehensive score of the optimal sowing parameters was calculated to determine the best combination of sowing parameters.

8. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 7 is characterized in that: The calculation formula for the optimal sowing parameter comprehensive score is: ； in, is the comprehensive score of the optimal sowing parameters, D is the actual sowing depth, The optimal sowing depth for crops, is the standard deviation of sowing depth, R is the actual row spacing, The optimal row spacing for crops, is the standard deviation of row spacing, S is the actual plant spacing, The optimal spacing between crops. is the standard deviation of plant spacing.

9. The crop sowing parameter control optimization method for multi-objective precision fertilization according to claim 8, characterized in that: In step 5, the process of precision fertilization and crop sowing is as follows: Based on the determined fertilizer type, application amount, fertilization time and fertilization method, as well as the sowing depth, row spacing and plant spacing, the intelligent fertilization equipment is calibrated, and the fertilization parameters and sowing parameters are input into the control system of the intelligent fertilization equipment; Use intelligent fertilization equipment to apply fertilizers while sowing, and use sensors to monitor soil moisture, temperature, and pH value, and then automatically adjust the amount of fertilizer based on real-time monitoring data; Record the time, location and amount of each fertilization, and regularly evaluate the fertilization results, including changes in crop growth conditions and soil nutrient levels, analyze fertilization data and crop growth data, and identify problems and room for improvement in fertilization strategies.

Images