A method for identifying dynamic frost resistance of winter wheat

Abstract

The present invention relates to the field of agricultural science, and in particular to a method for identifying the dynamic frost resistance of winter wheat. The present invention collects the time period, freezing temperature and duration of winter wheat growth, and the resulting tiller mortality rate and yield loss rate, and simultaneously determines the effective negative accumulated temperature of the soil; further, in combination with historical data, predicts the target growth score; determines the critical frost resistance temperature by analyzing the yield loss rate and tiller mortality rate, and evaluates the influence of these factors on the observed values, thereby obtaining the influence coefficient; determines the actual frost resistance index using the influence coefficient and the actual observed value, and compares it with the preset target to formulate a sowing strategy; finally, adjusts the optimization parameters according to the sowing strategy to improve the frost resistance of winter wheat. The present invention can effectively evaluate the frost resistance of winter wheat, optimize the sowing strategy, and increase the yield.

Description

Technical Field

[0001] The invention relates to the field of agricultural science, and in particular to a method for identifying the dynamic frost resistance of winter wheat. Background Art

[0002] Winter wheat is an important food crop, widely grown in temperate and cold regions such as China. Low temperatures in winter may cause frost damage to winter wheat, affecting its growth and yield. Therefore, studying and identifying the frost resistance of winter wheat is of great significance for the cultivation and breeding of winter wheat.

[0003] Patent document with publication number CN105875225A discloses a method for identifying spring frost resistance of wheat by using leaf freezing damage. The method selects the 3rd to 5th day after the temperature rises after the spring frost occurs as the investigation time; selects sample sections and conducts field positioning for the investigated sample points; after obtaining the data from the investigation, the prevalence rate P of frozen leaves, the severity rate S of frozen leaves, the spring frost resistance index I, and the spring frost resistance coefficient R are calculated respectively, and then the levels of the prevalence rate P of frozen leaves, the severity rate S of frozen leaves, the spring frost resistance index I, and the spring frost resistance coefficient R are determined respectively; the spring frost resistance coefficient R is suitable for identifying the spring frost resistance of a few varieties; the spring frost resistance index I is suitable for identifying the spring frost resistance of a large number of materials; if spring frost-resistant parent materials are to be screened from a large number of germplasm materials, the spring frost resistance index I is used for primary selection, and then the spring frost resistance coefficient R is used for fine selection.

[0004] It can be seen that the existing technology has the following problems: the selection and definition of indicators may not be sufficient to fully reflect the spring frost resistance of wheat varieties, resulting in poor evaluation of frost resistance. Summary of the invention

[0005] To this end, the present invention provides a method for identifying the dynamic frost resistance of winter wheat, so as to overcome the problem that the selection and definition of indicators in the prior art may not be sufficient to fully reflect the spring frost resistance of wheat varieties, thereby resulting in poor frost resistance assessment.

[0006] To achieve the above object, the present invention provides a method for identifying the dynamic frost resistance of winter wheat, comprising:

[0007] Step S1, obtaining the time period, freezing temperature and freezing duration of winter wheat, obtaining the stem tiller mortality rate and yield loss rate of the winter wheat according to the time period, freezing temperature and freezing duration, and also obtaining the effective negative accumulated temperature of the soil;

[0008] Step S2, obtaining historical data of winter wheat, and predicting a target growth score according to the time period, the freezing temperature, the freezing time, the tiller mortality rate, the yield loss rate and the historical data;

[0009] Step S3, determining the critical antifreeze temperature of winter wheat according to the yield loss rate and the tiller mortality rate, and analyzing the influence of the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score to obtain an influence coefficient on the target growth score;

[0010] Step S4, determining an actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat, comparing the actual frost resistance index with a preset target frost resistance index, and formulating a winter wheat sowing strategy according to the comparison result;

[0011] Step S5, adjusting the sowing strategy optimization parameters according to the winter wheat sowing strategy.

[0012] Furthermore, the process of obtaining the effective accumulated soil temperature includes:

[0013] Several sampling points were randomly selected in the winter wheat fields, and soil samples were collected using a soil sampler;

[0014] Installing a temperature sensor in the collected soil sample to measure the soil temperature at each sampling point;

[0015] Calculate the effective negative accumulated soil temperature of each day according to the soil temperature;

[0016] The soil effective accumulated temperature values ​​of each day are accumulated to obtain the soil effective negative accumulated temperature of the time period.

[0017] Furthermore, the process of step S2 includes:

[0018] The time period, the freezing temperature, the freezing time, the stem and tiller mortality rate, the yield loss rate and the historical data are cleaned and standardized to obtain historical data processing results and actual data processing results;

[0019] Constructing a feature vector according to the historical data results and the actual data results;

[0020] The characteristic vector is used as a model input parameter to construct a growth curve model to predict the target growth score.

[0021] Furthermore, the process of using the feature vector as a model input parameter to construct a growth curve model to predict the target growth score includes:

[0022] Divide the historical data set into a training data set and a validation data set;

[0023] Training the growth curve model according to the training data set to obtain a first training model;

[0024] Using the validation data set to validate the first training model to obtain a validation model;

[0025] The target growth score is predicted based on the validated model.

[0026] Further, the process of determining the critical frost resistance temperature of winter wheat according to the yield loss rate and the tiller mortality rate includes:

[0027] A statistical model is constructed by taking the critical antifreeze temperature as an independent variable and the yield loss rate and the stem and tiller mortality rate as dependent variables;

[0028] Using the training data set to train the statistical model to obtain a second training model;

[0029] The stem and tiller mortality rate and the yield loss rate are predicted within a preset temperature range according to the second training model to determine the critical antifreeze temperature.

[0030] Furthermore, the process of analyzing the influence of the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score to obtain the influence coefficient on the target growth score includes:

[0031] The correlation between the critical antifreeze temperature and the soil effective negative accumulated temperature on the target growth score is analyzed using the Pearson image relationship to construct a correlation matrix;

[0032] The influence coefficient between the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score is calculated based on the correlation matrix.

[0033] Furthermore, the process of determining the actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat includes:

[0034] Collecting actual observation data of winter wheat to obtain the actual observation value;

[0035] Performing data cleaning on the actual observation value to obtain a cleaning result;

[0036] The actual antifreeze ability index is calculated according to the cleaning result and the influence coefficient.

[0037] Furthermore, the process of comparing the actual antifreeze ability index with a preset target antifreeze ability index and formulating a winter wheat sowing strategy according to the comparison result includes:

[0038] Obtaining a preset target antifreeze capacity index;

[0039] Comparing the actual antifreeze ability index with the target antifreeze ability index to obtain a comparison result;

[0040] The winter wheat sowing strategy is formulated according to the comparison results, wherein:

[0041] If the frost resistance is insufficient, the soil fertility is improved or the planting time is adjusted;

[0042] If the antifreeze capacity reaches the target requirement, the sowing density is increased.

[0043] Further, the process of comparing the actual antifreeze ability index with the target antifreeze ability index to obtain a comparison result includes:

[0044] When the actual antifreeze ability index is less than the preset target antifreeze ability index, the antifreeze ability of the winter wheat is improved, such as by changing the freezing temperature or extending the freezing time;

[0045] When the actual antifreeze ability index is equal to or greater than the preset target antifreeze ability index, the existing sowing conditions are maintained or optimized.

[0046] Furthermore, the process of step S5 includes:

[0047] adjusting the sowing parameters of the winter wheat according to the sowing strategy;

[0048] Monitoring the growth of the winter wheat to evaluate the effect of the adjustment to obtain monitoring results;

[0049] The winter wheat sowing strategy is adjusted according to the monitoring results.

[0050] Compared with the prior art, the beneficial effect of the present invention is that, by determining the critical antifreeze temperature of winter wheat and the effective negative accumulated temperature of the soil, the present invention can help agricultural producers select winter wheat varieties suitable for local climatic conditions, thereby increasing yields and reducing frost damage losses. According to the comparison between the actual antifreeze ability index and the target antifreeze ability index, the sowing time can be adjusted to ensure planting under the most suitable climatic conditions, and the planting density can be adjusted to maximize the efficiency of photosynthesis and reduce the risk of frost damage. Through precise sowing strategies and optimized parameters, unnecessary use of fertilizers and pesticides can be reduced, thereby reducing pollution to the environment and saving costs. Accurate frost resistance assessment can help agricultural producers reduce stem and tiller death and yield losses caused by frost damage, thereby reducing economic losses.

[0051] In particular, by randomly selecting sampling points in winter wheat fields, soil temperature changes can be monitored more accurately to ensure the representativeness and accuracy of the data. By accurately calculating the effective negative accumulated soil temperature, farmers can reasonably arrange sowing time and take appropriate cultivation management measures, thereby improving the yield and quality of winter wheat.

[0052] In particular, the accuracy and consistency of the data are improved through cleaning and standardization. This helps the model to better understand and utilize the data, thereby improving the accuracy of predictions. By constructing feature vectors with historical data and actual data, features that have a significant impact on the target growth score can be screened out, and unimportant or redundant features can be excluded, which helps to simplify the model, reduce the risk of overfitting, and improve the interpretability and predictive power of the model. After building and training a suitable model, the prediction accuracy of the target growth score can be improved, thereby providing more accurate guidance for agricultural production.

[0053] In particular, the growth curve model is trained using the training data set, so that the model can learn the inherent laws and relationships in the data and establish an accurate mathematical model for predicting the target growth score. By validating the trained model using an independent validation data set, the accuracy and robustness of the model can be evaluated to ensure that the model can reliably predict the target growth score in practical applications. Based on the validation model, the target growth score in the new data set can be predicted, providing practical guidance value for agricultural production.

[0054] In particular, by constructing a statistical model, the yield loss rate and tiller mortality of winter wheat under different temperature conditions can be accurately predicted, so as to more accurately determine the critical frost resistance temperature that affects the growth of winter wheat. The precise critical frost resistance temperature can guide agricultural production, help farmers reasonably arrange sowing time and take corresponding anti-freeze measures, thereby reducing yield losses caused by low temperature frost damage and reducing economic losses.

[0055] In particular, by collecting comprehensive data, the impact of critical antifreeze temperature and soil effective negative accumulated temperature on the target growth score can be analyzed more accurately. Pearson correlation analysis can reveal the linear relationship between critical antifreeze temperature and soil effective negative accumulated temperature and the target growth score, helping to understand the interaction between variables. The correlation matrix provides an intuitive view showing the degree of correlation between critical antifreeze temperature and soil effective negative accumulated temperature and the target growth score. Calculating the influence coefficient can quantify the impact of critical antifreeze temperature and soil effective negative accumulated temperature on the target growth score, providing a quantitative basis for subsequent decision-making.

[0056] In particular, collecting actual observation data of winter wheat to obtain the actual observation values ​​is helpful to understand the actual performance of winter wheat at different growth stages. Data cleaning of the actual observation values ​​improves data quality, removes possible erroneous data or outliers, and reduces data noise. Ensure the accuracy and reliability of subsequent calculations and analyses. Calculating the frost resistance index based on the cleaning results and the influence coefficient helps to quantify the frost resistance of winter wheat, and can evaluate the frost resistance of winter wheat under different varieties or planting conditions.

[0057] In particular, by comparing the actual frost resistance index with the target frost resistance index, insufficient frost resistance can be identified, so that measures can be taken to improve the frost resistance of winter wheat. Improving soil fertility can help plants better resist cold conditions and enhance the physiological cold resistance of plants by providing necessary nutrients. Adjusting the planting time can avoid sowing in extremely cold periods and reduce the risk of frost damage. By taking precautions in advance and adjusting sowing strategies, yield losses caused by frost damage can be reduced, thereby reducing economic losses. Avoid sowing at unsuitable times to reduce the growth stunting or death of winter wheat caused by cold weather and ensure production stability.

[0058] In particular, changing the freezing temperature or extending the freezing time can help winter wheat better adapt to cold environments and reduce the risk of frost damage. By maintaining or optimizing sowing conditions, it is possible to ensure that winter wheat receives sufficient light, water and nutrients throughout the growth cycle to promote its healthy growth. By adjusting sowing conditions, the loss of winter wheat yield caused by frost damage can be reduced, thereby reducing economic losses. Avoid sowing when the frost resistance is insufficient, reduce the growth stagnation or death of winter wheat caused by cold weather, and ensure production stability.

[0059] In particular, by adjusting sowing parameters such as sowing time and density, the frost resistance of winter wheat can be improved and the risk of frost damage can be reduced. Through monitoring and evaluation, sowing strategies can be optimized to increase yield per unit area while making rational use of resources such as land, water and fertilizer. Through scientific adjustment of sowing strategies, yield losses caused by frost damage can be reduced, thereby reducing economic losses. By reducing the use of chemical fertilizers and pesticides, eco-friendly agricultural practices can be promoted to improve the adaptability and resilience of agricultural systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of a process for identifying the dynamic frost resistance of winter wheat provided by an embodiment of the present invention;

[0061] Figure 2 A schematic flow chart of step S2 in the method for identifying the dynamic frost resistance of winter wheat provided in an embodiment of the present invention;

[0062] Figure 3 A schematic diagram of a process for determining the critical antifreeze temperature of winter wheat according to the yield loss rate and the tiller mortality rate in the method for identifying the dynamic antifreeze ability of winter wheat provided by an embodiment of the present invention;

[0063] Figure 4 A schematic diagram of a process for determining an actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat in the method for identifying the dynamic frost resistance of winter wheat provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0066] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0067] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0068] See also Figure 1 As shown, the method for evaluating the dynamic frost resistance of winter wheat provided by the embodiment of the present invention comprises:

[0069] Step S1, obtaining the time period, freezing temperature and freezing duration of winter wheat, obtaining the stem tiller mortality rate and yield loss rate of the winter wheat according to the time period, freezing temperature and freezing duration, and also obtaining the effective negative accumulated temperature of the soil;

[0070] Step S2, obtaining historical data of winter wheat, and predicting a target growth score according to the time period, the freezing temperature, the freezing time, the tiller mortality rate, the yield loss rate and the historical data;

[0071] Step S3, determining the critical antifreeze temperature of winter wheat according to the yield loss rate and the tiller mortality rate, and analyzing the influence of the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score to obtain an influence coefficient on the target growth score;

[0072] Step S4, determining an actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat, comparing the actual frost resistance index with a preset target frost resistance index, and formulating a winter wheat sowing strategy according to the comparison result;

[0073] Step S5, adjusting the sowing strategy optimization parameters according to the winter wheat sowing strategy.

[0074] Specifically, the historical data refers to the historical data of the past three years. The time period refers to the wintering period, the midwinter period and the anti-greening period.

[0075] Specifically, the historical data includes growth indicator data, environmental factor data, physiological indicator data, pest and disease data, agricultural management measures data, and historical growth data.

[0076] Growth indicator data include plant height, leaf area index, dry matter accumulation, number of tillers, etc. These data can reflect the growth status and growth rate of winter wheat.

[0077] Environmental factor data include daily average temperature, daily minimum temperature, daily maximum temperature, precipitation, soil moisture, etc., which affect the growing environment and freezing risk of winter wheat.

[0078] Physiological indicator data include nitrogen content, phosphorus content, potassium content, starch content, soluble sugar content, etc. These data reflect the nutritional status and physiological health of winter wheat.

[0079] Pest and disease data include disease spot area, pest level, number of pathogens, etc. These data indicate the extent to which winter wheat is affected by pests and diseases.

[0080] Agricultural management measures data include sowing amount, fertilizer amount, irrigation amount, pesticide application amount, etc. These data reflect the management measures and interventions of agricultural producers on winter wheat.

[0081] Historical growth data include tiller mortality, yield loss rates, and growth curve model predictions from past years, which provide a record of winter wheat growth trends and historical performance.

[0082] Specifically, the wintering period, midwinter period and greening period of winter wheat were determined, which have an important impact on the growth and frost resistance of winter wheat. The specific date of each stage was recorded to calculate the freezing temperature and freezing duration. Data on tiller mortality and yield loss rate were collected through field surveys and sampling. Meteorological data were used to calculate the effective negative accumulated soil temperature, which was usually calculated by recording the minimum temperature of each day and accumulating the number of days below 0°C. Historical data and statistical models (such as linear regression, logistic regression, etc.) were used to predict the target growth scores under different freezing conditions, such as growth rate, number of tillers, and yield. Based on the data on tiller mortality and yield loss rate, the critical frost resistance temperature of winter wheat was determined, that is, below this temperature, winter wheat began to suffer from frost damage. The influence of critical frost resistance temperature and effective negative accumulated soil temperature on the target growth score was analyzed, and the influence coefficient was calculated. The actual frost resistance index of winter wheat was calculated by combining the influence coefficient and the actual observation value. The actual frost resistance index was compared with the preset target frost resistance index to formulate a sowing strategy. For example, if the actual frost tolerance index is lower than the target index, it may be necessary to select a more frost-resistant variety or adjust the sowing time.

[0083] Adjust the existing sowing strategy based on the calculation results, such as selecting more frost-resistant varieties, adjusting sowing time, changing fertilization plans, etc. Optimization parameters include but are not limited to planting density, variety selection, soil management, irrigation, and pest and disease control.

[0084] Specifically, by determining the critical frost resistance temperature of winter wheat and the effective negative accumulated temperature of the soil, agricultural producers can choose winter wheat varieties suitable for local climatic conditions, thereby increasing yields and reducing frost damage losses. Based on the comparison between the actual frost resistance index and the target frost resistance index, the sowing time can be adjusted to ensure planting under the most suitable climatic conditions, and the planting density can be adjusted to maximize the efficiency of photosynthesis and reduce the risk of frost damage. Through precise sowing strategies and optimized parameters, unnecessary use of fertilizers and pesticides can be reduced, thereby reducing pollution to the environment and saving costs. Accurate frost resistance assessment can help agricultural producers reduce stem and tiller death and yield losses caused by frost damage, thereby reducing economic losses.

[0085] Specifically, the process of obtaining the effective accumulated soil temperature includes:

[0086] Several sampling points were randomly selected in the winter wheat fields, and soil samples were collected using a soil sampler;

[0087] Installing a temperature sensor in the collected soil sample to measure the soil temperature at each sampling point;

[0088] Calculate the effective negative accumulated soil temperature of each day according to the soil temperature;

[0089] The soil effective accumulated temperature values ​​of each day are accumulated to obtain the soil effective negative accumulated temperature of the time period.

[0090] Specifically, several sampling points are randomly selected in the winter wheat field to ensure that the selection of sampling points is representative. Soil samples are collected at a predetermined depth using a soil sampler (such as a spiral sampler or a shovel). The predetermined depth ranges from 0 cm to 20 cm. The geographical location information of each sampling point is recorded for subsequent data analysis and processing. A temperature sensor is installed in the collected soil sample to ensure that the sensor is in full contact with the soil and can accurately reflect the soil temperature. If it is a portable soil thermometer, it can be directly inserted into the soil for measurement. The soil temperature measured at each sampling point is recorded, and multiple measurements are usually made at different times of the day to obtain a full picture of the temperature change. Based on the soil temperature measured each time, determine whether the soil is below 0°C. If the soil temperature is below 0°C, the temperature of that day is multiplied by the corresponding soil depth and calendar days to calculate the effective negative accumulated temperature of the soil on that day. The effective negative accumulated temperature values ​​of the soil for each day are accumulated to obtain the total effective negative accumulated temperature of the soil for the entire growing season. The measured soil temperature data and the calculated effective negative accumulated temperature of the soil are recorded in a special table or database. Analyze the data using statistical software or data analysis tools to determine the relationship between soil effective negative accumulated temperature and winter wheat growth and frost resistance.

[0091] Specifically, by randomly selecting sampling points in winter wheat fields, soil temperature changes can be monitored more accurately to ensure the representativeness and accuracy of the data. By accurately calculating the effective negative accumulated soil temperature, it can help farmers reasonably arrange sowing time and take appropriate cultivation management measures, thereby improving the yield and quality of winter wheat.

[0092] Specifically, if Figure 2 As shown, the process of step S2 includes:

[0093] Step S21, cleaning and standardizing the time period, the freezing temperature, the freezing time, the tiller mortality rate, the yield loss rate and the historical data to obtain historical data processing results and actual data processing results;

[0094] Step S22, constructing a feature vector according to the historical data results and the actual data results;

[0095] Step S23, using the feature vector as a model input parameter to construct a growth curve model to predict the target growth score.

[0096] Specifically, remove invalid records in the time period data, such as missing values ​​or data of abnormal size. Exclude unreasonable values ​​in temperature records, such as negative temperatures or values ​​far above the normal range. Remove unreasonable freezing duration records, such as negative values ​​or abnormally long freezing durations. Exclude outliers or missing data in tiller mortality records. Remove unreasonable values ​​or missing data in yield loss rate records. Clean historical data: handle missing values, outliers, and duplicate records to ensure data accuracy and consistency. Standardize the cleaned data, such as using Z-score standardization to scale the data to a range of -1 to 1. Select features that are highly correlated with the target growth score: for example, select daily average temperature, daily minimum temperature, daily maximum temperature, precipitation, plant height, leaf area index, etc. as features. Construct feature vectors based on historical data and actual data: for example, if the goal is to predict the yield loss rate of winter wheat, features such as freezing temperature, freezing duration, and tiller mortality can be selected to construct feature vectors. Select a growth curve model or a machine learning model: for example, a Logistic model. Use the feature vector and historical data of the target growth score to train the model to predict the target growth score. For example, the model is trained using feature vectors from historical data and the corresponding yield loss rate data.

[0097] Specifically, the accuracy and consistency of the data are improved through cleaning and standardization. This helps the model to better understand and utilize the data, thereby improving the accuracy of predictions. By constructing feature vectors with historical data and actual data, features that have a significant impact on the target growth score can be screened out, and unimportant or redundant features can be excluded, which helps to simplify the model, reduce the risk of overfitting, and improve the interpretability and predictive power of the model. After building a suitable model and training it, the prediction accuracy of the target growth score can be improved, thereby providing more accurate guidance for agricultural production.

[0098] Specifically, the process of using the feature vector as a model input parameter to construct a growth curve model to predict the target growth score includes:

[0099] Divide the historical data set into a training data set and a validation data set;

[0100] Training the growth curve model according to the training data set to obtain a first training model;

[0101] Using the validation data set to validate the first training model to obtain a validation model;

[0102] The target growth score is predicted based on the validated model.

[0103] Specifically, the training dataset is used to train the model, while the validation dataset is used to evaluate the performance of the model. Typically, 70%-80% of the data can be used as the training dataset, and the remaining 20%-30% as the validation dataset. Make sure that the training dataset and the validation dataset do not overlap in time to avoid the impact of historical data on the prediction of future data. The growth curve model can be a linear model, a nonlinear model, or another type of statistical model. During the training process, the model learns patterns and relationships in the data for subsequent prediction tasks. Apply techniques such as cross-validation to evaluate the generalization ability of the model, and adjust model parameters to optimize model performance. Evaluate the predictive performance of the model, for example, by calculating the mean square error (MSE), the coefficient of determination (R 2 ) or other relevant indicators. The validation process helps evaluate the generalization ability of the model on unknown data. If the model performance is poor, reconstruct the feature vector or adjust the model parameters. Perform model evaluation based on the model performance on the validation dataset. If the model performance is satisfactory, you can proceed to the next prediction task. If the model performance is poor, you may need to further optimize the model, such as through feature selection, model structure adjustment, parameter optimization, etc. Use the model to make real-time predictions on new data, such as predicting future yield loss rates. Ensure that the model can receive real-time data as input and generate predictions for the target growth score.

[0104] Specifically, the growth curve model is trained using the training data set, so that the model can learn the inherent laws and relationships in the data and establish an accurate mathematical model for predicting the target growth score. By verifying the trained model using an independent validation data set, the accuracy and robustness of the model can be evaluated to ensure that the model can reliably predict the target growth score in practical applications. Based on the validation model, the target growth score in the new data set can be predicted, providing practical guidance value for agricultural production.

[0105] Specifically, if Figure 3 As shown, the process of determining the critical frost resistance temperature of winter wheat according to the yield loss rate and the tiller mortality rate includes:

[0106] Step S31, constructing a statistical model using the critical antifreeze temperature as an independent variable, and the yield loss rate and the stem and tiller mortality rate as dependent variables;

[0107] Step S32, using the training data set to train the statistical model to obtain a second training model;

[0108] Step S33, predicting the tiller mortality rate and the yield loss rate within a preset temperature range according to the second training model to determine the critical antifreeze temperature.

[0109] Specifically, collect a large amount of data on yield loss rate and tiller mortality of winter wheat under different temperature conditions. The data should include yield loss rate and tiller mortality at different critical antifreeze temperatures. Select a suitable statistical model, such as a linear regression model, a logistic regression model, or a machine learning algorithm, with the critical antifreeze temperature as the independent variable and the yield loss rate and tiller mortality as the dependent variables. For example, if a linear regression model is used, the model may be in the form of: Y = β0 + β1 × X + ε, where Y represents the yield loss rate or tiller mortality, X represents the critical antifreeze temperature, β0 represents the intercept, β1 represents the slope, and ε represents the error term.

[0110] Use the training data set to train the constructed statistical model. Optimize the model parameters (β0 and β1) by minimizing the difference between the model's predicted values ​​and the actual values. During the training process, statistical software (such as R, Python, etc.) or machine learning frameworks (such as scikit-learn, etc.) can be used to implement model training. Use the validation data set to verify the accuracy of the trained model. Evaluate the predictive performance of the model, such as calculating the coefficient of determination (R 2 ), mean square error (MSE) or other appropriate evaluation indicators. According to the trained model, the tiller mortality rate and yield loss rate are predicted within the preset temperature range. The prediction results of the model can be used to determine the critical antifreeze temperature, that is, below this temperature, the yield loss rate and tiller mortality rate of winter wheat increase significantly. According to the results of model validation, the model is adjusted and optimized to improve the accuracy of the prediction. It involves selecting different models, adjusting model parameters or introducing additional variables. Finally, the critical antifreeze temperature is determined based on the tiller mortality rate and yield loss rate predicted by the model. The critical antifreeze temperature is the temperature point at which the yield loss rate and tiller mortality rate predicted by the model increase significantly.

[0111] Specifically, by constructing a statistical model, the yield loss rate and tiller mortality of winter wheat under different temperature conditions can be accurately predicted, so as to more accurately determine the critical antifreeze temperature that affects the growth of winter wheat. The precise critical antifreeze temperature can guide agricultural production, help farmers reasonably arrange sowing time and take corresponding antifreeze measures, thereby reducing yield losses caused by low temperature frost damage and reducing economic losses.

[0112] Specifically, the process of analyzing the influence of the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score to obtain the influence coefficient on the target growth score includes:

[0113] The correlation between the critical antifreeze temperature and the soil effective negative accumulated temperature on the target growth score is analyzed using the Pearson image relationship to construct a correlation matrix;

[0114] The influence coefficient between the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score is calculated based on the correlation matrix.

[0115] Specifically, the growth data of winter wheat under different critical antifreeze temperatures and soil effective negative accumulated temperatures were collected. The data should include critical antifreeze temperature, soil effective negative accumulated temperature, and the corresponding target growth score (such as plant height, number of tillers, yield, etc.). Pearson correlation analysis was performed using statistical software or programming languages ​​(such as R, Python, etc.). The Pearson correlation coefficient measures the degree of linear correlation between two variables, and its value ranges from -1 to 1, with values ​​close to 1 indicating a strong positive correlation, close to -1 indicating a strong negative correlation, and close to 0 indicating no correlation. Based on the collected data, the Pearson correlation coefficient between the critical antifreeze temperature and soil effective negative accumulated temperature and the target growth score was calculated. A correlation matrix was constructed to show the correlation between different variables. The influence coefficient refers to the degree of influence of one variable on the change of another variable, which can be approximately calculated by the correlation coefficient. The influence coefficient can be expressed by converting the square of the correlation coefficient into a percentage, that is, the influence coefficient = correlation coefficient × 100%. The correlation matrix and the influence coefficient were analyzed to understand the degree of influence of the critical antifreeze temperature and soil effective negative accumulated temperature on the target growth score. If the correlation coefficient or influence coefficient is close to 1 or -1, it indicates that there is a strong linear relationship between the variables. If the correlation coefficient or influence coefficient is close to 0, it indicates that there is almost no linear relationship between the variables.

[0116] Specifically, by collecting comprehensive data, the impact of critical antifreeze temperature and soil effective negative accumulated temperature on the target growth score can be analyzed more accurately. Pearson correlation analysis can reveal the linear relationship between critical antifreeze temperature and soil effective negative accumulated temperature and the target growth score, helping to understand the interaction between variables. The correlation matrix provides an intuitive view showing the degree of correlation between critical antifreeze temperature and soil effective negative accumulated temperature and the target growth score. Calculating the influence coefficient can quantify the impact of critical antifreeze temperature and soil effective negative accumulated temperature on the target growth score, providing a quantitative basis for subsequent decision-making.

[0117] Specifically, if Figure 4 As shown, the process of determining the actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat includes:

[0118] Step S41, collecting actual observation data of winter wheat to obtain the actual observation value;

[0119] Step S42, performing data cleaning on the actual observation value to obtain a cleaning result;

[0120] Step S43, calculating the actual antifreeze ability index according to the cleaning result and the influence coefficient.

[0121] Specifically, obtain the actual observation data of winter wheat at different growth stages, including freezing temperature, freezing time, stem and tiller mortality, yield loss rate, etc. At the same time, collect the corresponding soil effective negative accumulated temperature data. Check the consistency and accuracy of the data and remove possible erroneous data or outliers. To fill in the missing data, you can use interpolation or the use of mean, median and other methods. According to the actual observed data and influence coefficient after cleaning, calculate the actual frost resistance index of winter wheat at each observation point. The calculation formula of the actual frost resistance index can be simplified as follows: actual frost resistance index = (influence coefficient × actual observed value) / standard deviation, where the actual observed value is the observed data of winter wheat, the standard deviation is the standard deviation of the observed data, and the influence coefficient is the result obtained from correlation analysis or influence coefficient calculation.

[0122] In this embodiment, only the impact of critical antifreeze temperature and soil effective negative accumulated temperature on the yield loss rate of winter wheat is considered, and other factors that may affect the yield loss rate, such as variety, fertilization, etc., are ignored.

[0123] Assume the following data:

[0124] Critical antifreeze temperature (X1): -5℃, -3℃, -1℃, 0℃; effective negative accumulated soil temperature (X2): 100, 120, 150, 180; yield loss rate (Y): 10%, 5%, 2%, 0%.

[0125] First, calculate the standard deviation of each variable: standard deviation of critical antifreeze temperature (σX1): 2℃; standard deviation of effective negative accumulated soil temperature (σX2): 30; standard deviation of yield loss rate (σY): 5%.

[0126] Next, the correlation coefficient (r) was calculated and the following results were obtained: the correlation coefficient between critical antifreeze temperature and yield loss rate (r1): 0.8; the correlation coefficient between effective negative accumulated soil temperature and yield loss rate (r2): 0.6.

[0127] Now we can calculate the influence coefficient (β): influence coefficient of critical antifreeze temperature (β1): r1×(σY / σX1)=0.8×(5% / 2℃)=0.02; influence coefficient of effective negative accumulated temperature of soil (β2): r2×(σY / σX2)=0.6×(5% / 30)=0.01.

[0128] The antifreeze capacity index (ADCI) is calculated based on these influence coefficients and actual observations:

[0129] When the critical antifreeze temperature is -5°C: ADCI 1 = (β1×X1) / σX1 = (0.02×-5°C) / 2°C = -0.05.

[0130] When the effective negative accumulated temperature of soil is 100: ADCI2 = (β2×X2) / σX2 = (0.01×100) / 30 = 0.0333.

[0131] The frost resistance index is a relative value that indicates the degree of deviation of the actual observed value from the average value. The closer the values ​​of ADCI 1 and ADCI2 are to 1, the stronger the frost resistance of winter wheat under this condition.

[0132] Specifically, collecting actual observation data of winter wheat to obtain the actual observation values ​​helps to understand the actual performance of winter wheat at different growth stages. Data cleaning of the actual observation values ​​improves data quality, removes possible erroneous data or outliers, and reduces data noise. Ensures the accuracy and reliability of subsequent calculations and analyses. Calculating the frost resistance index based on the cleaning results and the influence coefficient helps to quantify the frost resistance of winter wheat, and can evaluate the frost resistance of winter wheat under different varieties or planting conditions.

[0133] Specifically, the process of comparing the actual frost resistance index with the preset target frost resistance index and formulating the winter wheat sowing strategy according to the comparison result includes:

[0134] Obtaining a preset target antifreeze capacity index;

[0135] Comparing the actual antifreeze ability index with the target antifreeze ability index to obtain a comparison result;

[0136] The winter wheat sowing strategy is formulated according to the comparison results, wherein:

[0137] If the frost resistance is insufficient, the soil fertility is improved or the planting time is adjusted;

[0138] If the antifreeze capacity reaches the target requirement, the sowing density is increased.

[0139] Specifically, the target frost resistance index is set according to the regional climate conditions, variety characteristics and expected yield level of winter wheat. The target frost resistance index can be based on historical data, the average performance of other varieties in the same region or an index recommended by experts. Collect actual observation data of winter wheat, including growth cycle, freezing temperature, freezing duration, stem and tiller mortality, yield loss rate and other indicators. Use these data to calculate the actual frost resistance index of winter wheat, which can be a comprehensive indicator reflecting the frost resistance performance of winter wheat. Compare the calculated actual frost resistance index with the preset target frost resistance index. If the actual frost resistance index is lower than the target frost resistance index, it indicates that the frost resistance of winter wheat is insufficient. If the actual frost resistance index is equal to or higher than the target frost resistance index, it indicates that the frost resistance of winter wheat meets expectations. If the frost resistance of winter wheat is insufficient, consider taking the following measures: Improve soil fertility and enhance the soil's heat preservation and water retention capacity by applying appropriate amounts of organic fertilizers and trace elements. Adjust the planting time to avoid sowing in the early cold season and choose a more suitable sowing period to reduce the risk of frost damage. If the frost resistance of winter wheat meets the target requirements, the following measures can be considered: Increase the sowing density to increase the yield potential per unit area. Ensure the appropriate supply of water and nutrients to support the growth and development of winter wheat.

[0140] Specifically, by comparing the actual frost resistance index with the target frost resistance index, insufficient frost resistance can be identified, so that measures can be taken to improve the frost resistance of winter wheat. Improving soil fertility can help plants better resist cold conditions and enhance the physiological cold resistance of plants by providing necessary nutrients. Adjusting the planting time can avoid sowing in extremely cold periods and reduce the risk of frost damage. By preventing and adjusting sowing strategies in advance, yield losses caused by frost damage can be reduced, thereby reducing economic losses. Avoid sowing in unsuitable periods to reduce the growth stunting or death of winter wheat caused by cold weather and ensure production stability.

[0141] Specifically, the process of comparing the actual antifreeze ability index with the target antifreeze ability index to obtain a comparison result includes:

[0142] When the actual antifreeze ability index is less than the preset target antifreeze ability index, the antifreeze ability of the winter wheat is improved, such as by changing the freezing temperature or extending the freezing time;

[0143] When the actual antifreeze ability index is equal to or greater than the preset target antifreeze ability index, the existing sowing conditions are maintained or optimized.

[0144] Specifically, if the actual frost resistance index is less than the target frost resistance index, change the freezing temperature, such as by adjusting the greenhouse temperature or using insulation measures to reduce the impact of freezing on winter wheat. Extend the freezing time and appropriately delay the sowing time in a suitable period to allow winter wheat to grow under milder climatic conditions.

[0145] If the actual frost resistance index is equal to or greater than the target frost resistance index, maintain or optimize the existing sowing conditions: maintain the current sowing time, density and fertilization plan to ensure that winter wheat can continue to grow under suitable conditions. Optimize existing conditions, such as adjusting fertilization ratios, water management and other factors to further improve the growth efficiency and yield of winter wheat.

[0146] Specifically, changing the freezing temperature or extending the freezing time can help winter wheat better adapt to cold environments and reduce the risk of frost damage. By maintaining or optimizing sowing conditions, it is possible to ensure that winter wheat receives sufficient light, water and nutrients throughout the growth cycle to promote its healthy growth. By adjusting sowing conditions, the loss of winter wheat yield caused by frost damage can be reduced, thereby reducing economic losses. Avoid sowing when the frost resistance is insufficient, reduce the growth stagnation or death of winter wheat caused by cold weather, and ensure production stability.

[0147] Specifically, the process of step S5 includes:

[0148] adjusting the sowing parameters of the winter wheat according to the sowing strategy;

[0149] Monitoring the growth of the winter wheat to evaluate the effect of the adjustment to obtain monitoring results;

[0150] The winter wheat sowing strategy is adjusted according to the monitoring results.

[0151] Specifically, according to the formulated sowing strategy, adjust the sowing parameters of winter wheat, such as sowing time, sowing density, fertilization plan, etc. Ensure that the adjusted sowing parameters meet the requirements of the optimized frost resistance index. Establish a monitoring system to regularly observe the growth status of winter wheat, including plant height, number of tillers, chlorophyll content, pests and diseases, etc. Use remote sensing technology, drone monitoring or ground surveys to collect growth data. Analyze the monitoring data and evaluate the impact of the adjusted sowing strategy on the growth of winter wheat. Compare the growth indicators before and after the adjustment to evaluate the changes in yield potential, disease resistance, frost resistance, etc. Comprehensively combine the monitoring data and growth indicator evaluation results to obtain the monitoring results of the sowing strategy adjustment. The results should include the impact on yield, frost resistance, resource utilization efficiency, etc. Analyze the effectiveness of the sowing strategy adjustment based on the monitoring results. If the adjustment effect is good, maintain the current sowing strategy and continue monitoring to confirm the long-term effect. If the adjustment effect is not ideal, re-evaluate the frost resistance of winter wheat and consider further adjustment measures.

[0152] In this embodiment, it is assumed that the target frost resistance index preset in a certain region is 60, and the actual frost resistance index of winter wheat in the region is measured to be 55 before planting. The target frost resistance index is set to 60, which represents the frost resistance performance level that winter wheat needs to achieve. Through laboratory testing or field observation, the actual frost resistance index of winter wheat is 55. The actual frost resistance index of 55 is compared with the target frost resistance index of 60, and it is found that the actual frost resistance index is lower than the target frost resistance index. Since the actual frost resistance index is less than the target frost resistance index, it is necessary to improve the frost resistance of winter wheat. Adjust the freezing temperature, reduce the temperature in the greenhouse from 10 ° C to 8 ° C to simulate colder environmental conditions and enhance the frost resistance of winter wheat. Extend the freezing time and extend the freezing time from 10 days to 12 days to ensure that winter wheat can fully adapt to the cold environment. During the growth period of winter wheat, its growth is regularly monitored, including indicators such as plant height, tiller number, and chlorophyll content. Compare the growth data of winter wheat before and after the adjustment to evaluate the impact of freezing temperature and duration adjustment on the growth of winter wheat. If the monitoring results show that the growth of winter wheat is good and its frost resistance is improved, the current sowing strategy will be maintained. If the monitoring results show that the growth of winter wheat does not meet expectations and its frost resistance is still insufficient, the sowing strategy needs to be further adjusted, such as changing the freezing temperature or duration again.

[0153] Specifically, by adjusting sowing parameters, such as sowing time and density, winter wheat's frost resistance can be improved and the risk of frost damage can be reduced. Through monitoring and evaluation, sowing strategies can be optimized to increase yield per unit area while making rational use of resources such as land, water and fertilizer. Through scientific adjustment of sowing strategies, yield losses caused by frost damage can be reduced, thereby reducing economic losses. By reducing the use of chemical fertilizers and pesticides, eco-friendly agricultural practices can be promoted to improve the adaptability and resilience of agricultural systems.

[0154] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0155] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying the dynamic frost resistance of winter wheat, characterized in that: include: Step S1, obtaining the time period, freezing temperature and freezing duration of winter wheat, obtaining the stem tiller mortality rate and yield loss rate of the winter wheat according to the time period, freezing temperature and freezing duration, and also obtaining the effective negative accumulated temperature of the soil; Step S2, obtaining historical data of winter wheat, and predicting a target growth score according to the time period, the freezing temperature, the freezing time, the tiller mortality rate, the yield loss rate and the historical data; Step S3, determining the critical antifreeze temperature of winter wheat according to the yield loss rate and the tiller mortality rate, and analyzing the influence of the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score to obtain an influence coefficient on the target growth score; Step S4, determining an actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat, comparing the actual frost resistance index with a preset target frost resistance index, and formulating a winter wheat sowing strategy according to the comparison result; Step S5, adjusting the sowing strategy optimization parameters according to the winter wheat sowing strategy; The process of step S2 includes: The time period, the freezing temperature, the freezing time, the stem and tiller mortality rate, the yield loss rate and the historical data are cleaned and standardized to obtain historical data processing results and actual data processing results; Constructing a feature vector according to the historical data results and the actual data results; Using the characteristic vector as a model input parameter to construct a growth curve model to predict the target growth score; The process of determining the critical frost resistance temperature of winter wheat according to the yield loss rate and the tiller mortality rate comprises: A statistical model is constructed by taking the critical antifreeze temperature as an independent variable and the yield loss rate and the stem and tiller mortality rate as dependent variables; Using the training data set to train the statistical model to obtain a second training model; The stem and tiller mortality rate and the yield loss rate are predicted within a preset temperature range according to the second training model to determine the critical antifreeze temperature.

2. The method for identifying the dynamic frost resistance of winter wheat according to claim 1, characterized in that: The process of obtaining the effective negative accumulated soil temperature includes: Several sampling points were randomly selected in the winter wheat fields, and soil samples were collected using a soil sampler; Installing a temperature sensor in the collected soil sample to measure the soil temperature at each sampling point; Calculate the effective negative accumulated soil temperature of each day according to the soil temperature; The soil effective accumulated temperature values ​​of each day are accumulated to obtain the soil effective negative accumulated temperature of the time period.

3. The method for identifying the dynamic frost resistance of winter wheat according to claim 2, characterized in that: The process of using the feature vector as a model input parameter to construct a growth curve model to predict the target growth score includes: Divide the historical data set into a training data set and a validation data set; Training the growth curve model according to the training data set to obtain a first training model; Using the validation data set to validate the first training model to obtain a validation model; The target growth score is predicted based on the validated model.

4. The method for identifying the dynamic frost resistance of winter wheat according to claim 3, characterized in that: The process of analyzing the influence of the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score to obtain the influence coefficient on the target growth score includes: The correlation between the critical antifreeze temperature and the effective negative accumulated temperature of the soil on the target growth score is analyzed using the Pearson image relationship to construct a correlation matrix; The influence coefficient between the critical antifreeze temperature and the effective negative accumulated soil temperature on the target growth score is calculated based on the correlation matrix.

5. The method for identifying the dynamic frost resistance of winter wheat according to claim 4, characterized in that: The process of determining the actual frost resistance index according to the influence coefficient and the actual observed value of winter wheat includes: Collecting actual observation data of winter wheat to obtain the actual observation value; Performing data cleaning on the actual observation value to obtain a cleaning result; The actual antifreeze ability index is calculated according to the cleaning result and the influence coefficient.

6. The method for identifying the dynamic frost resistance of winter wheat according to claim 5, characterized in that: The process of comparing the actual frost resistance index with the preset target frost resistance index and formulating the winter wheat sowing strategy according to the comparison result includes: Obtaining a preset target antifreeze capacity index; Comparing the actual antifreeze ability index with the target antifreeze ability index to obtain a comparison result; The winter wheat sowing strategy is formulated according to the comparison results, wherein: If the frost resistance is insufficient, the soil fertility is improved or the planting time is adjusted; If the antifreeze capacity reaches the target requirement, the sowing density is increased.

7. The method for identifying the dynamic frost resistance of winter wheat according to claim 6, characterized in that: The process of comparing the actual antifreeze ability index with the target antifreeze ability index to obtain a comparison result comprises: When the actual antifreeze ability index is less than the preset target antifreeze ability index, the antifreeze ability of the winter wheat is improved, such as by changing the freezing temperature or extending the freezing time; When the actual antifreeze ability index is equal to or greater than the preset target antifreeze ability index, the existing sowing conditions are maintained or optimized.

8. The method for identifying the dynamic frost resistance of winter wheat according to claim 7, characterized in that: The process of step S5 includes: adjusting the sowing parameters of the winter wheat according to the sowing strategy; Monitoring the growth of the winter wheat to evaluate the effect of the adjustment to obtain monitoring results; The winter wheat sowing strategy is adjusted according to the monitoring results.

Images