Ecological pasture cow breeding and health management method and system based on meteorological data

Abstract

The invention provides an ecological pasture cow breeding and health management method and system based on meteorological data, and relates to the technical field of cow breeding and health management. The method comprises the steps of collecting meteorological data and dairy cow breeding basic data in real time; key meteorological factors influencing cow breeding are extracted; defining a meteorological appropriate threshold value corresponding to each breeding stage; cattle herd screening adaptive to weather is realized; selecting a time period with proper temperature to carry out hybridization operation; formulating meteorological guarantee schemes according to pregnancy stages; and quantifying the influence of meteorological conditions on the breeding core indexes, and optimizing a breeding plan and resource allocation based on an evaluation result. Through a perfect dairy cow breeding management process, the breeding resource utilization efficiency is improved, a traceable and iterable analysis framework is provided for breeding plan optimization, the precise and efficient development of ecological pasture breeding management is promoted, the cost of a pasture is reduced, and meanwhile, the population quality and economic benefits are improved.

Description

Technical Field

[0001] This invention relates to the field of dairy cow reproduction and health management technology, and in particular to a method and system for dairy cow reproduction and health management in ecological ranches based on meteorological data. Background Technology

[0002] In the ecological dairy farming industry, dairy cow reproduction and health management are core aspects that determine the quality of the dairy cow herd, production performance, and the economic benefits of the farm. Traditional dairy cow reproduction and health management often relies on experience-based judgment, focusing on basic dimensions such as breed selection, pedigree analysis, and nutritional supply, but generally neglecting the crucial impact of meteorological conditions on the physiological state, reproductive performance, and stress resistance of dairy cows. This leads to frequent problems such as limited breeding efficiency and irrational resource allocation.

[0003] From the perspective of the current state of the industry, with the intensification of global warming and the increasing frequency of extreme weather events (such as heat waves, cold waves, and persistent rain), the impact on dairy cow reproduction is becoming increasingly significant. In high-temperature environments, dairy cows are prone to heat stress, manifesting as increased respiratory rate and elevated rectal temperature, leading to decreased estrus rates and reduced conception rates. Furthermore, calf survival rates are significantly affected by fluctuations in ambient temperature. Cold waves, on the other hand, increase energy consumption in dairy cows, triggering cold stress, resulting in reduced feed conversion rates and decreased immunity, indirectly affecting production performance throughout the breeding cycle. In addition, weather factors such as rain and strong winds can alter feed intake and activity patterns in dairy cows, interfering with the accuracy of estrus behavior identification and further exacerbating the incompleteness of breeding management. Summary of the Invention

[0004] This invention provides a method and system for managing the reproduction and health of dairy cows in ecological ranches based on meteorological data, in order to solve the shortcomings of incomplete breeding management in the existing technology.

[0005] On the one hand, this invention provides a method for managing the reproduction and health of dairy cows in an ecological ranch based on meteorological data, comprising: Real-time collection of meteorological data and basic data on dairy cow breeding are processed in a standardized manner.

[0006] Principal component analysis was used to extract key meteorological factors affecting dairy cow breeding. These key meteorological factors included temperature, weather, and rainfall.

[0007] Quantitative correlations between key meteorological factors and breeding indicators were established through correlation analysis and multiple regression methods. Suitable meteorological thresholds for each breeding stage were defined. Breeding indicators included estrus rate, conception rate, morbidity rate, and production performance of dairy cows.

[0008] Based on key meteorological factors and their suitable meteorological thresholds, breeding standards for cattle herds are formulated, the stress resistance of replacement heifers and lactating cattle under different meteorological conditions is dynamically evaluated, and the selection weights are adjusted to achieve meteorologically adapted cattle herd selection.

[0009] Based on meteorological data, the estrus period of dairy cows is predicted, and artificial intelligence technology is used to identify estrus behavior, and mating operations are carried out during periods of suitable temperature.

[0010] Meteorological support plans are developed according to different stages of pregnancy, and environmental control and nutritional adjustment measures are initiated based on real-time meteorological data to avoid stress reactions.

[0011] A breeding benefit evaluation model was constructed to quantify the impact of meteorological conditions on core breeding indicators, and breeding plans and resource allocation were optimized based on the evaluation results.

[0012] According to the method for managing dairy cow reproduction and health in ecological pastures based on meteorological data provided by this invention, the meteorological data includes daily average temperature, daily minimum temperature, daily maximum temperature, daily average relative humidity, daily average wind speed, daily cumulative precipitation, sunshine duration, and air pressure. Basic data for dairy cow breeding includes dairy cow breed, physiological stage, reproductive indicators, health indicators, and production performance.

[0013] The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data provided by this invention includes the following process for extracting key meteorological factors affecting dairy cow breeding using principal component analysis: Meteorological data and basic dairy cow breeding data for multiple complete production cycles were collected to construct a multi-dimensional data matrix.

[0014] For each feature in the multidimensional data matrix, calculate its mean and standard deviation, and obtain the standardized data matrix.

[0015] The covariance matrix is ​​calculated based on the standardized matrix, and eigenvalue decomposition is performed on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors.

[0016] The number of principal components is determined based on the contribution rate of eigenvalues, and the screening stops when the cumulative contribution rate reaches a preset ratio.

[0017] According to the ecological ranch dairy cow breeding and health management method based on meteorological data provided by the present invention, the process of determining the meteorological suitability thresholds corresponding to each breeding stage includes: Pearson correlation analysis was used to calculate the correlation coefficients between key meteorological factors and various breeding indicators.

[0018] Key meteorological factors whose correlation coefficients with breeding indicators reach a preset correlation threshold are screened through correlation tests.

[0019] A multiple linear regression model was established with key meteorological factors as independent variables and breeding indicators as dependent variables.

[0020] The least squares method was used to solve the regression coefficients to minimize the sum of squared residuals, and the suitable meteorological thresholds for each breeding stage were determined based on the regression model.

[0021] According to the ecological ranch dairy cow breeding and health management method based on meteorological data provided by the present invention, the process of formulating breeding herd selection standards includes: Based on the meteorological suitability thresholds for each breeding stage, the basic breeding indicators for the cattle herd were determined, including age, weight, and pedigree parameters.

[0022] A heat resistance rating standard was developed for temperature factors, and the rating was determined by measuring the respiratory rate and rectal temperature of dairy cows under specific temperature conditions.

[0023] To assess the resilience of dairy cows, we evaluated changes in feed intake under specific rainy conditions, taking into account weather factors.

[0024] To assess the adaptability of dairy cows under specific windy weather conditions, we observed their activity levels in response to rainfall factors.

[0025] The suitability of key meteorological factors is incorporated into the breeding weight calculation of the comprehensive score, and individuals with a comprehensive score of 10 or above are selected for inclusion in the breeding herd.

[0026] According to the meteorological data-based ecological ranch dairy cow breeding and health management method provided by the present invention, the process of meteorological-adapted herd selection includes: Replacement heifers and lactating cows were selected as the evaluation samples.

[0027] A stress resistance performance evaluation index system was constructed, which includes physiological indicators, production indicators, and health indicators. Physiological indicators include respiratory rate and rectal temperature. Production indicators include milk yield and milk protein percentage. Health indicators include morbidity and somatic cell count.

[0028] Conduct tracking and monitoring for a set period of time under different meteorological conditions.

[0029] When the temperature factor is within a specific heat stress range, the increase in respiratory rate of heifers compared to the suitable temperature range and the decrease in milk production of lactating cows are recorded.

[0030] When rainfall factors are in the high-influence range, the morbidity rate changes of the two types of cattle are recorded.

[0031] The weights of each evaluation index in the stress resistance performance evaluation index system were determined using the analytic hierarchy process (AHP).

[0032] Calculate the comprehensive index of stress resistance and adjust the breeding weights according to the comprehensive index.

[0033] By dynamically adjusting weights and filtering at set intervals, climate-adaptive cattle herd optimization can be achieved.

[0034] According to the ecological ranch dairy cow reproduction and health management method based on meteorological data provided by the present invention, the process of selecting a suitable temperature period for mating includes: Collect historical meteorological data and label the corresponding estrus rates of dairy cows based on the historical meteorological data.

[0035] Based on historical meteorological data, the ARIMA model in time series analysis is used to predict the changing trends of key meteorological factors over a set period of time in the future.

[0036] The optimal model parameters are determined using the AIC criterion, and the daily average temperature variation curve of the temperature factor is predicted.

[0037] Based on the correlation between estrus rate and temperature factors in historical data, when the predicted daily average temperature is within a specific range, it is determined to be the estrus period.

[0038] High-definition cameras and infrared sensors were installed on the ranch to collect behavioral and physiological data from the cows. The behavioral data included activity frequency, standing time, and mounting behavior. The physiological data included body temperature and activity level.

[0039] An artificial intelligence recognition model based on CNN-LSTM was constructed, which uses dairy cow behavioral data and physiological data as input to identify dairy cow estrus behavior.

[0040] Based on temperature prediction and estrus behavior recognition results, mating operations are carried out within a specific range of daily average temperature and within a set time period after the dairy cows are identified as being in estrus.

[0041] The method for managing dairy cow reproduction and health in ecological ranches based on meteorological data provided by this invention includes the following process: developing meteorological support plans for different gestation stages, and initiating environmental control and nutritional adjustment measures based on real-time meteorological data to avoid stress responses. The gestation process of dairy cows is divided into three stages: early, middle and late, and meteorological support plans are developed for each stage.

[0042] In the early stages, temperature factors are monitored. When the real-time daily average temperature is lower than the set value, the barn heating system is activated to regulate the temperature within a specific range. At the same time, the feed formula is adjusted to increase the proportion of energy feed and improve the dairy cows' cold resistance. When the temperature is higher than the set value, the sprinkler and fan combination system is turned on, the sprinkler interval and duration are set, and the fan speed is adjusted.

[0043] During the mid-term phase, pay attention to weather factors. When the sunshine duration is lower than the set value, supplement with artificial lighting to increase the set duration of light exposure. When the average daily relative humidity is higher than the set value, turn on the dehumidifier to control the humidity in the shed below the set value. At the same time, add anti-mold agents to the feed and set the addition amount.

[0044] During the later stages, monitor rainfall factors. When the cumulative daily rainfall reaches the set value, reinforce the roof of the cattle shed, clear drainage channels to prevent water accumulation, and when the average daily wind speed reaches the set value, close the side windows of the cattle shed and install windproof roller blinds to reduce the entry of cold air.

[0045] The system collects meteorological and physiological data of dairy cows in real time. When it detects abnormal respiratory rate or a decrease in feed intake that exceeds a set percentage, it automatically triggers emergency control measures.

[0046] According to the ecological ranch dairy cow reproduction and health management method based on meteorological data provided by this invention, the process of constructing a breeding benefit evaluation model and quantifying the impact of meteorological conditions on core breeding indicators includes: The estrus rate, conception rate, calf survival rate, and milk yield of dairy cows were selected as core breeding indicators. Key meteorological factors were used as input variables, and the core indicators were used as output variables. A breeding benefit evaluation model was constructed using a BP neural network.

[0047] The network structure of the breeding benefit evaluation model is set with a specific combination of nodes, including an input layer, a hidden layer, and an output layer. The input layer corresponds to the number of nodes corresponding to the key meteorological factors, the hidden layer has a set number of nodes, and the output layer corresponds to the number of nodes corresponding to the core indicators.

[0048] The Sigmoid function was chosen as the activation function, and the learning rate and number of iterations were set.

[0049] By training a breeding benefit evaluation model using historical data, the model's prediction error can be controlled within a set range.

[0050] Based on the trained model, the impact of different meteorological conditions on core indicators is quantified by calculating the meteorological impact benefit value.

[0051] On the other hand, the present invention also provides an ecological ranch dairy cow reproduction and health management system based on meteorological data, comprising: The data acquisition and feature extraction module is used to collect meteorological data and basic data on dairy cow breeding in real time, and to extract key meteorological factors affecting dairy cow breeding using principal component analysis.

[0052] The meteorological threshold delineation module is used to establish a quantitative correlation between key meteorological factors and breeding indicators through correlation analysis and multiple regression methods, and to delineate the meteorological suitable thresholds corresponding to each breeding stage.

[0053] The adaptive cattle selection module is used to formulate breeding cattle selection standards based on key meteorological factors and their meteorological suitability thresholds, dynamically evaluate the stress resistance of replacement cattle and lactating cattle under different meteorological conditions, and adjust the selection weights to achieve meteorologically adapted cattle selection.

[0054] The suitable time period selection module is used to predict the estrus period of dairy cows based on meteorological data, and to use artificial intelligence technology to identify estrus behavior and select a suitable time period for mating.

[0055] The meteorological support planning module is used to develop meteorological support plans for different stages of pregnancy, and to initiate environmental control and nutritional adjustment measures based on real-time meteorological data to avoid stress reactions.

[0056] The breeding effectiveness evaluation module is used to build a breeding benefit evaluation model, quantify the impact of meteorological conditions on core breeding indicators, and optimize breeding plans and resource allocation based on the evaluation results.

[0057] The present invention provides a method and system for managing dairy cow reproduction and health in ecological ranches based on meteorological data. Principal component analysis is used to accurately extract key meteorological factors, thus addressing the impact of meteorological factors. By employing correlation analysis and multiple regression methods, quantitative correlations are established between key meteorological factors and breeding indicators such as estrus rate and conception rate. Suitable meteorological thresholds for each breeding stage are defined, shifting breeding management from experience-based judgment to data-driven support.

[0058] By establishing meteorologically adapted breeding standards for cattle herds, incorporating the compatibility of temperature, weather, and rainfall factors into the selection weights, and constructing a stress resistance performance evaluation index system, dynamic screening of heifers and lactating cows can be achieved. Under high-temperature conditions, by monitoring the increase in respiratory rate of heifers and the decrease in milk production of lactating cows, and combining the analytic hierarchy process (AHP) to determine the index weights, a comprehensive stress resistance performance index can be calculated. This allows for the selection of individuals with strong heat resistance, reducing the loss of production performance in the herd under extreme high-temperature weather. Simultaneously, the selection weights are dynamically adjusted according to a set cycle to ensure that the cattle herds continuously adapt to regional meteorological characteristics, laying the foundation for building a core herd with strong stress resistance and stable production for ecological ranches.

[0059] By integrating historical meteorological data with the ARIMA time series model, the temperature change trend for a set period of time can be predicted. By combining the correlation between historical estrus rate and temperature, the estrus period can be accurately determined. Then, the CNN-LSTM artificial intelligence model is used to identify estrus characteristics such as mounting behavior and body temperature changes in dairy cows, achieving dual confirmation of meteorological prediction and behavioral recognition.

[0060] Dividing dairy cow pregnancy into three stages—early, middle, and late—and developing differentiated weather protection plans enables closed-loop management of prediction, prevention, and adjustment. In the early stage of pregnancy, heating or sprinkler systems are activated to address temperature factors. In the middle stage, artificial lighting is supplemented to address insufficient sunlight, humidity is controlled, and anti-mold agents are added. In the late stage, cowsheds are reinforced and windproof curtains are installed to address heavy rain and strong winds. This approach can prevent stress responses caused by weather stress from the outset.

[0061] A breeding benefit evaluation model based on a backpropagation neural network can quantify the impact of different meteorological conditions on core indicators such as estrus rate and calf survival rate, providing a precise basis for resource allocation. By using the meteorological impact benefit values ​​output by the model, farms can adjust their breeding plans accordingly, avoiding resource waste. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0063] Figure 1 This is a flowchart illustrating the ecological ranch dairy cow reproduction and health management method based on meteorological data provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the daily dynamic changes in temperature inside and outside the cattle shed during different seasons in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the ecological ranch dairy cow reproduction and health management system based on meteorological data provided in an embodiment of the present invention. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0065] The following is combined with Figures 1-3 This invention describes a method and system for managing dairy cow reproduction and health in ecological ranches based on meteorological data.

[0066] Figure 1 This is a flowchart illustrating the ecological ranch dairy cow reproduction and health management method based on meteorological data provided in this embodiment of the invention.

[0067] like Figure 1As shown in the embodiments of the present invention, the method and system for ecological ranch dairy cow reproduction and health management based on meteorological data can be implemented by an ecological ranch dairy cow reproduction and health management method based on meteorological data, the method including: Real-time collection of meteorological data and basic dairy cow breeding data. Meteorological data includes daily average temperature, daily minimum temperature, daily maximum temperature, daily average relative humidity, daily average wind speed, daily cumulative precipitation, sunshine duration, and air pressure. Basic dairy cow breeding data includes dairy cow breed, physiological stage, reproductive indicators, health indicators, and production performance.

[0068] Figure 2 This is a schematic diagram illustrating the daily dynamic changes in temperature inside and outside the cattle shed during different seasons in an embodiment of the present invention.

[0069] For fixed monitoring, integrated meteorological environment monitoring equipment was deployed in different types of demonstration farms, such as tunnel-type barns, open-air barns, and sun-heated constant-temperature barns, in accordance with the "Specifications for Automatic Monitoring of Meteorological Environment in Large-Scale Dairy Farms." Each set of equipment integrates 13 types of monitoring components, including temperature and humidity sensors, illuminance sensors, wind speed and direction sensors, carbon dioxide transmitters, ammonia temperature and humidity transmitters, odor gas sensors, and noise sensors. The equipment is connected to a cloud platform via NB-IoT / 4G network to monitor daily average temperature, daily minimum temperature, daily maximum temperature (measurement range -50~+50℃, accuracy ±0.2℃), and daily average relative humidity (measurement range 5~1). Meteorological elements such as daily average wind speed (0~60m / s, accuracy ±0.5m / s), daily cumulative precipitation (0~4mm / min, accuracy ±0.4mm), sunshine duration (0~2000W / m², accuracy ±5%FS), and air pressure (450~1100hPa, accuracy ±0.3hPa) are collected and uploaded in minutes. At the same time, data on the concentration of gases that affect the health of dairy cows, such as ammonia (0-50PPM, accuracy ≤1%FS) and hydrogen sulfide (0-100PPM, accuracy ≤1%FS), are collected simultaneously.

[0070] In the mobile monitoring phase, an automatic monitoring device for the meteorological environment of the cowshed was developed. This device is equipped with an automatic navigation vehicle module, a high-precision camera module, and a multi-element sensor module (including an infrared thermal imaging sensor). It can move autonomously within the cowshed along a preset route, focusing on collecting local meteorological data (such as temperature and humidity in the calf's respiratory zone) and physiological data of dairy cows (such as body surface temperature and activity frequency) in key areas such as the calf activity area and the lactating cow's resting area. This fills the gaps in the monitoring of fixed equipment and achieves comprehensive data coverage of both the macro-environment and micro-areas.

[0071] The basic data collection for dairy cow breeding adopts a collaborative approach of intelligent equipment and manual recording: the farm's existing herd management system (such as estrus monitoring collars and milking machine data terminals) automatically acquires data on dairy cow breeds (such as Holstein cows), physiological stages (heifers, lactating cows, pregnant cows), reproductive indicators (estrus records, mating time, conception results), and production performance (milk yield, milk protein percentage, milk fat percentage). In terms of health indicators, the data is combined with veterinary inspection records (morbidity rate, somatic cell count, disease type) and dairy cow body temperature data collected by infrared sensors to form a complete basic breeding database. All data is standardized (such as uniform time format and removal of outliers) and then stored in a cloud database in conjunction with meteorological data.

[0072] Analysis of monitoring data from a dairy farm from July 2021 to February 2022 clarified the impact of the spatial and temporal distribution of temperature inside and outside the barn on dairy cow breeding: In summer (July-August), the highest daily average temperature outside the barn reached 33℃, while the temperature inside was 0.32℃ lower than the outside due to control measures such as spraying and fans. Moreover, the temperature difference between different locations inside the barn was small (maximum temperature difference 0.14℃). During this period, it is necessary to focus on controlling temperature factors to avoid heat stress in dairy cows leading to a decrease in estrus rate. In winter (December-February), the daily average temperature inside the barn was 2℃ higher than the outside temperature. The temperature was 97℃, and the temperatures at monitoring points 1 and 2 (near the bedding area) were significantly higher than those at monitoring points 3 and 4 (near the ventilation openings), with a temperature difference of 1.89℃. This characteristic suggests that when formulating a winter weather protection plan for pregnant cows, heating strategies for the bedding area need to be optimized to prevent cold stress in calves. In spring and autumn (March-June and September-November), the temperature difference between inside and outside the cowshed ranges from 0.5 to 1.13℃, and the daytime temperature fluctuates greatly (e.g., afternoon temperatures in spring are 8-10℃ higher than morning temperatures). Therefore, the frequency of environmental control needs to be dynamically adjusted to ensure the stability of key breeding indicators. Based on the above temperature variation patterns, the suitable meteorological thresholds for each breeding stage can be further refined. For example, the suitable temperature range for lactating cows in summer can be defined as 22-26℃, and in winter as 12-16℃.

[0073] Meteorological data and basic breeding data were standardized, and principal component analysis was used to extract key meteorological factors affecting dairy cow breeding. These key meteorological factors included temperature, weather conditions, and rainfall. The process of extracting key meteorological factors affecting dairy cow breeding included: Meteorological data and corresponding basic dairy cow breeding data were collected across multiple complete production cycles to construct a multi-dimensional data matrix X, where X = [x ij ] (n×m) , where n represents the number of samples and m represents the number of features.

[0074] For each feature in the data matrix, calculate its mean μ. j and standard deviation σ j The formulas are as follows:

[0075] and through The standardized data matrix Z is obtained.

[0076] The covariance matrix S is calculated based on the standardized matrix Z, and the formula is expressed as follows:

[0077] Eigenvalue decomposition of the covariance matrix yields eigenvalues ​​λ1≥λ2≥…≥λ m and the corresponding eigenvectors.

[0078] The number of principal components is determined based on the contribution rate of eigenvalues. Screening stops when the cumulative contribution rate reaches a preset proportion. The top three principal components are ultimately selected as key meteorological factors. The first principal component is the temperature factor, composed of daily average temperature, daily minimum temperature, daily maximum temperature, and air pressure. The second principal component is the weather factor, composed of daily average relative humidity, sunshine duration, and daily minimum visibility. The third principal component is the rainfall factor, composed of daily average wind speed and daily cumulative precipitation.

[0079] Quantitative correlations between key meteorological factors and breeding indicators were established through correlation analysis and multiple regression methods. Suitable meteorological thresholds for each breeding stage were defined. Breeding indicators included estrus rate, conception rate, morbidity rate, and production performance of dairy cows.

[0080] The process of determining the meteorological suitability thresholds for each breeding stage includes: Pearson correlation analysis was used to calculate the correlation coefficients between key meteorological factors and various breeding indicators. The formula is as follows:

[0081] In the formula, For the i-th key meteorological factor data, For the i-th breeding indicator data, and These are the mean values ​​of the corresponding data.

[0082] Key meteorological factors whose correlation coefficients with breeding indicators reach a preset correlation threshold are screened out through correlation tests.

[0083] Using key meteorological factors as independent variables x k With the breeding index as the dependent variable y, a multiple linear regression model is established, expressed by the formula:

[0084] In the formula, For the intercept term, For regression coefficients, This is random error.

[0085] The regression coefficients are solved using the least squares method to achieve the sum of squared residuals. Minimum, of which These are predicted values.

[0086] Based on the optimal range of breeding indicators from regression models and historical data, suitable meteorological thresholds for each breeding stage were defined. For example, during the gilt breeding stage, the suitable range for the average daily temperature corresponding to the temperature factor is 10-16℃. When this range is exceeded, the estrus rate decreases by more than 15%. During the gestation stage, the suitable range for the sunshine duration corresponding to the weather factor is 6-8 hours / day. When it is less than 4 hours or more than 10 hours, the morbidity rate increases by more than 8%.

[0087] Based on key meteorological factors and their suitable meteorological thresholds, breeding standards for cattle herds are formulated, the stress resistance of replacement heifers and lactating cattle under different meteorological conditions is dynamically evaluated, and the selection weights are adjusted to achieve meteorologically adapted cattle herd selection.

[0088] The process of developing breeding standards for cattle herds includes: Based on the meteorological suitability thresholds for each breeding stage, the basic breeding indicators for the breeding cattle herd are determined, including basic parameters such as age, weight, and pedigree. Among them, the age of the replacement cattle should be 14-16 months and the weight should not be less than 380kg.

[0089] A heat resistance rating standard was developed based on temperature factors. By testing the respiratory rate and rectal temperature of dairy cows at an average daily temperature of 30℃, cows with a respiratory rate of 50-70 breaths / minute and a rectal temperature of 39.0-39.5℃ were rated as having excellent heat resistance.

[0090] Regarding weather factors, the change in feed intake of dairy cows under continuous rainy conditions (daily cumulative rainfall ≥20mm, sunshine duration ≤3 hours) was assessed. Cows with a feed intake decrease of no more than 10% were rated as having good stress resistance.

[0091] Regarding rainfall factors, the activity level of dairy cows under strong winds (daily average wind speed ≥6m / s) was observed. Cows whose activity range decreased by no more than 20% were considered to have strong adaptability.

[0092] The suitability of key meteorological factors was included in the selection weight, with basic parameters accounting for 50%, temperature factor suitability accounting for 25%, weather factor suitability accounting for 15%, and rainfall factor suitability accounting for 10%. The comprehensive score was calculated as follows: basic parameter score × 0.5 + temperature suitability score × 0.25 + weather suitability score × 0.15 + rainfall suitability score × 0.1. Individuals with a comprehensive score of 80 or above were selected for inclusion in the breeding herd.

[0093] The process of selecting climate-adapted cattle herds includes: One hundred heifers and 80 lactating cows were selected as the evaluation sample to construct a stress resistance performance evaluation index system, which included physiological, production, and health indicators. Physiological indicators included respiratory rate and rectal temperature. Production indicators included milk yield and milk protein percentage. Health indicators included morbidity and somatic cell count.

[0094] A 12-month follow-up monitoring was conducted under different meteorological conditions. When the temperature factor was in the mild heat stress range (daily average temperature 25-28℃), the increase in respiratory rate of heifers compared to the suitable temperature range and the decrease in milk production of lactating cows were recorded.

[0095] When the rainfall factor is in the high-impact range (daily average wind speed ≥8m / s), record the changes in the incidence rate of the two types of cattle.

[0096] The weights of each evaluation indicator were determined using the analytic hierarchy process (AHP): physiological indicators had a weight of 0.35, production indicators had a weight of 0.4, and health indicators had a weight of 0.25. The comprehensive stress resistance index was then calculated using the following formula:

[0097] In the formula, To evaluate the weight of the indicators, Standardize the scores for the evaluation indicators.

[0098] The selection weights are adjusted according to the comprehensive index. For the top 30% of the replacement cattle in terms of temperature factor stress resistance performance index, the selection weight is increased by 15%.

[0099] For lactating cows ranking in the bottom 20% of the rainfall factor stress resistance index, their breeding weight is reduced by 10%. Through dynamic weight adjustment, screening is conducted quarterly to optimize the climate-suitable herd, increasing the proportion of suitable herds from the initial 65% to over 85%.

[0100] Based on meteorological data, the peak estrus period for dairy cows is predicted, and artificial intelligence technology is used to identify estrus behavior, selecting a suitable temperature period for mating. The process includes: Based on meteorological data from the past five years, the ARIMA model in time series analysis is used to predict the changing trends of key meteorological factors over the next three months. The model formula is as follows:

[0101] In the formula, φ(L) is the autoregressive operator, θ(L) is the moving average operator, and d is the difference order. Let be the observation values ​​of the time series at time t. Let t be the random error term. The optimal model parameters are determined using the AIC criterion to predict the daily average temperature change curve of the temperature factor.

[0102] Based on the correlation between estrus rate and temperature factors in historical data, when the predicted daily average temperature is in the range of 18-22℃, it is determined to be a high estrus period, during which the estrus rate of dairy cows is 25% higher than in other temperature ranges.

[0103] High-definition cameras and infrared sensors were installed on the ranch to collect behavioral data (such as activity frequency, standing time, and mounting behavior) and physiological data (such as body temperature and activity level) of dairy cows. An artificial intelligence recognition model based on CNN-LSTM was constructed to identify the estrus behavior of dairy cows. The training set of the model used 5,000 labeled estrus behavior data, and the accuracy of the test set reached 92%.

[0104] Based on temperature forecasts and estrus behavior identification results, mating operations were performed within 6-18 hours after the cows were identified as being in estrus, when the average daily temperature was 18-22℃. The conception rate during this period was 30% higher than that during other periods. Real-time meteorological data was also recorded during mating for subsequent effect analysis.

[0105] Develop meteorological support plans for different stages of pregnancy, and initiate environmental control and nutritional adjustment measures based on real-time meteorological data to avoid stress responses. The process includes: The gestation process of dairy cows is divided into three stages: early (1-3 months), middle (4-6 months), and late (7-9 months), and meteorological support plans are formulated for each stage.

[0106] In the early stages, the focus is on monitoring temperature factors. When the real-time daily average temperature is below 5℃, the cattle shed heating system is activated to regulate the temperature inside the shed to 10-12℃. At the same time, the feed formula is adjusted to increase the proportion of energy feed (such as corn) to 50% to improve the dairy cows' cold resistance.

[0107] When the temperature is above 28℃, turn on the combined spray and fan system. Set the spray interval to 10 minutes / time, 1 minute each time, and adjust the fan speed to 3m / s.

[0108] In the medium term, focus on weather factors. When sunshine duration is less than 5 hours, supplement with artificial lighting, increasing the sunshine duration by 3 hours per day.

[0109] When the average daily relative humidity is higher than 80%, turn on the dehumidifier to control the humidity in the shed to below 65%, and add a mold inhibitor to the feed at a rate of 0.2%.

[0110] In the later stage, focus on monitoring rainfall factors. When the cumulative rainfall on a given day is ≥30mm, reinforce the roof of the cattle shed and clear the drainage channels to prevent water accumulation.

[0111] When the average daily wind speed is ≥7m / s, close the side windows of the cattle shed and install windproof roller blinds to reduce the entry of cold air.

[0112] Real-time collection of meteorological data and dairy cow physiological data (such as body temperature and feed intake) will automatically trigger emergency control measures when the dairy cows are detected to have abnormal respiratory rate (above 60 breaths / minute) or feed intake decreases by more than 15%, such as increasing the spraying frequency or adjusting the feed nutrient ratio.

[0113] Table 1: Evaluation criteria for heat stress in dairy cows.

[0114]

[0115] A breeding benefit evaluation model was constructed to quantify the impact of meteorological conditions on core breeding indicators, and breeding plans and resource allocation were optimized based on the evaluation results. The process included: The estrus rate, conception rate, calf survival rate, and milk production of dairy cows were selected as core breeding indicators to construct a breeding benefit evaluation model.

[0116] Using key meteorological factors as input variables and core indicators as output variables, a BP neural network was used to construct the model. The network structure was set to 3-19-4 (3 nodes in the input layer corresponding to key meteorological factors, 19 nodes in the hidden layer, and 4 nodes in the output layer corresponding to core indicators). The activation function was the Sigmoid function, the learning rate was set to 0.01, and the number of iterations was set to 1000.

[0117] The model was trained using historical data (1000 sets of meteorological and breeding data) to keep the model prediction error within 8%.

[0118] Based on the trained model, the impact of different meteorological conditions on core indicators is quantified by calculating the meteorological impact benefit value. For example, for every 1°C increase in temperature factor, the estrus rate decreases by 2.1% and the conception rate decreases by 1.8%.

[0119] For every 1 m / s increase in the daily average wind speed among the rainfall factors, the calf survival rate decreases by 0.5%.

[0120] The formula for calculating the value of meteorological impact benefits is expressed as follows:

[0121] In the formula, The core indicator values ​​are optimized based on meteorological conditions. These are the core indicator values ​​under the original meteorological conditions. The core indicators are weighted as follows: estrus rate 0.25, conception rate 0.3, calf survival rate 0.2, and milk production 0.25.

[0122] In summary, this embodiment provides a method for the breeding and health management of dairy cows in ecological ranches based on meteorological data. Principal component analysis is used to accurately extract key meteorological factors, thus addressing the impact of meteorological factors. Correlation analysis and multiple regression methods are employed to establish quantitative correlations between key meteorological factors and breeding indicators such as estrus rate and conception rate, defining suitable meteorological thresholds for each breeding stage, thereby shifting breeding management from experience-based judgment to data-driven support.

[0123] By establishing meteorologically adapted breeding standards for cattle herds, incorporating the compatibility of temperature, weather, and rainfall factors into the selection weights, and constructing a stress resistance performance evaluation index system, dynamic screening of heifers and lactating cows can be achieved. Under high-temperature conditions, by monitoring the increase in respiratory rate of heifers and the decrease in milk production of lactating cows, and combining the analytic hierarchy process (AHP) to determine the index weights, a comprehensive stress resistance performance index can be calculated. This allows for the selection of individuals with strong heat resistance, reducing the loss of production performance in the herd under extreme high-temperature weather. Simultaneously, the selection weights are dynamically adjusted according to a set cycle to ensure that the cattle herds continuously adapt to regional meteorological characteristics, laying the foundation for building a core herd with strong stress resistance and stable production for ecological ranches.

[0124] By integrating historical meteorological data with the ARIMA time series model, the temperature change trend for a set period of time can be predicted. By combining the correlation between historical estrus rate and temperature, the estrus period can be accurately determined. Then, the CNN-LSTM artificial intelligence model is used to identify estrus characteristics such as mounting behavior and body temperature changes in dairy cows, achieving dual confirmation of meteorological prediction and behavioral recognition.

[0125] Dividing dairy cow pregnancy into three stages—early, middle, and late—and developing differentiated weather protection plans enables closed-loop management of prediction, prevention, and adjustment. In the early stage of pregnancy, heating or sprinkler systems are activated to address temperature factors. In the middle stage, artificial lighting is supplemented to address insufficient sunlight, humidity is controlled, and anti-mold agents are added. In the late stage, cowsheds are reinforced and windproof curtains are installed to address heavy rain and strong winds. This approach can prevent stress responses caused by weather stress from the outset.

[0126] A breeding benefit evaluation model based on a backpropagation neural network can quantify the impact of different meteorological conditions on core indicators such as estrus rate and calf survival rate, providing a precise basis for resource allocation. By using the meteorological impact benefit values ​​output by the model, farms can adjust their breeding plans accordingly, avoiding resource waste.

[0127] Based on the same general inventive concept, this invention also protects an ecological ranch dairy cow breeding and health management system based on meteorological data. The following describes the ecological ranch dairy cow breeding and health management system based on meteorological data provided by this invention. The ecological ranch dairy cow breeding and health management system based on meteorological data described below can be referred to in correspondence with the ecological ranch dairy cow breeding and health management method based on meteorological data described above.

[0128] Figure 3This is a schematic diagram of the structure of the ecological ranch dairy cow reproduction and health management system based on meteorological data provided in an embodiment of the present invention.

[0129] like Figure 3 As shown, the ecological ranch dairy cow breeding and health management system based on meteorological data includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The processor includes a data acquisition and feature extraction module, a meteorological threshold delineation module, a suitable cattle herd screening module, a suitable time period selection module, a meteorological support formulation module, and a breeding effect evaluation module.

[0130] The data acquisition and feature extraction module is used to collect meteorological data and basic data on dairy cow breeding in real time, and uses principal component analysis to extract key meteorological factors that affect dairy cow breeding.

[0131] The meteorological threshold delineation module is used to establish a quantitative correlation between key meteorological factors and breeding indicators through correlation analysis and multiple regression methods, and to delineate the appropriate meteorological thresholds for each breeding stage.

[0132] The adaptive cattle selection module is used to formulate breeding cattle selection standards based on key meteorological factors and their meteorological suitability thresholds, dynamically evaluate the stress resistance of replacement cattle and lactating cattle under different meteorological conditions, and adjust the selection weights to achieve meteorologically adapted cattle selection.

[0133] The suitable time period selection module is used to predict the estrus period of dairy cows based on meteorological data, and to use artificial intelligence technology to identify estrus behavior and select a suitable time period for mating.

[0134] The meteorological support planning module is used to develop meteorological support plans for different stages of pregnancy, and to initiate environmental control and nutritional adjustment measures based on real-time meteorological data to avoid stress reactions.

[0135] The breeding effectiveness evaluation module is used to build a breeding benefit evaluation model, quantify the impact of meteorological conditions on core breeding indicators, and optimize breeding plans and resource allocation based on the evaluation results.

[0136] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for managing dairy cow reproduction and health in an ecological ranch based on meteorological data, characterized in that, include: Real-time collection of meteorological data and basic dairy cow breeding data, followed by standardized processing; Principal component analysis was used to extract key meteorological factors affecting dairy cow breeding. These key meteorological factors included temperature, weather, and rainfall. The quantitative correlation between the key meteorological factors and breeding indicators was established by using correlation analysis and multiple regression methods, and the meteorological suitable thresholds corresponding to each breeding stage were defined. The breeding indicators include estrus rate, conception rate, morbidity rate and production performance of dairy cows. Based on the key meteorological factors and their suitable meteorological thresholds, breeding standards for cattle herds are formulated, the stress resistance of replacement heifers and lactating cattle under different meteorological conditions is dynamically evaluated, and the selection weights are adjusted to achieve meteorologically adapted cattle herd selection. Based on meteorological data, the estrus period of dairy cows is predicted, and artificial intelligence technology is used to identify estrus behavior and select a suitable time for mating. Meteorological support plans are developed according to the stages of pregnancy, and environmental control and nutritional adjustment measures are initiated based on real-time meteorological data to avoid stress reactions; A breeding benefit evaluation model was constructed to quantify the impact of meteorological conditions on core breeding indicators, and breeding plans and resource allocation were optimized based on the evaluation results.

2. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The meteorological data includes daily average temperature, daily minimum temperature, daily maximum temperature, daily average relative humidity, daily average wind speed, daily cumulative precipitation, sunshine duration, and air pressure; the basic data on dairy cow breeding includes dairy cow breed, physiological stage, reproductive indicators, health indicators, and production performance.

3. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of extracting key meteorological factors affecting dairy cow breeding using principal component analysis includes: Collect meteorological data and corresponding basic dairy cow breeding data for multiple complete production cycles to construct a multi-dimensional data matrix; For each feature in the multidimensional data matrix, calculate its mean and standard deviation, and obtain the standardized data matrix; The covariance matrix is ​​calculated based on the standardized matrix, and the covariance matrix is ​​decomposed into eigenvalues ​​to obtain eigenvalues ​​and corresponding eigenvectors. The number of principal components is determined based on the contribution rate of eigenvalues, and the screening stops when the cumulative contribution rate reaches a preset ratio.

4. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of determining the meteorological suitability thresholds for each breeding stage includes: Pearson correlation analysis was used to calculate the correlation coefficients between key meteorological factors and various breeding indicators; Key meteorological factors whose correlation coefficients with breeding indicators reach a preset correlation threshold are screened through correlation tests. A multiple linear regression model was established with key meteorological factors as independent variables and breeding indicators as dependent variables. The least squares method was used to solve the regression coefficients to minimize the sum of squared residuals, and the suitable meteorological thresholds for each breeding stage were determined based on the regression model.

5. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of developing breeding standards for cattle herds includes: Based on the meteorological suitability thresholds for each breeding stage, the basic breeding indicators for the breeding cattle herd were determined, including age, weight, and pedigree parameters. A heat resistance rating standard was developed for temperature factors, and the rating was determined by measuring the respiratory rate and rectal temperature of dairy cows under specific temperature conditions. To assess the resilience of dairy cows, we evaluated changes in feed intake under specific rainy conditions in response to weather factors. To assess the adaptability of dairy cows under specific windy weather conditions, we observed their activity levels in response to rainfall factors. The suitability of key meteorological factors is incorporated into the breeding weight calculation of the comprehensive score, and individuals with a comprehensive score of 10 or above are selected for inclusion in the breeding herd.

6. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of selecting climate-adapted cattle herds includes: Replacement heifers and lactating cows were selected as the evaluation samples; A stress resistance performance evaluation index system is constructed, which includes physiological indicators, production indicators, and health indicators; the physiological indicators include respiratory rate and rectal temperature; the production indicators include milk yield and milk protein percentage; and the health indicators include morbidity and somatic cell count. Conduct tracking and monitoring for a set period of time under different meteorological conditions; When the temperature factor is within a specific heat stress range, record the increase in respiratory rate of heifers compared to the suitable temperature range, and the decrease in milk production of lactating cows. When rainfall factors are in the high-impact range, record the changes in morbidity rates in the two types of cattle; The weights of each evaluation index in the stress resistance performance evaluation index system were determined using the analytic hierarchy process (AHP). Calculate the comprehensive index of stress resistance and adjust the breeding weights according to the comprehensive index; By dynamically adjusting weights and filtering at set intervals, climate-adaptive cattle herd optimization can be achieved.

7. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of selecting a suitable temperature period for mating includes: Collect historical meteorological data and label the estrus rate of dairy cows corresponding to the historical meteorological data; Based on the historical meteorological data, the ARIMA model in time series analysis is used to predict the changing trends of key meteorological factors for a future set duration. The optimal model parameters are determined using the AIC criterion, and the daily average temperature variation curve of the temperature factor is predicted. Based on the correlation between estrus rate and temperature factors in historical data, when the predicted daily average temperature is within a specific range, it is determined to be the estrus period; High-definition cameras and infrared sensors are installed on the ranch to collect behavioral and physiological data of dairy cows. The behavioral data includes activity frequency, standing time, and mounting behavior; the physiological data includes body temperature and activity level. An artificial intelligence recognition model based on CNN-LSTM was constructed, and the cow behavior data and physiological data were used as input to identify the estrus behavior of cows. Based on temperature prediction and estrus behavior recognition results, mating operations are carried out within a specific range of daily average temperature and within a set time period after the dairy cows are identified as being in estrus.

8. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of developing meteorological support plans based on pregnancy stages and initiating environmental control and nutritional adjustment measures based on real-time meteorological data to avoid stress responses includes: The process of dairy cow pregnancy is divided into three stages: early, middle and late stages, and meteorological support plans are developed for different stages. In the early stages, temperature factors are monitored. When the real-time daily average temperature is lower than the set value, the barn heating system is activated to regulate the temperature inside the barn to a specific range. At the same time, the feed formula is adjusted to increase the proportion of energy feed and improve the dairy cows' cold resistance. When the temperature is higher than the set value, the sprinkler and fan combination system is turned on, the sprinkler interval and the duration of each sprinkler are set, and the fan speed is adjusted. In the mid-term stage, pay attention to weather factors. When the sunshine duration is lower than the set value, supplement with artificial lighting to increase the set sunshine duration. When the daily average relative humidity is higher than the set value, turn on the dehumidification equipment to control the humidity in the shed below the set value. At the same time, add anti-mold agent to the feed and set the addition amount. During the late stage, monitor rainfall factors. When the cumulative rainfall reaches the set value, reinforce the roof of the cattle shed, clear the drainage channels to prevent water accumulation. When the average wind speed reaches the set value, close the side windows of the cattle shed and install windproof roller blinds to reduce the entry of cold air. The system collects meteorological and physiological data of dairy cows in real time. When it detects abnormal respiratory rate or a decrease in feed intake that exceeds a set percentage, it automatically triggers emergency control measures.

9. The method for managing dairy cow reproduction and health in ecological pastures based on meteorological data according to claim 1, characterized in that, The process of constructing a breeding benefit evaluation model and quantifying the impact of meteorological conditions on core breeding indicators includes: The estrus rate, conception rate, calf survival rate, and milk yield of dairy cows were selected as core breeding indicators. Key meteorological factors were used as input variables, and the core indicators were used as output variables. A breeding benefit evaluation model was constructed using a BP neural network. The network structure of the breeding benefit evaluation model is set to a specific combination of nodes, including an input layer, a hidden layer, and an output layer; the input layer corresponds to the number of nodes of key meteorological factors, the hidden layer has a set number of nodes, and the output layer corresponds to the number of nodes of core indicators. The Sigmoid function was chosen as the activation function, and the learning rate and number of iterations were set. The breeding benefit evaluation model is trained using historical data to keep the model prediction error within a set ratio. Based on the trained model, the impact of different meteorological conditions on core indicators is quantified by calculating the meteorological impact benefit value.

10. A dairy cow breeding and health management system based on meteorological data for an ecological ranch, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the ecological ranch dairy cow breeding and health management method based on meteorological data as described in any one of claims 1 to 9.

Images