Meteorological data-based ecological pasture carbon reserve dynamic prediction method and system

Abstract

The invention provides an ecological pasture carbon reserve dynamic prediction method and system based on meteorological data, and relates to the technical field of carbon reserve prediction, and the method comprises the steps: collecting a variety of data, constructing a carbon reserve calculation model, and calculating the basic carbon reserve of a pasture according to pasture parameter data. Analyzing the influence of the pasture parameter data on the target ecological pasture area to obtain a carbon cycle parameter, and calculating a carbon reserve influence index according to the influence of the cow breeding factor on the pasture basic carbon reserve. And constructing a multitask learning model optimized based on a secretary bird algorithm, inputting carbon cycle parameters and meteorological data, and outputting to obtain meteorological influence carbon data. And generating a carbon reserve change rule according to the carbon reserve influence index and the meteorological influence carbon data, and making a carbon management strategy according to the carbon reserve change rule. According to the method, the accuracy and scientificity of dynamic prediction of the carbon reserves of the ecological pasture are improved, and powerful support is provided for sustainable management and carbon emission reduction of the ecological pasture.

Description

Technical Field

[0001] This invention relates to the field of carbon storage prediction technology, and in particular to a method and system for dynamic prediction of carbon storage in ecological pastures based on meteorological data. Background Technology

[0002] Against the backdrop of the "dual-carbon" strategy and the green transformation of agriculture, ecological pastures, as the core carriers of the livestock carbon cycle, are crucial for achieving agricultural emission reduction and carbon sequestration, and ensuring the sustainable development of the dairy industry through precise carbon storage management. According to IPCC data, methane emissions from ruminants account for 28% of global methane emissions from human activities, and carbon emissions from dairy farming in my country account for 20% of total livestock and poultry farming emissions. Furthermore, the carbon footprint per unit of milk in China is significantly higher than in countries like New Zealand, making dynamic carbon storage management an urgent necessity.

[0003] Meteorology is a core driving factor in the carbon cycle. Temperature affects the rate of soil carbon decomposition, while precipitation and sunshine directly determine the efficiency of vegetation carbon sequestration. However, existing technologies often use meteorological data as an auxiliary reference or only use a single indicator for rough correction, ignoring the synergistic effects of factors and regional differences, and relying on static emission coefficients. This leads to large deviations between carbon cycle simulations and reality, and fails to accurately reflect the driving role of meteorology in carbon storage.

[0004] Changes in carbon storage are the result of the combined effects of livestock farming (livestock, diet, and manure treatment) and meteorological factors. For example, excessively high dietary crude protein can increase nitrogen excretion in feces and urine by 15%-20%, while yucca extract can reduce methane emissions by 10%-15%. However, existing technologies mostly focus on single factors, ignoring coupling effects, and are mainly qualitative descriptions, resulting in unclear emission reduction effects and a lack of basis for strategy formulation.

[0005] Existing technologies are mainly based on static accounting, making it difficult to predict future trends; some prediction models have single input features, do not integrate meteorological forecast data, and have not optimized algorithms for multi-objective prediction, resulting in poor adaptability and low accuracy. They cannot identify carbon loss risks in advance, thus restricting the initiative of pasture carbon management.

[0006] In summary, there is an urgent need for a dynamic prediction method and system for carbon storage in ecological pastures based on meteorological data, in order to support precise decision-making, quantify emission reduction effects, address climate risks, and promote the low-carbon transformation of the dairy industry. Summary of the Invention

[0007] This invention provides a method and system for dynamic prediction of carbon storage in ecological pastures based on meteorological data, in order to address the shortcomings of existing technologies that lack analysis of the impact of meteorology on the carbon cycle and insufficient assessment of the impact of changes in carbon storage.

[0008] On the one hand, this invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data, including:

[0009] Meteorological data, dairy farming factors, and pasture parameter data of the target ecological pasture area are collected to construct a carbon storage calculation model and calculate the basic carbon storage of the pasture based on the pasture parameter data.

[0010] Carbon cycle parameters are obtained by analyzing the impact of pasture parameter data on the target ecological pasture area, and the carbon storage impact index is calculated based on the impact of dairy farming factors on the basic carbon storage of the pasture.

[0011] A multi-task learning model based on the Secretary Bird algorithm was constructed. The inputs were carbon cycle parameters and meteorological data, and the output was the carbon data affected by meteorology.

[0012] Based on the carbon storage impact index and combined with meteorological carbon data, a carbon storage change pattern is generated, and a carbon management strategy is formulated based on the carbon storage change pattern.

[0013] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for constructing a carbon storage calculation model include:

[0014] For different forms of carbon storage, corresponding influencing factors and carbon conversion pathways are determined as carbon characteristic parameters.

[0015] Based on carbon characteristic parameters, a vegetation sub-model was constructed by combining the correlation between vegetation growth and meteorological factors. A soil sub-model was constructed by calculating soil organic carbon storage based on soil layer differences and temperature decomposition depth.

[0016] The carbon storage of dairy cows is quantified by the effects of body weight, stock size, and temperature to construct a carbon storage model for dairy cows. The carbon loss patterns between manure and stubble are combined with the effects of temperature and wind speed to construct a waste sub-model.

[0017] A carbon storage calculation model is formed by coupling the vegetation sub-model, soil sub-model, dairy cow carbon storage, and waste sub-model.

[0018] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for calculating the basic carbon storage of pastures include:

[0019] The Laida criterion was used to remove data from pasture parameter data that exceeded a preset multiple of the standard deviation, and the missing values ​​were filled with the average value of pastures of the same type in the same region to obtain pasture processing parameter data.

[0020] The pasture processing parameter data is input into the carbon storage calculation model to calculate the corrected carbon storage of vegetation, soil, dairy cows and waste, and then summed to obtain the basic carbon storage of the pasture.

[0021] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for obtaining carbon cycle parameters include:

[0022] Based on the carbon flow patterns of ecological pastures, we analyze the carbon cycle pathways among different carbon storage carriers, classify pasture parameter data, and establish the correspondence between cycle parameters.

[0023] Correlation analysis was used to calculate the degree of correlation between pasture parameter data and carbon cycle process indicators, thereby determining the influence weights.

[0024] Based on the correspondence and influence weights of the cycle parameters, the process parameters of carbon input, carbon output, and carbon conversion are calculated as carbon cycle parameters.

[0025] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for calculating the carbon storage impact index include:

[0026] Based on the actual farming scenario, the factors are adjusted, and the total carbon storage is calculated according to the correlation logic between dairy farming factors and carbon storage carriers.

[0027] The carbon storage impact index is obtained by calculating the relative change in carbon storage after adjusting for different farming factors based on the basic carbon storage and total carbon storage of the ranch.

[0028] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for constructing a multi-task learning model include:

[0029] Based on the feature extraction network shared by multiple tasks, common features between different tasks are learned as shared layers, and task-specific features are learned by the independent output layers of each task.

[0030] The model framework is constructed based on the shared layer and the task-specific layer, and the parameters to be optimized in the model framework are encoded as the positions of individual secretary birds. The comprehensive loss function is selected as the fitness function.

[0031] Based on the upper and lower bounds of the parameters to be optimized, multiple individual secretary birds are randomly generated.

[0032] The process of a secretary bird searching for prey is simulated by generating a secretary bird's location through differential mutation.

[0033] By combining Brownian motion for local search and simulating the secretary bird's precise attack, the digestion location and attack location of the secretary bird are generated.

[0034] The process of a secretary bird evading predators was simulated, and a dynamic perturbation strategy was used to balance exploration and development to obtain the escape location of the secretary bird.

[0035] After reaching the preset number of iterations, the update stops. The fitness value of different secretary bird positions is calculated according to the fitness function, and the parameter to be optimized with the smallest fitness value is selected to construct a multi-task learning model.

[0036] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for outputting meteorological impact carbon data include:

[0037] The meteorological data is aligned with the time scale of carbon cycle parameters and then standardized before being input into a multi-task learning model.

[0038] Based on the common characteristics of meteorological data learned from the shared layer, the prediction accuracy index of each carbon cycle parameter is calculated based on the task-specific layer.

[0039] Sensitivity coefficients were obtained by quantifying the impact of individual meteorological factors on carbon cycle parameters using the controlled variable method.

[0040] For each carbon cycle parameter, output the relationship curve with meteorological factors, and sort them according to the magnitude of the absolute value of the sensitivity coefficient to obtain the meteorological impact carbon data.

[0041] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data. The steps for generating the carbon storage change pattern include:

[0042] Based on a preset time period, the impact path is determined by correlation analysis between meteorological carbon data and carbon storage impact index and the basic carbon storage of pastures.

[0043] By integrating climate and aquaculture impacts based on the impact pathways, a dynamic change formula is obtained by adjusting the carbon storage calculation model.

[0044] The dynamic changes of vegetation carbon pool, soil carbon pool, dairy cow carbon pool and waste carbon pool are calculated based on the dynamic change formula and integrated to obtain the change in total carbon storage.

[0045] By altering meteorological conditions and aquaculture factors, the study simulates changes in total carbon storage under different scenarios, analyzes the trends over time, and identifies periodic and trend characteristics to obtain the patterns of carbon storage change.

[0046] This invention provides a method for dynamic prediction of carbon storage in ecological pastures based on meteorological data, and the steps for formulating carbon management strategies include:

[0047] By analyzing the patterns of carbon storage changes over time, considering factors of contribution, and considering scenario thresholds, we can identify problems at different stages of the carbon cycle.

[0048] Based on the impact on costs, issues at different stages are prioritized to set overall goals, which are then broken down into phased goals to match the time-varying patterns of carbon reserves.

[0049] Based on the changing characteristics of carbon storage over a preset time period, carbon loss prevention and control measures and carbon accumulation enhancement measures are formulated, and differentiated measures are developed according to the contribution of factors. Boundary management schemes are developed based on scenario thresholds, and these are integrated to form a carbon management strategy.

[0050] On the other hand, the present invention provides a dynamic prediction system for carbon storage in ecological pastures based on meteorological data, comprising:

[0051] The carbon storage base calculation module is used to collect meteorological data, dairy farming factors and pasture parameter data of the target ecological pasture area, construct a carbon storage calculation model, and calculate the basic carbon storage of the pasture based on the pasture parameter data.

[0052] The carbon cycle impact measurement module is used to analyze the impact of pasture parameter data on the target ecological pasture area to obtain carbon cycle parameters, and to calculate the carbon storage impact index based on the impact of dairy farming factors on the basic carbon storage of the pasture.

[0053] The atmospheric carbon impact module is used to build a multi-task learning model based on the Secretary Bird algorithm. It takes carbon cycle parameters and meteorological data as input and outputs meteorological impact carbon data.

[0054] The carbon policy formulation module is used to generate carbon storage change patterns based on the carbon storage impact index and combined with meteorological carbon data, and to formulate carbon management strategies based on the carbon storage change patterns.

[0055] This invention provides a method and system for dynamic prediction of carbon storage in ecological pastures based on meteorological data. By comprehensively considering multiple factors to construct a model, it accurately calculates the basic carbon storage of pastures and, through analyzing the impact of meteorological and livestock factors on carbon storage, achieves precise prediction of dynamic changes in carbon storage, providing reliable data support for pasture carbon management. The method quantifies the impact of dairy farming factors and meteorological factors on carbon storage, clarifying key influencing factors and their degree of influence. For example, it determines the specific impact of livestock factors such as stock size and dietary crude protein content, as well as meteorological factors such as temperature and precipitation, on carbon storage, providing a basis for targeted measures. Furthermore, it utilizes the Secretary Bird algorithm to optimize the multi-task learning model, improving the model's ability to analyze meteorological impact carbon data, enabling the model to better adapt to complex ecological pasture environments and improving the accuracy and reliability of predictions. Finally, it formulates scientific carbon management strategies based on the patterns of carbon storage changes, covering multiple aspects such as time dimensions, factor contributions, and scenario thresholds, effectively guiding pasture carbon resource management, improving carbon sequestration capacity, reducing carbon emissions, and helping pastures achieve low-carbon sustainable development. Attached Figure Description

[0056] 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.

[0057] Figure 1This is one of the flowcharts illustrating the dynamic prediction method for carbon storage in ecological pastures based on meteorological data provided in this embodiment of the invention.

[0058] Figure 2 This is the second flowchart of the dynamic prediction method for carbon storage in ecological pastures based on meteorological data provided in this embodiment of the invention.

[0059] Figure 3 This is a flowchart illustrating the impact of dairy cow manure on carbon storage in the dynamic prediction method for carbon storage in ecological pastures based on meteorological data provided in this embodiment of the invention.

[0060] Figure 4 This is a flowchart illustrating the dynamic prediction system for carbon storage in ecological pastures based on meteorological data provided in an embodiment of the present invention. Detailed Implementation

[0061] 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.

[0062] The following is combined Figures 1-4 This invention describes a method and system for dynamic prediction of carbon storage in ecological pastures based on meteorological data.

[0063] like Figure 1 As shown in the embodiment of the present invention, the method for dynamic prediction of carbon storage in ecological pastures based on meteorological data includes:

[0064] Meteorological data, dairy farming factors, and pasture parameter data of the target ecological pasture area are collected to construct a carbon storage calculation model, and the basic carbon storage of the pasture is calculated based on the pasture parameter data. Pasture parameter data may include carbon pools from vegetation, soil, dairy cows, and waste.

[0065] The steps involved in constructing a carbon storage calculation model include:

[0066] For different forms of carbon storage, corresponding influencing factors and carbon conversion pathways are determined as carbon characteristic parameters.

[0067] Based on carbon characteristic parameters, a vegetation sub-model was constructed by combining the correlation between vegetation growth and meteorological factors. A soil sub-model was constructed by calculating soil organic carbon storage based on soil layer differences and temperature decomposition depth.

[0068] The carbon storage of dairy cows is quantified by the effects of body weight, stock size, and temperature to construct a carbon storage model for dairy cows. The carbon loss patterns between manure and stubble are combined with the effects of temperature and wind speed to construct a waste sub-model.

[0069] A carbon storage calculation model is formed by coupling the vegetation sub-model, soil sub-model, dairy cow carbon storage, and waste sub-model.

[0070] The steps for calculating basic carbon storage in pastures include:

[0071] The Laida criterion was used to remove data from pasture parameter data that exceeded a preset multiple of the standard deviation, and the missing values ​​were filled with the average value of pastures of the same type in the same region to obtain pasture processing parameter data.

[0072] The pasture processing parameter data is input into the carbon storage calculation model to calculate the corrected carbon storage of vegetation, soil, dairy cows and waste, and then summed to obtain the basic carbon storage of the pasture.

[0073] For example: Total carbon reserves are 29,427 tons, rounded to two decimal places.

[0074] Inventory Distribution Ratio Table:

[0075] carbon pool Carbon reserves (tons) percentage vegetation 4,214.02 14.32% soil 11,969.30 40.67% dairy cow 1,851.00 6.29% waste 11,393.00 38.72%

[0076] Carbon cycle parameters are obtained by analyzing the impact of pasture parameter data on the target ecological pasture area, and the carbon storage impact index is calculated based on the impact of dairy farming factors on the basic carbon storage of the pasture.

[0077] The steps to obtain carbon cycle parameters include:

[0078] Based on the carbon flow patterns of ecological pastures, we analyze the carbon cycle pathways among different carbon storage carriers, classify pasture parameter data, and establish the correspondence between cycle parameters.

[0079] The correspondence between cycle parameters can include: vegetation carbon pool parameters: biomass, carbon content, growth cycle → associated carbon input, carbon output, carbon transformation.

[0080] Soil carbon pool parameters: organic carbon content, bulk density, soil layer thickness → associated carbon input and carbon output.

[0081] Dairy cow carbon pool parameters: number of cows, body weight, feed intake, carbon content → related to carbon input, carbon output, and carbon conversion.

[0082] Waste carbon pool parameters: manure production, stubble production, carbon content → associated carbon input, carbon output, carbon conversion.

[0083] Correlation analysis was used to calculate the degree of correlation between pasture parameter data and carbon cycle process indicators, thereby determining the influence weights.

[0084] Based on the correspondence and influence weights of the cycle parameters, the process parameters of carbon input, carbon output, and carbon conversion are calculated as carbon cycle parameters.

[0085] Carbon input parameters can include vegetation photosynthetic carbon sequestration rate, external feed carbon input, stubble carbon input to soil, and manure carbon input to soil.

[0086] Carbon output parameters can include: carbon release rate from vegetation respiration, carbon release rate from soil respiration, methane emissions from dairy cows, and carbon loss rate from waste decomposition.

[0087] Carbon conversion parameters can include: vegetation-cattle carbon conversion rate, vegetation-waste carbon transfer rate, dairy cow-waste carbon transfer rate, and waste-soil carbon conversion rate.

[0088] The steps for calculating the carbon storage impact index include:

[0089] Based on the actual farming scenario, the factors are adjusted, and the total carbon storage is calculated according to the correlation logic between dairy farming factors and carbon storage carriers.

[0090] Factors in dairy farming can include the number of cows, feed, and additives.

[0091] Herd size directly affects the carbon pool of dairy cows and the carbon pool of waste, and indirectly affects the carbon pool of soil and vegetation. Feed directly affects the carbon pool of vegetation, dairy cows, and waste. Additives directly affect the carbon pool of dairy cows and the carbon pool of waste, causing dairy cows to gain weight and reduce manure emissions.

[0092] For example, the addition of nanobubble water can disrupt the cellulose structure and reduce the crystallinity of cellulose, which is beneficial for microorganisms to decompose cellulose into VFA. VFA can then be used to produce methanogenic compounds to generate more methane. From an economic perspective, micro-nanobubble generators can be used for pretreatment, and the micro-nanobubble water they produce can be used for anaerobic fermentation of manure, improving fermentation efficiency. The gas required to generate bubbles can be air, etc., which is relatively inexpensive. Considering the characteristics of dairy farm wastewater and economic factors, this project uses milking parlor wastewater and drinking trough cleaning wastewater as water sources to conduct relevant research on the preparation of air nanobubble water.

[0093] like Figure 3As shown, dairy farming generates the largest volume of wastewater, and the storage process results in the emission of large amounts of gases such as CH4 and NH3, polluting the atmospheric environment and causing nutrient resource loss. Although large-scale dairy manure storage facilities have gradually adopted black film covering to reduce carbon and nitrogen emissions, open-type manure storage facilities are still relatively common in dairy farms, and the demand for emission reduction remains strong. Adding acidifying agents is considered to promote NH3 emission reduction without increasing GHG emissions, making it a technical measure with relatively good overall effects. However, it often requires a matching stirring device for thorough mixing, which is not available in many scenarios. In view of the above characteristics, this project selected three types of additives that can be industrially used: citric acid, wood vinegar, and microbial ammonia immobilization agents, and used a surface spraying method to investigate the carbon and nitrogen emissions during the storage process of dairy manure.

[0094] The carbon storage impact index is calculated based on the basic carbon storage and total carbon storage of the pasture, after adjusting for different farming factors using factor adjustment values. The formula is as follows:

[0095]

[0096] In the formula, It is an index affecting carbon reserves. It is the basic carbon storage of pastures. This is the total carbon storage. When Current factors have adjusted for an increase in carbon storage. Current factors have led to a reduction in carbon storage. The larger it is, the greater its impact.

[0097] A multi-task learning model based on the Secretary Bird algorithm was constructed. The inputs were carbon cycle parameters and meteorological data, and the output was the carbon data affected by meteorology.

[0098] like Figure 2 As shown, the steps for constructing a multi-task learning model include:

[0099] Based on the feature extraction network shared by multiple tasks, common features between different tasks are learned as shared layers, and task-specific features are learned by the independent output layers of each task.

[0100] A model framework is constructed based on the shared layer and the task-specific layer. The parameters to be optimized in the model framework are encoded as the individual positions of the secretary bird. The comprehensive loss function is selected as the fitness function, and the formula is expressed as follows:

[0101]

[0102] In the formula, It's the number of tasks. It is a task The weight, It's a loss for the mission. It is the fitness function.

[0103] Based on the upper and lower bounds of the parameters to be optimized, multiple individual Secretary Birds are randomly generated, as expressed by the formula:

[0104]

[0105] In the formula, It is the first The location of each secretary bird individual It is the first An upper bound for the parameters to be optimized. It is the first The lower bound of the parameter to be optimized. It is a random number between [0, 1].

[0106] Simulating the process of a secretary bird searching for prey, the location of the secretary bird is generated through differential mutation, expressed by the formula:

[0107]

[0108] In the formula, They are randomly selected individuals. It is a scaling factor. The secretary bird is searching for its location.

[0109] By combining Brownian motion for local search and simulating the secretary bird's precise attack to generate the secretary bird's digestion location and attack location, the formula is expressed as:

[0110]

[0111] In the formula, These are standard normally distributed random numbers. It is the current globally optimal solution. It is the secretary bird's digestive location. This is the Secretary Bird's attack position. It is a nonlinear perturbation factor.

[0112] in

[0113] In the formula, It is a fixed constant. yes index, It is a random number between [0,1]. yes The power of.

[0114] The process of a secretary bird evading predators is simulated. A dynamic perturbation strategy is used to balance exploration and development to determine the secretary bird's escape location. The formula is expressed as:

[0115]

[0116] In the formula, It is a random candidate solution. It is a dynamic disturbance factor. That's where the secretary bird escaped.

[0117] After reaching the preset number of iterations, the update stops. The fitness value of different secretary bird positions is calculated according to the fitness function, and the parameter to be optimized with the smallest fitness value is selected to construct a multi-task learning model.

[0118] The steps to obtain carbon data related to meteorological impacts include:

[0119] The meteorological data is aligned with the time scale of carbon cycle parameters and then standardized before being input into a multi-task learning model.

[0120] Based on the common characteristics of meteorological data learned from the shared layer, the prediction accuracy index of each carbon cycle parameter is calculated based on the task-specific layer.

[0121] Sensitivity coefficients were obtained by quantifying the impact of individual meteorological factors on carbon cycle parameters using the controlled variable method.

[0122] The steps to obtain the sensitivity coefficient may include: fixing other meteorological factors as mean values ​​and changing only the target meteorological factor.

[0123] The changes in corresponding carbon cycle parameters are predicted using a trained multi-task learning model.

[0124] The sensitivity coefficient (the change in carbon cycle parameters for every 1 unit change in meteorological factors) is calculated using the following formula:

[0125]

[0126] In the formula, It's a meteorological factor. These are carbon cycle parameters. It is the change in meteorological factors. It is the change in parameters.

[0127] For each carbon cycle parameter, output the relationship curve with meteorological factors, and sort them according to the magnitude of the absolute value of the sensitivity coefficient to obtain the meteorological impact carbon data.

[0128] When the carbon cycle parameter is methane emissions, the most sensitive meteorological factor is temperature, with a sensitivity coefficient of 0.025 kgC / (head·d·℃). When the carbon cycle parameter is soil respiration, the most sensitive meteorological factor is temperature, with a sensitivity coefficient of 0.01 kgC / (hm²·d·℃). For example, for every 1℃ increase in temperature, the methane emission rate of dairy cows increases by 0.025 kgC / (head·d) (sensitivity coefficient). For every 100 hours of additional sunshine, the vegetation photosynthetic carbon sequestration rate (GPP) increases by 3 kgC / (hm²·d).

[0129] Based on the carbon storage impact index and combined with meteorological carbon data, a carbon storage change pattern is generated, and a carbon management strategy is formulated based on the carbon storage change pattern.

[0130] The steps involved in understanding the changing patterns of carbon reserves include:

[0131] Based on a preset time period, the impact path is determined by correlation analysis between meteorological carbon data and carbon storage impact index and the basic carbon storage of pastures.

[0132] By integrating climate and aquaculture impacts based on the impact pathways, a dynamic change formula is obtained by adjusting the carbon storage calculation model.

[0133] The dynamic change formula includes the vegetation dynamic change formula, which is expressed as:

[0134]

[0135] In the formula, It is the baseline value of vegetation carbon pool. Carbon data based on meteorological impacts Change yes Benchmark value It is the first The impact index of dietary crude protein on vegetation carbon pool over a time period. It is a change in vegetation carbon.

[0136] The formula for soil dynamics is expressed as:

[0137]

[0138] In the formula, It is the baseline value of the soil carbon pool. Carbon data based on meteorological impacts Change yes The baseline value, It is the first The impact index of time-dependent micro-nano bubble technology on soil carbon pool It is a change in soil carbon.

[0139] The formula for the dynamic changes of dairy cows is expressed as:

[0140]

[0141] In the formula, This is the baseline value for dairy cow carbon stocks. It is the change in body weight of a single dairy cow based on the carbon data affected by meteorological conditions. yes The baseline value, It is the first The impact of time-based stocking on dairy cow carbon pool index. It refers to the carbon changes in dairy cows.

[0142] The formula for the dynamic change of waste is expressed as:

[0143]

[0144] In the formula, It is the baseline value for the waste carbon pool. Carbon data based on meteorological impacts Change yes The baseline value, It is the first The impact index of yucca extract on waste carbon pool. It refers to carbon changes in waste.

[0145] The dynamic changes of vegetation carbon pool, soil carbon pool, dairy cow carbon pool and waste carbon pool are calculated based on the dynamic change formula and integrated to obtain the change in total carbon storage.

[0146] By altering meteorological conditions and aquaculture factors, the study simulates changes in total carbon storage under different scenarios, analyzes the trends over time, and identifies periodic and trend characteristics to obtain the patterns of carbon storage change.

[0147] The steps involved in developing a carbon management strategy include:

[0148] By analyzing the patterns of carbon storage changes over time, considering factors of contribution, and considering scenario thresholds, we can identify problems at different stages of the carbon cycle.

[0149] Based on the impact on costs, issues at different stages are prioritized to set overall goals, which are then broken down into phased goals to match the time-varying patterns of carbon reserves.

[0150] Based on the changing characteristics of carbon storage over a preset time period, carbon loss prevention and control measures and carbon accumulation enhancement measures are formulated, and differentiated measures are developed according to the contribution of factors. Boundary management schemes are developed based on scenario thresholds, and these are integrated to form a carbon management strategy.

[0151] Carbon loss control measures can include weather-adaptive measures: installing shade nets and misting systems in dairy barns to keep the temperature below 25°C; and adjusting vegetation irrigation cycles to mitigate drought-induced GPP declines.

[0152] Carbon accumulation enhancement measures can include improving the soil carbon pool: after winter pasture harvesting, all stubble should be returned to the field, combined with microbial carbon fixation agents to improve soil carbon conversion rate.

[0153] Control the amount of soil irrigation to maintain the soil moisture content at 60% of field capacity.

[0154] Stabilizing the carbon pool in dairy cows: Adding 1% betaine to the diet reduces weight loss caused by low temperatures.

[0155] The number of animals in stock is adjusted slightly each quarter (increasing to 7,800 in winter and decreasing to 7,500 in spring) to match the feed supply capacity to the vegetation growth cycle.

[0156] Boundary management solutions may include threshold control of livestock numbers: establishing a linkage mechanism between livestock numbers and manure treatment capacity: when the number of livestock reaches 7,800, the manure treatment system is expanded.

[0157] Implement "precise stocking": Combine monthly milk production to cull low-producing dairy cows (annual milk production <8 tons / head) and maintain the stocking in the optimal range of 7,800-8,000 head.

[0158] Dietary CP threshold control: Establish a "CP-Dairy Cow Production Performance" monitoring system: When CP drops to 14.5%, test the milk protein percentage (≥3.1%) and weight change (weekly increase ≥0.5kg / head) of dairy cows weekly, based on the rule of "CP < 14% → (C_{animal}\) decrease".

[0159] like Figure 3 As shown, based on the same general inventive concept, this invention also protects a dynamic prediction system for carbon storage in ecological pastures based on meteorological data. The dynamic prediction system includes:

[0160] The carbon storage base calculation module is used to collect meteorological data, dairy farming factors and pasture parameter data of the target ecological pasture area, construct a carbon storage calculation model, and calculate the basic carbon storage of the pasture based on the pasture parameter data.

[0161] The carbon cycle impact measurement module is used to analyze the impact of pasture parameter data on the target ecological pasture area to obtain carbon cycle parameters, and to calculate the carbon storage impact index based on the impact of dairy farming factors on the basic carbon storage of the pasture.

[0162] The atmospheric carbon impact module is used to build a multi-task learning model based on the Secretary Bird algorithm. It takes carbon cycle parameters and meteorological data as input and outputs meteorological impact carbon data.

[0163] The carbon policy formulation module is used to generate carbon storage change patterns based on the carbon storage impact index and combined with meteorological carbon data, and to formulate carbon management strategies based on the carbon storage change patterns.

[0164] This embodiment provides a method and system for dynamic prediction of carbon storage in ecological pastures based on meteorological data. By collecting meteorological data, dairy farming factors, and pasture parameter data, a coupled model integrating multi-source data is constructed, effectively improving data quality and better reflecting the actual carbon storage situation of ecological pastures. Based on the carbon flow patterns of ecological pastures, the carbon cycle pathways among different carbon storage carriers (vegetation, soil, dairy cows, and waste) are analyzed. Correlation analysis is used to calculate the degree of correlation between pasture parameter data and carbon cycle process indicators, determining the influence weights, and thus quantifying the process parameters of carbon input, carbon output, and carbon conversion. This method makes carbon cycle parameters more consistent with the actual situation of pastures, providing a reliable foundation for subsequent dynamic prediction of carbon storage. The carbon storage impact index incorporates farming factors into the dynamic prediction framework. By combining meteorological impact carbon data with the carbon storage impact index, a "farming-meteorological synergy" carbon storage change pattern is generated. This method is more consistent with the actual operation scenario of ecological pastures, and the prediction results are more practical. Furthermore, by deconstructing the carbon storage change pattern, problems in different stages of the carbon cycle are identified; and boundary management schemes are formulated based on scenario thresholds. This strategy effectively improves the efficiency and effectiveness of carbon management.

[0165] 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.

[0166] 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 dynamic prediction of carbon storage in ecological pastures based on meteorological data, characterized in that, include: Collect meteorological data, dairy farming factors and pasture parameter data of the target ecological pasture area, construct a carbon storage calculation model, and calculate the basic carbon storage of the pasture based on the pasture parameter data; Carbon cycle parameters are obtained by analyzing the impact of the pasture parameter data on the target ecological pasture area, and carbon storage impact index is calculated based on the impact of dairy farming factors on the basic carbon storage of the pasture. A multi-task learning model based on the Secretary Bird algorithm optimization is constructed. The carbon cycle parameters and the meteorological data are input, and the meteorological impact carbon data is output. Based on the carbon storage impact index and the meteorological impact carbon data, a carbon storage change pattern is generated, and a carbon management strategy is formulated based on the carbon storage change pattern.

2. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 1, characterized in that, The steps for constructing the carbon storage calculation model include: For different forms of carbon storage, the corresponding influencing factors and carbon conversion pathways are determined as carbon characteristic parameters; Based on the carbon characteristic parameters, a vegetation sub-model is constructed by combining the correlation between vegetation growth and meteorological factors, and a soil sub-model is constructed by calculating the soil organic carbon storage based on soil layer differences and temperature decomposition depth. The carbon storage of dairy cows is quantified by the effects of body weight, stock size and temperature to construct a carbon storage model of dairy cows. The carbon loss pattern between manure and stubble is combined with the effects of temperature and wind speed to construct a waste sub-model. The vegetation sub-model, the soil sub-model, the dairy cow carbon storage, and the waste sub-model are coupled to form the carbon storage calculation model.

3. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 1, characterized in that, The steps for calculating the basic carbon storage of the pasture include: The Laida criterion was used to remove data exceeding a preset multiple of standard deviation from the pasture parameter data, and the missing values ​​were filled with the average value of pastures of the same type in the same region to obtain the pasture processing parameter data. The pasture processing parameter data is input into the carbon storage calculation model to calculate the corrected carbon storage of vegetation, soil, dairy cows and waste, and then summed to obtain the basic carbon storage of the pasture.

4. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 3, characterized in that, The steps for obtaining the carbon cycle parameters include: Based on the carbon flow patterns of ecological pastures, the carbon cycle pathways among different carbon storage carriers are analyzed, the pasture parameter data are classified, and the correspondence between cycle parameters is established. Correlation analysis was used to calculate the degree of correlation between the pasture parameter data and carbon cycle process indicators, thereby determining the influencing weights; Based on the correspondence of the cycle parameters and the influence weights, the process parameters of carbon input, carbon output and carbon conversion are calculated as the carbon cycle parameters.

5. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 4, characterized in that, The steps for calculating the carbon storage impact index include: Based on the actual farming scenario, the factor adjustment value is set, and the total carbon storage is calculated according to the correlation logic between the dairy farming factors and the carbon storage carrier. The carbon storage impact index is obtained by calculating the relative change in carbon storage after adjustment based on the adjustment values ​​of different farming factors, using the basic carbon storage of the pasture and the total carbon storage.

6. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 1, characterized in that, The steps for constructing the multi-task learning model include: Based on the feature extraction network shared by multiple tasks, common features between different tasks are learned as shared layers, and task-specific features are learned by the independent output layers of each task. A model framework is constructed based on the shared layer and the task-specific layer, and the parameters to be optimized in the model framework are encoded as the individual positions of the secretary bird. A comprehensive loss function is selected as the fitness function. Based on the upper and lower bounds of the parameters to be optimized, multiple individual secretary birds are randomly generated; Simulate the process of a secretary bird searching for prey by generating a location for the secretary bird through differential mutation; By combining Brownian motion for local search and simulating the secretary bird's precise attack, the digestion location and attack location of the secretary bird are generated. Simulating the process of a secretary bird evading predators, a dynamic perturbation strategy was used to balance exploration and development to obtain the secretary bird's escape location; After reaching the preset number of iterations, the update stops. The fitness value of different secretary bird positions is calculated according to the fitness function, and the parameter to be optimized with the smallest fitness value is selected to construct the multi-task learning model.

7. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 6, characterized in that, The steps for outputting the meteorological impact carbon data include: The meteorological data is aligned with the time scale of the carbon cycle parameters and then standardized before being input into the multi-task learning model. The common features of the meteorological data are learned based on the shared layer, and the prediction accuracy index of each carbon cycle parameter is calculated based on the task-specific layer. Sensitivity coefficients were obtained by quantifying the impact of individual meteorological factors on the carbon cycle parameters using the controlled variable method. For each carbon cycle parameter, output the relationship curve with meteorological factors, and sort them according to the magnitude of the absolute value of the sensitivity coefficient to obtain the meteorological impact carbon data.

8. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 1, characterized in that, The steps for generating the aforementioned carbon storage change pattern include: Based on a preset time period, the meteorological impact carbon data and the carbon storage impact index are correlated with the basic carbon storage of the pasture to determine the impact path; Based on the aforementioned impact pathways, climate and aquaculture impacts are integrated, and the carbon storage calculation model is adjusted to obtain a dynamic change formula; The dynamic changes of vegetation carbon pool, soil carbon pool, dairy cow carbon pool and waste carbon pool are calculated based on the dynamic change formula and integrated to obtain the change in total carbon storage. By changing meteorological conditions and the aforementioned aquaculture factors, the total carbon storage changes under different scenarios are simulated, and the changing trend over time is analyzed to identify periodic and trend characteristics and obtain the carbon storage change pattern.

9. The method for dynamic prediction of carbon storage in ecological pastures based on meteorological data according to claim 1, characterized in that, The steps for developing the carbon management strategy include: The changes in carbon storage are analyzed from the perspectives of time, factor contributions, and scenario thresholds to identify problems at different stages of the carbon cycle. Based on the impact on costs, the problems in different stages are prioritized to set overall goals, which are then broken down into phased goals to match the time-varying patterns of carbon reserves. Based on the changing characteristics of carbon reserves over a preset time period, carbon loss prevention and control measures and carbon accumulation enhancement measures are formulated, and differentiated measures are formulated according to the contribution of the factors. Boundary management schemes are formulated based on the scenario thresholds, and these are integrated to form the carbon management strategy.

10. A dynamic prediction system for carbon storage in ecological pastures based on meteorological data, applied to the dynamic prediction method for carbon storage in ecological pastures based on meteorological data as described in any one of claims 1 to 9, characterized in that, The dynamic prediction system includes: The carbon storage base calculation module is used to collect meteorological data, dairy farming factors and pasture parameter data of the target ecological pasture area, construct a carbon storage calculation model, and calculate the basic carbon storage of the pasture based on the pasture parameter data. The carbon cycle impact calculation module is used to analyze the impact of the pasture parameter data on the target ecological pasture area to obtain carbon cycle parameters, and to calculate the carbon storage impact index based on the impact of dairy farming factors on the basic carbon storage of the pasture. The atmospheric carbon impact module is used to construct a multi-task learning model based on the Secretary Bird algorithm optimization. It takes the carbon cycle parameters and the meteorological data as input and outputs the meteorological impact carbon data. The carbon policy formulation module is used to generate carbon storage change patterns based on the carbon storage impact index and the meteorological impact carbon data, and to formulate carbon management strategies based on the carbon storage change patterns.

Images