An automated control method for the agricultural and rural environment based on the collaborative control of carbon and nitrogen emissions

Abstract

The present invention discloses an automated control method for the rural agricultural environment based on the co-control of carbon and nitrogen emissions, including: obtaining the co-emission data of carbon and nitrogen during the agricultural and rural production process and the resource utilization process of domestic waste, and collecting the carbon content information in the soil and air; fusing the co-emission data of carbon and nitrogen, and the carbon content information in the soil and air to generate a unified co-emission dataset of carbon and nitrogen; establishing a dynamic adjustment model for the co-emission of carbon and nitrogen according to the crop type and seasonal changes, and combining with climate conditions, soil properties and tillage methods to judge the co-emission law of carbon and nitrogen during different crop growth cycles; according to the co-emission law of carbon and nitrogen, using machine learning algorithms to train a co-emission prediction model of carbon and nitrogen, inputting the co-emission dataset of carbon and nitrogen, and outputting the predicted value of the co-emission of carbon and nitrogen in the future time period; according to the prediction results, dynamically adjusting the co-emission standards of carbon and nitrogen to generate a control plan adapted to different crop types and seasonal changes.

Description

Technical Field

[0001] The present invention belongs to the field of automation control technology, and specifically relates to an automation control method for agricultural and rural environments based on coordinated carbon and nitrogen emission management. Background Art

[0002] In the agricultural environment automation control method based on carbon-nitrogen co-emission control, a key technical issue is how to formulate and implement dynamic carbon-nitrogen co-emission standards in different links of agricultural production according to the growth characteristics and seasonal changes of different crops. In the agricultural and rural production process and the resource utilization of domestic waste, the sources of carbon-nitrogen co-emissions are diverse, including soil respiration, fertilizer application, agricultural machinery operations, irrigation systems, etc. The carbon-nitrogen co-emissions in these links are not only affected by the crop type, but also by multiple factors such as climatic conditions, soil properties, and farming methods. Therefore, in order to achieve precise carbon-nitrogen co-emission management, it is first necessary to establish a carbon-nitrogen co-emission monitoring system that can comprehensively cover all links of agricultural production.

[0003] However, existing technologies make it difficult to achieve real-time and accurate monitoring of carbon-nitrogen co-emissions in agricultural and rural production processes and the resource utilization of domestic waste. Although agricultural IoT sensors can collect data on carbon content in soil and air, these data often have temporal and spatial heterogeneity and are greatly interfered by environmental factors. For example, the carbon-nitrogen co-emissions produced by soil respiration will vary significantly in different time periods and depths, while the carbon content in the air is easily affected by fluctuations in meteorological conditions such as wind speed and temperature. In addition, different crops have different patterns of carbon absorption and release during their growth cycle, and biological processes such as crop root activity and leaf photosynthesis will also have a dynamic impact on carbon-nitrogen co-emissions. These complex factors make it difficult for a single sensor data to fully reflect the true situation of carbon-nitrogen co-emissions.

[0004] What is even more complicated is that the carbon-nitrogen co-emission standards in agricultural production need to be dynamically adjusted according to different crop types and seasonal changes. For example, rice fields will produce methane emissions under flooded conditions, while dryland crops will release more carbon dioxide. Changes in temperature and humidity in different seasons will also significantly affect soil microbial activity, thereby changing the intensity of carbon-nitrogen co-emissions. Therefore, how to incorporate these complex factors into the formulation of carbon-nitrogen co-emission standards to form a dynamic standard system that can reflect the laws of crop growth and adapt to environmental changes is a technical problem that needs to be solved urgently.

[0005] In addition, the decision-making basis of the agricultural environment automation control system relies on accurate carbon-nitrogen co-emission data, and it is difficult for existing technologies to effectively integrate and analyze multi-source data. The data formats, accuracies, and time scales collected by different sensors vary. How to fuse these data into a unified decision-making model while ensuring data quality is also a technical bottleneck. Especially in large-scale agricultural production scenarios, how to achieve efficient and low-cost carbon-nitrogen co-emission monitoring and control remains a technical problem that has not been fully solved. Summary of the Invention

[0006] To solve the problems existing in the prior art, the present invention provides an agricultural and rural environment automation control method based on carbon-nitrogen co-emission control. By using an automation control system to monitor carbon-nitrogen co-emission data in real time and perform corresponding emission reduction operations according to preset standards, it realizes the intelligent management of carbon-nitrogen co-emissions in the process of agricultural and rural production and the resource utilization process of domestic waste, effectively improving the accuracy and adaptability of carbon-nitrogen co-emission control.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] An agricultural and rural environment automation control method based on carbon-nitrogen co-emission control, the method comprising:

[0009] Obtain carbon-nitrogen co-emission data in the process of agricultural and rural production and the resource utilization process of domestic waste, and collect carbon content information in the soil and air;

[0010] Fuse the carbon-nitrogen co-emission data in the process of agricultural and rural production and the resource utilization process of domestic waste, and the carbon content information in the soil and air to generate a unified carbon-nitrogen co-emission data set;

[0011] According to the crop type and seasonal changes, establish a carbon-nitrogen co-emission dynamic adjustment model, and combine climate conditions, soil properties, and farming methods to judge the carbon-nitrogen co-emission laws during different crop growth cycles;

[0012] According to the carbon-nitrogen co-emission laws during different crop growth cycles, use a machine learning algorithm to train a carbon-nitrogen co-emission prediction model, input the unified carbon-nitrogen co-emission data set, and output the predicted value of carbon-nitrogen co-emissions in the future time period;

[0013] According to the prediction results, dynamically adjust the carbon-nitrogen co-emission standards in the process of agricultural and rural production and the resource utilization process of domestic waste, and generate a control plan adapted to different crop types and seasonal changes.

[0014] Preferably, the method for obtaining the carbon-nitrogen co-emission data in the agricultural and rural production process and the resource utilization process of domestic waste, and collecting the carbon content information in the soil and air includes:

[0015] Obtain the carbon-nitrogen co-emission data of soil respiration, chemical fertilizer application, agricultural machinery operation, and irrigation system in the agricultural and rural production process and the resource utilization process of domestic waste;

[0016] Obtain the carbon content data in the soil and air according to the Internet of Things sensors;

[0017] Process the collected data using a sensor data fusion algorithm to obtain the values of soil carbon and air carbon;

[0018] Judge whether the values of soil carbon and air carbon exceed the preset threshold. If they exceed the preset threshold, analyze the impacts of chemical fertilizer amount, agricultural machinery amount, and irrigation amount through a machine learning algorithm to determine the main sources of carbon-nitrogen co-emissions;

[0019] Adopt a regression analysis model to predict the contribution rate of soil respiration to carbon-nitrogen co-emissions and generate a carbon-nitrogen co-emission distribution map for agricultural production.

[0020] Preferably, the method for fusing the carbon-nitrogen co-emission data, the carbon content information in the soil and air in the agricultural and rural production process and the resource utilization process of domestic waste to generate a unified carbon-nitrogen co-emission dataset includes:

[0021] ;

[0022] Where: is the total amount of carbon-nitrogen co-emissions in the farmland ecosystem, kg; is emissions, kg; is Convert the emissions in the form of to emissions, kg; is Convert the emissions in the form of to emissions, kg; is the carbon-nitrogen co-emission intensity, kg / yuan; is the agricultural output value, yuan.

[0023] Preferably, under flooded conditions, for the methane emission characteristics of paddy fields, adjust the calculation weight of methane emissions through the monitoring data of soil microbial activities, and based on the weight of methane emissions, convert the emissions in the form of to emissions.

[0024] Preferably, under the conditions of dryland crops, the dynamic change trend of carbon dioxide-nitrogen co-emission is determined through root activity and leaf photosynthesis data.

[0025] Preferably, the method for judging the carbon-nitrogen co-emission law during different crop growth cycles in combination with climate conditions, soil properties and tillage methods includes:

[0026] Obtain historical data of crop types and growth cycles, integrate multi-source data and preprocess them in combination with climate conditions, soil properties and tillage methods;

[0027] Adopt time series analysis method to segment the carbon-nitrogen co-emission data in the crop growth stage and extract the carbon-nitrogen co-emission characteristics of each stage;

[0028] According to the carbon-nitrogen co-emission dynamic adjustment model, calculate the carbon-nitrogen co-emission amount in different crop growth cycles; among them, the carbon-nitrogen co-emission dynamic adjustment model is: DNDC model;

[0029] If there are significant differences in soil properties and tillage methods, use the clustering algorithm to group the data and judge the carbon-nitrogen co-emission law of each group;

[0030] Through the carbon-nitrogen co-emission dynamic adjustment model, map the carbon-nitrogen co-emission data to a unified time series to generate the carbon-nitrogen co-emission curve of the crop growth stage;

[0031] According to the clustering results and the carbon-nitrogen co-emission curve, analyze the carbon-nitrogen co-emission change trend of different crop types and growth stages;

[0032] Adopt the regression algorithm to optimize the carbon-nitrogen co-emission dynamic adjustment model to obtain the carbon-nitrogen co-emission law of the final crop growth cycle.

[0033] Preferably, the established carbon-nitrogen co-emission prediction model is:

[0034] ;

[0035] In the formula: is the original carbon-nitrogen co-emission data according to crop types and seasonal changes; is the generated sequence obtained by accumulating the original carbon-nitrogen co-emission data sequence according to crop types and seasonal changes; is the development coefficient; is the grey action amount;

[0036] After evolution calculation, it becomes the whitenization equation:

[0037] ;

[0038] Posterior residual ratio Verify the accuracy of the model, indicating that the accuracy of the prediction model is qualified.

[0039] Preferably, according to the prediction results, the method for dynamically adjusting the carbon-nitrogen co-emission standards in the agricultural and rural production processes and the resource utilization processes of domestic waste, and generating control plans adapted to different crop types and seasonal changes includes:

[0040] If the deviation between the predicted value and the actual value exceeds the preset threshold, use the support vector machine algorithm to group and train the data, and adjust the parameters of the carbon-nitrogen co-emission prediction model;

[0041] According to the adjusted parameters of the carbon-nitrogen co-emission prediction model, re-output the carbon-nitrogen co-emission predicted value;

[0042] Use the gradient descent algorithm to optimize the parameters of the carbon-nitrogen co-emission prediction model, judge the deviation between the predicted value and the actual value, and update the parameters of the carbon-nitrogen co-emission prediction model;

[0043] Generate a carbon-nitrogen co-emission control plan adapted to different crop types and seasonal changes according to the optimized carbon-nitrogen co-emission prediction model.

[0044] Compared with the prior art, the beneficial effects of the present invention are:

[0045] The present invention discloses an automatic control method for the agricultural and rural environment based on carbon-nitrogen co-emission control. Carbon-nitrogen co-emission data in the agricultural and rural production processes and the resource utilization processes of domestic waste are collected through sensors, heterogeneous data is integrated using a multi-source data fusion algorithm, and a dynamic carbon-nitrogen co-emission model is established in combination with crop characteristics and environmental conditions. Considering the different characteristics of paddy fields and dryland crops, the co-emission characteristics of methane and carbon dioxide nitrogen are considered separately. The carbon-nitrogen co-emission prediction model is trained using machine learning algorithms, and the carbon-nitrogen co-emission standards are dynamically adjusted according to the prediction results to generate control plans adapted to different crops and seasons. The present invention realizes the intelligent management of carbon-nitrogen co-emissions in the agricultural and rural production processes and the resource utilization processes of domestic waste by using an automatic control system to monitor carbon-nitrogen co-emission data in real time and perform corresponding emission reduction operations according to preset standards, effectively improving the accuracy and adaptability of carbon-nitrogen co-emission control. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0047] Figure 1Schematic flow chart of an agricultural and rural environment automatic control method based on carbon-nitrogen co-emission control according to an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of carbon-nitrogen co-emission sources in a farmland ecosystem according to an embodiment of the present invention. Detailed implementation manners

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners.

[0051] Embodiment 1

[0052] As Figure 1 shown, an embodiment of the present invention discloses an automatic control method for agricultural and rural environment based on carbon-nitrogen co-emission control, and the method includes:

[0053] Obtain carbon-nitrogen co-emission data in the process of agricultural and rural production and the process of resource utilization of domestic waste, and collect carbon content information in soil and air;

[0054] Fuse the carbon-nitrogen co-emission data in the process of agricultural and rural production and the process of resource utilization of domestic waste, and the carbon content information in soil and air to generate a unified carbon-nitrogen co-emission data set;

[0055] According to the crop type and seasonal changes, establish a dynamic adjustment model for carbon-nitrogen co-emission, and combine climate conditions, soil properties, and tillage methods to judge the carbon-nitrogen co-emission law during different crop growth cycles;

[0056] According to the carbon-nitrogen co-emission law during different crop growth cycles, use a machine learning algorithm to train a carbon-nitrogen co-emission prediction model, input the unified carbon-nitrogen co-emission data set, and output the predicted value of carbon-nitrogen co-emission in the future time period;

[0057] According to the prediction results, dynamically adjust the carbon-nitrogen co-emission standards in the process of agricultural and rural production and the process of resource utilization of domestic waste, and generate a control plan adapted to different crop types and seasonal changes.

[0058] In this embodiment, the method for obtaining the carbon-nitrogen co-emission data in the process of agricultural and rural production and the resource utilization of domestic waste, and collecting the carbon content information in the soil and air includes:

[0059] Obtain the carbon-nitrogen co-emission data in the links of soil respiration, chemical fertilizer application, agricultural machinery operation, and irrigation system in the process of agricultural and rural production and the resource utilization of domestic waste;

[0060] Obtain the carbon content data in the soil and air according to the Internet of Things sensors;

[0061] Use the sensor data fusion algorithm to process the collected data to obtain the values of soil carbon and air carbon;

[0062] Judge whether the values of soil carbon and air carbon exceed the preset threshold. If they exceed the preset threshold, analyze the impacts of chemical fertilizer amount, agricultural machinery amount, and irrigation amount through the machine learning algorithm to determine the main sources of carbon-nitrogen co-emission;

[0063] Use the regression analysis model to predict the contribution rate of soil respiration to carbon-nitrogen co-emission and generate the carbon-nitrogen co-emission distribution map of agricultural production.

[0064] In this embodiment, aiming at the spatio-temporal heterogeneity of sensor data, a multi-source data fusion algorithm is adopted to integrate data with different time scales, spatial ranges, and precisions to generate a unified carbon-nitrogen co-emission dataset, including:

[0065] Obtain sensor data with different time scales and spatial ranges, and process the spatio-temporal heterogeneity based on the multi-source data fusion algorithm;

[0066] Adopt data preprocessing technology to eliminate the noise and outliers in the sensor data and improve the data quality;

[0067] Map the data with different precisions into a unified time series and spatial grid through the spatio-temporal alignment method;

[0068] If there are missing values in the data fusion process, use the interpolation algorithm to supplement the complete dataset;

[0069] Use the clustering algorithm to analyze the spatial distribution characteristics of the carbon-nitrogen co-emission data and identify the high-emission areas and low-emission areas;

[0070] According to the time series analysis model, judge the periodic change law and trend characteristics of the carbon-nitrogen co-emission data;

[0071] Generate a unified carbon-nitrogen co-emission dataset to provide data support for subsequent carbon-nitrogen co-emission management and optimization.

[0072] Specifically, such as Figure 2As shown in the figure, the method for fusing the carbon-nitrogen co-emission data in the agricultural and rural production processes and the resource utilization processes of domestic waste, as well as the carbon content information in the soil and air, to generate a unified carbon-nitrogen co-emission dataset includes:

[0073] ;

[0074] In the formula: is the total amount of carbon-nitrogen co-emissions in the farmland ecosystem, kg; is emission amount, kg; is the conversion of the emission form to emission amount, kg; the conversion of the emission form to emission amount, kg; is the carbon-nitrogen co-emission intensity, kg / yuan;

[0075] Among them, under the flooding condition, for the methane emission characteristics of paddy fields, the calculation weight of methane emission is adjusted through the monitoring data of soil microbial activities. Specifically:

[0076] Obtain the monitoring data of soil microbial activities in the flooded environment of paddy fields, and combine the soil properties and climate conditions to extract the methane emission characteristics;

[0077] Adopt the time series analysis method to segment the monitoring data to obtain the methane emission characteristic values in different growth cycles;

[0078] Establish a methane emission weight adjustment model according to the soil properties and tillage methods to correct the calculation weight;

[0079] If there are significant differences in the flooding degree and soil properties, use the clustering algorithm to group the data and judge the methane emission laws of each group;

[0080] Through the weight adjustment model, map the methane emission data to a unified time series to generate a methane emission curve under the flooding condition of paddy fields;

[0081] Optimize the weight adjustment model using the regression algorithm to determine the final methane emission calculation weight;

[0082] Analyze the methane emission change trend in the flooded environment of paddy fields based on the optimization results and emission curve.

[0083] Based on the weight of methane emission, convert the emission form to emission amount. Specifically:

[0084] ;

[0085] Where: is the paddy field emission factor, kg / hm², i represents the paddy field type, is the rice sown area corresponding to this emission factor, hm²; 25 is conversion equivalent coefficient.

[0086] Among them, under the conditions of dryland crops, the methods for determining the dynamic change trend of carbon dioxide and nitrogen co-emission through root activity and leaf photosynthesis data include:

[0087] Obtain the root activity and leaf photosynthesis data of dryland crops, and combine the soil moisture and soil temperature conditions to extract the dynamic characteristics of carbon dioxide and nitrogen co-emission;

[0088] Adopt the sequence analysis method to segment the root activity and leaf photosynthesis data to obtain the characteristic values of carbon dioxide and nitrogen co-emission in the growth stage;

[0089] Establish a carbon dioxide and nitrogen co-emission weight adjustment model according to the soil type and crop variety to correct the calculation weight;

[0090] If there are significant differences in soil moisture and soil temperature, use the clustering algorithm to group the data and judge the carbon dioxide and nitrogen co-emission laws of each group;

[0091] Through the weight adjustment model, map the carbon dioxide and nitrogen co-emission data to a unified time series to generate a carbon dioxide and nitrogen co-emission curve under the conditions of dryland crops;

[0092] Optimize the weight adjustment model using the regression algorithm to determine the final carbon dioxide and nitrogen co-emission calculation weight;

[0093] According to the optimization results and emission curves, analyze the dynamic change trend of carbon dioxide and nitrogen co-emission under the conditions of dryland crops.

[0094] Specifically: Calculate The method for calculating the emissions is as follows:

[0095] ;

[0096] Where: is the jth type of agricultural input, kg; is the carbon and nitrogen co-emission coefficient of the jth type of agricultural input; 44 / 12 is the ratio of the molecular weights of

[0097] Among them, calculating the form emissions and converting them to The emission calculation method is as follows:

[0098] ;

[0099] In the formula: is the direct nitrogen emission, in kg; is the indirect nitrogen emission, in kg; 44 / 28 is the ratio of the molecular weight of to that of N; 298 is converted equivalent coefficient.

[0100] In this embodiment, the method for judging the carbon-nitrogen co-emission law during the growth cycles of different crops in combination with climate conditions, soil properties, and tillage methods includes:

[0101] Obtain historical data on crop types and growth cycles, integrate multi-source data and preprocess it in combination with climate conditions, soil properties, and tillage methods;

[0102] Adopt time series analysis method to segment the carbon-nitrogen co-emission data during the crop growth stage and extract the carbon-nitrogen co-emission characteristics of each stage;

[0103] Calculate the carbon-nitrogen co-emission amount during the growth cycles of different crops according to the carbon-nitrogen co-emission dynamic adjustment model; among them, the carbon-nitrogen co-emission dynamic adjustment model is: DNDC model;

[0104] If there are significant differences in soil properties and tillage methods, use clustering algorithm to group the data and judge the carbon-nitrogen co-emission law of each group;

[0105] Through the carbon-nitrogen co-emission dynamic adjustment model, map the carbon-nitrogen co-emission data to a unified time series to generate the carbon-nitrogen co-emission curve during the crop growth stage;

[0106] According to the clustering results and the carbon-nitrogen co-emission curve, analyze the changing trends of carbon-nitrogen co-emission in different crop types and growth stages;

[0107] Adopt regression algorithm to optimize the carbon-nitrogen co-emission dynamic adjustment model to obtain the carbon-nitrogen co-emission law during the final crop growth cycle.

[0108] In this embodiment, the established carbon-nitrogen co-emission prediction model is:

[0109] ;

[0110] In the formula: is the original carbon-nitrogen co-emission data according to crop types and seasonal variations; is the generated sequence obtained by accumulating the original carbon-nitrogen co-emission data sequence according to crop types and seasonal variations; is the development coefficient; is the grey action;

[0111] After evolution calculation, it becomes the whitenization equation:

[0112] ;

[0113] The posterior difference ratio verifies the accuracy of the model, indicating that the accuracy of the prediction model is qualified.

[0114] Among them, the posterior difference ratio ( ) is a concept in Bayesian statistics used to measure the relative probabilities of two hypotheses given the data. It is usually used in Bayesian hypothesis testing and can be expressed as:

[0115] ;

[0116] Among them, is the posterior probability of hypothesis given the data ; is the posterior probability of hypothesis given the data ;

[0117] The posterior probability can be calculated by Bayes' theorem, and Bayes' theorem is expressed as:

[0118] ;

[0119] Among them, is the likelihood probability of data D assuming H is true; is the prior probability of hypothesis H; is the marginal probability of data D, which can be obtained by summing over all possible hypotheses:

[0120] ;

[0121] Therefore, the posterior difference ratio can be rewritten as:

[0122] ;

[0123] Here, appears in both the numerator and the denominator, so it can be canceled out.

[0124] Calculation steps: 1. Determine the hypotheses: Define two hypotheses and . 2. Collect data: Collect relevant data . 3. Calculate the likelihood probability: Calculate the likelihood probability of the data under each hypothesis and . 4. Determine the prior probability: Determine the prior probability of the hypothesis and . 5. Calculate the posterior odds ratio: Calculate the posterior odds ratio using the above formula .

[0125] In this embodiment, a machine learning algorithm is adopted to train a carbon-nitrogen co-emission prediction model. By inputting crop growth characteristics, environmental conditions, and sensor data, the predicted value of carbon-nitrogen co-emissions in a future time period is output, including:

[0126] Obtain the growth characteristic data of the crop growth stage, combine the environmental temperature, environmental humidity, soil temperature, and soil moisture, and extract the crop growth dynamic information;

[0127] Fuse the sensor value data, construct an associated data set of crop growth and environmental conditions, and generate an initial training sample;

[0128] Adopt a random forest algorithm, input the initial training sample, train the carbon-nitrogen co-emission prediction model, and obtain the initial value of the model parameters;

[0129] If the difference between the environmental temperature and the soil temperature exceeds the preset threshold, adopt a support vector machine algorithm to group and train the data and adjust the model parameters;

[0130] According to the time series data, input the crop growth characteristics and environmental conditions, and through the trained model, output the predicted value of carbon emissions in a future time period;

[0131] Adopt a gradient descent algorithm to optimize the model parameters, judge the deviation between the predicted value and the actual value, and update the model parameters;

[0132] Generate an optimized carbon-nitrogen co-emission prediction model, input the real-time crop growth characteristics, environmental conditions, and sensor values, and output the predicted value of carbon emissions in a future time period.

[0133] In this embodiment, according to the prediction results, the method for dynamically adjusting the carbon-nitrogen co-emission standards in the agricultural and rural production processes and the resource utilization process of domestic waste, and generating a control plan adapted to different crop types and seasonal changes includes:

[0134] If the deviation between the predicted value and the actual value exceeds the preset threshold, adopt a support vector machine algorithm to group and train the data and adjust the parameters of the carbon-nitrogen co-emission prediction model;

[0135] According to the adjusted parameters of the carbon-nitrogen co-emission prediction model, re-output the predicted value of carbon-nitrogen co-emissions;

[0136] The gradient descent algorithm is adopted to optimize the parameters of the carbon-nitrogen co-emission prediction model, judge the deviation between the predicted value and the actual value, and update the parameters of the carbon-nitrogen co-emission prediction model;

[0137] According to the optimized carbon-nitrogen co-emission prediction model, a carbon-nitrogen co-emission control plan adaptable to different crop types and seasonal changes is generated.

[0138] In this embodiment, through the automatic control system, the carbon-nitrogen co-emission data is monitored in real time, combined with the preset dynamic standard, to judge whether to trigger the control measures and execute the corresponding emission reduction operations.

[0139] Obtain the carbon-nitrogen co-emission data stream collected by the monitor, and judge whether the carbon-nitrogen co-emission exceeds the preset threshold in combination with the dynamic standard. If the carbon-nitrogen co-emission data stream exceeds the preset threshold, trigger the control measures and call the actuator to start the emission reduction operation. The carbon-nitrogen co-emission data stream is updated in real time through the automatic control system to judge the execution effect of the control measures. The random forest algorithm is used to analyze the relationship between the data stream and the dynamic standard, and the judgment conditions are optimized. According to the optimized judgment conditions, the triggering mechanism is adjusted to generate more accurate control measures. The support vector machine algorithm is used to classify the data stream to determine the priority of the emission reduction operation. The execution effect of the emission reduction operation is monitored in real time through the control system, the data stream is updated and fed back to the monitor.

[0140] The embodiments described above are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. An automated control method for the rural environment based on the co - control of carbon and nitrogen emissions, characterized in that The method includes: Obtaining the carbon-nitrogen co-emission data in the process of agricultural and rural production and the resource utilization of domestic waste, and collecting the carbon content information in the soil and air; Fusing the carbon-nitrogen co-emission data in the process of agricultural and rural production and the resource utilization of domestic waste, and the carbon content information in the soil and air to generate a unified carbon-nitrogen co-emission dataset; According to the crop type and seasonal changes, establishing a dynamic adjustment model for carbon-nitrogen co-emission, and combining climate conditions, soil properties and tillage methods to judge the carbon-nitrogen co-emission law during different crop growth cycles; According to the carbon-nitrogen co-emission law during different crop growth cycles, using machine learning algorithms to train a carbon-nitrogen co-emission prediction model, inputting the unified carbon-nitrogen co-emission dataset, and outputting the predicted value of carbon-nitrogen co-emission in the future time period; According to the prediction results, dynamically adjusting the carbon-nitrogen co-emission standards in the process of agricultural and rural production and the resource utilization of domestic waste, and generating a control plan adapted to different crop types and seasonal changes; The method for judging the carbon-nitrogen co-emission law during different crop growth cycles by combining climate conditions, soil properties and tillage methods includes: Obtaining the historical data of crop types and growth cycles, and combining climate conditions, soil properties and tillage methods to integrate multi-source data and preprocess; Using the time series analysis method to segment the carbon-nitrogen co-emission data in the crop growth stage and extract the carbon-nitrogen co-emission characteristics of each stage; According to the dynamic adjustment model of carbon-nitrogen co-emission, calculating the carbon-nitrogen co-emission amount in different crop growth cycles; among them, the dynamic adjustment model of carbon-nitrogen co-emission is: DNDC model; If there are significant differences in soil properties and tillage methods, the clustering algorithm is used to group the data and judge the carbon-nitrogen co-emission law of each group; Through the dynamic adjustment model of carbon-nitrogen co-emission, mapping the carbon-nitrogen co-emission data to a unified time series to generate the carbon-nitrogen co-emission curve in the crop growth stage; According to the clustering results and the carbon-nitrogen co-emission curve, analyzing the carbon-nitrogen co-emission change trend of different crop types and growth stages; Using the regression algorithm to optimize the dynamic adjustment model of carbon-nitrogen co-emission to obtain the final carbon-nitrogen co-emission law in the crop growth cycle.

2. The method according to claim 1, wherein The method for obtaining the carbon-nitrogen co-emission data in the process of agricultural and rural production and the resource utilization of domestic waste, and collecting the carbon content information in the soil and air includes: Obtaining the carbon-nitrogen co-emission data in the links of soil respiration, chemical fertilizer application, agricultural machinery operation and irrigation system in the process of agricultural and rural production and the resource utilization of domestic waste; Obtaining the carbon content data in the soil and air according to the Internet of Things sensors; Using the sensor data fusion algorithm to process the collected quantity to obtain the values of soil carbon and air carbon; Judging whether the values of soil carbon and air carbon exceed the preset threshold. If they exceed the preset threshold, the influence of chemical fertilizer amount, agricultural machinery amount and irrigation amount is analyzed through machine learning algorithms to determine the main sources of carbon-nitrogen co-emission; Using the regression analysis model to predict the contribution rate of soil respiration to carbon-nitrogen co-emission and generating the carbon-nitrogen co-emission distribution map of agricultural production.

3. The method according to claim 1, wherein A method for fusing carbon-nitrogen co-emission data in the agricultural and rural production process and the resource utilization process of domestic waste, as well as carbon content information in soil and air to generate a unified carbon-nitrogen co-emission dataset, includes: ； Where: is the total carbon and nitrogen co-emissions from farmland ecosystem, kg; for Emission, kg; for Emissions are converted into Emission, kg; for Emissions are converted into Emission, kg; is the carbon and nitrogen co-emission intensity, kg / yuan; is the agricultural output value, yuan.

4. The method according to claim 1, wherein Under flooded conditions, for the methane emission characteristics of paddy fields, by monitoring the data of soil microbial activities, adjust the calculation weight of methane emissions, and based on the weight of methane emissions, convert the form emissions into emissions.

5. The method according to claim 1, wherein Under dryland crop conditions, determine the dynamic change trend of carbon dioxide-nitrogen co-emission through root activity and leaf photosynthesis data.

6. The method according to claim 1, wherein The established carbon-nitrogen co-emission prediction model is: ； In the formula: is the original data of carbon-nitrogen synergistic emissions according to crop types and seasonal variations; is the generated sequence obtained by accumulating the original data sequence of carbon-nitrogen synergistic emissions according to crop types and seasonal variations; is the development coefficient; is the grey action amount; After evolution calculation, it becomes a whitenization equation: ； Posterior difference ratio Verify the accuracy of the model, indicating that the accuracy of the prediction model is qualified.

7. The method according to claim 1, characterized in that, According to the prediction results, a method for dynamically adjusting the carbon-nitrogen co-emission standards in the agricultural and rural production process and the resource utilization process of domestic waste to generate control plans adapted to different crop types and seasonal changes includes: If the deviation between the predicted value and the actual value exceeds the preset threshold, use the support vector machine algorithm to group and train the data and adjust the parameters of the carbon-nitrogen co-emission prediction model; According to the adjusted parameters of the carbon-nitrogen co-emission prediction model, re-output the carbon-nitrogen co-emission predicted value; Use the gradient descent algorithm to optimize the parameters of the carbon-nitrogen co-emission prediction model, judge the deviation between the predicted value and the actual value, and update the parameters of the carbon-nitrogen co-emission prediction model; According to the optimized carbon-nitrogen co-emission prediction model, generate carbon-nitrogen co-emission control plans adapted to different crop types and seasonal changes.

Images