Smoking area nitrogen management and efficiency evaluation system

Abstract

The invention provides a tobacco area nitrogen management and efficiency evaluation system, which comprises a data acquisition module for acquiring meteorological data, soil nitrogen data, crop growth data and historical fertilization data in real time; the data preprocessing module is used for carrying out noise filtering, space-time alignment and multi-source data fusion; the dynamic nitrogen prediction module is coupled with the soil nitrogen migration and crop absorption model to generate a prediction value; the optimization decision module is used for generating an application strategy based on a dynamic programming algorithm and calculating the optimal application amount and the fertilization time; the efficiency evaluation module is used for calculating nitrogen utilization efficiency (NUE) and environmental benefit index (EBI) by combining the application amount, the environmental loss amount and the crop yield; the self-adaptive feedback module is used for dynamically correcting prediction model parameters according to the deviation degree of the NUE and the EBI; and the visual output module is used for generating a multi-dimensional evaluation report and a fertilization decision map. The nitrogen utilization efficiency and the environmental benefit index can be improved, the environmental risk is reduced, and the tobacco yield and quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural informatization and precision agriculture technology, and more specifically, to a tobacco field nitrogen management and efficiency evaluation system. Background Art

[0002] In modern agricultural production, nitrogen management is one of the key links to improve crop yield and quality. Nitrogen management in traditional tobacco areas mainly relies on empirical fertilization, lacking accurate monitoring and analysis of dynamic changes in soil nitrogen, crop growth requirements, and environmental factors. This method often leads to excessive or insufficient nitrogen fertilizer application, which not only affects the yield and quality of tobacco leaves, but may also cause environmental problems such as soil acidification and water eutrophication. In recent years, with the development of agricultural information technology, some regions have begun to try to use technical means such as sensor networks, geographic information systems (GIS), and crop growth models to optimize nitrogen management. However, the application of these technologies mostly remains in a single link, lacks systematicity and dynamism, and it is difficult to achieve a balance between precision fertilization and environmental benefits.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: First, the accuracy of data collection and processing is insufficient, and it is impossible to accurately reflect the soil nitrogen dynamics and crop growth requirements in tobacco areas in real time; second, there is a lack of effective nitrogen dynamic prediction models, and it is difficult to accurately predict the migration, transformation and absorption process of nitrogen; third, there is a lack of scientific basis for optimization decisions, and it is impossible to dynamically adjust fertilization strategies according to real-time data; fourth, there is a lack of comprehensive evaluation of nitrogen utilization efficiency and environmental benefits, and it is difficult to achieve coordinated optimization of precision fertilization and environmental protection. Summary of the invention

[0004] The present invention provides a tobacco field nitrogen management and efficiency evaluation system, comprising:

[0005] Data collection module, used to obtain tobacco area meteorological data, soil nitrogen data, crop growth data and historical fertilization data in real time;

[0006] A data preprocessing module, used for performing noise filtering, spatiotemporal alignment and multi-source data fusion on the data;

[0007] The nitrogen dynamic prediction module is used to generate nitrogen dynamic prediction values ​​by coupling the soil nitrogen migration model and the crop absorption model;

[0008] The optimization decision module is used to generate nitrogen application strategies based on dynamic programming algorithms and calculate the optimal application amount and fertilization time;

[0009] The efficiency evaluation module is used to calculate the nitrogen utilization efficiency NUE and environmental benefit index EBI by combining nitrogen application amount, environmental loss and crop yield;

[0010] An adaptive feedback module is used to dynamically correct the model parameters of the nitrogen dynamic prediction module according to the deviation between NUE and EBI;

[0011] A visualization output module is used to generate a multi-dimensional evaluation report and a fertilization decision map; wherein the data preprocessing module, the nitrogen dynamic prediction module, the optimization decision module, the efficiency evaluation module and the adaptive feedback module form a recursive optimization link through real-time data flow and logical judgment rules.

[0012] Furthermore, the data preprocessing module includes:

[0013] The spatiotemporal alignment unit is used to match meteorological data with soil data in a gridded manner according to geographic coordinates. The matching formula is:

[0014]

[0015] Among them, G(x, y, t) is the grid data, W i is the spatial weight of the ith sensor, D i is the raw data of sensor i;

[0016] The data fusion unit is used to fuse multi-sensor data through the Kalman filter algorithm. The state equation and observation equation are:

[0017] X k =AX k-1 +BU k +w k

[0018] Z k =HX k +v k

[0019] Among them, X k is the system state vector at time k, Z k is the observation vector, w k and v k are process noise and observation noise, respectively.

[0020] Further, the nitrogen dynamic prediction module performs the following steps:

[0021] Step S1: Construct a soil nitrogen migration model, and the migration rate formula is:

[0022]

[0023] Among them, N soil is the soil nitrogen concentration, D is the diffusion coefficient, V is the water migration rate, k d is the nitrogen degradation rate;

[0024] Step S2: Construct a crop nitrogen absorption model, and the absorption formula is:

[0025]

[0026] Among them, α and β are crop absorption characteristic parameters, and LAI is the leaf area index.

[0027] Furthermore, the nitrogen dynamic prediction module further calculates the real-time nitrogen profit and loss through the following formula:

[0028] ΔN=N input +N mineralization -N uptake -N leaching

[0029] Among them, N input is the fertilizer input, N minetalization is the amount of soil mineralization, N leaching is the leaching loss, and the leaching loss is calculated by the following formula:

[0030] N leaching =γ·R·N soil

[0031] γ is the leaching coefficient and R is the rainfall intensity.

[0032] Furthermore, the objective function of the optimization decision module is a multi-objective optimization model:

[0033]

[0034] Among them, λ 1 +λ 2 +λ 3 =1 is the dynamic weight coefficient, N max is the maximum allowable nitrogen application rate, Y target is the target yield; the constraints include: soil nitrogen concentration threshold N soil ≤200mg / kg, fertilization interval Δt≥5 days.

[0035] Furthermore, the dynamic weight coefficient is adjusted according to the crop growth stage:

[0036] Vegetative growth period 2 =0.6, reproductive growth periodλ 1 =0.5, and the weight update formula is:

[0037]

[0038] Where η is the learning rate, The partial derivative of the objective function with respect to the weights.

[0039] Furthermore, in the efficiency evaluation module:

[0040] The calculation formula for nitrogen utilization efficiency NUE is:

[0041]

[0042] The calculation formula of environmental benefit index EBI is:

[0043]

[0044] Among them, C N is the nitrogen content of crops, N volatilization is the amount of nitrogen volatilization.

[0045] Furthermore, the efficiency evaluation module sets a three-level judgment logic: if NUE≥65% and EBI≥0.8, it is judged as "high efficiency and environmental protection"; if 60%≤NUE<65% or 0.6≤EBI<0.8, it is judged as "needs optimization"; if NUE<60% or EBI<0.6, it is judged as "high risk" and triggers the adaptive feedback module.

[0046] Furthermore, the adaptive feedback module corrects the model parameters by the following steps:

[0047] Step T1: Calculate the deviation e between NUE and target value NUE =NUE target -NUE actual ;

[0048] Step T2: Use fuzzy PID controller to generate parameter adjustment, proportional term K p ·e NUE 、Integral term K i ·∫e NUE dt, differential term

[0049] Step T3: Update the degradation rate k in the soil nitrogen transport model d With the diffusion coefficient D, the update formula is:

[0050] Among them, φ is the attenuation factor and ΔN is the nitrogen adjustment amount.

[0051] Furthermore, the visualization output module generates a decision map including the following contents:

[0052] Thermal map of spatiotemporal distribution of soil nitrogen, generated based on the Kriging interpolation algorithm;

[0053] Fertilization path planning map, using ant colony algorithm to calculate the optimal mechanical travel route;

[0054] Risk warning area marking, meeting Nsoil Grid area where the drug concentration is >180 mg / kg or EBI is <0.5.

[0055] The above-mentioned embodiments according to the present invention have at least the following beneficial effects: the tobacco field nitrogen management and efficiency evaluation system of the present invention can realize the precision and intelligence of nitrogen management in tobacco fields. The data acquisition module acquires meteorological, soil nitrogen, crop growth and historical fertilization data in real time, and combines the noise filtering, spatiotemporal alignment and multi-source data fusion of the data preprocessing module to provide high-precision basic data for dynamic prediction of nitrogen. The dynamic prediction module of nitrogen couples the soil nitrogen migration model with the crop absorption model, and can accurately predict the dynamic changes of nitrogen, providing a scientific basis for the optimization decision module. The optimization decision module generates a nitrogen application strategy based on a dynamic programming algorithm, calculates the optimal application amount and fertilization time, thereby realizing precise fertilization, improving nitrogen utilization efficiency (NUE), and reducing the environmental loss of nitrogen.

[0056] At the same time, the present invention can also realize the comprehensive evaluation and dynamic optimization of nitrogen management in tobacco fields. The efficiency evaluation module calculates the nitrogen utilization efficiency (NUE) and environmental benefit index (EBI) based on the nitrogen application amount, environmental loss and crop yield, and evaluates the management effect through three-level judgment logic. The adaptive feedback module dynamically corrects the model parameters of the nitrogen dynamic prediction module according to the deviation between NUE and EBI to ensure that the system can adapt to changes in the tobacco field environment and crop growth. The visual output module generates a multi-dimensional evaluation report and a fertilization decision map to provide intuitive decision support for tobacco farmers and managers. This closed-loop optimization mechanism not only improves the scientificity and flexibility of nitrogen management, but also can effectively reduce environmental risks, improve tobacco yield and quality, and achieve a win-win situation of economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0058] Figure 1 This is a schematic diagram of the structure of a tobacco field nitrogen management and efficiency evaluation system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0059] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0060] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0061] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0062] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of a tobacco field nitrogen management and efficiency evaluation system provided by an embodiment of the present invention. Figure 1 As shown, a tobacco field nitrogen management and efficiency evaluation system 100 includes:

[0063] The data acquisition module 101 is used to obtain tobacco-growing area meteorological data, soil nitrogen data, crop growth data and historical fertilization data in real time;

[0064] A data preprocessing module 102 is used to perform noise filtering, spatiotemporal alignment and multi-source data fusion on the data;

[0065] A nitrogen dynamic prediction module 103, used to generate a nitrogen dynamic prediction value by coupling a soil nitrogen migration model with a crop absorption model;

[0066] An optimization decision module 104 is used to generate a nitrogen application strategy based on a dynamic programming algorithm and calculate the optimal application amount and fertilization time;

[0067] The efficiency evaluation module 105 is used to calculate the nitrogen utilization efficiency NUE and the environmental benefit index EBI by combining the nitrogen application amount, environmental loss amount and crop yield;

[0068] An adaptive feedback module 106, used to dynamically correct the model parameters of the nitrogen dynamic prediction module according to the deviation between NUE and EBI;

[0069] The visualization output module 107 is used to generate a multi-dimensional evaluation report and a fertilization decision map; wherein the data preprocessing module, the nitrogen dynamic prediction module, the optimization decision module, the efficiency evaluation module and the adaptive feedback module form a recursive optimization link through real-time data flow and logical judgment rules.

[0070] It should be noted that the present invention relates to a tobacco area nitrogen management and efficiency evaluation system, including a data acquisition module, a data preprocessing module, a nitrogen dynamic prediction module, an optimization decision module, an efficiency evaluation module, an adaptive feedback module and a visual output module. The data acquisition module is used to obtain meteorological data, soil nitrogen data, crop growth data and historical fertilization data of the tobacco area in real time. The data preprocessing module is used to perform noise filtering, spatiotemporal alignment and multi-source data fusion on the collected data. The nitrogen dynamic prediction module generates a nitrogen dynamic prediction value by coupling the soil nitrogen migration model with the crop absorption model. The optimization decision module generates a nitrogen application strategy based on a dynamic programming algorithm and calculates the optimal application amount and fertilization time. The efficiency evaluation module calculates nitrogen utilization efficiency (NUE) and environmental benefit index (EBI) in combination with nitrogen application amount, environmental loss amount and crop yield. The adaptive feedback module dynamically corrects the model parameters of the nitrogen dynamic prediction module according to the deviation between NUE and EBI. The visual output module is used to generate a multi-dimensional evaluation report and a fertilization decision map. Each module forms a recursive optimization link through real-time data flow and logical judgment rules.

[0071] Specifically, the data acquisition module includes a sensor network and a data acquisition terminal. The sensor network is used to collect meteorological data, soil nitrogen data and crop growth data, and the data acquisition terminal is used to summarize and transmit data. The data preprocessing module includes a noise filtering unit, a spatiotemporal alignment unit and a data fusion unit. The noise filtering unit is used to remove noise from the data, the spatiotemporal alignment unit is used to match data from different sources according to geographic coordinates, and the data fusion unit is used to fuse multi-sensor data through the Kalman filter algorithm. The nitrogen dynamic prediction module includes a soil nitrogen migration model and a crop nitrogen absorption model. The soil nitrogen migration model is used to simulate the migration process of nitrogen in the soil, and the crop nitrogen absorption model is used to simulate the nitrogen absorption process of crops. The optimization decision module uses a dynamic programming algorithm to generate a fertilization strategy based on the dynamic prediction value of nitrogen. The efficiency evaluation module evaluates the fertilization effect by calculating the nitrogen utilization efficiency (NUE) and the environmental benefit index (EBI). The adaptive feedback module adjusts the model parameters according to the deviation of NUE and EBI through a fuzzy PID controller. The visual output module generates an evaluation report and a fertilization decision map.

[0072] Preferably, the sensor network in the data acquisition module may include a meteorological sensor, a soil nitrogen sensor and a crop growth sensor. The meteorological sensor is used to collect meteorological data such as temperature, rainfall, and humidity. The soil nitrogen sensor is used to measure the nitrogen content in the soil, and the crop growth sensor is used to monitor the growth status of the crop. The spatiotemporal alignment unit in the data preprocessing module can use a grid matching algorithm to match the meteorological data with the soil data according to geographic coordinates. The soil nitrogen migration model in the nitrogen dynamic prediction module can use a diffusion equation to simulate the migration process of nitrogen in the soil, and the crop nitrogen absorption model can use a nonlinear absorption equation to simulate the nitrogen absorption process of crops. The optimization decision module can adjust the fertilization strategy according to the growth stage of different crops, and the efficiency evaluation module can set different NUE and EBI thresholds for evaluation. The adaptive feedback module can realize the dynamic correction of model parameters by adjusting the degradation rate and diffusion coefficient of the soil nitrogen migration model. The visual output module can generate a thermal map of the spatiotemporal distribution of soil nitrogen, a fertilization path planning map, and a risk warning area marking map.

[0073] In some embodiments, the data preprocessing module includes:

[0074] The time-space alignment unit (210) is used to match the meteorological data with the soil data according to the geographic coordinate grid. The matching formula is:

[0075]

[0076] Among them, G(x, y, t) is the grid data, W i is the spatial weight of the ith sensor, D i is the raw data of sensor i;

[0077] The data fusion unit (220) is used to fuse multi-sensor data through a Kalman filter algorithm, and the state equation and observation equation are:

[0078] X k =AX k-1 +BU k +w k

[0079] Z k =HX k +v k

[0080] Among them, X k is the system state vector at time k, Z k is the observation vector, w k and v k are process noise and observation noise, respectively.

[0081] It should be noted that the core function of the data preprocessing module in the present invention is to process various types of collected data so that it can meet the needs of subsequent dynamic prediction and optimization decision-making of nitrogen. Among them, the role of the spatiotemporal alignment unit is to standardize data from different sources with spatiotemporal differences to ensure the correspondence of data in geographic space and synchronization in time. The data fusion unit fuses multi-source data through the Kalman filter algorithm to improve the accuracy and reliability of the data. The grid matching formula in the spatiotemporal alignment unit and the Kalman filter algorithm in the data fusion unit are key technical means to achieve data preprocessing.

[0082] Specifically, the spatiotemporal alignment unit matches meteorological data with soil data according to geographic coordinates through a gridded matching formula. The spatial weight (w i ) is used to adjust the contribution of different sensor data in the gridding process, while the original data of the sensor (x i ) is the actual meteorological or soil data collected. The data fusion unit uses the Kalman filter algorithm, in which the state equation (x k =F k x k-1 +B k u k +w k ) is used to describe the evolution of the system state, and the observation equation (z k =H k x k +v k ) is used to relate the system state to the observed data. Process noise (w k ) and observation noise (v k ) reflects the uncertainty in the system and observation process. Through this algorithm, multi-sensor data can be effectively fused, noise interference can be reduced, and the accuracy and reliability of data can be improved.

[0083] Preferably, the grid matching in the spatiotemporal alignment unit can use a higher precision interpolation method, such as Kriging interpolation, to improve the spatial resolution and accuracy of the data. In the data fusion unit, the parameter setting of the Kalman filter algorithm can be optimized according to the specific application scenario. For example, the state transfer matrix (F k ), control input matrix (B k ) and the observation matrix (H k ) parameters to better adapt to the dynamic characteristics of actual data. In addition, an adaptive Kalman filter algorithm can be introduced to dynamically adjust the filter parameters according to the statistical characteristics of real-time data to further improve the effect of data fusion.

[0084] In some embodiments, the nitrogen dynamic prediction module performs the following steps:

[0085] Step S1: Construct a soil nitrogen migration model, and the migration rate formula is:

[0086]

[0087] Among them, N soil is the soil nitrogen concentration, D is the diffusion coefficient, V is the water migration rate, k d is the nitrogen degradation rate;

[0088] Step S2: Construct a crop nitrogen absorption model, and the absorption formula is:

[0089]

[0090] Among them, α and β are crop absorption characteristic parameters, and LAI is the leaf area index.

[0091] It should be noted that the nitrogen dynamic prediction module is the core part of the system of the present invention. Its main function is to predict the dynamic changes of nitrogen in the soil and the absorption of nitrogen by crops by constructing a soil nitrogen migration model and a crop nitrogen absorption model. The soil nitrogen migration model is used to describe the diffusion, degradation and leaching of nitrogen in the soil, while the crop nitrogen absorption model is used to simulate the nitrogen absorption efficiency of crops. The combination of these two models can provide a scientific basis for subsequent optimization decisions, thereby achieving precision fertilization.

[0092] Specifically, the migration rate formula of the soil nitrogen migration model is:

[0093]

[0094] Where C is the soil nitrogen concentration, D is the diffusion coefficient, which indicates the diffusion capacity of nitrogen in the soil; v is the water migration rate, which reflects the effect of water flow in the soil on nitrogen migration; k d is the nitrogen degradation rate, which represents the natural degradation process of nitrogen in the soil. The absorption formula of the crop nitrogen absorption model is:

[0095] N abs =a·LAI·(1-e -b·C )

[0096] Among them, a and b are crop absorption characteristic parameters, which are used to characterize the crop's ability to absorb nitrogen; LAI is the leaf area index, which reflects the coverage area of ​​crop leaves and directly affects the crop's nitrogen absorption efficiency. Through these two models, the real-time nitrogen surplus and deficit can be calculated to provide a basis for fertilization decisions.

[0097] Preferably, the soil nitrogen migration model in the nitrogen dynamic prediction module can be further refined, for example, considering the influence of soil texture and structure on nitrogen migration, and adjusting the diffusion coefficient D and water migration rate v by introducing parameters such as soil porosity and permeability. For the crop nitrogen absorption model, the absorption characteristic parameters a and b can be adjusted according to different crop varieties and growth stages to more accurately reflect the nitrogen absorption capacity of crops. In addition, the influence of environmental factors such as temperature and light on nitrogen absorption can also be introduced, and the parameters in the formula can be modified to adapt to the growth needs of crops under different environmental conditions.

[0098] In some embodiments, the nitrogen dynamic prediction module further calculates the real-time nitrogen surplus and deficit by the following formula:

[0099] ΔN=N input +N mineralization -N uptake -N leaching

[0100] Among them, N input is the fertilizer input, N mineralization is the amount of soil mineralization, N leaching is the leaching loss, and the leaching loss is calculated by the following formula:

[0101] N leaching =γ·R·N soil

[0102] γ is the leaching coefficient and R is the rainfall intensity.

[0103] It should be noted that the dynamic nitrogen prediction module takes into account multiple factors such as fertilizer input, soil mineralization, crop absorption, and leaching loss when calculating the real-time nitrogen profit and loss. Fertilizer input refers to the amount of nitrogen added to the soil through fertilization operations; soil mineralization refers to the amount of organic nitrogen in the soil converted into inorganic nitrogen through mineralization; crop absorption refers to the amount of nitrogen absorbed by crops from the soil; and leaching loss refers to the amount of nitrogen lost through soil leaching. The comprehensive calculation of these parameters can more comprehensively reflect the dynamic changes of nitrogen in tobacco areas and provide a scientific basis for precision fertilization.

[0104] Specifically, the calculation formula for real-time nitrogen profit and loss is:

[0105] ΔN=N fertilizer +N mineralization -N absorption -N leaching

[0106] Among them, N fertilizer N is the fertilizer input, which is usually determined according to the fertilization plan and fertilizer amount; mineralizationis the amount of soil mineralization, which can be estimated by soil microbial activity and soil organic matter content; N absorption is the crop absorption amount, which is calculated by the crop nitrogen absorption model; N leaching is the leaching loss, and the calculation formula is:

[0107] N leaching =k leach ·P·C

[0108] Among them, k leach is the leaching coefficient, which reflects the soil's ability to leach nitrogen; P is the rainfall intensity, which indicates the amount of rainfall per unit time; and C is the soil nitrogen concentration. By setting these parameters, the real-time nitrogen surplus and deficit can be accurately calculated, thus providing data support for optimizing fertilization strategies.

[0109] Preferably, the leaching coefficient k leach It can be adjusted according to soil texture and structure. For example, in sandy soil, the leaching coefficient can be set higher because the porosity of sandy soil is large and nitrogen is more easily lost through leaching. At the same time, the rainfall intensity P can be obtained in real time through meteorological data to improve the accuracy of the calculation. In addition, the soil mineralization amount can be dynamically adjusted by regularly monitoring the soil organic matter content and microbial activity to more accurately reflect the actual mineralization capacity of the soil. In practical applications, soil moisture sensors can also be introduced to monitor soil moisture in real time, and the calculation formula of leaching loss can be further refined to adapt to the dynamic changes of nitrogen under different environmental conditions.

[0110] In some embodiments, the objective function of the optimization decision module is a multi-objective optimization model:

[0111]

[0112] Among them, λ 1 +λ 2 +λ 3 =1 is the dynamic weight coefficient, N max is the maximum allowable nitrogen application rate, Y target is the target yield; the constraints include: soil nitrogen concentration threshold N soil ≤200mg / kg, fertilization interval Δt≥5 days.

[0113] It should be noted that the goal of the optimization decision module is to generate a nitrogen application strategy through a multi-objective optimization model. The model comprehensively considers multiple factors such as nitrogen use efficiency (NUE), crop yield, and environmental benefits to ensure that while increasing crop yield, the environmental loss of nitrogen is reduced. 1 , w 2 , w 3) is used to balance the priorities among different objectives, while constraints ensure that the fertilization strategy is feasible in actual operation and meets environmental protection requirements.

[0114] Specifically, the objective function of the optimization decision module is:

[0115]

[0116] Among them, Y is the actual crop yield, Y target is the target output; N fertilizer is the amount of fertilizer applied, N max is the maximum allowable nitrogen application rate; N leaching is the leaching loss, N leaching_limit is the maximum allowable leaching loss. Dynamic weight coefficient (w 1 +w 2 +w 3 =1) is adjusted according to the crop growth stage and management objectives. Constraints include soil nitrogen concentration threshold (C≤200mg / kg) and fertilization interval (Δt≥5 days). By setting these parameters, the optimization decision module can generate the optimal fertilization strategy to ensure the scientific and rational application of nitrogen.

[0117] Preferably, the dynamic weight coefficient can be adjusted according to the crop growth stage. For example, during the vegetative growth period, the weight coefficient w 2 Set it to 0.6 to prioritize the nitrogen demand of crops; during the reproductive growth period, the weight coefficient w 1 Set to 0.5 to ensure crop yield. At the same time, the maximum allowable nitrogen application rate (N max ) can be adjusted according to soil type and crop variety. For example, for crops with high nitrogen demand, N max In addition, the optimization decision module can also introduce machine learning algorithms, such as genetic algorithms or particle swarm optimization algorithms, to further improve the optimization effect. These algorithms can dynamically adjust the fertilization strategy based on historical data and real-time monitoring data to make it more adaptable to complex farmland environments.

[0118] In some embodiments, the dynamic weight coefficient is adjusted according to the crop growth stage:

[0119] Vegetative growth period 2 =0.6, reproductive growth periodλ 1 =0.5, and the weight update formula is:

[0120]

[0121] Where η is the learning rate, The partial derivative of the objective function with respect to the weights.

[0122] It should be noted that the adjustment of dynamic weight coefficients is an important part of the optimization decision module. Its purpose is to dynamically balance the relationship between nitrogen use efficiency (NUE), crop yield and environmental benefits according to different crop growth stages. The adjustment of dynamic weight coefficients is based on the physiological characteristics of crop growth and management objectives, and the weights are dynamically updated through the learning rate and the partial derivative of the objective function to the weights. This dynamic adjustment mechanism can ensure that the optimization decision module can generate the most suitable fertilization strategy at different growth stages.

[0123] Specifically, the adjustment formula of the dynamic weight coefficient is:

[0124]

[0125] Among them, w i is the dynamic weight coefficient, η is the learning rate, which is a parameter used to control the speed of weight adjustment, usually between 0 and 1; is the partial derivative of the objective function with respect to the weight, reflecting the sensitivity of the objective function to the change of the weight. During the vegetative growth period, the demand for nitrogen by crops is mainly concentrated on the accumulation of growth, so the weight coefficient w 2 Set to 0.6 to give priority to meeting the nitrogen needs of crops; in the reproductive growth period, the focus of crop growth shifts to yield formation, at this time the weight coefficient w 1 Set it to 0.5 to ensure crop yield. In this way, the dynamic weight coefficient can be adjusted according to the changes in crop growth stage, so as to better balance the fertilization needs at different growth stages.

[0126] Preferably, the learning rate η can be adjusted according to the optimization effect in practical applications. For example, in the initial optimization stage, a larger learning rate (such as 0.1) can be set to quickly adjust the weights so that the system approaches the optimal solution faster; as the optimization process proceeds, the learning rate can be gradually reduced (such as reduced to 0.01) to improve the accuracy of the optimization. In addition, an adaptive learning rate adjustment mechanism can be introduced to dynamically adjust the learning rate according to the rate of change of the objective function to further improve the optimization effect. In practical applications, it is also possible to consider the introduction of seasonal factors or the influence of soil types on weight adjustment. For example, in soil types with a higher risk of nitrogen loss, the weight coefficient related to environmental benefits can be appropriately increased to reduce the environmental loss of nitrogen.

[0127] In some embodiments, in the efficiency assessment module:

[0128] The calculation formula for nitrogen use efficiency (NUE) is:

[0129]

[0130] The calculation formula of Environmental Benefit Index (EBI) is:

[0131]

[0132] Among them, C N is the nitrogen content of crops, N volatilization is the amount of nitrogen volatilization.

[0133] It should be noted that the core function of the efficiency evaluation module is to comprehensively evaluate the effect of nitrogen management by calculating nitrogen use efficiency (NUE) and environmental benefit index (EBI). Nitrogen use efficiency (NUE) reflects the efficiency of crops in absorbing and utilizing applied nitrogen, while the environmental benefit index (EBI) is used to evaluate the impact of nitrogen management on the environment. The combination of these two indicators can provide a scientific basis for the optimization of nitrogen management strategies, ensuring that negative impacts on the environment are reduced while increasing crop yields.

[0134] Specifically, the calculation formula for nitrogen utilization efficiency (NUE) is:

[0135]

[0136] Among them, Y is the crop yield, N c is the nitrogen content of crops, N fertilizer is the amount of nitrogen fertilizer applied. The calculation formula of environmental benefit index (EBI) is:

[0137]

[0138] Among them, N volatilization is the nitrogen volatilization amount, N volatilization_limit is the maximum permissible volatilization amount; N leaching is the nitrogen leaching loss, N leaching_limit The setting of these parameters needs to be adjusted according to the specific crop varieties, soil types and environmental conditions to ensure the accuracy and reliability of the evaluation results.

[0139] Preferably, for the calculation of nitrogen use efficiency (NUE), the crop nitrogen content (N c ), such as by regularly collecting crop samples and conducting laboratory analysis, or by using rapid detection equipment such as spectrometers for on-site measurement. For the environmental benefit index (EBI), more environmental factors, such as soil acidification and greenhouse gas emissions, can be introduced to more comprehensively evaluate the environmental impact of nitrogen management. In addition, different thresholds can be set according to different assessment objectives. For example, stricter environmental benefit index thresholds can be set in ecological protection areas to ensure that the impact of nitrogen management on the ecological environment is minimized.

[0140] In some embodiments, the efficiency evaluation module sets a three-level judgment logic: if NUE ≥ 65% and EBI ≥ 0.8, it is judged to be highly efficient and environmentally friendly; if 60% ≤ NUE < 65% or 0.6 ≤ EBI < 0.8, it is judged to be in need of optimization; if NUE < 60% or EBI < 0.6, it is judged to be high risk and trigger the adaptive feedback module.

[0141] It should be noted that the three-level judgment logic set in the efficiency evaluation module is an important tool for classifying and evaluating the effects of nitrogen management. By setting different nitrogen utilization efficiency (NUE) and environmental benefit index (EBI) thresholds, the nitrogen management effect can be divided into three levels: high efficiency and environmental protection, optimization required, and high risk. This classification method can intuitively reflect the comprehensive effect of nitrogen management and provide clear guidance for subsequent decision-making and adjustments.

[0142] Specifically, the three-level judgment logic is set as follows: when the nitrogen utilization efficiency (NUE) is greater than or equal to 65%, and the environmental benefit index (EBI) is greater than or equal to 0.8, it is judged as efficient and environmentally friendly, indicating that the nitrogen management effect is good and the impact on the environment is small; when 60% ≤ NUE < 65% or 0.6 ≤ EBI < 0.8, it is judged as needing optimization, indicating that the nitrogen management effect is acceptable, but there is still room for improvement; when NUE is less than 60% or EBI is less than 0.6, it is judged as high risk, indicating that the nitrogen management effect is not good and there may be greater environmental risks. The setting of these thresholds is based on a comprehensive consideration of the effect of nitrogen management, aiming to balance the relationship between crop yield and environmental protection.

[0143] Preferably, the thresholds can be adjusted according to different crop varieties and planting environments. For example, in some ecological protection areas with high environmental requirements, the thresholds of NUE and EBI can be set higher to ensure that the impact of nitrogen management on the environment is minimized. At the same time, in order to more accurately reflect the effect of nitrogen management, more evaluation indicators can be introduced, such as soil fertility changes, crop quality, etc. In addition, the thresholds can be dynamically adjusted by combining historical data and real-time monitoring data to adapt to different planting conditions and management goals.

[0144] In some embodiments, the adaptive feedback module modifies the model parameters by:

[0145] Step T1: Calculate the deviation e between NUE and target value NUE =NUE target -NUE actual ;

[0146] Step T2: Use fuzzy PID controller to generate parameter adjustment, proportional term K p ·e NUE 、Integral term K i ·∫eNUE dt, differential term

[0147] Step T3: Update the degradation rate k in the soil nitrogen transport model d With the diffusion coefficient D, the update formula is:

[0148] Among them, φ is the attenuation factor and ΔN is the nitrogen adjustment amount.

[0149] It should be noted that the core function of the adaptive feedback module is to dynamically correct the model parameters of the nitrogen dynamic prediction module according to the deviation between the nitrogen utilization efficiency (NUE) and the target value. This process is implemented through a fuzzy PID controller, which can effectively adjust the key parameters in the soil nitrogen migration model, such as degradation rate and diffusion coefficient, thereby improving the prediction accuracy and adaptability of the model. This feedback mechanism ensures that the system can continuously optimize the nitrogen management strategy when facing different environmental conditions and crop growth stages.

[0150] Specifically, the operation steps of the adaptive feedback module include: firstly calculating the deviation between NUE and the target value (ΔNUE = NUE target -NUE actual ), and then generate the parameter adjustment through the fuzzy PID controller. The fuzzy PID controller combines the proportional term (K p ·ΔNUE), integral term (K i ∫ΔNUEdt) and the differential term Dynamically adjust model parameters. The update formula is:

[0151] Parameter new =Parameter old (1+Adjustment)

[0152] Among them, Adjustment is the adjustment amount, which is calculated by the fuzzy PID controller based on the deviation. For example, for the degradation rate (k d ) and diffusion coefficient (D), whose values ​​can be dynamically updated by adjusting the amount to adapt to the actual dynamic changes of nitrogen.

[0153] Preferably, the parameters of the fuzzy PID controller (K p , K i , K d ) can be adjusted according to the system response characteristics in actual applications. For example, when the system response is slow, the proportional term coefficient (K p ) to speed up the response; when there is a steady-state error in the system, the integral term coefficient (K i) to eliminate errors. In addition, an adaptive learning mechanism can be introduced to dynamically adjust the parameters of the fuzzy PID controller according to historical data to further improve the adaptability and robustness of the system. In practical applications, other advanced control algorithms, such as adaptive fuzzy control or neural network control, can also be considered to replace or supplement the fuzzy PID controller to achieve more accurate parameter adjustment.

[0154] In some embodiments, the visualization output module generates a decision map including the following:

[0155] Thermal map of spatiotemporal distribution of soil nitrogen, generated based on the Kriging interpolation algorithm;

[0156] Fertilization path planning map, using ant colony algorithm to calculate the optimal mechanical travel route;

[0157] Risk warning area marking, meeting N soil Grid area where the concentration is >180 mg / kg or eBI is <0.5.

[0158] It should be noted that the main function of the visualization output module is to present the multi-dimensional evaluation reports and fertilization decision maps generated by the system to users in an intuitive way. These maps include soil nitrogen spatiotemporal distribution heat maps, fertilization path planning maps, and risk warning area markers, aiming to provide clear and easy-to-understand decision support for tobacco farmers and managers. Through these visualization tools, users can quickly understand the status of nitrogen management, optimize fertilization paths, and identify potential environmental risk areas.

[0159] Specifically, the heat map of the spatiotemporal distribution of soil nitrogen is generated based on the Kriging interpolation algorithm, which converts discrete soil nitrogen data into a continuous distribution map through spatial interpolation technology, and can intuitively display the spatial variation of soil nitrogen concentration. The fertilization path planning map calculates the optimal mechanical travel route through the ant colony algorithm, which simulates the behavior of ants looking for food and finds the shortest path from the starting point to the end point through iterative optimization, thereby improving fertilization efficiency and reducing mechanical operation time. The risk warning area marker marks high-risk areas according to the set threshold (such as soil nitrogen concentration exceeding 180 mg / kg or NUE below 0.5), reminding users to pay attention to these areas to avoid potential environmental problems.

[0160] Preferably, the visualization output module can be further refined and optimized. For example, for the heat map of the spatiotemporal distribution of soil nitrogen, the time dimension can be introduced to generate a dynamic heat map to show the change of nitrogen concentration over time, helping users to better understand nitrogen dynamics. In the fertilization path planning map, the optimal path can be dynamically adjusted in combination with terrain data and crop growth stages to adapt to different operating conditions. In addition, the risk warning area marking can be combined with geographic information system (GIS) technology to provide more detailed geographic information and risk levels, helping users to formulate more accurate risk response strategies.

[0161] The above-mentioned embodiments of the present invention have the following beneficial effects: The tobacco field nitrogen management and efficiency evaluation system of the present invention can realize the comprehensive optimization of nitrogen management in tobacco fields. The data acquisition module acquires meteorological, soil nitrogen, crop growth and historical fertilization data in real time, and combines the noise filtering, spatiotemporal alignment and multi-source data fusion of the data preprocessing module to provide high-precision basic data for dynamic prediction of nitrogen. The dynamic prediction module of nitrogen couples the soil nitrogen migration model with the crop absorption model, and can accurately predict the dynamic changes of nitrogen, providing a scientific basis for the optimization decision module. The optimization decision module generates a nitrogen application strategy based on a dynamic programming algorithm, calculates the optimal application amount and fertilization time, thereby realizing precise fertilization, improving nitrogen utilization efficiency (NUE), and reducing the environmental loss of nitrogen.

[0162] At the same time, the present invention can also realize the comprehensive evaluation and dynamic optimization of nitrogen management in tobacco fields. The efficiency evaluation module calculates the nitrogen utilization efficiency (NUE) and environmental benefit index (EBI) based on the nitrogen application amount, environmental loss and crop yield, and evaluates the management effect through three-level judgment logic. The adaptive feedback module dynamically corrects the model parameters of the nitrogen dynamic prediction module according to the deviation between NUE and EBI to ensure that the system can adapt to changes in the tobacco field environment and crop growth. The visual output module generates a multi-dimensional evaluation report and a fertilization decision map to provide intuitive decision support for tobacco farmers and managers. This closed-loop optimization mechanism can not only improve the scientificity and flexibility of nitrogen management, but also effectively reduce environmental risks, improve tobacco leaf yield and quality, and achieve a win-win situation of economic and environmental benefits.

[0163] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0164] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention to form a technical solution.

Claims

1. A tobacco field nitrogen management and efficiency evaluation system, characterized in that: include: Data collection module, used to obtain tobacco area meteorological data, soil nitrogen data, crop growth data and historical fertilization data in real time; A data preprocessing module, used for performing noise filtering, spatiotemporal alignment and multi-source data fusion on the data; The nitrogen dynamic prediction module is used to generate nitrogen dynamic prediction values ​​by coupling the soil nitrogen migration model and the crop absorption model; The optimization decision module is used to generate nitrogen application strategies based on dynamic programming algorithms and calculate the optimal application amount and fertilization time; The efficiency evaluation module is used to calculate the nitrogen utilization efficiency NUE and environmental benefit index EBI by combining nitrogen application amount, environmental loss and crop yield; An adaptive feedback module is used to dynamically correct the model parameters of the nitrogen dynamic prediction module according to the deviation between NUE and EBI; A visualization output module is used to generate a multi-dimensional evaluation report and a fertilization decision map; wherein the data preprocessing module, the nitrogen dynamic prediction module, the optimization decision module, the efficiency evaluation module and the adaptive feedback module form a recursive optimization link through real-time data flow and logical judgment rules.

2. The system according to claim 1, characterized in that The data preprocessing module comprises: The spatiotemporal alignment unit is used to match meteorological data with soil data in a gridded manner according to geographic coordinates. The matching formula is: Among them, G(x,y,t) is the grid data, W i is the spatial weight of the ith sensor, D i is the raw data of sensor i; The data fusion unit is used to fuse multi-sensor data through the Kalman filter algorithm. The state equation and observation equation are: X k =AX k-1 +BU k +w k Z k =HX k +v k Among them, X k is the system state vector at time k, Z k is the observation vector, w k and v k are process noise and observation noise, respectively.

3. The system according to claim 1, characterized in that The nitrogen dynamic prediction module performs the following steps: Step S1: Construct a soil nitrogen migration model, and the migration rate formula is: Among them, N soil is the soil nitrogen concentration, D is the diffusion coefficient, V is the water migration rate, k d is the nitrogen degradation rate; Step S2: Construct a crop nitrogen absorption model, and the absorption formula is: Among them, α and β are crop absorption characteristic parameters, and LAI is the leaf area index.

4. The system according to claim 3, characterized in that The nitrogen dynamic prediction module further calculates the real-time nitrogen profit and loss through the following formula: ΔN=N input +N mineralization -N uptake -N leaching Among them, N input is the fertilizer input, N mineralization is the amount of soil mineralization, N leaching is the leaching loss, and the leaching loss is calculated by the following formula: N leaching =γ·R·N soil γ is the leaching coefficient and R is the rainfall intensity.

5. The system according to claim 1, characterized in that The objective function of the optimization decision module is a multi-objective optimization model: Among them, λ1+λ2+λ3=1 is the dynamic weight coefficient, N max is the maximum allowable nitrogen application rate, T target is the target yield; the constraints include: soil nitrogen concentration threshold N soil ≤200mg / kg, fertilization interval Δt≥5 days.

6. The system according to claim 5, characterized in that The dynamic weight coefficient is adjusted according to the crop growth stage: During the vegetative growth period, λ2=0.6, during the reproductive growth period, λ1=0.5, and the weight update formula is: Where η is the learning rate, The partial derivative of the objective function with respect to the weights.

7. The system according to claim 1, characterized in that In the efficiency evaluation module: The calculation formula for nitrogen utilization efficiency NUE is: The calculation formula of environmental benefit index EBI is: Among them, C N is the nitrogen content of crops, N volatilization is the amount of nitrogen volatilization.

8. The system according to claim 7, characterized in that The efficiency evaluation module sets a three-level judgment logic: if NUE≥65% and EBI≥0.8, it is judged as "high efficiency and environmental protection"; if 60%≤NUE<65% or 0.6≤EBI<0.8, it is judged as "needs optimization"; if NUE<60% or EBI<0.6, it is judged as "high risk" and triggers the adaptive feedback module.

9. The system according to claim 1, characterized in that The adaptive feedback module modifies the model parameters by the following steps: Step T1: Calculate the deviation e between NUE and target value NUE =NUE target -NUE actual ; Step T2: Use fuzzy PID controller to generate parameter adjustment, proportional term K p ·e NUE , integral term K i ·∫e NUE dt, differential term Step T3: Update the degradation rate k in the soil nitrogen transport model d With the diffusion coefficient D, the update formula is: Among them, φ is the attenuation factor and ΔN is the nitrogen adjustment amount.

10. The system according to claim 1, characterized in that The visualization output module generates a decision map containing the following contents: Thermal map of spatiotemporal distribution of soil nitrogen, generated based on the Kriging interpolation algorithm; Fertilization path planning map, using ant colony algorithm to calculate the optimal mechanical travel route; Risk warning area marking, meeting N soil Grid area with >180 mg / kg, or EBI <0.5.

Images