An intelligent regulation method and device for greenhouse gases in corn fields

Abstract

The present invention provides a method and device for intelligent regulation of greenhouse gases in a corn field, including the following steps: Step S1: Divide the corn field into micro-regions, deploy environmental sensors in the divided micro-regions, collect soil moisture content and greenhouse gas flux indicators through the environmental sensors, and preprocess the collected data; Step S2: Extract the micro-region environmental stability perception factor and the micro-region environmental evolution dynamic feature enhancement perception factor based on the data preprocessed in Step S1, and calculate the micro-region environmental regulation priority index according to the sum; Step S3: Perform hierarchical regulation response on the micro-regions based on the micro-region environmental regulation priority index in Step S2. The present invention relates to the field of intelligent control, realizes multi-dimensional joint perception of micro-region environmental abnormal accumulation and environmental dynamic evolution trend, and breaks through the technical bottleneck that the existing greenhouse gas regulation system depends on macroscopic average data and lacks dynamic micro-region perception ability.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to a method and device for intelligent regulation of greenhouse gases in a corn field. Background Art

[0002] In the actual process of corn field management, due to the superposition of various factors such as undulating terrain, heterogeneity of soil texture, differences in crop growth status, uneven coverage of irrigation systems, and microclimate changes, even within the same field block, there are often obvious spatial variations in soil moisture and greenhouse gas concentrations. Specifically, in a corn field, the soil water content can vary by 10% - 30% between different small regions within the field block, and the emission fluxes of greenhouse gases (such as , ) can also show local variations of 2 - 5 times due to differences in soil water - gas conditions. Such micro - regional differences in the field are not only caused by natural laws but also the result of insufficient micro - management of agricultural activities such as fertilization, irrigation, and tillage.

[0003] Current intelligent regulation systems generally make decisions and execute based on the whole field block as a unit, that is, formulate unified fertilization amounts, unified irrigation amounts, and unified management strategies based on the average value of sensor node data or the results of coarse - grained spatial sampling, lacking a fine - grained recognition and response mechanism for the environmental heterogeneity of the field micro - regions. Due to the failure to fully consider the soil moisture levels and greenhouse gas emission characteristics of local areas, this "one - size - fits - fits - all" management method is likely to lead to the following series of problems in practical applications: for areas with lower soil moisture, unified fertilization and irrigation may result in low nitrogen application efficiency, restricting crop growth; while for areas with higher soil moisture or local waterlogging, it may trigger the large release of and under anaerobic conditions, significantly increasing the total amount of greenhouse gas emissions. In addition, due to insufficient oxygen supply in locally over - wet areas, it may also lead to restricted root development, increasing the probability of disease occurrence, thus reducing crop yield and quality.

[0004] If the environmental differences in the field micro - regions are not identified and differentially regulated, not only will it be difficult to achieve the greenhouse gas emission reduction target, but also the crop resource utilization efficiency (such as nitrogen fertilizer utilization rate, water utilization rate) will continue to be at a low level, resulting in an increase in agricultural production costs and a decline in sustainability. More importantly, with the increasing frequency of extreme weather events, the problem of micro - regional differences within the field block will be further exacerbated, and the limitations of the existing coarse - grained management method will become more prominent.

[0005] Therefore, intelligent perception and refined regulation of the differences in soil moisture and greenhouse gas concentrations in the micro-regions of corn fields have significant practical value and implementation potential. Through data fusion analysis based on sensor networks, extraction of local environmental characteristics, and formulation of differential regulation strategies, it is not only possible to effectively reduce greenhouse gas emissions and improve the consistency of crop growth, but also to provide key support for the development of precision agriculture and climate-smart agriculture, with important prospects for popularization and application and actual industrial value.

[0006] In the existing greenhouse gas regulation technologies for corn fields, they usually rely on coarse-grained control strategies based on macro-scale environmental parameters (such as average soil moisture and average gas flux in the field block), lacking the ability to accurately perceive and zone respond to the dynamic changes in the spatial heterogeneity at the micro-scale in the field. This extensive control method leads to the following prominent problems in the regulation of greenhouse gas emissions in the actual environment where soil moisture is unevenly distributed, the terrain has significant micro-undulations, and the influence of local fertilization and irrigation operations is complex:

[0007] Firstly, there is a lack of systematic identification of the cumulative abnormal process of the internal environmental state in the micro-regions of the field. Existing methods often only trigger regulation uniformly after the overall environmental indicators reach the preset threshold, ignoring the slowly accumulating environmental anomalies at the micro-region level, which easily leads to the instability and expansion of local regions and increases the overall emission risk.

[0008] Secondly, there is a lack of sensitive capture of the dynamic evolution trend of the micro-region environment. The process of environmental change in the field is affected by multiple factors such as differences in soil texture, uneven local water supply, and micro-climate disturbances, and the environmental evolution presents complex dynamic patterns such as slow change type, mutation type, periodic type, and hidden rebound type. The existing regulation system cannot sensitively adjust the response strategy based on the dynamic trend characteristics, resulting in delays in the regulation timing or excessive regulation measures, affecting the resource utilization efficiency and the effect of environmental improvement.

[0009] Thirdly, there is a lack of a dynamic differential intelligent response mechanism based on micro-region risk grading. Existing methods mostly use fixed threshold decisions and are difficult to conduct hierarchical and priority-based dynamic regulation according to the potential instability risk levels of micro-regions, resulting in high-risk micro-regions not being intervened in a timely manner, while low-risk micro-regions are over-intervened, and the overall regulation efficiency is insufficient.

[0010] Therefore, how to systematically perceive the abnormal accumulation and evolution dynamic characteristics of the micro-region environmental state under the complex heterogeneous environmental conditions in corn fields, construct multi-level instability risk perception indicators, and optimize intelligent regulation decisions based on the perception results to achieve precise, dynamic, and hierarchical intelligent regulation of greenhouse gases in the field has become a key technical problem that urgently needs to be solved. Summary of the Invention

[0011] In view of this, the present invention aims to propose a method for intelligent regulation of greenhouse gases in corn fields to achieve precise, dynamic, and hierarchical intelligent regulation of greenhouse gases in the field.

[0012] To achieve the above object, the technical solution of the present invention is realized as follows:

[0013] An intelligent regulation method for greenhouse gases in a corn field, comprising the following steps:

[0014] Step S1: Divide the corn field into micro-regions, deploy environmental sensors in the divided micro-regions, collect soil moisture content and greenhouse gas flux indicators through the environmental sensors, and preprocess the collected data;

[0015] Step S2: Extract the micro-region environmental stability perception factor and the micro-region environmental evolution dynamic characteristic strengthening perception factor from the data preprocessed in step S1, and calculate the micro-region environmental regulation priority index according to the and ; ;

[0016] Step S2.1: The micro-region environmental stability perception factor is obtained through the joint analysis of the dynamic abnormal accumulation characteristics of soil moisture and greenhouse gas concentration and the environmental resilience evolution trend in the micro-regions of the corn field;

[0017] The micro-region environmental stability perception factor is calculated by the following formula:

[0018] ;

[0019] Wherein, represents the micro-region environmental stability perception factor of the th micro-region in the time period , represents the cumulative abnormal evaluation of the th micro-region in the time period , represents the number of time points in the time period , represents the environmental resilience collapse degree of the th micro-region at the moment;

[0020] Step S2.2: The micro-region environmental evolution dynamic characteristic strengthening perception factor is obtained through the mapping analysis of multiple characteristics of the micro-region environmental dynamic evolution;

[0021] The micro-region environmental evolution dynamic characteristic strengthening perception factor is calculated by the following formula:

[0022] ;

[0023] Among them, represents the enhanced perception factor of the environmental evolution dynamic characteristics of the th micro-region in the time period . represents the overall trend energy density of the th micro-region in the time period . represents the cumulative degree of slope drift of the th micro-region in the time period . represents the cumulative evaluation of local micro-perturbations of the th micro-region in the time period .

[0024] Step S2.3: The micro-region environmental regulation priority index is calculated by the following formula:

[0025] ;

[0026] Among them, represents the micro-region environmental regulation priority index of the th micro-region in the time period . represents the micro-region environmental stability perception factor of the th micro-region in the time period . represents the enhanced perception factor of the environmental evolution dynamic characteristics of the th micro-region in the time period .

[0027] Step S3: Based on the micro-region environmental regulation priority index obtained in Step S2, a hierarchical regulation response is carried out on the micro-regions.

[0028] Furthermore, the in Step S2.1 is calculated by the following formula:

[0029] ;

[0030] Among them, represents the cumulative anomaly evaluation of the th micro-region in the time period . represents the time weight parameter at the moment, which is set according to the different sensitivities of different growth stages of corn to environmental anomalies. represents the th micro-region in the moment. The greenhouse gas concentration change rate of a micro-region at the moment, represents the abnormal amplification index.

[0031] Furthermore, the in step S2.1 is calculated by the following formula:

[0032] ;

[0033] where, represents the environmental resilience collapse degree of the th micro-region at the moment, represents the first-order delayed autocorrelation coefficient of the soil moisture change rate of the th micro-region at the moment, represents the first-order delayed autocorrelation coefficient of the greenhouse gas concentration change rate of the th micro-region at the moment, represents the disturbance event weight function at the moment. When there are human disturbance operations such as irrigation and fertilization in the window, the disturbance weight increases, reflecting the enhancement of the impact of management operations on soil environmental resilience.

[0034] Furthermore, the in step S2.2 is calculated by the following formula:

[0035] ;

[0036] where, represents the overall trend energy density of the th micro-region in the time period , represents the number of sub-intervals with length in the time period , represents the micro-region environmental stability perception factor of the th micro-region in the time period , represents a very small positive number to prevent the denominator from being zero.

[0037] Furthermore, the in step S2.2 is calculated by the following formula:

[0038] ;

[0039] where, represents the slope drift accumulation degree of the th micro-region in the time period ​ Indicates a time period The number of sub - intervals of length in it, Indicates the th micro - region's change amount in the th sub - interval.

[0040] Furthermore, the of step S2.2 is calculated by the following formula:

[0041] ;

[0042] wherein, Indicates the cumulative evaluation of the local minute perturbation of the th micro - region in the time period , Indicates a time period The number of sub - intervals of length in it, Indicates the th micro - region's change amount in the th sub - interval. The average value of the absolute value of the local change amount per unit time reflects the activity level of the local dynamic activity. If the overall environment is stable and the local fluctuation is small, then is lower. If the local perturbation is frequent and the accumulated energy is large, then increases.

[0043] Furthermore, the hierarchical regulation response of step S3 includes:

[0044] Based on the micro - region environment regulation priority index , define the micro - region intelligent regulation response priority to achieve the dynamic sorting and hierarchical response of all micro - regions in the whole field:

[0045] ;

[0046] wherein, Indicates the intelligent regulation response priority of the th micro - region in the time period ; Indicates the micro - region environment regulation priority index of the th micro - region in the time period , that is, the comprehensive instability risk index of the th micro - region; The denominator is the highest instability risk index among all micro - regions at the current moment, used for normalization;

[0047] According to the micro - region intelligent regulation response priority , the following response logic is proposed:

[0048] Level - 1 high - priority response ( ): Immediately initiate the local rapid response strategy, including encrypted micro-irrigation, increased local soil aeration, and enhanced local shading and cooling treatments, to quickly suppress the instability and expansion of the micro-environment;

[0049] Secondary medium-priority response ( ): Conduct routine micro-region regulation adjustments, such as adjusting the intensity of conventional irrigation and slightly adjusting the opening ratio of greenhouse gas emission channels, to slowly optimize the micro-environment state;

[0050] Tertiary low-priority observation ( ): Maintain monitoring, do not perform direct intervention, continue to collect data to observe the evolution trend, and only upgrade the response level when the trend deteriorates.

[0051] Compared with the prior art, the present invention has the following advantages:

[0052] The intelligent greenhouse gas regulation method for corn fields of the present invention realizes multi-dimensional joint perception of abnormal accumulation of the micro-environment and the dynamic evolution trend of the environment by introducing an environmental stability perception factor and an environmental evolution dynamic feature enhancement perception factor at the micro-region scale of corn fields, breaking through the technical bottleneck that the existing greenhouse gas regulation system relies on macroscopic average data and lacks the ability of dynamic micro-region perception.

[0053] Another object of the present invention is to propose an intelligent greenhouse gas regulation device for corn fields to realize the intelligent regulation of greenhouse gases in corn fields.

[0054] To achieve the above object, the technical solution of the present invention is realized as follows:

[0055] An intelligent greenhouse gas regulation device for corn fields includes a field intelligent control box, a sensor device, and an execution device. The field intelligent control box communicates wirelessly with the sensor device and the execution device;

[0056] The field intelligent control box includes a data processing unit, a communication gateway, an energy module, and a user interface. The energy module includes a solar panel and a lithium battery pack;

[0057] The sensor device includes a TDR or FDR type soil moisture sensor and a portable gas flux monitoring device. The portable gas flux monitoring device includes a sensor and a sensor;

[0058] The execution device includes an intelligent irrigation valve, a micro air pump, a sunshade net, and a sunshade net motor. The intelligent irrigation valve includes an electromagnetic valve and a flow meter;

[0059] The algorithm logic of the data processing unit is consistent with the above-mentioned intelligent regulation method for greenhouse gases in corn fields.

[0060] Further, the data processing unit is used to receive the data monitored by the sensor device, and calculate the priority index for micro-region environment regulation and perform hierarchical regulation response on the micro-region according to the monitored data;

[0061] The communication gateway is used for long-distance and low-power data transmission in the field;

[0062] The energy module is used to provide continuous power and adapt to the environment without grid coverage;

[0063] The user interface is used to display the micro-region risk map, regulation status and historical data in real time;

[0064] The TDR or FDR type soil moisture sensors are deployed in layers at the depths of 0-10 cm and 10-30 cm of the corn field soil for detecting soil moisture:

[0065] The sensor is used to monitor flux;

[0066] The sensor is used to monitor flux;

[0067] The portable gas flux monitoring device is used for and periodic scanning of the flux.

[0068] Further, the intelligent irrigation valve is used to respond to the moisture regulation of the micro-region in the logic;

[0069] The micro air pump is used to improve the soil ventilation of the micro-region in the response logic;

[0070] The sunshade net motor is used to control the unfolding or retraction of the sunshade net, regulate the local light intensity and temperature in the response logic, and reduce the soil evaporation rate.

[0071] Compared with the prior art, the present invention has the following advantages:

[0072] The device for intelligent regulation of greenhouse gases in corn fields according to the present invention realizes the intelligent regulation of greenhouse gases in corn fields through the "perception - analysis - execution" closed loop, and has the characteristics of high efficiency, reliability and practicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0074] Figure 1 It is a flowchart of the intelligent regulation method for greenhouse gases in corn fields according to the embodiments of the present invention;

[0075] Figure 2 It is a schematic diagram of the intelligent regulation device for greenhouse gases in corn fields according to the embodiments of the present invention; Detailed implementation manners

[0076] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0077] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "inner", "back", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0078] The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0079] Embodiment 1

[0080] This embodiment relates to an intelligent regulation method and device for greenhouse gases in corn fields. As Figure 1 and Figure 2 shown, it includes the following steps:

[0081] Step S1: Conduct micro-zoning on the corn field, deploy environmental sensors in the divided micro-zones, collect soil moisture content and greenhouse gas flux indicators through the environmental sensors, and preprocess the collected data;

[0082] Micro-zoning: According to the natural conditions of the corn field plot, such as soil texture, terrain undulation, water spatial distribution characteristics, etc., and management operation units, such as irrigation units and fertilization units, conduct preliminary micro-zoning. The micro-zone scale is controlled between 20 square meters and 100 square meters to ensure that it can reflect local heterogeneity and is convenient for the implementation of regulation operations.

[0083] After micro-zoning, assign a unique identification ID to each micro-zone as the basic unit for subsequent data collection and management.

[0084] Deployment of environmental sensors: Deploy basic environmental sensors in each micro-zone to mainly collect the following core environmental parameters:

[0085] Soil moisture content: TDR or FDR type soil moisture sensors are used, and the sampling depth is stratified at 0–10 cm and 10–30 cm.

[0086] Greenhouse gas flux index: Collect , flux data, and use a portable gas flux monitoring device to scan periodically to establish a dynamic curve of greenhouse gas emissions in the micro-region.

[0087] The sampling frequency of the sensor is set to once every 30 minutes. During critical change periods, such as after irrigation, fertilization, or extreme weather, it is increased to once every 5 minutes to ensure capturing the rapid environmental change process.

[0088] Step S2: Extract the micro-region environmental stability perception factor and the micro-region environmental evolution dynamic feature enhancement perception factor from the data preprocessed in step S1, and calculate the micro-region environmental regulation priority index and ; ;

[0089] Step S2.1: The micro-region environmental stability perception factor is obtained through the joint analysis of the dynamic abnormal accumulation characteristics of soil moisture and greenhouse gas concentration and the environmental resilience evolution trend in the micro-region of the corn field;

[0090] The micro-region environmental stability perception factor is calculated by the following formula:

[0091] ;

[0092] where represents the cumulative anomaly assessment of the th micro-region in the time period , represents the number of time points in the time period , represents the environmental resilience collapse degree of the th micro-region at the moment ;

[0093] Step S2.2: The micro-region environmental evolution dynamic feature enhancement perception factor is obtained through the mapping analysis of multiple features of the micro-region environmental dynamic evolution;

[0094] The micro-region environmental evolution dynamic feature enhancement perception factor is calculated by the following formula:

[0095] ;

[0096] where represents the overall trend energy density of the th micro-region in the time period ; represents the cumulative degree of slope drift of the th micro-region in the time period ; represents the cumulative evaluation of local micro-perturbations of the th micro-region in the time period ;

[0097] Step S2.3: The priority index of micro-region environmental regulation is calculated by the following formula:

[0098] ;

[0099] Step S3: Based on the priority index of micro-region environmental regulation in Step S2 perform hierarchical regulation response on the micro-region.

[0100] In the process of dynamic evolution of the micro-region environment in the corn field, the changes in soil moisture and greenhouse gas concentration are often not isolated instantaneous anomalies, but cumulative abnormal stresses formed under the combined action of multiple factors such as crop growth demand changes, continuous irrigation and fertilization operations, and weather condition changes. At the same time, the soil environment itself has a certain self-regulating and repairing ability, but after the abnormal accumulation reaches a certain level, the soil toughness gradually decreases, eventually leading to dynamic instability of the environment and abnormal explosion of greenhouse gas emissions. Therefore, the traditional anomaly detection method based solely on instantaneous changes is difficult to effectively capture this dynamic evolution process, and there are problems of identification delay and regulation failure.

[0101] Based on the above scenario problems, this embodiment proposes to extract the micro-region environmental stability perception factor with the cumulative abnormal degree of micro-region soil moisture and gas concentration changes and the environmental toughness evolution trend within a continuous time window, so as to quantify the dynamic instability risk of the micro-region and provide a precise decision-making basis for the intelligent regulation system.

[0102] Specifically, first, model and analyze the cumulative abnormal degree of the micro-region environment. Within a certain time window, collect the micro-region soil moisture data and greenhouse gas concentration data, and calculate the change rate sequences of the soil moisture data and greenhouse gas concentration respectively.

[0103] ;

[0104] ;

[0105] where represents the soil moisture change rate of the th micro-region at the moment; represents the soil moisture data of the micro-region at the moment; denote the soil moisture data of the micro-region at the moment; denote the change rate of greenhouse gas concentration of the micro-region at the moment; denote the greenhouse gas concentration data of the micro-region at the moment; denote the greenhouse gas concentration data of the micro-region at the

[0106] In the actual maize field environment, the changes in soil moisture and greenhouse gas concentration in the micro-region usually show obvious dynamic evolution characteristics, and this kind of change often has the characteristics of continuity and cumulativeness. Due to the significant changes in the water and nutrient requirements of maize at different growth stages, coupled with the periodic intervention of management operations such as irrigation and fertilization, the micro-region environmental state is no longer a simple response driven by a single instantaneous event, but a complex dynamic process formed by the superposition of multiple natural and human factors. In this process, even if the amplitude of a single environmental fluctuation is small, if there are continuous moisture fluctuations or abnormal gas releases deviating from the normal range and cannot be effectively restored in a short time, it will lead to the continuous accumulation of soil hydrothermal environmental stress, and ultimately trigger the functional instability of the environmental system.

[0107] Based on the characteristics of this actual scenario, it is difficult to comprehensively and accurately identify the micro-regions that are truly at potential instability risk by simply using the instantaneous anomalies of soil moisture or gas concentration at a certain moment. Therefore, this application proposes to define the cumulative anomaly amount of the micro-region as a cumulative quantitative index of the degree of environmental change anomaly within a continuous time window. By introducing the absolute value accumulation of the soil moisture change rate and the greenhouse gas concentration change rate, and setting time weights according to the sensitivity differences at different growth stages of maize, it can more accurately reflect the true accumulation state of the micro-region environmental pressure under actual growth and management conditions. The cumulative anomaly amount of the micro-region can not only capture the high-stress impact brought by short-term drastic changes, but also identify the chronic increase in environmental pressure caused by the gradual accumulation of multiple small fluctuations, thus providing a reliable basis for the early warning of the dynamic instability of the micro-region environment and the dynamic adjustment of the response strategy of the intelligent control system.

[0108] Therefore, after obtaining the change rate sequences of soil moisture data and greenhouse gas concentration data, continue to evaluate the cumulative anomaly amount of the micro-region through the change rate sequences. The calculation expression for the cumulative anomaly evaluation of the th micro-region in the maize field is the calculated by the following formula:

[0109] ;

[0110] Among them, represents the cumulative anomaly assessment of the th micro-region in the time period , represents the time weight parameter at the moment, which is set according to the different sensitivities of different growth stages of corn to environmental anomalies, represents the soil moisture change rate of the th micro-region at the moment, represents the greenhouse gas concentration change rate of the th micro-region at the represents the anomaly amplification index, which is used to enhance the sensitivity to large changes. In this embodiment, is set, which can be adjusted according to the actual scenario and there is no requirement.

[0111] It should be noted that the absolute value of the change rate , reflects the intensity of instantaneous environmental changes, and the cumulative summation process reflects the continuous accumulation of abnormal stress. The time weight then dynamically adjusts the contribution of abnormal changes to the instability risk in combination with the corn growth cycle. For example, during the sensitive period from jointing to filling, a higher weight is given to more accurately reflect the impact of environmental changes in this stage on the overall environmental stability. Through calculation, the cumulative degree of micro-region environmental abnormal changes within the given time window can be effectively reflected. The larger the value, the more serious the cumulative environmental pressure of the micro-region and the higher the instability risk.

[0112] In the actual planting environment of corn fields, although the soil moisture and greenhouse gas concentration in the micro-regions are constantly affected by external meteorological conditions and field management operations, such as irrigation, fertilization, etc., and fluctuate, the soil ecosystem itself has a certain self-regulation and recovery ability. When the environment is slightly disturbed in the short term, if the soil environmental toughness is good, it can quickly return to a relatively stable state through natural processes. However, under the condition of continuous strong disturbance or continuous superposition of cumulative stress, the repair ability of the soil environment gradually weakens, manifested in the fluctuation mode of water change and gas concentration change gradually changing from predictable and orderly to unpredictable and disorderly, until the soil environmental toughness collapses, resulting in local environmental instability and abnormal explosion of greenhouse gas emissions.

[0113] In this context, if only relying on the magnitude of environmental changes for anomaly detection, it is easy to overlook the potential hidden instability risks brought about by changes in the adaptive capacity of the soil system within microzones. Practical scenarios indicate that the autocorrelation characteristics of environmental changes are important indicators for evaluating soil resilience: when the autocorrelation of the change rates of moisture and gas concentration is relatively high, it indicates that there is a certain recoverability in environmental fluctuations; when the autocorrelation decreases and the change pattern tends to be disordered, it shows that the environmental system has entered a stage of declining resilience or even collapse. Therefore, the present invention proposes to introduce the degree of environmental resilience collapse in microzones as a supplementary evaluation indicator, and based on the short-term autocorrelation analysis of the change rate sequence, quantify the downward trend of the self-repair ability of the microzone soil environment during the dynamic change process. Combining the disturbance factors of field management operations, through the identification and weight amplification and correction of disturbance events, the perception accuracy of the resilience change characteristics under management intervention is further improved, so as to achieve the forward-looking warning and precise perception of the dynamic instability of the microzone environment.

[0114] Specifically, after completing the cumulative anomaly amount modeling, further analyze the evolution of soil environmental resilience. Considering that the soil environment has a certain self-recovery ability, short-term small fluctuations may be quickly repaired through natural processes, but when the fluctuations persist or the recovery ability declines, the environmental resilience collapse will accelerate environmental instability. Therefore, evaluate the degree of environmental resilience collapse in microzones through autocorrelation assessment based on the time-series data of change rates, that is, Calculate through the following formula:

[0115] ;

[0116] Wherein, represents the degree of environmental resilience collapse of the th microzone at the th moment; represents the first-order delayed autocorrelation coefficient of the soil moisture change rate of the th microzone at the th moment, represents the first-order delayed autocorrelation coefficient of the greenhouse gas concentration change rate of the th microzone at the th moment, represents the disturbance event weight function at the

[0117] th moment. When there are artificial disturbance operations such as irrigation and fertilization within the window, the disturbance weight increases, reflecting the enhanced impact of management operations on soil environmental resilience. It should be noted that in the above formula, Further magnify the effect of reduced resilience caused by external operations such as irrigation and fertilization, which conforms to the actual situation of the environmental evolution characteristics under the actual field management mode of corn fields.

[0118] Based on the dynamic evolution characteristics of the corn field environment, the present invention proposes to construct a micro-region environmental stability perception factor as a quantitative index that comprehensively reflects the interactive effect of cumulative anomalies and resilience evolution. Different from the traditional method of fusing multi-source features through a simple linear weighting method, the construction of the micro-region environmental stability perception factor emphasizes the internal coupling relationship between two key features during the dynamic evolution process: on the one hand, the cumulative anomaly reflects the degree of environmental pressure accumulation; on the other hand, the environmental resilience collapse degree reflects the ability of the soil system to resist and repair abnormal pressure. When the cumulative anomaly is high and the resilience collapse degree is also high, the risk of environmental instability shows a non-linear superposition and amplification trend, rather than a simple linear superposition.

[0119] Therefore, in this application, the construction of the micro-region environmental stability perception factor is defined by a fusion method based on the interactive enhancement mechanism of abnormal pressure and resilience weakening. Specifically, the cumulative anomaly of the micro-region and the environmental resilience collapse degree are respectively standardized and then fused by the product enhancement method to define the micro-region environmental stability perception factor as:

[0120] ;

[0121] wherein, represents the micro-region environmental stability perception factor of the st micro-region in the time period ; represents the cumulative anomaly assessment of the th micro-region in the time period ; represents the number of time points in the time period ; represents the environmental resilience collapse degree of the th micro-region at the moment.

[0122] It should be noted that through the method of product enhancement, the micro-region environmental stability perception factor can more realistically reflect the actual scenario where the environmental instability risk shows an accelerating outbreak characteristic when both the abnormal pressure accumulation and the resilience weakening in the micro-region environment coexist, avoiding the problem of insufficient recognition sensitivity for extremely high-risk regions in the linear weighting method. This construction logic fully reflects the non-linear synergistic action law of the two factors of cumulative anomalies and resilience decline in the instability process during the dynamic evolution of the micro-region environment in the corn field, ensuring that the micro-region environmental stability perception factor can accurately and timely capture the high-risk regions of local environmental instability, providing more reliable decision-making support for the dynamic correction of the target value of the intelligent control system and the differential adjustment of response strategies.

[0123] During the intelligent regulation of greenhouse gases in the micro-region of the corn field, by introducing the micro-region environmental stability perception factor, the preliminary identification and intelligent response to the dynamic instability risk of the micro-region environment in the field have been achieved. However, although the introduction of the micro-region environmental stability perception factor can effectively perceive significant environmental anomalies on a large scale, there are still obvious deficiencies in the accuracy and forward-looking of risk identification during the dynamic evolution process of slow accumulative changes or hidden rebound changes in some micro-region environments, becoming the key shortcoming restricting the response accuracy and timeliness of the overall regulation system.

[0124] In the existing monitoring and application process, the time-series changes of the micro-region environmental stability perception factor mainly show four typical dynamic characteristics, including slow-change type, mutation type, periodic type, and hidden rebound type. Among them, the slow-change type feature is manifested as the slow and continuous accumulation of micro-region environmental pressure, usually corresponding to the slow deterioration processes such as long-term insufficient water supply in the field and the decline of soil oxygen exchange efficiency; the mutation type feature is mostly related to short-term extreme meteorological events (such as heavy rain, dry and hot wind), sudden large-scale irrigation or fertilization operations that lead to the rapid instability of the environment; the periodic type feature is commonly found in micro-regions significantly affected by irrigation cycle management and natural rainfall cycle, showing periodic rises and falls of environmental parameters; while the hidden rebound type feature often stems from the cumulative risk during the initial restorative decline of the soil environment, and then the rapid rebound of environmental indicators in the short term due to external disturbances (such as increased soil denitrification after fertilization).

[0125] Among them, the slow-change type and hidden rebound type micro-region environmental evolution patterns have highly concealed and continuous characteristics in the actual scenario. Specifically, the slow-change type micro-region usually shows a slow decline in soil water supply or a gradual weakening of oxygen exchange efficiency, with continuous accumulation of environmental pressure but a small change range in the short term; the hidden rebound type micro-region shows a local rebound phenomenon caused by external disturbances (such as local fertilization, short-term rainfall) after the initial decline of environmental indicators. The environmental evolution of these two types is characterized by slow initial changes, weak abnormal signals, and being easily interfered and covered up by other factors, thus posing higher requirements for the sensitive perception and dynamic adjustment of the regulation system.

[0126] Further in-depth analysis reveals that in the actual micro-region environment of corn fields, small-scale spatial heterogeneity is widespread, which is the main root cause factor leading to the fuzzy identification of the changing trends of slow-variant and hidden rebound micro-region environments. Due to the superimposed effects of natural conditions such as soil texture differences, micro-topography undulations, and different local vegetation coverage, the field water supply shows obvious spatial non-uniformity. Even within a single micro-region, there may be significant differences in the local water status, resulting in small-scale and high-frequency irregular fluctuations in the soil hydrothermal environment changes. Especially after irrigation and fertilization operations, the uneven diffusion of local water replenishment exacerbates this spatial heterogeneity effect, masking or distorting the originally stable and slow environmental change trends by local abnormal fluctuations.

[0127] In this case, traditional trend identification methods based on the sequence of overall micro-region environmental stability perception factors are often interfered by local short-term fluctuation signals and are difficult to accurately capture the true slow deterioration trend or hidden risk rebound process of the overall micro-region environmental state. This identification ambiguity not only reduces the forward-looking perception ability of the regulation system for potential environmental instability risks but also easily leads to delays in the timing or deviations in the intensity of regulation responses, further exacerbating the expansion of local environmental instability and having an adverse impact on the overall greenhouse gas emission regulation target in the field.

[0128] Based on the above actual scenario analysis, it is clear that in the process of intelligent regulation of greenhouse gases in corn field micro-regions, for the slow-variant and hidden rebound environmental evolution patterns, due to the local water non-uniformity effect caused by small-scale spatial heterogeneity, the core problems of fuzzy identification of environmental change trends, lagging risk perception, and inaccurate regulation decision responses are formed. To effectively solve this problem, it is urgent to further extract characteristic indicators that can suppress the influence of local short-term abnormal fluctuations and enhance the sensitivity to long-term slow change trends and hidden rebound signals on the basis of the existing micro-region environmental stability perception factor perception framework, and construct dynamic trend strengthening and optimization factors for slow-variant and hidden rebound environmental evolution characteristics, so as to improve the accurate perception and dynamic response ability of the intelligent regulation system to potential instability risks in micro-regions.

[0129] In the dynamic evolution process of slow-variant and hidden rebound micro-region environments, due to soil small-scale spatial heterogeneity and local water replenishment non-uniformity effects, the time series of micro-region environmental stability perception factors show long-term slow change or short-term hidden rebound characteristics macroscopically, while at the microscopic local scale, there are accompanied by local fluctuation phenomena with weak but continuous accumulation of energy density. Traditional perception methods based on the amplitude of the overall change trend are difficult to accurately capture the potential instability signals in this unique evolution process.

[0130] To address this problem, this step proposes to construct a dynamic feature enhancement perception factor for the evolution of the micro-area environment by extracting the trend energy density change feature, the slope drift accumulation feature and the local fluctuation accumulation rate feature, so as to comprehensively reflect the real physical dynamic characteristics of the micro-area environment in the actual evolution process.

[0131] Specifically, the first energy density change evaluation quantifies the ratio between the total energy and the net change of the micro-region environmental stability perception factor within a set time window. The calculation expression of the overall trend energy density of each micro-region is the same as step S2.2 Calculated by the following formula:

[0132] ;

[0133] in, Indicates Micro-areas in time period The overall trend of energy density; Indicates time period The medium length is The number of subintervals of ; Indicates Micro-areas in time period The perceived factor of micro-region environmental stability; Indicates a very small positive number that prevents the denominator from being 0. In this embodiment, .

[0134] It should be noted that the numerator calculates the total energy of all small changes within the sequence, reflecting the overall dynamic activity of the system; the denominator calculates the net change energy between the starting point and the end point, representing the strength of the overall evolution trend. If it is close to 1, it means that environmental changes are mainly concentrated in the direction of net change, and the trend is clear; If it is significantly greater than 1, it means that most of the change energy is dissipated in local high-frequency fluctuations, the trend is unclear, and the risk of hidden instability is high.

[0135] In order to further accurately capture the dynamic evolution characteristics of the slow-changing and hidden rebound micro-region environments, the cumulative slope drift degree is further evaluated through the sub-interval sequence formed by the micro-region environmental stability perception factor, thereby reflecting the continuity and cumulative characteristics of the dynamic changes in the environment, especially the slow but continuous change of the hidden instability trend in the slow-changing micro-region. The cumulative degree of slope drift in each micro-region is the value of step S2.2. Calculated by the following formula:

[0136] ;

[0137] in, Indicates the cumulative degree of slope drift of the th micro-region in the time period ; Indicates the number of sub-intervals of length in the time period ; Indicates the change amount of the th micro-region in the th sub-interval.

[0138] It should be noted that logically, if the environmental change rate remains stable, the difference between consecutive change amounts is small, and the value is low; if the environmental change rate is slowly shifting or accumulating drift, especially in the early stage of hidden rebound, the rate continues to change but the amplitude is not large, then the value gradually increases. In the actual scenario, when the soil moisture status in the field micro-region deteriorates slowly due to factors such as deep leakage and evaporation changes, the environmental change rate is not drastic, but the direction continuously shifts, which can sensitively capture this cumulative risk signal and serve as the basis for early warning.

[0139] However, in the process of dynamic evolution of the micro-region environment of the slow-variation type and the hidden-rebound type, in addition to the impact of the overall trend and change rate drift on environmental instability, a large number of local micro-fluctuations caused by factors such as uneven soil moisture, local fertilization and irrigation differences, and micro-climate disturbances within the interval cannot be ignored. Especially when the overall environmental change is not significant, the frequent accumulation of local disturbances often becomes an important driving force for the hidden instability process. Therefore, to comprehensively reflect the environmental dynamic change characteristics of the th micro-region within the time window, it is urgent to introduce the evaluation of the overall accumulation level of local micro-disturbances. Through the evaluation of the local fluctuation accumulation rate, the perception and quantification ability of the hidden risk accumulation process of the micro-region environment can be further strengthened. For the evaluation of the local micro-disturbance accumulation of the th micro-region in the time period is calculated by the following formula in step S2.2: ;

[0140] ;

[0141] where indicates the number of sub-intervals of length in the time period ; indicates the change amount of the th micro-region in the th sub-interval. The average value of the absolute value of the local change amount per unit time reflects the activity degree of local dynamic activities; if the overall environment is stable and the local fluctuations are small, then Lower; if the local disturbances are frequent and the accumulated energy is large, then it will increase. In the actual field scenario, if the local environmental state in a certain micro-region fluctuates slightly and frequently due to factors such as uneven soil texture and local irrigation leakage, even if the overall environment seems to change slowly, the accumulation of local fluctuations may lead to an instability chain reaction at the microscopic level. It provides the ability to quantitatively perceive such local hidden risks.

[0142] Finally, through the fusion evaluation of the overall trend energy density of the micro-region, the cumulative degree of slope drift of the micro-region, and the cumulative evaluation of local minor disturbances in the micro-region, the enhanced perception factor of the environmental evolution dynamic characteristics of the micro-region is obtained.

[0143] ;

[0144] Among them, represents the enhanced perception factor of the environmental evolution dynamic characteristics of the th micro-region in the time period ; represents the overall trend energy density of the th micro-region in the time period ; represents the cumulative degree of slope drift of the th micro-region in the time period ; represents the cumulative evaluation of local minor disturbances of the th micro-region in the time period .

[0145] It should be noted that for the overall trend energy density , since in the slow-changing and hidden rebound environments, the energy dissipation caused by local fluctuation noise often shows an exponential amplification effect, this step uses logarithmic normalization mapping to strengthen the reflection of the energy dispersion trend on the instability risk. Through logarithmic mapping, when is small (the trend is clear), changes slowly; when increases (severe local fluctuation dissipation), rises rapidly, highlighting the phenomenon of increased instability risk caused by blurred environmental trends. For the cumulative slope drift , since the continuous micro-drift of the environmental change rate often shows a linear cumulative characteristic, and the cumulative amount directly corresponds to the evolution intensity of the slow instability of the environment, this step uses linear normalization. Linear normalization ensures that changes in a proportional relationship with the cumulative process of instability risk, and at the same time avoids the outbreak of extreme values, controls the numerical stability, and conforms to the cumulative evolution characteristics of the slow deterioration of the environment. For the local fluctuation accumulation rate , since the influence of local perturbations on the latent instability of the environment exhibits a threshold activation characteristic (i.e., the risk of instability increases rapidly after the perturbation accumulation reaches a certain level), this step uses function for normalization mapping. When is small, is close to 0, indicating that the local perturbation has little influence on the environmental stability; when is large, rapidly rises to close to 1, reflecting the phenomenon of a sharp increase in the instability risk caused by local perturbation accumulation.

[0146] In the process of intelligent regulation of greenhouse gases in the micro-region of the corn field, in view of the slow-changing and latent rebound characteristics of the micro-region environment evolution, the aforementioned step S2.1 and step S2.2 respectively extract the micro-region environmental stability perception factor and the micro-region environmental evolution dynamic characteristic enhanced perception factor. The micro-region environmental stability perception factor mainly quantifies the cumulative abnormal level of the micro-region within the time interval, reflecting the overall abnormal accumulation trend of the environment; the micro-region environmental evolution dynamic characteristic enhanced perception factor comprehensively considers the environmental trend fuzziness, the drift of the change rate, and the local perturbation accumulation, reflecting the potential instability acceleration risk of the micro-region environment. Therefore, in this step S2.3, it is necessary to jointly model the micro-region environmental stability perception factor and the micro-region environmental evolution dynamic characteristic enhanced perception factor, comprehensively evaluate the current state and evolution trend of the micro-region environment, and then guide the dynamic response decision of the greenhouse gas intelligent regulation system.

[0147] For the th micro-region in the time period , the calculation expression of the micro-region environmental regulation priority index in step S2.3 is:

[0148] ;

[0149] where represents the micro-region environmental stability perception factor of the th micro-region in the time period ; represents the micro-region environmental evolution dynamic characteristic enhanced perception factor of the th micro-region in the time period . The product relationship reflects the synergistic amplification effect of the current environmental abnormal accumulation level and the future environmental evolution acceleration risk. The constant 1 is used to ensure that when the micro-region environmental evolution dynamic characteristic enhanced perception factor is small, that is, the environmental trend is stable, the abnormal quantity discrimination ability of the micro-region environmental stability perception factor itself can still be retained.

[0150] The hierarchical regulation response in step S3 includes:

[0151] Based on the micro-region environmental regulation priority index , define the micro-region intelligent regulation response priority , to achieve dynamic sorting and hierarchical response to all micro-regions in the field:

[0152] ;

[0153] Among them, represents the intelligent regulation response priority of the th micro-region in the time period ; represents the micro-region environment regulation priority index of the th micro-region in the time period , that is, the comprehensive instability risk index of the th micro-region; the denominator is the highest instability risk index among all micro-regions at the current moment, used for normalization;

[0154] After normalization, is limited to the range of . The closer the value is to 1, the higher the instability risk of the micro-region and the higher the regulation response priority; the closer the value is to 0, the more stable the environment and the lower the response priority.

[0155] According to the intelligent regulation response priority of the micro-region, the following response logic is proposed:

[0156] First-level high-priority response ( ): Immediately start the local rapid response strategy, including intensifying micro-irrigation, increasing local soil ventilation, and enhancing local shading and cooling treatment, to quickly suppress the expansion of micro-region environmental instability;

[0157] Second-level medium-priority response ( ): Conduct routine regulation adjustments for the micro-region, such as adjusting the intensity of routine irrigation and slightly adjusting the opening ratio of greenhouse gas emission channels, to slowly optimize the micro-region environmental state;

[0158] Third-level low-priority observation ( ): Keep monitoring, do not conduct direct intervention, continue to collect data to observe the evolution trend, and only upgrade the response level when the trend deteriorates.

[0159] Among them, and are the response thresholds set by the intelligent regulation system. In the embodiments of the present invention, the first-level high-priority response threshold , and the second-level medium-priority response threshold can be adjusted according to the actual scenario, because is the risk index of all micro-regions normalized to , means that the instability risk of this micro-region has been in the highest 25% risk range among all micro-regions in the field, and rapid response is required to prevent the expansion of instability. At Within the range, it belongs to the medium environmental state and requires dynamic fine-tuning to prevent the aggravation of risk accumulation.

[0160] This dynamic hierarchical regulation mechanism based on the joint modeling of micro-region environmental perception factors can significantly improve the response sensitivity and regulation resource utilization efficiency of the field greenhouse gas emission management system in complex heterogeneous environments, ensure priority intervention in high-risk areas, save regulation resources in stable areas, and achieve the optimal operation of the overall system.

[0161] The present invention realizes the multi-dimensional joint perception of the abnormal accumulation of the micro-region environment and the dynamic evolution trend of the environment by introducing environmental stability perception factors and environmental evolution dynamic characteristic enhancement perception factors at the micro-region scale in the corn field, breaking through the technical bottleneck that the existing greenhouse gas regulation system relies on macroscopic average data and lacks dynamic micro-region perception ability.

[0162] First of all, the micro-region environmental stability perception factor proposed by the present invention can accurately quantify the degree of abnormal accumulation of the internal environment of the micro-region on the time interval scale, and combine the dynamic changes of soil moisture and greenhouse gas flux to realize the forward-looking identification of the slow-changing micro-region environmental abnormal process, significantly improving the system's early perception ability of local potential instability risks.

[0163] Secondly, by constructing a micro-region environmental evolution dynamic characteristic enhancement perception factor, the present invention system captures the trend energy density change, change rate drift accumulation and local fluctuation accumulation characteristics in the process of micro-region environmental change, and effectively identifies the hidden rebound type micro-region environmental evolution characteristics. Through the differential normalization mapping and natural fusion mechanism, the present invention avoids the dependence on traditional weight setting, ensures a high degree of correspondence between the perception result and the real physical process of environmental dynamic change, and enhances the universality and adaptability of the perception factor.

[0164] Furthermore, based on the joint modeling of the environmental stability perception factor and the micro-region environmental evolution dynamic characteristic enhancement perception factor, the present technical invention constructs a micro-region environmental instability risk priority assessment system and designs a dynamic hierarchical intelligent regulation response mechanism to realize the real-time hierarchical intervention optimization of the field micro-region. Compared with the existing fixed threshold trigger mechanism, the present invention can intelligently adjust the regulation timing and intervention intensity according to the actual dynamic evolution state of the micro-region environment, significantly improving the resource utilization efficiency, response timeliness and overall regulation effect of the greenhouse gas emission control system.

[0165] Example 2

[0166] A smart greenhouse gas regulating device for corn fields, as Figure 2 shown, comprising a field intelligent control box, a sensor device and an execution device, and the field intelligent control box communicates wirelessly with the sensor device and the execution device;

[0167] The field intelligent control box includes a data processing unit, a communication gateway, an energy module, and a user interaction interface. The energy module includes a solar panel and a lithium battery pack;

[0168] The sensor device includes a TDR or FDR type soil moisture sensor and a portable gas flux monitoring device. The portable gas flux monitoring device includes a sensor and a sensor;

[0169] The actuating device includes an intelligent irrigation valve, a micro air pump, a sunshade net, and a sunshade net motor. The intelligent irrigation valve includes an electromagnetic valve and a flow meter.

[0170] The algorithm logic of the data processing unit is the same as that in the method for intelligent regulation of greenhouse gases in corn fields in the above embodiments.

[0171] The data processing unit is used to receive the data monitored by the sensor device, and calculate the microzone environment regulation priority index and perform hierarchical regulation response on the microzone according to the monitored data;

[0172] The communication gateway is used for long-distance and low-power data transmission in the field;

[0173] The energy module is used to provide continuous power and adapt to the environment without grid coverage;

[0174] The user interaction interface is used to display the microzone risk map, regulation status, and historical data in real time;

[0175] The TDR or FDR type soil moisture sensor is deployed in layers at the depths of 0-10 cm and 10-30 cm of the soil in the corn field to detect soil moisture:

[0176] The sensor is used to monitor flux;

[0177] The sensor is used to monitor flux;

[0178] The portable gas flux monitoring device is used for and periodic scanning of flux.

[0179] The intelligent irrigation valve is used for moisture regulation in the microzone in the response logic;

[0180] The micro air pump is used to improve soil aeration in the microzone in the response logic;

[0181] The sunshade net motor is used to control the unfolding or contraction of the sunshade net, adjust the local light intensity and temperature in the response logic, and reduce the soil evaporation rate.

[0182] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent regulation method for greenhouse gases in corn fields, characterized in that, Including the following steps: Step S1: Conduct micro-zoning on the corn field, deploy environmental sensors in the divided micro-zones, collect soil moisture content and greenhouse gas flux indicators through the environmental sensors, and preprocess the collected data; Step S2: Extract the micro-region environmental stability perception factor based on the data preprocessed in Step S1 and the micro-region environmental evolution dynamic feature enhancement perception factor , and calculate the micro-region environmental regulation priority index according to the and ; ; Step S2.1: The micro-region environmental stability perception factor is obtained through the joint analysis of the dynamic abnormal accumulation characteristics of soil moisture and greenhouse gas concentration and the evolution trend of environmental resilience in the micro-region of the corn field; The micro-region environmental stability perception factor is calculated by the following formula: ； Among them, represents the micro-region environmental stability perception factor of the th micro-region in the time period , represents the cumulative anomaly assessment of the th micro-region in the time period , represents the number of time points in the time period , represents the environmental resilience collapse degree of the th micro-region at the moment ; Step S2.2: The enhanced perception factor for the dynamic characteristics of the micro-region environment evolution is obtained through mapping analysis of multiple characteristics of the dynamic evolution of the micro-region environment; The enhanced perception factor for the dynamic characteristics of the micro-region environmental evolution It is calculated by the following formula: ； Among them, represents the enhanced perception factor of the environmental evolution dynamic characteristics of the th micro-region during the time period , represents the overall trend energy density of the th micro-region during the time period , represents the cumulative degree of slope drift of the th micro-region during the time period , represents the cumulative evaluation of local minor perturbations of the th micro-region during the time period . Step S2.3: The priority index for micro-region environment regulation is calculated by the following formula: ； Among them, represents the micro-region environmental regulation priority index of the th micro-region in the time period . represents the micro-region environmental stability perception factor of the th micro-region in the time period . represents the enhanced perception factor of the environmental evolution dynamic characteristics of the th micro-region in the time period . Step S3: Based on the micro-region environment regulation priority index in Step S2 Perform hierarchical regulation response on the micro-region.

2. The intelligent greenhouse gas regulation method for corn fields according to claim 1, wherein: In the above step S2.1 is calculated by the following formula: ； Among them, represents the cumulative anomaly assessment of the th micro-region in the time period . represents the time weight parameter at the moment, which is set according to the different sensitivities of different growth stages of corn to environmental anomalies. represents the soil moisture change rate of the th micro-region at the moment. represents the greenhouse gas concentration change rate of the th micro-region at the moment. represents the anomaly amplification index.

3. The intelligent greenhouse gas regulation method for corn fields according to claim 1, wherein: In the step S2.1, is calculated by the following formula: ； Among them, represents the environmental resilience collapse degree of the th micro-region at the moment. represents the first-order delayed autocorrelation coefficient of the soil moisture change rate of the th micro-region at the moment. represents the first-order delayed autocorrelation coefficient of the greenhouse gas concentration change rate of the th micro-region at the moment. represents the disturbance event weight function at the moment. When there are human disturbance operations such as irrigation and fertilization in the window, the disturbance weight increases, reflecting the enhancement of the impact of management operations on soil environmental resilience.

4. The intelligent greenhouse gas regulation method for corn fields according to claim 1, wherein: In the step S2.2 is calculated by the following formula: ； Among them, represents the overall trend energy density of the th micro-region in the time period ; represents the number of sub-intervals with length in the time period ; represents the micro-region environmental stability perception factor of the th micro-region in the time period ; represents a very small positive number to prevent the denominator from being zero.

5. The intelligent greenhouse gas regulation method for corn fields according to claim 1, wherein: In the step S2.2 is calculated by the following formula: ； Among them, represents the cumulative degree of slope drift of the th micro-region in the time period ; represents the number of sub-intervals of length in the time period ; represents the change amount of the th micro-region in the th sub-interval.

6. The intelligent greenhouse gas regulation method for corn fields according to claim 1, wherein: In the said step S2.2 is calculated by the following formula: ； Among them, represents the cumulative evaluation of the local micro-perturbation of the th micro-region in the time period ; represents the number of sub-intervals of length in the time period ; represents the change amount of the th micro-region in the th sub-interval. The average value of the absolute value of the local change amount per unit time reflects the activity level of the local dynamic activity. If the overall environment is stable and the local fluctuation is small, then is relatively low; if the local perturbation is frequent and the accumulated energy is large, then increases.

7. The intelligent greenhouse gas regulation method for corn fields according to claim 1, wherein: The hierarchical regulation response of step S3 includes: Based on the priority index of micro-region environment regulation , define the priority of micro-region intelligent regulation response , so as to achieve dynamic sorting and hierarchical response to the micro-regions in the whole field: ； Among them, represents the intelligent regulation response priority of the th micro-region in the time period ; represents the micro-region environment regulation priority index of the th micro-region in the time period , that is, the comprehensive instability risk index of the th micro-region; the denominator is the highest instability risk index among all micro-regions at the current moment, which is used for normalization; According to the response priority of micro-region intelligent regulation , the following response logic is proposed: First-level high-priority response ( ): Immediately initiate a local rapid response strategy, including encrypted micro-irrigation, increased local soil aeration, and enhanced local shading and cooling treatments, to quickly suppress the instability expansion of the micro-environment; Secondary medium-priority response ( ): Conduct micro-region conventional regulation and adjustment, adjust the conventional irrigation intensity, slightly adjust the opening ratio of greenhouse gas emission channels, and slowly optimize the micro-region environmental state; Third-level low-priority observation ( ): Keep monitoring, do not conduct direct intervention, continue to collect data to observe the evolution trend, and only upgrade the response level when the trend deteriorates.

8. An intelligent greenhouse gas regulation device for corn fields, characterized in that: It includes a field intelligent control box, a sensor device and an execution device, and the field intelligent control box communicates wirelessly with the sensor device and the execution device; The field intelligent control box includes a data processing unit, a communication gateway, an energy module and a user interface, and the energy module includes a solar panel and a lithium battery pack; The sensor device includes a TDR or FDR type soil moisture sensor and a portable gas flux monitoring device, and the portable gas flux monitoring device includes a sensor and a sensor; The execution device includes an intelligent irrigation valve, a micro air pump, a sunshade net and a sunshade net motor, and the intelligent irrigation valve includes a solenoid valve and a flow meter; The algorithm logic of the data processing unit is consistent with the method described in any one of claims 1-7.

9. The intelligent greenhouse gas regulation device for corn fields according to claim 8, wherein: The data processing unit is used to receive the data monitored by the sensor device, and calculate the micro-zone environmental regulation priority index and perform hierarchical regulation response on the micro-zones according to the monitored data; The communication gateway is used for long-distance and low-power data transmission in the field; The energy module is used to provide continuous power and adapt to the environment without grid coverage; The user interface is used to display the micro-zone risk map, regulation status and historical data in real time; The TDR or FDR type soil moisture sensor is deployed in layers at the depths of 0-10 cm and 10-30 cm of the corn field soil to detect soil moisture: The sensor is used to monitor flux; The said sensor is used to monitor flux; The portable gas flux monitoring device is used for and periodic scanning of the flux.

10. The intelligent greenhouse gas regulation device for corn fields according to claim 8, wherein: The intelligent irrigation valve is used for water regulation in the micro-zone in the response logic; The micro air pump is used to improve soil ventilation in the micro-zone in the response logic; The sunshade net motor is used to control the deployment or contraction of the sunshade net, adjust the local light intensity and temperature in the response logic, and reduce the soil evaporation rate.

Images