An agricultural resource carrying capacity evaluation and early warning system

Abstract

The application relates to the technical field of intelligent early warning, and relates to an agricultural resource carrying capacity evaluation and early warning system. The system comprises a data acquisition module, a resource index module, a dynamic coupling calibration module, a carrying grade acquisition module, an early warning and prediction module and an early warning module. The system carries out standardization processing on multi-source agricultural basic data of a target region in an evaluation period to obtain standardized data. The system carries out weighted summation on index values of a resource pressure sub-platform to obtain resource pressure values, and simultaneously carries out weighted summation on index values of a resource state-response composite sub-platform to obtain response composite values. The system determines a dynamic coupling coordination degree. The system couples multi-dimensional index values in the standardized data to obtain an agricultural resource carrying capacity grade. The system carries out early warning triggering prediction on the target region to obtain an early warning triggering probability. When the early warning triggering probability exceeds a preset interval, early warning information of the target region is generated. The application can improve the evaluation and early warning efficiency of the agricultural resource carrying capacity.

Description

Technical Field

[0001] This invention relates to the field of intelligent early warning technology, and in particular to an agricultural resource carrying capacity assessment and early warning system. Background Technology

[0002] Current agricultural resource carrying capacity assessment processes lack standardized data processing procedures and have insufficient capacity for integrating and organizing multi-source agricultural basic data, resulting in inconsistent data quality and difficulty in accurately supporting subsequent indicator calculations and level assessments. Furthermore, traditional assessment methods do not fully consider the dynamic relationship between resource pressure and state-response, and the fixed allocation of indicator weights cannot adapt to changes in data characteristics across different assessment periods. This leads to discrepancies between the assessment results and the actual agricultural resource carrying capacity, making it difficult to objectively reflect the true carrying capacity level of regional agricultural resources.

[0003] In the early warning and forecasting stage, existing technologies mostly rely on single-dimensional carrying capacity level data, failing to delve into historical level transition patterns and lacking scientific quantitative models and dynamic considerations over time for calculating the probability of early warning triggering. This results in insufficient timeliness and accuracy in generating early warning information, making it impossible to effectively predict agricultural resource carrying capacity risks in advance, and hindering reliable decision support for agricultural production planning and rational resource allocation, thereby affecting the efficiency of promoting sustainable agricultural development. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides an agricultural resource carrying capacity assessment and early warning system, characterized in that the system includes a data acquisition module, a resource index module, a dynamic coupling calibration module, a carrying capacity level acquisition module, an early warning prediction module, and an early warning module, wherein:

[0005] The data acquisition module is used to standardize the multi-source agricultural basic data of the target area within the evaluation period to obtain standardized data of the target area.

[0006] The resource index module is used to perform weighted summation of the index values ​​of the resource pressure sub-platform based on the degree of dispersion of different dimensions in the standardized data to obtain the resource pressure value of the resource pressure sub-platform, and at the same time, to perform weighted summation of the index values ​​of the resource status-response composite sub-platform to obtain the response composite value of the resource status-response composite sub-platform.

[0007] The dynamic coupling calibration module is used to determine the dynamic coupling coordination degree between the resource pressure sub-platform and the resource state-response composite sub-platform based on the interaction strength between the resource pressure value and the response composite value.

[0008] The carrying capacity level acquisition module is used to couple the multi-dimensional indicator values ​​in the standardized data according to the dynamic coupling coordination degree to obtain the agricultural resource carrying capacity level of the target area.

[0009] The early warning prediction module is used to predict the early warning trigger probability of the target area based on the transfer pattern of the agricultural resource carrying capacity level and the historical carrying capacity level.

[0010] The early warning module is used to generate early warning information for the target area when the early warning trigger probability exceeds a preset range.

[0011] In a preferred embodiment, when the data acquisition module performs standardization processing on multi-source agricultural basic data of the target area within the evaluation period to obtain standardized data of the target area, it is specifically used for:

[0012] Acquire meteorological data, soil data, water resource utilization data, and agricultural production input-output data for the target area during the assessment period;

[0013] Outlier removal and missing value filling are performed on the meteorological data, soil data, water resource utilization data, and agricultural production input-output data to obtain a standard dataset for the target area.

[0014] In a preferred embodiment, when the resource indicator module performs a weighted summation of the indicator values ​​of the resource pressure sub-platform based on the degree of dispersion of different dimensions in the standardized data to obtain the resource pressure value of the resource pressure sub-platform, it is specifically used for:

[0015] Based on the fluctuation range of each indicator in the resource pressure sub-platform within the historical evaluation period, the dispersion characteristics of the indicator are generated.

[0016] Based on the dispersion characteristics, corresponding contribution weights are assigned to the indicators to obtain the resource pressure indicator weight set of the resource pressure sub-platform;

[0017] The resource pressure indicators within the current assessment period from the standardized data are used as the current indicator values;

[0018] Based on the weights in the resource pressure indicator weight set, the current indicator value is weighted and fused to obtain the resource pressure value of the resource pressure sub-platform.

[0019] In a preferred embodiment, when the resource index module performs a weighted summation of the index values ​​of the resource status-response composite sub-platform to obtain the composite response value of the resource status-response composite sub-platform, it is specifically used for:

[0020] From the standardized data, extract the indicator values ​​belonging to the resource status category and the indicator values ​​belonging to the system response category to obtain the initial set of composite indicator values ​​for the resource status-response composite sub-platform.

[0021] The interaction relationship between resource status indicators and system response indicators in the initial set of composite indicators is used as the association feature of the resource status-response composite sub-platform.

[0022] Based on the correlation characteristics, corresponding weights are assigned to the indicators in the initial value set of the composite indicators to obtain the composite indicator weight set of the resource status-response composite sub-platform.

[0023] Using the weight set of the composite indicators, the initial value set of the composite indicators in the current evaluation period is weighted and fused to obtain the composite response value of the resource status-response composite sub-platform.

[0024] In a preferred embodiment, when the dynamic coupling calibration module determines the dynamic coupling coordination degree between the resource pressure sub-platform and the resource state-response composite sub-platform based on the interaction strength of the resource pressure value and the response composite value, it is specifically used for:

[0025] Based on the change trajectory of the resource pressure value and the response composite value in a continuous time series, the traction or constraint relationship between the resource pressure value and the response composite value is identified, and the interaction relationship characteristics between the resource pressure value and the response composite value are obtained.

[0026] Based on the aforementioned interaction characteristics, a coordination analysis model is constructed between the resource pressure sub-platform and the resource status-response composite sub-platform.

[0027] The resource pressure value and the response composite value are input into the coordination analysis model to calculate the dynamic coupling coordination degree between the resource pressure sub-platform and the resource status-response composite sub-platform.

[0028] In a preferred embodiment, when the dynamic coupling calibration module executes the coordination analysis model for constructing the resource pressure sub-platform and the resource status-response composite sub-platform based on the interaction relationship characteristics, it is specifically used for:

[0029] Based on the interaction characteristics, the dominant-subordinate relationship between the resource pressure value and the response composite value is determined, and the core quantitative direction of the coordination analysis model is obtained.

[0030] Based on the aforementioned core quantitative direction, a method for measuring the gap between the development of the resource pressure sub-platform and the resource status-response composite sub-platform is defined.

[0031] Based on the constraint or traction strength identified in the gap measurement method and the interaction relationship characteristics, configure the internal evaluation mechanism of the coordination analysis model;

[0032] The gap measurement method and the internal evaluation mechanism are integrated to generate the coordination analysis model.

[0033] In a preferred embodiment, the formula for calculating the dynamic coupling coordination degree is as follows:

[0034] ;

[0035] In the formula, The dynamic coupling coordination degree, This is a dynamic attenuation factor determined based on the changing trend of the resource pressure value over a continuous assessment period. The resource pressure value for the current assessment period. The composite value of the response for the current evaluation period. For adjustment coefficients, The weight of the resource pressure sub-platform in the development level. The weight of the resource status-response composite sub-platform in the development level.

[0036] In a preferred embodiment, when the carrying capacity level acquisition module performs the coupling of multi-dimensional indicator values ​​in the standardized data according to the dynamic coupling coordination degree to obtain the agricultural resource carrying capacity level of the target area, it is specifically used for:

[0037] From the standardized data, the key status indicator values ​​of the target area are selected;

[0038] Based on the quantified value of the dynamic coupling coordination degree, each index value in the key state index value is adjusted for coordination state compensation to generate a corrected set of key index values.

[0039] The values ​​of each item in the modified set of key indicator values ​​are aggregated to obtain the comprehensive evaluation value of the target area.

[0040] The comprehensive evaluation value is matched with a preset level threshold range to determine the agricultural resource carrying capacity level of the target area.

[0041] In a preferred embodiment, when the early warning prediction module performs early warning trigger prediction on the target area based on the transfer patterns of the agricultural resource carrying capacity level and historical carrying capacity level, and obtains the early warning trigger probability of the target area, it is specifically used for:

[0042] Based on the time series of the agricultural resource carrying capacity levels within the historical assessment period, the frequency of transitions from each level to other levels is statistically analyzed to obtain the level transition frequency matrix of the target area within the historical assessment period.

[0043] The state transition frequency matrix is ​​normalized to obtain the state transition probability matrix of the target area within the historical evaluation period.

[0044] From the state transition probability matrix, the probability of transitioning from the current level state to all worse level states is extracted to obtain the risk transition probability set of the target area within the current assessment period;

[0045] The basic early warning probability of the target area within the historical assessment period is obtained by summing all the probability values ​​in the risk transfer probability set.

[0046] The early warning trigger probability of the target area is calculated based on the basic early warning probability.

[0047] In a preferred embodiment, the formula for calculating the early warning trigger probability is as follows:

[0048] ;

[0049] In the formula, The probability of triggering the warning is given. The aforementioned basic early warning probability, It is a natural constant. The preset time-related factors, The number of consecutive evaluation cycles that the current level status has been maintained.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. This invention effectively ensures the stability and reliability of data quality by standardizing multi-source agricultural basic data. At the same time, it dynamically allocates weights based on the dispersion and correlation characteristics of indicators, and calculates the dynamic coupling coordination degree by combining the interaction strength between resource pressure and state-response. This significantly improves the scientificity and accuracy of agricultural resource carrying capacity assessment, and can comprehensively and objectively present the actual carrying capacity of agricultural resources in the target area.

[0052] 2. The system of this invention constructs a state transition probability matrix based on the historical carrying capacity level transfer pattern, and incorporates time-dimensional influencing factors to quantify the early warning trigger probability, making the early warning prediction more dynamic and quantitatively supported. It can accurately capture agricultural resource carrying capacity risks in advance, generate targeted early warning information in a timely manner, provide strong decision support for optimizing agricultural production layout and efficient resource allocation, and help improve agricultural resource utilization efficiency and sustainable development capabilities. Attached Figure Description

[0053] Figure 1 A system architecture diagram of an agricultural resource carrying capacity assessment and early warning system provided in an embodiment of the present invention;

[0054] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0057] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0058] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0059] In practice, the server-side equipment deployed in an agricultural resource carrying capacity assessment and early warning system may consist of one or more devices. This system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node, providing an agricultural resource carrying capacity assessment and early warning system to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage various user terminals. Or, it can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more devices configured to provide an agricultural resource carrying capacity assessment and early warning system to various user terminals.

[0060] In terms of implementation, the agricultural resource carrying capacity assessment and early warning system and the user terminal are mutually compatible. That is, if the agricultural resource carrying capacity assessment and early warning system is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the agricultural resource carrying capacity assessment and early warning system is implemented as a website, then the user terminal is implemented as a webpage; or if the agricultural resource carrying capacity assessment and early warning system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0061] like Figure 1 The diagram shown is a system architecture diagram of an agricultural resource carrying capacity assessment and early warning system provided in an embodiment of the present invention.

[0062] The agricultural resource carrying capacity assessment and early warning system 100 described in this invention can be set up in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the agricultural resource carrying capacity assessment and early warning system 100 may include a data acquisition module 101, a resource index module 102, a dynamic coupling calibration module 103, a carrying capacity level acquisition module 104, an early warning prediction module 105, and an early warning module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0063] In this embodiment of the invention, in an agricultural resource carrying capacity assessment and early warning system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the agricultural resource carrying capacity assessment and early warning system provided by this embodiment of the invention, without modifying the program code, the applicability of the agricultural resource carrying capacity assessment and early warning system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the agricultural resource carrying capacity assessment and early warning system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0064] The following describes, with reference to specific embodiments, each component and its specific workflow of an agricultural resource carrying capacity assessment and early warning system:

[0065] The data acquisition module 101 is used to standardize the multi-source agricultural basic data of the target area within the evaluation period to obtain standardized data of the target area.

[0066] In this embodiment of the invention, when the data acquisition module performs standardization processing on multi-source agricultural basic data of the target area within the evaluation period to obtain standardized data of the target area, it is specifically used for:

[0067] Acquire meteorological data, soil data, water resource utilization data, and agricultural production input-output data for the target area during the assessment period;

[0068] Outlier removal and missing value filling are performed on the meteorological data, soil data, water resource utilization data, and agricultural production input-output data to obtain a standard dataset for the target area.

[0069] The data acquisition module collects hourly temperature, precipitation, sunshine duration, wind speed, and wind direction data within the assessment period through automatic weather stations deployed within the target area. Simultaneously, it retrieves supplementary gridded meteorological data released by the regional meteorological department, covering meteorological information for all plots within the target area. Soil sampling points are deployed in a 500m x 500m grid within the target area. At each sampling point, a stratified sampling method is used to collect soil samples from the 0-20cm topsoil layer. Soil pH, organic matter content, available nitrogen, phosphorus, and potassium content, and soil moisture content are measured. The geographical location information of each sampling point is recorded, forming the original soil data record. The operation of all irrigation facilities within the target area is statistically analyzed. Records are kept, including irrigation time, irrigation volume, and irrigation method. At the same time, surface water and groundwater level monitoring data and agricultural water withdrawal permit records are collected in the area. These are compiled into raw water resource utilization data. By visiting agricultural production entities in the target area one by one, the types and amounts of seeds, fertilizers, pesticides, and agricultural films used during the assessment period are recorded, as well as the duration and frequency of agricultural machinery operations, and the planting area, harvest yield, and sales price of crops. At the same time, the production ledgers of agricultural production entities are checked to ensure the accuracy and completeness of input and output data. In this way, meteorological data, soil data, water resource utilization data, and agricultural production input and output data of the target area during the assessment period are obtained.

[0070] The data acquisition module identifies meteorological data as outliers, distinguishing those exceeding the historical extreme values ​​for the same period in the region. For example, data showing temperatures exceeding the historical highest temperature by more than 5°C or the historical lowest temperature by less than 5°C during the assessment period are directly discarded. For soil data, data showing test results exceeding the reasonable range of conventional soil indicators are identified as outliers, such as soil pH values ​​less than 3 or greater than 9. For water resource utilization data, data showing a single irrigation volume exceeding three times the conventional irrigation quota for similar crops in the region are identified as outliers and directly discarded. For agricultural production input-output data, data showing fertilizer usage per acre exceeding twice the recommended usage for similar crops in the region are identified as outliers and directly discarded. After outlier removal is completed... For missing values ​​in meteorological data, the arithmetic mean of similar meteorological data from three adjacent meteorological stations during the same period is used for imputation. For missing values ​​in soil data, the arithmetic mean of similar soil index data from three adjacent sampling points within the same grid is used for imputation. For missing values ​​in water resource utilization data, the average irrigation water volume of similar irrigation facilities during the same period is used for imputation. For missing values ​​in agricultural production input-output data, the arithmetic mean of similar input-output data from other agricultural production entities with the same planting scale and crop type during the same period is used for imputation. Finally, the processed meteorological data, soil data, water resource utilization data, and agricultural production input-output data are integrated according to a unified geographic coding and time dimension to obtain the standard dataset for the target area.

[0071] The beneficial effects are that by standardizing the acquisition of meteorological, soil, water resource utilization, and agricultural production input-output data within the target area assessment period, outliers in various data are accurately removed, and missing data are filled in using scientific and reasonable methods. The resulting standard dataset is comprehensive, accurate, and consistent, providing stable and reliable basic data support for subsequent agricultural-related assessments in the target area.

[0072] The resource index module 102 is used to perform weighted summation of the index values ​​of the resource pressure sub-platform based on the degree of dispersion of different dimensions in the standardized data to obtain the resource pressure value of the resource pressure sub-platform, and at the same time, to perform weighted summation of the index values ​​of the resource status-response composite sub-platform to obtain the response composite value of the resource status-response composite sub-platform.

[0073] In this embodiment of the invention, when the resource indicator module performs a weighted summation of the indicator values ​​of the resource pressure sub-platform based on the degree of dispersion of different dimensions in the standardized data to obtain the resource pressure value of the resource pressure sub-platform, it is specifically used for:

[0074] Based on the fluctuation range of each indicator in the resource pressure sub-platform within the historical evaluation period, the dispersion characteristics of the indicator are generated.

[0075] Based on the dispersion characteristics, corresponding contribution weights are assigned to the indicators to obtain the resource pressure indicator weight set of the resource pressure sub-platform;

[0076] The resource pressure indicators within the current assessment period from the standardized data are used as the current indicator values;

[0077] Based on the weights in the resource pressure indicator weight set, the current indicator value is weighted and fused to obtain the resource pressure value of the resource pressure sub-platform.

[0078] When the resource indicator module performs a weighted summation of the indicator values ​​of the resource status-response composite sub-platform to obtain the composite response value of the resource status-response composite sub-platform, it is specifically used for:

[0079] From the standardized data, extract the indicator values ​​belonging to the resource status category and the indicator values ​​belonging to the system response category to obtain the initial set of composite indicator values ​​for the resource status-response composite sub-platform.

[0080] The interaction relationship between resource status indicators and system response indicators in the initial set of composite indicators is used as the association feature of the resource status-response composite sub-platform.

[0081] Based on the correlation characteristics, corresponding weights are assigned to the indicators in the initial value set of the composite indicators to obtain the composite indicator weight set of the resource status-response composite sub-platform.

[0082] Using the weight set of the composite indicators, the initial value set of the composite indicators in the current evaluation period is weighted and fused to obtain the composite response value of the resource status-response composite sub-platform.

[0083] The resource indicator module retrieves the indicator values ​​of each indicator in the resource pressure sub-platform across all historical evaluation periods. It compares the maximum and minimum values ​​of each indicator within a single historical evaluation period to determine the range of value variation for that indicator within that period. It then calculates the overall coverage of this range across all historical evaluation periods; this overall coverage represents the fluctuation range of the corresponding indicator. Based on the magnitude of the fluctuation range, the indicator's dispersion characteristic is defined: a larger fluctuation range indicates a more significant dispersion characteristic, while a smaller fluctuation range indicates a smoother dispersion characteristic. The resource indicator module uses this dispersion characteristic as the sole basis for allocating indicator contribution weights. Indicators with more significant dispersion characteristics represent a higher degree of influence on resource pressure changes and are assigned higher contribution weights; conversely, indicators with smoother dispersion characteristics represent a lower degree of influence on resource pressure changes and are assigned lower contribution weights. Specific contribution weight values ​​are assigned to each indicator in the resource pressure sub-platform according to this correspondence. Finally, the contribution weight values ​​of all indicators are aggregated and integrated to obtain the resource pressure indicator weight set of the resource pressure sub-platform. The resource indicator module extracts all data from the standardized data within the current assessment period, filters out relevant data that corresponds one-to-one with each indicator in the resource pressure sub-platform, and directly determines each filtered data item as the specific value of the corresponding resource pressure indicator within the current assessment period. All specific values ​​of resource pressure indicators within the current assessment period are summarized as the current indicator value. The resource indicator module matches each specific value in the current indicator value with its corresponding contribution weight in the resource pressure indicator weight set, integrates and calculates each current indicator value with its corresponding contribution weight, and sums the results of all integrated calculations. The summed result is the resource pressure value of the resource pressure sub-platform.

[0084] The resource indicator module retrieves standardized agricultural basic data from the target area and clarifies the criteria for classifying resource status indicators and system response indicators. Resource status indicators include soil fertility indicators, water resource stock indicators, meteorological suitability indicators, and land use saturation indicators. System response indicators include crop growth status indicators, pest and disease occurrence indicators, agricultural production input efficiency indicators, and agricultural product yield stability indicators. According to this classification criteria, the data items in the standardized data are screened one by one. All indicator values ​​belonging to the resource status category and all indicator values ​​belonging to the system response category are summarized and organized to form a set containing all values ​​of both types of indicators, thus obtaining the initial set of composite indicator values ​​for the resource status-response composite sub-platform.

[0085] The resource indicator module performs correlation analysis on resource status indicators and system response indicators in the initial value set of composite indicators. It systematically analyzes the specific impact of changes in each resource status indicator on system response indicators, recording the interaction between all two types of indicators, such as the relationship between improved soil fertility indicators and improved crop growth status indicators, the relationship between decreased water resource inventory indicators and decreased agricultural product yield stability indicators, and the relationship between optimized meteorological suitability indicators and improved agricultural production input efficiency indicators. At the same time, it clarifies the degree of interaction between different indicators and takes these specific interaction relationships and degree of interaction as a whole to determine the correlation characteristics of the resource status-response composite sub-platform.

[0086] The resource indicator module uses correlation features as the core basis for indicator weight allocation. For each indicator in the initial value set of composite indicators, it determines the degree of interaction between the indicator and the corresponding category indicator in the correlation features. The closer the interaction, the higher the influence of the indicator on the resource status-response composite situation, and the higher the weight is assigned to it. The weaker the interaction, the lower the influence of the indicator on the resource status-response composite situation, and the lower the weight is assigned to it. According to this rule, all indicators in the initial value set of composite indicators are assigned corresponding specific weight values ​​one by one. The weight values ​​of all indicators are summarized and integrated to obtain the composite indicator weight set of the resource status-response composite sub-platform.

[0087] The resource indicator module matches each indicator value in the initial set of composite indicators within the current evaluation period with the corresponding indicator weight in the set of composite indicator weights. It integrates each indicator value with its corresponding weight, and then sums up all the integrated indicator results. The final result after summing up is the response composite value of the resource status-response composite sub-platform.

[0088] The beneficial effects are that the dispersion features generated based on the historical index fluctuation range are used to allocate contribution weights, ensuring the rationality and pertinence of the weight allocation. By extracting the corresponding data from the standardized data as the current index value and combining it with the weights for weighted fusion, the resource pressure value is obtained, which improves the accuracy and reliability of the resource pressure value calculation and provides scientific and effective data support for resource pressure assessment.

[0089] The system accurately extracts resource status and system response index values ​​to form a composite index initial value set. By analyzing the interaction between the two types of indicators, the system identifies the correlation characteristics. Based on the correlation characteristics, the system assigns index weights to form a composite index weight set. The initial values ​​are then weighted and fused together to obtain the response composite value. This ensures the rationality and accuracy of the response composite value calculation and provides reliable data support for the assessment of resource status response composite conditions.

[0090] The dynamic coupling calibration module 103 is used to determine the dynamic coupling coordination degree between the resource pressure sub-platform and the resource state-response composite sub-platform based on the interaction strength between the resource pressure value and the response composite value.

[0091] In this embodiment of the invention, when the dynamic coupling calibration module determines the dynamic coupling coordination degree between the resource pressure sub-platform and the resource state-response composite sub-platform based on the interaction strength of the resource pressure value and the response composite value, it is specifically used for:

[0092] Based on the change trajectory of the resource pressure value and the response composite value in a continuous time series, the traction or constraint relationship between the resource pressure value and the response composite value is identified, and the interaction relationship characteristics between the resource pressure value and the response composite value are obtained.

[0093] Based on the aforementioned interaction characteristics, a coordination analysis model is constructed between the resource pressure sub-platform and the resource status-response composite sub-platform.

[0094] The resource pressure value and the response composite value are input into the coordination analysis model to calculate the dynamic coupling coordination degree between the resource pressure sub-platform and the resource status-response composite sub-platform.

[0095] The formula for calculating the dynamic coupling coordination degree is as follows:

[0096] ;

[0097] In the formula, The dynamic coupling coordination degree, This is a dynamic attenuation factor determined based on the changing trend of the resource pressure value over a continuous assessment period. The resource pressure value for the current assessment period. The composite value of the response for the current evaluation period. For adjustment coefficients, The weight of the resource pressure sub-platform in the development level. The weight of the resource status-response composite sub-platform in the development level.

[0098] The dynamic decay factor is a value determined based on the changing trend of resource pressure values ​​over a continuous assessment period. The resource pressure value for the current assessment period is taken from the statistical or calculation results related to the corresponding resource pressure within the current assessment period. The response composite value for the current assessment period is taken from the statistical or calculation results related to the corresponding resource status-response composite within the current assessment period. The adjustment coefficient is a set value used to adjust the relevant numerical relationships during the calculation process. The weight of the resource pressure sub-platform in the development level is a set value representing the proportion of the resource pressure sub-platform in the overall development level. The weight of the resource status-response composite sub-platform in the development level is a set value representing the proportion of the resource status-response composite sub-platform in the overall development level.

[0099] The dynamic coupling coordination degree is a numerical result obtained by integrating and calculating various corresponding defined and set values. By combining the resource pressure-related results and response composite-related results of the current assessment period, and introducing a defined dynamic attenuation factor, a set adjustment coefficient, and the weights of the two sub-platforms, the calculation is carried out to quantitatively characterize the degree of dynamic coupling coordination between resource pressure and response composite. This quantitative characterization result can reflect the coupling coordination between the resource pressure sub-platform and the resource state-response composite sub-platform at the development level. The introduction of the dynamic attenuation factor can combine the changing trend of resource pressure values ​​in continuous assessment periods, making the final coupling coordination degree more closely reflect the actual dynamic change process.

[0100] The dynamic coupling calibration module first defines the scope of the continuous time series, which covers the current assessment period and several previous consecutive historical assessment periods. It retrieves the calculated resource pressure values ​​and response composite values ​​from all these periods and organizes them chronologically for each time point, forming two parallel continuous change trajectories: one for resource pressure values ​​changing over time, and the other for response composite values. The changing trends of the two trajectories are then compared and analyzed synchronously. When the resource pressure value increases or decreases, it is observed whether the corresponding response composite value changes in the same direction. If they change in the same direction, a traction relationship is determined, meaning the former's change tractions the latter's change in the same direction; if they change in opposite directions, a constraint relationship is determined, meaning the former's change constrains the latter's trend. Simultaneously, the time point of the traction or constraint relationship, its duration, and the degree of correlation between the magnitudes of change are recorded. These identified relationship types, occurrence sequences, durations, and magnitude correlation information are summarized and integrated to obtain the interaction characteristics between the resource pressure value and the response composite value. The dynamic coupling calibration module takes the interaction relationship characteristics as the core basis, and first transforms the traction / constraint type, action sequence, duration, and magnitude correlation degree in the interaction relationship characteristics into the core dimensions of coordination analysis, clarifying the core role of each dimension in the coupling coordination judgment.

[0101] The collaborative operation logic of the resource pressure sub-platform and the resource status-response composite sub-platform maps the traction relationship to collaborative promotion logic and the constraint relationship to conflict-balancing logic. Simultaneously, it transforms the duration and magnitude of the effects into weighted influencing factors for logical judgment. The basic structure of the model is then constructed, comprising an input layer, an analysis layer, and an output layer. The input layer receives resource pressure values ​​and response composite values; the analysis layer embeds the aforementioned core analysis logic; and the output layer outputs the coupling coordination degree results. By integrating the core analysis dimensions, logical rules, and basic structure, a coordinated analysis model of the resource pressure sub-platform and the resource status-response composite sub-platform is constructed. The dynamic coupling calibration module first performs a consistency check on the currently calculated resource pressure value and response composite value, confirming that the evaluation periods corresponding to the two values ​​are consistent and that the data sources are standardized data derived results from the same target region, ensuring the matching and validity of the input data.

[0102] The verified resource pressure value and response composite value are imported into the input layer of the coordination analysis model. The input layer synchronously transmits the data to the analysis layer. The analysis layer invokes preset core analysis logic and, combined with the determined interaction relationship characteristics, decomposes and analyzes the degree of coordinated change and conflict balance of the two values ​​in the continuous time series layer by layer to determine the overall coupling status of the two in the current and historical continuous periods. After the analysis is completed, the analysis results are transmitted to the output layer. The output layer generates a specific result that characterizes the degree of coordination between the two sub-platforms based on the coupling status judgment result of the analysis layer. This result is the dynamic coupling coordination degree of the resource pressure sub-platform and the resource state-response composite sub-platform.

[0103] The dynamic coupling calibration module first retrieves the identified interaction relationship features, extracting core information such as the type of traction / constraint relationship, change sequence, and magnitude correlation between the resource pressure value and the response composite value. By comparing the order of change and the direction of influence transmission of the two in a continuous time series, the dominant-subordinate relationship is determined. Specifically, when the change in the resource pressure value occurs before the change in the response composite value, and the magnitude of the change in the resource pressure value has a decisive influence on the magnitude of the change in the response composite value, the resource pressure value is determined to be the dominant party and the response composite value to be the subordinate party; when the change in the response composite value occurs before the change in the resource pressure value, and the magnitude of the change in the response composite value dominates the trend of the change in the resource pressure value, the response composite value is determined to be the dominant party and the resource pressure value to be the subordinate party.

[0104] The dominant-subordinate relationship identified above is defined as the core quantitative direction of the coordination analysis model, thus obtaining the core quantitative direction of the coordination analysis model. Based on the determined core quantitative direction of the coordination analysis model, and using the changing trend and development level of the dominant party's indicator values ​​as the benchmark, a gap measurement method is defined.

[0105] If the core quantification direction is dominated by resource pressure value and followed by response composite value, then the gap measurement method is set to compare the difference between the response composite value and the adapted value under the dominant trend of resource pressure value at the same time point. If the core quantification direction is dominated by response composite value and followed by resource pressure value, then the gap measurement method is set to compare the difference between the resource pressure value and the adapted value under the dominant trend of response composite value at the same time point. This method accurately measures the gap between the development of the resource pressure sub-platform and the resource status-response composite sub-platform, resulting in a gap measurement method for measuring the development gap between the two. First, information related to the constraint or traction strength is extracted from the interaction relationship characteristics. This strength information is determined by the correlation between the magnitude of change and the duration of the effect. The closer the correlation between the magnitude of change and the longer the duration of the effect, the higher the corresponding constraint or traction strength.

[0106] Based on the defined gap measurement methods, an internal evaluation mechanism for the coordination analysis model is configured. Specifically, the constraint or traction intensity is divided into different levels, and a corresponding gap evaluation standard is matched for each level. After the development gap is obtained through the gap measurement method, the internal evaluation mechanism judges whether the gap meets the coordination requirements according to the corresponding constraint or traction intensity level and the matched evaluation standard. The evaluation process is defined as follows: first, input the gap data and the corresponding constraint / traction intensity level; then, complete the judgment according to the evaluation standard; and finally, output the evaluation result. This completes the configuration of the internal evaluation mechanism for the coordination analysis model. The dynamic coupling calibration module first builds the basic framework of the coordination analysis model. This framework includes a data input layer, an evaluation calculation layer, and a result output layer. The data input layer is used to receive resource pressure values ​​and response composite values; the evaluation calculation layer is used to perform gap measurement and internal evaluation; and the result output layer is used to output the coordination analysis results.

[0107] The defined gap measurement method is embedded into the gap analysis stage of the evaluation calculation layer, and the configured internal evaluation mechanism is embedded into the core judgment stage of the evaluation calculation layer. At the same time, data flow connections are established between the data input layer and the evaluation calculation layer, and between the evaluation calculation layer and the result output layer to ensure that the data can flow smoothly according to the logic of "input-gap measurement-internal evaluation-output". Through the above integration process, the coordination analysis model is generated.

[0108] The beneficial effects are that by identifying the interaction characteristics between resource pressure values ​​and response composite values ​​through continuous time series trajectories, the accuracy and comprehensiveness of relationship identification are ensured. Based on these characteristics, a coordination analysis model is constructed to ensure the model's relevance and adaptability. Valid input data is used to calculate the dynamic coupling coordination degree, improving the scientificity and reliability of the coupling coordination degree determination. This provides strong support for evaluating the coupling coordination relationship between the resource pressure sub-platform and the resource status response composite sub-platform.

[0109] Based on the characteristics of interactive relationships, the dominant and subordinate relationships are accurately determined to clarify the core quantitative direction and ensure the pertinence of model quantification. Based on the core quantitative direction, a scientific gap measurement method is defined to ensure the rationality of the measurement of the development gap of the sub-platform. Combined with the configuration of the constraint or traction strength, the internal evaluation mechanism is configured to improve the adaptability of model evaluation. The two are integrated to generate a coordination analysis model, ensuring the scientificity and practicality of the model, and providing reliable model support for the subsequent analysis of the coupling and coordination relationship of the sub-platform.

[0110] The carrying capacity level acquisition module 104 is used to couple the multi-dimensional indicator values ​​in the standardized data according to the dynamic coupling coordination degree to obtain the agricultural resource carrying capacity level of the target area.

[0111] In this embodiment of the invention, when the carrying capacity level acquisition module performs coupling of multi-dimensional indicator values ​​in the standardized data according to the dynamic coupling coordination degree to obtain the agricultural resource carrying capacity level of the target area, it is specifically used for:

[0112] From the standardized data, the key status indicator values ​​of the target area are selected;

[0113] Based on the quantified value of the dynamic coupling coordination degree, each index value in the key state index value is adjusted for coordination state compensation to generate a corrected set of key index values.

[0114] The values ​​of each item in the modified set of key indicator values ​​are aggregated to obtain the comprehensive evaluation value of the target area.

[0115] The comprehensive evaluation value is matched with a preset level threshold range to determine the agricultural resource carrying capacity level of the target area.

[0116] The carrying capacity level acquisition module retrieves standardized data of the target area and clarifies that the selection criterion for key status indicators is the direct correlation between the indicators and agricultural resource carrying capacity. Specifically, the key status indicators selected cover core indicators of soil fertility, core indicators of water resource supply and demand, core indicators of meteorological suitability, and core indicators of agricultural production input-output efficiency. Each indicator in the standardized data is compared with the matching of the above core indicator types. Indicator values ​​that fully match the core indicator types and can directly reflect agricultural resource carrying capacity are retained, while indicator values ​​with weak correlation and only used for auxiliary explanation are eliminated. All retained indicator values ​​are summarized and organized to obtain the key status indicator values ​​of the target area.

[0117] The significance of the dynamic coupling coordination quantification value is clarified. A higher dynamic coupling coordination quantification value indicates a better coordination between the resource pressure sub-platform and the resource status-response composite sub-platform, while a lower quantification value indicates a worse coordination between the two sub-platforms. For each key status indicator value, compensation and adjustment are made according to the coordination status corresponding to the dynamic coupling coordination quantification value. When the dynamic coupling coordination quantification value is in a high range, a small positive compensation is made to the key status indicator value to reflect the positive impact of good coordination status on the indicator. When the dynamic coupling coordination quantification value is in a low range, a moderately conservative adjustment is made to the key status indicator value to reflect the constraining effect of coordination status deviation on the indicator. After completing the compensation and adjustment of each key status indicator value, all adjusted indicator values ​​are summarized to generate a corrected set of key indicator values.

[0118] The aggregation basis for the revised key indicator value set is the influence weight of each indicator on agricultural resource carrying capacity. This weight is determined according to the core role of the indicator in agricultural production. The influence weight of indicators related to soil fertility and water supply and demand is higher than that of indicators related to meteorological suitability and production input-output efficiency. Each value in the revised key indicator value set is converted into a unified contribution to agricultural resource carrying capacity according to its corresponding influence weight. The conversion process involves comparing the actual performance of the indicator with its optimal performance to obtain the carrying capacity contribution ratio of a single indicator. This ratio is then combined with the indicator weight to form the final contribution. The final contribution of all indicators is summed up, and the summed result is the comprehensive evaluation value of the target area.

[0119] The preset threshold range for agricultural resource carrying capacity is retrieved. This threshold range is defined based on historical agricultural resource carrying capacity data of the target area, requirements of agricultural sustainable development planning, and carrying capacity assessment standards for similar areas. Specifically, it is divided into three level ranges: high carrying capacity, medium carrying capacity, and low carrying capacity. The calculated comprehensive evaluation value is compared with the above three level threshold ranges one by one to determine which level threshold range the comprehensive evaluation value falls into. If the comprehensive evaluation value falls into the corresponding range, the level corresponding to that range can be directly determined as the agricultural resource carrying capacity level of the target area.

[0120] The beneficial effects include accurately screening key status indicator values ​​for target areas, ensuring the relevance and effectiveness of assessment data, and adjusting key indicator values ​​through dynamic coupling and coordination of quantitative values ​​to improve the accuracy and adaptability of indicator values. By aggregating and correcting the indicator values, a comprehensive evaluation value is obtained, which fully reflects the regional agricultural resource carrying capacity. The comprehensive evaluation value is matched with the preset level threshold range to determine the carrying capacity level, ensuring the scientificity and reliability of the assessment results and providing precise support for the rational utilization and planning of agricultural resources.

[0121] The early warning prediction module 105 is used to predict the early warning trigger for the target area based on the transfer pattern of the agricultural resource carrying capacity level and the historical carrying capacity level, and to obtain the early warning trigger probability of the target area.

[0122] In this embodiment of the invention, when the early warning prediction module performs early warning trigger prediction on the target area based on the transfer patterns of the agricultural resource carrying capacity level and historical carrying capacity level, and obtains the early warning trigger probability of the target area, it is specifically used for:

[0123] Based on the time series of the agricultural resource carrying capacity levels within the historical assessment period, the frequency of transitions from each level to other levels is statistically analyzed to obtain the level transition frequency matrix of the target area within the historical assessment period.

[0124] The state transition frequency matrix is ​​normalized to obtain the state transition probability matrix of the target area within the historical evaluation period.

[0125] From the state transition probability matrix, the probability of transitioning from the current level state to all worse level states is extracted to obtain the risk transition probability set of the target area within the current assessment period;

[0126] The basic early warning probability of the target area within the historical assessment period is obtained by summing all the probability values ​​in the risk transfer probability set.

[0127] The early warning trigger probability of the target area is calculated based on the basic early warning probability.

[0128] The formula for calculating the probability of triggering the early warning is as follows:

[0129] ;

[0130] In the formula, The probability of triggering the warning is given. The aforementioned basic early warning probability, It is a natural constant. The preset time-related factors, The number of consecutive evaluation cycles that the current level status has been maintained.

[0131] The base warning probability is a pre-set initial probability value related to warnings. The natural constant is an inherent constant value in mathematics. The time influence factor is a pre-set value used to reflect the degree to which time factors affect the warning trigger probability.

[0132] The number of consecutive assessment periods for which the current risk level has been maintained is a statistical value obtained by counting the number of consecutive assessment periods for which the current risk level has been maintained. The warning trigger probability is a result obtained by integrating various set and statistical values ​​and performing calculations. By combining the pre-set basic warning probability, natural constant, time influence factor, and the statistically obtained number of consecutive assessment periods for which the current risk level has been maintained, the warning trigger probability is quantitatively determined.

[0133] This calculation process demonstrates the impact of the number of consecutive assessment periods for the current risk level on the probability of triggering a warning. The setting of a time influence factor can adjust the degree of influence of the number of consecutive assessment periods for the current risk level on the probability of triggering a warning. The baseline warning probability serves as an initial value, providing a benchmark for calculating the warning trigger probability. As the number of consecutive assessment periods for the current risk level increases, the probability of triggering a warning will show a corresponding upward trend.

[0134] The early warning and prediction module first retrieves agricultural resource carrying capacity level data for all historical assessment periods of the target area. It then sorts this data according to the chronological order of the historical assessment periods, forming a complete time series of agricultural resource carrying capacity levels. The module defines a level shift as a change in level between two adjacent assessment periods within the time series. For each level state in the time series, the module counts the specific number of times that level state shifts to other level states within adjacent periods. For example, it counts the number of times a high carrying capacity level shifts to a high carrying capacity level, a medium carrying capacity level, and a low carrying capacity level, the number of times a medium carrying capacity level shifts to each level, and the number of times a low carrying capacity level shifts to each level.

[0135] All statistically obtained grade transition frequencies are organized into a matrix according to the correspondence between "initial grade - subsequent grade". Rows in the matrix correspond to the initial grade state, and columns correspond to the subsequent grade state. Each cell in the matrix is ​​filled with the frequency of transition from the corresponding initial grade to the corresponding subsequent grade, resulting in a grade transition frequency matrix for the target area within the historical evaluation period. When normalizing the grade transition frequency matrix, each row of data is processed separately, with each row corresponding to the frequency of transition from a specific initial grade state to all other grade states. The sum of the frequencies of all cells in each row is calculated to obtain the total transition frequency for that initial grade state. Then, the specific transition frequency of each cell in that row is divided by the total transition frequency for that initial grade state to obtain the relative proportion of each initial grade transitioning to the corresponding subsequent grade. The frequencies of all cells in the matrix are then replaced with the corresponding relative proportions to complete the normalization process of the grade transition frequency matrix, resulting in a state transition probability matrix for the target area within the historical evaluation period.

[0136] The ranking rules for agricultural resource carrying capacity levels are clearly defined: high carrying capacity level is superior to medium carrying capacity level, medium carrying capacity level is superior to low carrying capacity level, and the worst carrying capacity level is the level following the current level in the ranking. The agricultural resource carrying capacity level of the target area in the current assessment period is determined as the current level state. The row corresponding to the current level state is located in the state transition probability matrix. All cells in this row that correspond to a worse level state after transition are selected, and the probability values ​​within these cells are extracted. All extracted probability values ​​are summarized and organized to form a set containing the probability of transition from the current level to all worse levels, resulting in the risk transition probability set for the target area in the current assessment period. The early warning prediction module accumulates all probability values ​​in the risk transition probability set. Each probability value is extracted sequentially from the set, and the first probability value is used as the initial accumulation value. Each subsequent probability value is then added to the current accumulation value until all probability values ​​in the set are accumulated. The final value obtained after accumulation is the basic early warning probability for the target area in the historical assessment period.

[0137] First, retrieve standardized data for the current assessment period of the target area, extract the current fluctuations of key status indicators, and determine whether the key status indicators are in a stable state. If all key status indicators are in a stable state and there are no obvious abnormal fluctuations, the basic warning probability is directly determined as the warning trigger probability of the target area. If there are abnormal fluctuations in the key status indicators, and the direction of the fluctuation is not conducive to improving agricultural resource carrying capacity, the basic warning probability is corrected according to the duration of the fluctuation. The longer the duration of the fluctuation, the greater the amplification of the basic warning probability. The value obtained after correction is the warning trigger probability of the target area.

[0138] The beneficial effects are as follows: based on the historical carrying capacity level time series statistics, a level transition frequency matrix is ​​obtained, which comprehensively explores the level transition patterns. The frequency matrix is ​​normalized to obtain a state transition probability matrix, ensuring the rationality of the transition probabilities. The probability of the current level transitioning to a worse level is extracted to form a risk transition probability set, which accurately identifies the risk direction. The basic early warning probability is obtained by summing, which clarifies the basic risk level. The early warning trigger probability is corrected by combining the current fluctuation of key indicators, thereby improving the accuracy and pertinence of early warning prediction and providing a reliable basis for the prevention and control of agricultural resource carrying capacity risks in the target area.

[0139] In this embodiment of the invention, the early warning module 106 is used to generate early warning information for the target area when the early warning trigger probability exceeds a preset range.

[0140] The preset interval is a reasonable range of early warning trigger probabilities determined after comprehensive analysis, combining historical agricultural resource carrying capacity risk data, agricultural production safety threshold requirements, and regional agricultural sustainable development plans for the target area. It is used to define whether the agricultural resource carrying capacity of the target area is in a safe and controllable state. After obtaining the early warning trigger probability for the target area, the early warning prediction module directly compares this probability value with the preset interval. If the early warning trigger probability is higher than the upper limit of the preset interval, it indicates that the risk of the target area shifting from its current agricultural resource carrying capacity level to a worse level has exceeded acceptable limits, and there is a potential imbalance in the agricultural resource carrying capacity system. If the early warning trigger probability is lower than the lower limit of the preset interval, although it indicates that the current risk is low, continuous monitoring is sufficient and an early warning is not required. Only when the probability value exceeds the upper limit of the preset interval is it determined that an early warning mechanism needs to be activated. At this time, the early warning prediction module automatically integrates basic information about the target area, the current agricultural resource carrying capacity level, the specific value of the early warning trigger probability, the extent to which it exceeds the preset interval, and key influencing factors that may lead to a deterioration in the carrying capacity level. This information is then organized according to a unified early warning information standard format to generate early warning information for the target area containing the above core content, providing clear and accurate warning basis for subsequent risk prevention and control decisions.

[0141] The beneficial effects are that by scientifically defining the preset range of the probability of early warning triggering, the risk status of agricultural resource carrying capacity in the target area can be accurately determined. When the probability exceeds the preset range, the basic information of the region, the carrying capacity level, the risk magnitude, and key influencing factors are integrated to generate early warning information, providing reliable support for the timely prevention and control of agricultural resource carrying capacity risks and precise policy implementation.

[0142] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0143] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An agricultural resource carrying capacity assessment and early warning system, characterized in that, The system includes a data acquisition module, a resource indicator module, a dynamic coupling calibration module, a load-bearing level acquisition module, an early warning and prediction module, and an early warning module, wherein: The data acquisition module is used to standardize the multi-source agricultural basic data of the target area within the evaluation period to obtain standardized data of the target area. The resource index module is used to perform weighted summation of the index values ​​of the resource pressure sub-platform based on the degree of dispersion of different dimensions in the standardized data to obtain the resource pressure value of the resource pressure sub-platform, and at the same time, to perform weighted summation of the index values ​​of the resource status-response composite sub-platform to obtain the response composite value of the resource status-response composite sub-platform. The dynamic coupling calibration module is used to determine the dynamic coupling coordination degree between the resource pressure sub-platform and the resource state-response composite sub-platform based on the interaction strength between the resource pressure value and the response composite value, specifically for: Based on the change trajectory of the resource pressure value and the response composite value in a continuous time series, the traction or constraint relationship between the resource pressure value and the response composite value is identified, and the interaction relationship characteristics between the resource pressure value and the response composite value are obtained. Based on the aforementioned interaction characteristics, a coordination analysis model is constructed between the resource pressure sub-platform and the resource status-response composite sub-platform. The resource pressure value and the response composite value are input into the coordination analysis model to calculate the dynamic coupling coordination degree between the resource pressure sub-platform and the resource status-response composite sub-platform. When the dynamic coupling calibration module executes the coordination analysis model for constructing the resource pressure sub-platform and the resource status-response composite sub-platform based on the interaction relationship characteristics, it is specifically used for: Based on the interaction characteristics, the dominant-subordinate relationship between the resource pressure value and the response composite value is determined, and the core quantitative direction of the coordination analysis model is obtained. Based on the aforementioned core quantitative direction, a method for measuring the gap between the development of the resource pressure sub-platform and the resource status-response composite sub-platform is defined. Based on the constraint or traction strength identified in the gap measurement method and the interaction relationship characteristics, configure the internal evaluation mechanism of the coordination analysis model; The gap measurement method and the internal evaluation mechanism are integrated to generate the coordination analysis model; The formula for calculating the dynamic coupling coordination degree is as follows: ； In the formula, The dynamic coupling coordination degree, This is a dynamic attenuation factor determined based on the changing trend of the resource pressure value over a continuous assessment period. The resource pressure value for the current assessment period. The composite value of the response for the current evaluation period. For adjustment coefficients, The weight of the resource pressure sub-platform in the development level. The weight of the resource status-response composite sub-platform in the development level; The carrying capacity level acquisition module is used to couple the multi-dimensional indicator values ​​in the standardized data according to the dynamic coupling coordination degree to obtain the agricultural resource carrying capacity level of the target area. The early warning prediction module is used to predict the early warning trigger probability of the target area based on the transfer pattern of the agricultural resource carrying capacity level and the historical carrying capacity level. The early warning module is used to generate early warning information for the target area when the early warning trigger probability exceeds a preset range.

2. The agricultural resource carrying capacity assessment and early warning system as described in claim 1, characterized in that, When the data acquisition module performs standardization processing on multi-source agricultural basic data of the target area within the evaluation period to obtain standardized data of the target area, it is specifically used for: Acquire meteorological data, soil data, water resource utilization data, and agricultural production input-output data for the target area during the assessment period; Outlier removal and missing value filling are performed on the meteorological data, soil data, water resource utilization data, and agricultural production input-output data to obtain a standard dataset for the target area.

3. The agricultural resource carrying capacity assessment and early warning system as described in claim 1, characterized in that, When the resource indicator module performs a weighted summation of the indicator values ​​of the resource pressure sub-platform based on the degree of dispersion of different dimensions in the standardized data to obtain the resource pressure value of the resource pressure sub-platform, it is specifically used for: Based on the fluctuation range of each indicator in the resource pressure sub-platform within the historical evaluation period, the dispersion characteristics of the indicator are generated. Based on the dispersion characteristics, corresponding contribution weights are assigned to the indicators to obtain the resource pressure indicator weight set of the resource pressure sub-platform; The resource pressure indicators within the current assessment period from the standardized data are used as the current indicator values; Based on the weights in the resource pressure indicator weight set, the current indicator value is weighted and fused to obtain the resource pressure value of the resource pressure sub-platform.

4. The agricultural resource carrying capacity assessment and early warning system as described in claim 3, characterized in that, When the resource indicator module performs a weighted summation of the indicator values ​​of the resource status-response composite sub-platform to obtain the composite response value of the resource status-response composite sub-platform, it is specifically used for: From the standardized data, extract the indicator values ​​belonging to the resource status category and the indicator values ​​belonging to the system response category to obtain the initial set of composite indicator values ​​for the resource status-response composite sub-platform. The interaction relationship between resource status indicators and system response indicators in the initial set of composite indicators is used as the association feature of the resource status-response composite sub-platform. Based on the correlation characteristics, corresponding weights are assigned to the indicators in the initial value set of the composite indicators to obtain the composite indicator weight set of the resource status-response composite sub-platform. Using the weight set of the composite indicators, the initial value set of the composite indicators in the current evaluation period is weighted and fused to obtain the composite response value of the resource status-response composite sub-platform.

5. The agricultural resource carrying capacity assessment and early warning system as described in claim 1, characterized in that, When the carrying capacity level acquisition module performs coupling of multi-dimensional indicator values ​​in the standardized data based on the dynamic coupling coordination degree to obtain the agricultural resource carrying capacity level of the target area, it is specifically used for: From the standardized data, the key status indicator values ​​of the target area are selected; Based on the quantified value of the dynamic coupling coordination degree, each index value in the key state index value is adjusted for coordination state compensation to generate a corrected set of key index values. The values ​​of each item in the modified set of key indicator values ​​are aggregated to obtain the comprehensive evaluation value of the target area. The comprehensive evaluation value is matched with a preset level threshold range to determine the agricultural resource carrying capacity level of the target area.

6. The agricultural resource carrying capacity assessment and early warning system as described in claim 1, characterized in that, When the early warning prediction module performs early warning trigger prediction on the target area based on the transfer patterns of the agricultural resource carrying capacity level and historical carrying capacity level, and obtains the early warning trigger probability of the target area, it is specifically used for: Based on the time series of the agricultural resource carrying capacity levels within the historical assessment period, the frequency of transitions from each level to other levels is statistically analyzed to obtain the level transition frequency matrix of the target area within the historical assessment period. The state transition frequency matrix is ​​normalized to obtain the state transition probability matrix of the target area within the historical evaluation period. From the state transition probability matrix, the probability of transitioning from the current level state to all worse level states is extracted to obtain the risk transition probability set of the target area within the current assessment period; The basic early warning probability of the target area within the historical assessment period is obtained by summing all the probability values ​​in the risk transfer probability set. The early warning trigger probability of the target area is calculated based on the basic early warning probability.

7. The agricultural resource carrying capacity assessment and early warning system as described in claim 6, characterized in that, The formula for calculating the probability of triggering the early warning is as follows: ； In the formula, The probability of triggering the warning is given. The aforementioned basic early warning probability, It is a natural constant. The preset time-related factors, The number of consecutive evaluation cycles that the current level status has been maintained.

Images