Irrigation oasis regulation potential quantification and targeted intervention strategy generation method and system

Abstract

The invention discloses an irrigation oasis regulation potential quantification and targeted intervention strategy generation method and system, and the method comprises the steps: dividing a target irrigation oasis region into a plurality of management units, obtaining the multi-source data of all management units, and calculating the coupling coordination degree of each management unit; the management unit with the coupling coordination degree smaller than the regulation lower limit serves as a unit needing to be regulated, and the difference value between the coupling coordination degree of the unit needing to be regulated and the corresponding regulation lower limit or regulation upper limit serves as the regulation potential; constructing and training a Bayesian causal network, and calculating mutual information or belief variance of each driving node of the unit needing regulation and control to a target node by adopting the probability output by the trained Bayesian causal network according to the coupling coordination degree and the index of the unit needing regulation and control; and taking the driving node with the highest mutual information or belief variance as a main control factor of the corresponding unit needing to be regulated and controlled, and searching a targeted intervention strategy of the unit needing to be regulated and controlled in the factor-strategy knowledge base by adopting the main control factor.

Description

Technical Field

[0001] The present invention relates to oasis irrigation technology, and in particular to a method and system for quantifying irrigation oasis regulation potential and generating targeted intervention strategies. Background Art

[0002] Irrigated oases are important agricultural production bases and human settlements in arid regions, and water resources are the lifeblood of their survival and development. Amidst increasing water scarcity and tightening ecological constraints, achieving efficient water utilization, ensuring stable grain production, and maintaining ecological health have become core challenges for the sustainable development of irrigated oases. Precision irrigation and fertilization are key management measures for improving resource utilization efficiency.

[0003] Existing related technologies mainly include:

[0004] (1) Irrigation control technology based on soil moisture monitoring: Real-time soil moisture information is obtained through field sensors, and irrigation start and stop are controlled according to preset thresholds. Disadvantages: This method often ignores the dynamic water demand differences during the actual growth stage of crops, future changes in meteorological conditions, and the interaction of other environmental factors such as water, fertilizer, and salt, which can easily lead to one-sidedness and lag in irrigation decisions. At the same time, the density, cost, and maintenance and calibration of sensors also limit the accuracy and feasibility of its large-scale application.

[0005] (2) Irrigation decision-making technology based on weather forecasts and crop models: Combine weather forecasts and crop growth models (such as the FAO-56 method, DSSAT, etc.) to predict crop water requirements and formulate irrigation plans. Disadvantages: The accuracy of the model is highly dependent on the accuracy of weather forecasts and the local calibration of crop model parameters, which is subject to uncertainty. It also rarely considers the actual soil conditions and the overall coordination of the water-crop-ecosystem in the region, which may lead to a disconnect between decision-making and actual needs.

[0006] (3) Irrigation management technology based on remote sensing monitoring: Using satellite or drone remote sensing to obtain information such as vegetation index and surface temperature, inverting crop water stress or evapotranspiration to guide irrigation. Disadvantages: Remote sensing data is easily affected by cloudy and rainy weather, and the temporal and spatial resolution may not meet the needs of real-time decision-making; the data inversion model is complex, and it is also rare to directly convert the assessment results into precise intervention measures for specific management units that take into account multiple factors.

[0007] Therefore, existing technologies have obvious shortcomings in dynamically quantifying the potential for improving system coordination of specific management units, accurately diagnosing limiting factors, and generating targeted intervention strategies. Summary of the Invention

[0008] In response to the above-mentioned deficiencies in the prior art, the method and system for quantifying the irrigation oasis regulation potential and generating targeted intervention strategies provided by the present invention can accurately locate the main controlling factors of the management units that need to be regulated, thereby providing accurate intervention strategies.

[0009] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

[0010] In a first aspect, a method for quantifying the regulation potential of an irrigation oasis and generating a targeted intervention strategy is provided, comprising the steps of:

[0011] S1. Divide the target irrigation oasis area into several management units, obtain multi-source data for all management units, and then calculate the coupling coordination degree of each management unit based on the multi-source data;

[0012] S2. The management unit whose coupling coordination degree is less than its lower control limit is regarded as the unit requiring regulation, and the difference between the coupling coordination degree of the unit requiring regulation and its corresponding lower control limit or upper control limit is regarded as the regulation potential;

[0013] S3. Construct and train a Bayesian causal network, where the target nodes are the regulatory potentials of the units to be regulated, and the driving nodes are the controllable management factors and the indicators of the units to be regulated;

[0014] S4. Based on the coupling coordination degree and index of the unit to be regulated, the mutual information or belief variance of each driver node of the unit to be regulated with respect to the target node is calculated using the probability output by the trained Bayesian causal network;

[0015] S5. The driving node with the highest mutual information or belief variance is used as the master control factor of its corresponding unit to be regulated, and the master control factor is used to search for the targeted intervention strategy of the unit to be regulated in the factor-strategy knowledge base.

[0016] Furthermore, based on multi-source data, a method for calculating the coupling coordination degree of each management unit includes:

[0017] S11. Use multi-source data to calculate the indicators of the water resources subsystem, crop growth subsystem, and ecological environment subsystem for each management unit at the selected time step;

[0018] S12. Calculate the weight of each indicator of the management unit, and calculate the comprehensive score of the three subsystems of each management unit based on the normalized indicators and weights;

[0019] S13. Based on the comprehensive scores of the three subsystems, calculate the coupling coordination degree of each management unit at the set time step.

[0020] Furthermore, the indicators of the water resources subsystem include maximum temperature, average humidity, ET0 and root zone soil moisture; the indicators of the crop growth subsystem include chlorophyll index GI, leaf area index LAI, normalized vegetation index NDVI, and actual crop evapotranspiration ETc; the indicators of the ecological environment system include normalized salinity index SI, atmospheric impedance vegetation index ARVI, salinity index S2 and groundwater level changes; and the controllable management factors include actual irrigation water volume and fertilizer application amount.

[0021] Furthermore, in step S12, the method for calculating the comprehensive score of each subsystem in the management unit includes the following steps:

[0022] S121. Standardize the indicators of each subsystem and calculate the proportion of the standardized indicators:

[0023]

[0024] Among them, X′ ij is the standardized indicator of item j in year i; m is the total number of evaluation years; Y′ ij X′ ij proportion;

[0025] S122. Calculate the information entropy of each indicator in all evaluation years based on the indicator weight:

[0026]

[0027] Where n is the total number of indicators of each subsystem; e i is the information entropy of the jth indicator in the i-th year, 0≤e i ≤1;

[0028] S123. Calculate the indicator weight based on information entropy:

[0029]

[0030] Among them, w i is the indicator weight for year i;

[0031] S124. Calculate the comprehensive score of each subsystem based on the standardized indicators and their corresponding indicator weights:

[0032]

[0033] Among them, S is the comprehensive score of the subsystem, and f(X), g(X) and h(X) are used to represent the comprehensive scores of the water resources subsystem, crop growth subsystem, and ecological environment subsystem respectively.

[0034] Furthermore, step S13 further includes:

[0035] According to the comprehensive scores of the three subsystems, the coupling degree and coupling coordination degree of each management unit at the selected time step are calculated:

[0036]

[0037] Among them, C is the coupling degree; T is the comprehensive coordination index; α, β and γ are the weights of the water resources subsystem, crop growth subsystem and ecological environment subsystem respectively;

[0038] According to the coupling degree and comprehensive coordination index of each management unit, the coupling coordination degree of the management unit is calculated:

[0039]

[0040] Where D is the coupling coordination degree.

[0041] Furthermore, the method for obtaining the lower and upper control limits of each management unit includes:

[0042] S21. Perform a normality test on the coupling coordination degrees of all management units. If they do not meet the normal distribution, adjust all coupling coordination degrees using quantile standardization until they meet the normal distribution.

[0043] S22. When the normal distribution is satisfied, all coupling coordination degrees are fitted into a normal distribution curve and their confidence intervals are calculated;

[0044] S23. The upper and lower limits of the confidence interval are used as the lower and upper control limits of the management unit respectively.

[0045] Furthermore, the expressions for calculating mutual information and belief variance are:

[0046]

[0047] Among them, MI and VB are mutual information and belief variance respectively; H is entropy; Q is the target node; F is the driving node; q and f are the states of Q and F respectively; X q is the true value corresponding to state q; P(q) is the probability predicted by the Bayesian causal network when the target node Q takes state q; P(f) is the probability predicted by the Bayesian causal network when the driving node F takes state f; P(q,f) is the joint probability distribution of state q and state f; P(q|f) is the probability of state q occurring under the condition that state f occurs.

[0048] Furthermore, the method for quantifying the regulation potential of the irrigation oasis and generating targeted intervention strategies also includes visualizing the regulation potential, main controlling factors and targeted intervention strategies of the units to be regulated, so as to present them to managers of the irrigation oasis area.

[0049] In a second aspect, a system for quantifying the regulation potential of irrigation oases and generating targeted intervention strategies is provided, comprising:

[0050] The coordination degree determination module is used to divide the target irrigation oasis area into several management units, obtain multi-source data of all management units, and calculate the coupling coordination degree of each management unit based on the multi-source data;

[0051] A control potential quantification module is used to identify management units with a coupling coordination degree less than their lower control limit as units that need to be controlled, and to identify the difference between the coupling coordination degree of the units that need to be controlled and their corresponding lower control limit or upper control limit as the control potential;

[0052] The master control factor diagnosis module is used to construct and train a Bayesian causal network. The target node in the network is the control potential of the unit to be regulated, and the driving node is the controllable management factor and the indicator of the unit to be regulated. Based on the coupling coordination degree and indicator of the unit to be regulated, the mutual information or belief variance of each driving node of the unit to be regulated with respect to the target node is calculated using the probability output by the trained Bayesian causal network.

[0053] The targeted strategy generation module is used to take the driving node with the highest mutual information or belief variance as the main control factor of its corresponding unit to be regulated, and use the main control factor to search for the targeted intervention strategy of the unit to be regulated in the factor-strategy knowledge base.

[0054] Furthermore, the targeted intervention strategy generation system also includes a user interaction and visualization module for visualizing the regulation potential, main control factors and targeted intervention strategies of the units to be regulated so as to present them to managers of the irrigation oasis area.

[0055] The beneficial effects of the present invention are:

[0056] 1) Accurately quantify the potential for regulation and control: This solution overcomes the shortcomings of existing technologies that make it difficult to quantitatively evaluate the improvement space of specific management units. Based on a method based on the statistical distribution of dynamic coordination degrees, the present invention can objectively and accurately quantify the "regulation and control potential" of each management unit that needs improvement, providing a clear goal and basis for optimal resource allocation.

[0057] 2) Targeted diagnosis of bottleneck factors: Different from the general evaluation or correlation-based analysis in existing technologies, the present invention uses Bayesian causal networks to specifically diagnose the "main controlling factors" that lead to low coordination (potential) in specific management units, achieving in-depth, causal problem positioning from "what is wrong" to "why is it not good".

[0058] 3) Generate spatiotemporal-specific strategies: Based on the diagnosed main controlling factors, the present invention can generate highly customized, spatiotemporal-specific targeted intervention strategies (especially water and fertilizer management recommendations) through the factor-strategy knowledge base, which is significantly better than the general recommendations of the existing technology and greatly improves the accuracy and effectiveness of management measures.

[0059] 4) Improve system coordination efficiency: By accurately identifying potential, diagnosing bottlenecks and implementing targeted interventions, the present invention can more effectively guide management measures to act on key links, thereby accelerating the improvement of the coupling and coordination level of the entire irrigation oasis water-crop-ecosystem, promoting efficient resource utilization and ecological environment improvement.

[0060] 5) Strong operability of decision support: The present invention provides a complete process from evaluation, quantification, diagnosis to strategy generation, and presents the results in a clear and visual manner, providing managers with intuitive and operational decision support, reducing the difficulty of complex system management. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 Flowchart of the methodology for quantifying the regulatory potential of irrigated oases and generating targeted intervention strategies.

[0062] Figure 2 is the network structure of the Bayesian causal network.

[0063] Figure 3 Schematic diagram of a system for quantifying the regulatory potential of irrigated oases and generating targeted intervention strategies. DETAILED DESCRIPTION

[0064] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0065] refer to Figure 1 , Figure 1 The flowchart of the method for quantifying the regulation potential of irrigated oases and generating targeted intervention strategies is shown; Figure 1 As shown, the method S includes steps S1 to S5.

[0066] In step S1, the target irrigation oasis area is divided into several management units (for example, using a 1050m×1352m grid), and multi-source data of all management units are obtained. Then, based on the multi-source data, the coupling coordination degree of each management unit is calculated.

[0067] The multi-source data used in this solution include but are not limited to the following:

[0068] 1) Remote sensing data: Multispectral and thermal infrared images acquired by satellites such as Landsat, MODIS, and Sentinel are used to extract vegetation indices (NDVI, GI), salinity indices (SI, S2), surface temperature, albedo, etc.

[0069] 2) Meteorological data: including temperature (maximum, average), humidity, precipitation, wind speed, radiation and other data at each meteorological station or grid, which are used to calculate reference evapotranspiration (ET0).

[0070] 3) Hydrological / water resources data: groundwater level monitoring data, irrigation canal water supply data, soil moisture monitoring data (sensor or model simulation / remote sensing inversion).

[0071] 4) Agricultural statistics and basic data: historical or current data on crop type distribution, soil physical and chemical properties, irrigation quotas, fertilizer application rates, pesticide usage, etc.

[0072] In one embodiment of the present invention, a method for calculating the coupling coordination degree of each management unit based on multi-source data includes:

[0073] S11. Use multi-source data to calculate the indicators of the water resources subsystem, crop growth subsystem, and ecological environment subsystem corresponding to each management unit at the selected time step (for example, monthly). These indicators can be calculated using existing relatively mature calculation formulas, such as NDVI, SI, ET0, ETc, root zone soil moisture estimation model and other models.

[0074] During implementation, this plan prioritizes indicators of the water resources subsystem, including maximum temperature, average humidity, ET0, and root zone soil moisture; indicators of the crop growth subsystem include chlorophyll index GI, leaf area index LAI, normalized difference vegetation index NDVI, and actual crop evapotranspiration ETc; indicators of the ecological environment system include normalized salinity index SI, atmospheric impedance vegetation index ARVI, salinity index S2, and groundwater level changes; and controllable management factors include actual irrigation water volume and fertilizer application amount.

[0075] The indicators of the three subsystems constitute a comprehensive evaluation index system, which can be comprehensively determined by using the literature frequency method to count high-frequency indicators and the expert scoring method.

[0076] S12. Calculate the weight of each indicator of the management unit, and calculate the comprehensive score of the three subsystems of each management unit based on the normalized indicators and weights;

[0077] In one embodiment of the present invention, in step S12, the method for calculating the comprehensive score of each subsystem in the management unit includes the following steps:

[0078] S121. Standardize the indicators of each subsystem and calculate the proportion of the standardized indicators:

[0079]

[0080] Among them, X′ ij is the standardized indicator of item j in year i; m is the total number of evaluation years; Y′ ij X′ ij proportion;

[0081] Since the dimensions, magnitudes, and positive and negative orientations of the indicators are different, the initial data needs to be standardized before step S121. For the positive and negative indicators, the standardization method is as follows:

[0082] For positive indicators:

[0083] For negative indicators:

[0084] Among them, X j is the jth indicator among all indicators.

[0085] S122. Calculate the information entropy of each indicator in all evaluation years based on the indicator weight:

[0086]

[0087] Where n is the total number of indicators of each subsystem; e i is the information entropy of the jth indicator in the i-th year, 0≤e i ≤1;

[0088] S123. Calculate the indicator weight based on information entropy:

[0089]

[0090] Among them, w i is the indicator weight for year i;

[0091] S124. Calculate the comprehensive score of each subsystem based on the standardized indicators and their corresponding indicator weights:

[0092]

[0093] Among them, S is the comprehensive score of the subsystem, and f(X), g(X) and h(X) are used to represent the comprehensive scores of the water resources subsystem, crop growth subsystem, and ecological environment subsystem respectively.

[0094] S13. Calculate the coupling coordination degree of each management unit at a set time step based on the comprehensive scores of the three subsystems; Step S13 further includes:

[0095] According to the comprehensive scores of the three subsystems, the coupling degree and coupling coordination degree of each management unit at the selected time step are calculated:

[0096]

[0097] Among them, C is the coupling degree; T is the comprehensive coordination index; α, β and γ are the weights of the water resources subsystem, crop growth subsystem and ecological environment subsystem respectively;

[0098] According to the coupling degree and comprehensive coordination index of each management unit, the coupling coordination degree of the management unit is calculated:

[0099]

[0100] Where D is the coupling coordination degree.

[0101] In step S2, the management unit whose coupling coordination degree is less than its lower control limit is regarded as a unit requiring regulation, and the difference between the coupling coordination degree of the unit requiring regulation and its corresponding lower control limit or upper control limit is regarded as the regulation potential.

[0102] During implementation, the method for obtaining the lower and upper control limits of each management unit preferably includes:

[0103] S21. Perform a normality test on the coupling coordination degrees of all management units. If they do not meet the normal distribution, adjust all coupling coordination degrees using quantile standardization until they meet the normal distribution.

[0104] When the data do not conform to a normal distribution, the following methods can be used to adjust the analysis strategy to ensure the robustness and rationality of the results. Mild skewness: Logarithmic transformation: x′=ln(x+1) (applicable to right-skewed data, such as income and GDP). Square root transformation: x′=x (applicable to mild right skewness). Severe skewness: Box-Cox transformation: Determine the optimal transformation parameter λ through maximum likelihood estimation. Reciprocal transformation: x′=1 / x (applicable to right-skewed indicators with positive values). Quantile standardization: Use the median and interquartile range instead of the mean and standard deviation for standardization.

[0105] S22. When the normal distribution is satisfied, all coupling coordination degrees are fitted into a normal distribution curve and their confidence intervals are calculated;

[0106] S23. The upper and lower limits of the confidence interval are used as the lower and upper control limits of the management unit respectively.

[0107] In step S3, a Bayesian causal network is constructed and trained, where the target nodes in the network are the regulatory potentials of the units to be regulated, and the driving nodes are the controllable management factors and the indicators of the units to be regulated; Figure 2 The diagram shows the architecture of the Bayesian causal network of this scheme, in which the regulatory potential serves as the dependent variable of the network, the three subsystems serve as direct factors, and all influencing factors, i.e., driving nodes, serve as indirect factors.

[0108] This solution uses the data of the units to be regulated (indicator data and regulation potential) to learn the parameters of the Bayesian network (calculate the conditional probability table). It can be implemented using software such as Netica, and the weights of prior knowledge and data are adjusted based on experience and the number of training times.

[0109] This solution can identify ecological and other constraints on high water efficiency by establishing a Bayesian causal network for irrigation areas. In the process of constructing a Bayesian causal network, a preliminary model of the Bayesian causal network is first performed, and the EM algorithm (Expectation-Maxmization algorithm) is used to iteratively calculate the expectation and maximum likelihood estimates of the parameters. Netica software is used here to implement the Bayesian network, which is widely used in Bayesian network modeling research. In Netica, the "experience" variable represents the credibility of the observation data represented by the prior knowledge, while the "degree" variable represents the number of training times for the observation data. Combining the two can dynamically adjust the weights of prior knowledge and observation data in determining the probability distribution.

[0110] Experience:P(N)

[0111] Degree:

[0112] In the formula, P represents probability, N represents network, and d i Represents each observation data, and D represents the observation data set.

[0113] Parameterize the Bayesian network model, input data, and implement parameterization; finally, perform sensitivity analysis on the Bayesian network model using mutual information (MI) based on entropy reduction and variance (VB) based on variance reduction. The calculation formula is as follows:

[0114]

[0115] Among them, MI and VB are mutual information and belief variance respectively; H is entropy; Q is the target node; F is the driving node; q and f are the states of Q and F respectively; X q is the true value corresponding to state q; P(q) is the probability predicted by the Bayesian causal network when the target node Q takes state q; P(f) is the probability predicted by the Bayesian causal network when the driver node F takes state f; P(q,f) is the joint probability distribution of states q and f; and P(q|f) is the probability of state q occurring given state f. For ease of comparison, the mutual information and belief variance are normalized to the range of 0–100% to obtain the mutual information ratio and belief variance ratio, respectively.

[0116] In step S4, according to the coupling coordination degree and index of the unit to be regulated, the mutual information or belief variance of each driving node of the unit to be regulated to the target node is calculated using the probability output by the trained Bayesian causal network.

[0117] In step S5, the driving node with the highest mutual information or belief variance is used as the main control factor of its corresponding unit to be regulated, and the main control factor is used to search for the targeted intervention strategy of the unit to be regulated in the factor-strategy knowledge base.

[0118] The method of establishing a "factor-strategy" knowledge base is to pre-establish a mapping relationship library to associate the main controlling factors that may be diagnosed with recommended intervention measures (especially water and fertilizer management measures). For example:

[0119] Controlling factor: Low soil moisture in the root zone -> Strategy: Increase irrigation volume / frequency.

[0120] Main controlling factors: low crop GI / LAI + low soil nutrient index -> Strategy: Supplement with specific types of fertilizers.

[0121] Main controlling factor: SI / S2 high -> Strategy: Implement leaching irrigation, improve soil, and adjust irrigation water quality.

[0122] Main controlling factor: unreasonable irrigation quota (based on historical data inference) -> Strategy: adjust the irrigation system.

[0123] Controlling factor: Excessive application of agricultural fertilizers (based on historical data) -> Strategy: Reduce fertilizer application and optimize fertilizer ratios.

[0124] Generate targeted strategies: For each unit that needs to be regulated, based on the diagnosed master controlling factors, match and generate specific, quantitative (if possible) intervention recommendations from the knowledge base. For example, the recommendations may be:

[0125] Spatial specificity: Grid division is performed on the monitoring plot to obtain specific management units (grids).

[0126] Time specificity: diagnostic results based on the current time step (month).

[0127] Targeted: Directly address the major bottlenecks identified.

[0128] During implementation, this plan's preferred method for quantifying the irrigation oasis regulation potential and generating targeted intervention strategies also includes visualizing the regulation potential, main controlling factors, and targeted intervention strategies of the units to be regulated, so as to present them to managers of the irrigation oasis area.

[0129] like Figure 3 As shown, this solution also provides a system for quantifying the regulation potential of irrigation oases and generating targeted intervention strategies, which includes:

[0130] The coordination degree determination module is used to divide the target irrigation oasis area into several management units, obtain multi-source data of all management units, and calculate the coupling coordination degree of each management unit based on the multi-source data;

[0131] The coordination degree determination module includes a data management and preprocessing module and a dynamic coordination degree evaluation module; the data management and preprocessing module is used to divide the target irrigation oasis area into several management units, obtain multi-source data of all management units, and access, store, clean and integrate multi-source data; the dynamic coordination degree evaluation module is used to calculate the coupling coordination degree of each management unit based on multi-source data.

[0132] A control potential quantification module is used to identify management units with a coupling coordination degree less than their lower control limit as units that need to be controlled, and to identify the difference between the coupling coordination degree of the units that need to be controlled and their corresponding lower control limit or upper control limit as the control potential;

[0133] The master control factor diagnosis module is used to construct and train a Bayesian causal network. The target node in the network is the control potential of the unit to be regulated, and the driving node is the controllable management factor and the indicator of the unit to be regulated. Based on the coupling coordination degree and indicator of the unit to be regulated, the mutual information or belief variance of each driving node of the unit to be regulated with respect to the target node is calculated using the probability output by the trained Bayesian causal network.

[0134] The targeted strategy generation module is used to take the driving node with the highest mutual information or belief variance as the main control factor of its corresponding unit to be regulated, and use the main control factor to search for the targeted intervention strategy of the unit to be regulated in the factor-strategy knowledge base.

[0135] The targeted intervention strategy generation system also includes a user interaction and visualization module, which is used to visualize the regulation potential, main controlling factors and targeted intervention strategies of the units to be regulated, so as to present them to the managers of the irrigation oasis area.

Claims

1. A method for quantifying the regulation potential of irrigation oases and generating targeted intervention strategies, characterized by: Including steps: S1. Divide the target irrigation oasis area into several management units, obtain multi-source data for all management units, and then calculate the coupling coordination degree of each management unit based on the multi-source data; S2. The management unit whose coupling coordination degree is less than its lower control limit is regarded as the unit requiring regulation, and the difference between the coupling coordination degree of the unit requiring regulation and its corresponding lower control limit or upper control limit is regarded as the regulation potential; S3. Construct and train a Bayesian causal network, where the target nodes are the regulatory potentials of the units to be regulated, and the driving nodes are the controllable management factors and the indicators of the units to be regulated; S4. Based on the coupling coordination degree and index of the unit to be regulated, the mutual information or belief variance of each driver node of the unit to be regulated with respect to the target node is calculated using the probability output by the trained Bayesian causal network; S5. The driving node with the highest mutual information or belief variance is used as the master control factor of its corresponding unit to be regulated, and the master control factor is used to search for the targeted intervention strategy of the unit to be regulated in the factor-strategy knowledge base.

2. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 1, characterized in that: Based on multi-source data, the method for calculating the coupling coordination degree of each management unit includes: S11. Use multi-source data to calculate the indicators of the water resources subsystem, crop growth subsystem, and ecological environment subsystem for each management unit at the selected time step; S12. Calculate the weight of each indicator of the management unit, and calculate the comprehensive score of the three subsystems of each management unit based on the normalized indicators and weights; S13. Based on the comprehensive scores of the three subsystems, calculate the coupling coordination degree of each management unit at the set time step.

3. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 2, characterized in that: The indicators of the water resources subsystem include maximum temperature, average humidity, ET0 and root zone soil moisture; the indicators of the crop growth subsystem include chlorophyll index GI, leaf area index LAI, normalized vegetation index NDVI, and actual crop evapotranspiration ETc; the indicators of the ecological environment system include normalized salinity index SI, atmospheric impedance vegetation index ARVI, salinity index S2 and groundwater level changes; controllable management factors include actual irrigation water volume and fertilizer application amount.

4. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 3, characterized in that: In step S12, the method for calculating the comprehensive score of each subsystem in the management unit includes the following steps: S121. Standardize the indicators of each subsystem and calculate the proportion of the standardized indicators: Among them, X′ ij is the standardized indicator of item j in year i; m is the total number of evaluation years; Y′ ij X′ ij proportion; S122. Calculate the information entropy of each indicator in all evaluation years based on the indicator weight: Where n is the total number of indicators of each subsystem; e i is the information entropy of the jth indicator in the i-th year, 0≤e i ≤1; S123. Calculate the indicator weight based on information entropy: Among them, w i is the indicator weight for year i; S124. Calculate the comprehensive score of each subsystem based on the standardized indicators and their corresponding indicator weights: Among them, S is the comprehensive score of the subsystem, and f(X), g(X) and h(X) are used to represent the comprehensive scores of the water resources subsystem, crop growth subsystem, and ecological environment subsystem respectively.

5. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 4, characterized in that: Step S13 further includes: According to the comprehensive scores of the three subsystems, the coupling degree and coupling coordination degree of each management unit at the selected time step are calculated: Among them, C is the coupling degree; T is the comprehensive coordination index; α, β and γ are the weights of the water resources subsystem, crop growth subsystem and ecological environment subsystem respectively; According to the coupling degree and comprehensive coordination index of each management unit, the coupling coordination degree of the management unit is calculated: Where D is the coupling coordination degree.

6. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 1, characterized in that: The methods for obtaining the lower and upper control limits of each management unit include: S21. Perform a normality test on the coupling coordination degrees of all management units. If they do not meet the normal distribution, adjust all coupling coordination degrees using quantile standardization until they meet the normal distribution. S22. When the normal distribution is satisfied, all coupling coordination degrees are fitted into a normal distribution curve and their confidence intervals are calculated; S23. The upper and lower limits of the confidence interval are used as the lower and upper control limits of the management unit respectively.

7. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 1, characterized in that: The expressions for calculating mutual information and belief variance are: VB=∑qP(q)[X q ―∑qP(q)X q ] 2 ―∑qP(q|f)[X q ―∑qP(q|f)X q ] 2 Among them, MI and VB are mutual information and belief variance respectively; H is entropy; Q is the target node; F is the driving node; q and f are the states of Q and F respectively; X q is the true value corresponding to state q; P(q) is the probability predicted by the Bayesian causal network when the target node Q takes state q; P(f) is the probability predicted by the Bayesian causal network when the driving node F takes state f; P(q,f) is the joint probability distribution of state q and state f; P(q|f) is the probability of state q occurring under the condition that state f occurs.

8. The method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to claim 1, characterized in that: It also includes visualizing the regulatory potential, main controlling factors and targeted intervention strategies of the units to be regulated so as to present them to managers of the irrigation oasis area.

9. A system for use in the method for quantifying irrigation oasis regulation potential and generating targeted intervention strategies according to any one of claims 1 to 8, characterized in that: include: The coordination degree determination module is used to divide the target irrigation oasis area into several management units, obtain multi-source data of all management units, and calculate the coupling coordination degree of each management unit based on the multi-source data; A control potential quantification module is used to identify management units with a coupling coordination degree less than their lower control limit as units that need to be controlled, and to identify the difference between the coupling coordination degree of the units that need to be controlled and their corresponding lower control limit or upper control limit as the control potential; The master control factor diagnosis module is used to construct and train a Bayesian causal network. The target nodes in the network are the control potential of the units to be regulated, and the driving nodes are the controllable management factors and the indicators of the units to be regulated. According to the coupling coordination degree and index of the unit to be regulated, the mutual information or belief variance of each driver node of the unit to be regulated to the target node is calculated using the probability output by the trained Bayesian causal network; The targeted strategy generation module is used to take the driving node with the highest mutual information or belief variance as the main control factor of its corresponding unit to be regulated, and use the main control factor to search for the targeted intervention strategy of the unit to be regulated in the factor-strategy knowledge base.

10. The system according to claim 9, characterized in that It also includes a user interaction and visualization module for visualizing the regulation potential, main controlling factors and targeted intervention strategies of the units to be regulated so as to present them to managers of the irrigation oasis area.

Images