A Crop High-Efficiency Water Use Model Coupling Multiple Evaluation Indexes and Multiple Weighting Methods

Abstract

The present invention discloses a crop high-efficient water use model coupled with multiple evaluation indicators and multiple weighting methods, comprising the following steps: obtaining relevant data in the research area; inputting the relevant data into the crop model for simulation to obtain various index parameters affecting the research results of different planting scenarios in the research area; constructing sample data to optimize the crop model and outputting various optimized parameter indicators; using the analytic hierarchy process to establish a crop high-efficient water use evaluation model; calculating and analyzing the subjective weights and objective weights of the index layer and the criterion layer; and obtaining the evaluation result of the crop high-efficient water use model. The present invention uses the crop model and the random forest algorithm to simulate and optimize various indicators and factors affecting the high-efficient water use of crops, combines the analytic hierarchy process to establish a crop high-efficient water use model, and couples the subjective and objective weight assignments to obtain a more scientific crop high-efficient water use evaluation model, and further promotes the implementation of water-saving and water-preserving measures according to the high-efficient water use model.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural water conservation and utilization, and particularly to a crop high-efficiency water use model that couples multiple evaluation indicators and multiple weighting methods. Background Art

[0002] With the continuous growth of China's population and the continuous development of industry and agriculture, water resource shortage has become an increasingly serious problem. Agriculture is a major water user in China, and agricultural water security is an important part of China's water security. However, in recent years, the available water volume for agricultural production has been continuously decreasing, and the contradiction between water supply and demand has become an important factor restricting agricultural production and rural life. It is necessary to propose high-efficiency water use for agricultural crops to achieve water conservation and water preservation.

[0003] High-efficiency water use of crops refers to the regulation purpose of crops to actively adapt to the external environment through their own genetic potential, reduce wasteful transpiration water consumption and ineffective water loss through a series of physiological and ecological regulation measures, and improve the utilization rate of water resources to achieve water conservation and water preservation. A large number of studies have shown that the water use efficiency of crops is affected by water-saving irrigation technologies, planting structures and conditions, and climate factors, etc. However, at present, there is no unified standard for the evaluation theory and related methods of crop high-efficiency water use. Although there are many existing studies on crop high-efficiency water use evaluation, most of the existing studies conduct an overall evaluation of agricultural water use from a single direction, and there are relatively few comprehensive evaluation studies that combine multiple evaluation indicators and use multiple methods for coupled weighting, and it is impossible to give a scientific evaluation model or system that combines multiple influencing factors, objective evaluation, and subjective evaluation. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the related technologies to some extent.

[0005] To this end, an embodiment of the present invention proposes a crop high-efficiency water use model that couples multiple evaluation indicators and multiple weighting methods, including the following steps:

[0006] S1. Obtain relevant data in the study area, including meteorological data, soil data, water resource data, and irrigation and fertilization systems in the study area;

[0007] S2. According to the planting scenarios of different crops and the relevant data obtained under the corresponding scenarios, input them into the crop model for simulation to obtain various index parameters that affect the research results of different planting scenarios in the study area;

[0008] S3. Use the various parameter indexes obtained in S2 as prediction variables to construct sample data, input them into the random forest algorithm to make up for the deviation caused by unclear information or insufficient knowledge reserve in the crop model, optimize the crop model, and output the optimized various parameter indexes;

[0009] S4. Use the Analytic Hierarchy Process (AHP) to establish an evaluation model for efficient crop water use. Take the efficient crop water use model as the target layer, various factors affecting the research results of different planting scenarios in the research area as the criterion layer, and the optimized various index parameters obtained in step S3 as the index layer.

[0010] S5. Calculate and analyze the subjective weights and objective weights for the index layer and the criterion layer. Use the AHP to calculate the subjective weights and the CRITIC weight method to calculate the objective weights. Re-weight the subjective weights obtained by the AHP and the objective weights obtained by the CRITIC weight method to finally obtain the comprehensive weights of the criterion layer and the index layer.

[0011] S6. Combine steps S4 and S5 to obtain the evaluation results of the efficient crop water use model.

[0012] According to the embodiments of the present invention, use the crop model and the random forest algorithm to simulate and optimize various indicators and factors affecting efficient crop water use, establish an efficient crop water use model in combination with the Analytic Hierarchy Process, and further optimize the process of the efficient crop water use model obtained by the Analytic Hierarchy Process by coupling subjective and objective weight assignments, so as to obtain a more scientific evaluation model for efficient crop water use, and then promote the implementation of water-saving and water-preserving measures according to the efficient water use model and improve the water resource utilization rate.

[0013] Optionally, the crop model adopts the DSSAT model.

[0014] Further, the various index parameters obtained in step S2 include water use efficiency, crop water productivity, and nitrogen fertilizer use efficiency.

[0015] Further, the various factors affecting the research results of different planting scenarios in step S4 include resource input and utilization efficiency, yield and quality, and environmental benefit factors.

[0016] Further, in step S3, the regression decision tree of the random forest algorithm is expressed as: where h(x) is the final prediction result of the random forest algorithm, h(x,θ i ) is the prediction result of a certain regression decision tree in the random forest algorithm, x is the set of corresponding feature variables used by this decision tree, θ i is an independent and identically distributed random vector, K is the number of decision trees, and N is the number of training sample subsets.

[0017] Further, the corresponding feature variables used by the decision tree include water use efficiency (WUE), crop water productivity (WP), and nitrogen fertilizer use efficiency (NUE), where:

[0018] WUE = Y / W

[0019] In the formula, WUE is the water use efficiency; Y is the grain yield per unit area; W is the water resource input;

[0020] WP = Y / ET

[0021] In the formula, WP is the crop water productivity; Y is the grain yield per unit area; ET is the field evapotranspiration;

[0022] NUE = Y / N

[0023] In the formula, NUE is the nitrogen fertilizer utilization rate; Y is the grain yield per unit area; N is the nitrogen application rate.

[0024] Furthermore, when optimizing the crop model using the random forest algorithm, the following steps are included:

[0025] S31. Take the crop yield, soil water content, water use efficiency (WUE), crop water productivity (WP), and nitrogen fertilizer utilization rate (NUE) indicators as the characteristic variables of the random forest algorithm;

[0026] S32. Adjust and optimize the crop parameters, the soil parameters, and the irrigation and fertilization parameters according to the random forest algorithm, and correspondingly obtain the optimized crop model;

[0027] S33. Input the meteorological data, soil data, crop yield, and irrigation and fertilization regime data in different combinations into the adjusted and optimized crop model for simulation, and output the optimized simulation values for various index parameters obtained in step S2;

[0028] S34. Take the output optimized simulation values as the index layer of the analytic hierarchy process.

[0029] Furthermore, in S34, the output simulation values include crop yield, simulated crop irrigation water use efficiency, simulated crop fertilizer use efficiency, and simulated crop soil water content.

[0030] Furthermore, in step S5, calculating the subjective weight using the analytic hierarchy process includes the following steps:

[0031] Construct an expert judgment matrix, make pairwise comparisons for scaling; calculate the weight of the judgment matrix by the arithmetic mean method; conduct a consistency test; calculate the subjective weight.

[0032] Furthermore, in step S5, calculating the objective weight using the CRITIC weight method includes the following steps:

[0033] Construct an original data matrix; standardize the positive and negative indicators; calculate the information bearing capacity; calculate the objective weight.

[0034] Further, in step S5, when calculating the comprehensive level of the crop high-efficient water use model, the comprehensive weighting formula is as follows:

[0035] Q i = a × v i + (1 - a)w i ;

[0036] Wherein, Q i is the total weight of the i-th factor, v i is the objective weight of the i-th factor, w i is the subjective weight of the i-th factor, and a is the coefficient of the combined weight.

[0037] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of embodiments in conjunction with the drawings, wherein:

[0039] Figure 1 is a schematic flow chart of a method for a crop high-efficient water use model coupled with multiple evaluation indicators and multiple weighting methods according to the present invention;

[0040] Figure 2 is a schematic diagram of the steps for optimizing a crop model by a random forest algorithm in step S2 of a crop high-efficient water use model coupled with multiple evaluation indicators and multiple weighting methods according to the present invention;

[0041] Figure 3 is a schematic diagram of the weighted results of each index after calculating the objective weight by the CRITIC weight method and weighting in an embodiment of a crop high-efficient water use model coupled with multiple evaluation indicators and multiple weighting methods according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] Embodiments of the present invention will be described in detail below, and examples of the embodiments are shown in the drawings. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0043] The present invention provides a crop high-efficient water use model coupled with multiple evaluation indicators and multiple weighting methods, which will be described in detail below with reference to Figures 1 to 3 and includes the following steps:

[0044] S1. Obtain relevant data in the study area, including meteorological data, soil data, water resource data, and irrigation and fertilization systems in the study area;

[0045] S2. Input the planting scenarios of different crops and the relevant data obtained under the corresponding scenarios into the crop model for simulation to obtain various index parameters affecting the research results of different planting scenarios in the research area;

[0046] S3. Use the various parameter indexes obtained in S2 as prediction variables to construct sample data and input them into the random forest algorithm to make up for the deviations caused by unclear information or insufficient knowledge reserve in the crop model, optimize the crop model, and output the optimized various parameter indexes;

[0047] S4. Use the analytic hierarchy process to establish an evaluation model for efficient water use of crops. Take the crop efficient water use model as the target layer, take the various factors affecting the research results of different planting scenarios in the research area as the criterion layer, and take the optimized various index parameters obtained in step S3 as the index layer;

[0048] S5. Calculate and analyze the subjective weight and objective weight of the index layer and the criterion layer. Use the analytic hierarchy process to calculate the subjective weight, use the CRITIC weight method to calculate the objective weight, and perform re-weighting calculation on the subjective weight obtained by the analytic hierarchy process and the objective weight obtained by the CRITIC weight method to finally obtain the comprehensive weight of the criterion layer and the index layer;

[0049] S6. Combine steps S4 and S5 to obtain the evaluation result of the crop efficient water use model.

[0050] The present invention uses the crop model and the random forest algorithm to simulate and optimize various indexes and factors affecting the efficient water use of crops, combines the analytic hierarchy process to establish a crop efficient water use model, and couples the subjective and objective weight distributions to further optimize the process of the crop efficient water use model obtained by the analytic hierarchy process, so as to obtain a more scientific crop efficient water use evaluation model, and then promote the implementation of water-saving and water-preserving measures according to the efficient water use model, and improve the water resource utilization rate.

[0051] In some embodiments, the relevant data in the research area in S1 includes multi-temporal and multi-spatial scale data, that is, meteorological data, soil data, water resource data, irrigation and fertilization systems, crop quality data, and crop yield data in the research area are obtained at one or more time points.

[0052] Among them, the meteorological data includes daily precipitation, minimum temperature, minimum temperature, sunshine duration, winter wheat sowing date, development period data, and water resource data, all of which can be obtained through official data, and the total short-wave radiation on the ground can be calculated through the obtained sunshine-related data. In some embodiments, the total short-wave radiation on the ground can be included in the relevant data in the research area, and its calculation method refers to the calculation in the FAO-Penman Monteith method, and the formula is as follows:

[0053]

[0054]

[0055] ω s = cos -1 [-tan(ψ)tan(δ)];

[0056]

[0057] where R s is shortwave radiation; n is the actual sunshine hours; N is the maximum possible sunshine hours; is relative sunshine; G SC is the solar constant, 0.082; R a is extraterrestrial radiation; a s , b s are regression constants; d r is the relative Earth-sun distance; δ is the solar declination; ω is the hour angle of sunset; J is the day sequence number.

[0058] Due to artificial irrigation, meteorological data should also include data such as the irrigation method, irrigation quota, irrigation norm, and irrigation time.

[0059] Soil data includes soil data such as the depth, texture, total nitrogen content, soil bulk density, pH value, and organic carbon content of each soil layer, and the soil data can be obtained through official data and existing field experiment data.

[0060] Input the various data obtained into the crop model to perform step S2.

[0061] In some embodiments, when performing step S2, the selected crop model is the DSSAT model. The full name of the DSSAT model is the Decision Support System for Agrotechnology Transfer, which is one of the most widely used crop model systems at present. It is a comprehensive computer model jointly developed by multiple scientific research institutions under the sponsorship and support of the International Benchmark Network for Agrotechnology Transfer (IBSNAT). The DSSAT model has a standardized input and output format, is powerful in function and simple in operation, can be applied to a variety of widely planted crops, and can provide decisions and countermeasures for reasonably and effectively utilizing water, nitrogen, fertilizers, and other various natural resources to improve agricultural production efficiency.

[0062] After the simulation of the DSSAT model is completed, the first simulation values of various index parameters that affect the research results of different planting scenarios in the research area are obtained. The various index parameters obtained in step S2 include, but are not limited to, water use efficiency, crop water productivity, and nitrogen fertilizer use efficiency.

[0063] Since there may be some deviations in the DSSAT model during use due to unclear information or insufficient knowledge reserves, the random forest algorithm in step S3 is introduced to optimize the first simulation values obtained by the DSSAT model.

[0064] In some embodiments, in step S3, the regression decision tree of the random forest algorithm is expressed as: where h(x) is the final prediction result of the random forest algorithm, and h(x,θ i ) is the prediction result of a certain regression decision tree in the random forest algorithm, x is the set of corresponding feature variables used by the decision tree, and θ i is an independent and identically distributed random vector, K is the number of decision trees, and N is the number of training sample subsets.

[0065] Among them, the corresponding feature variables used by the decision tree of the random forest algorithm include, but are not limited to, water use efficiency (WUE), crop water productivity (WP), and nitrogen fertilizer use efficiency (NUE), where:

[0066] WUE = Y / W

[0067] In the formula, WUE is water use efficiency; Y is the grain yield per unit area; W is the water resource input;

[0068] WP = Y / ET

[0069] In the formula, WP is crop water productivity; Y is the grain yield per unit area; ET is the field evapotranspiration;

[0070] NUE = Y / N

[0071] In the formula, NUE is nitrogen fertilizer use efficiency; Y is the grain yield per unit area; N is the nitrogen application rate.

[0072] In some embodiments, in step S3, when using the random forest algorithm to optimize the crop model, the following steps are included:

[0073] S31. Take the crop yield, soil water content, water use efficiency (WUE), crop water productivity (WP), and nitrogen fertilizer use efficiency (NUE) indicators as the feature variables of the random forest algorithm;

[0074] S32. Adjust and optimize the crop parameters, the soil parameters, and the irrigation and fertilization parameters according to the random forest algorithm, and correspondingly obtain an optimized crop model;

[0075] S33. Input meteorological data, soil data, crop yield, and irrigation and fertilization regime data in different combinations into the adjusted and optimized crop model for simulation, and output optimized simulation values for various index parameters obtained in step S2.

[0076] S34. Use the output optimized simulation values as the index layer of the analytic hierarchy process.

[0077] The optimized simulation values after being optimized by the random forest algorithm include water use efficiency, nitrogen fertilizer use efficiency, water and fertilizer application rates; crop yield, crop quality, sustainability, planting area; water leakage, water runoff, and nitrogen leaching / surplus and other data.

[0078] The above-mentioned various simulation values correspond to multiple factors that affect the research results of different planting scenarios in the research area in step S4, corresponding respectively to form the index layer and criterion layer of step S4.

[0079] Among them, in S34, the output simulation values include crop yield, simulated crop irrigation water use efficiency, simulated crop fertilizer use efficiency, and simulated crop soil water content.

[0080] In some embodiments, when performing step S4, the multiple factors that affect the research results of different planting scenarios in the research area include resource input and utilization efficiency, yield and quality, and environmental benefit factors, and these three factors form the criterion layer of the analytic hierarchy process.

[0081] In step S5, calculating the subjective weight using the analytic hierarchy process includes the following steps:

[0082] Construct an expert judgment matrix, make pairwise comparisons for scaling; calculate the weight of the judgment matrix using the arithmetic mean method; perform a consistency test; calculate the subjective weight.

[0083] Taking the criterion layer as an example below, the expert judgment matrix is as follows:

[0084]

[0085] Among them, a 1 represents the scale corresponding to the resource input and utilization efficiency criterion, a 2 represents the scale corresponding to the crop yield and quality criterion, and a 3 represents the scale corresponding to the environmental benefit criterion.

[0086] At the same time, perform step S5, calculate the weight of the judgment matrix using the arithmetic mean method, that is, calculate the subjective weight of the analytic hierarchy process, and the calculation process is as follows:

[0087]

[0088] After completion, perform a consistency check and calculate the one-time index CI.

[0089]

[0090] where i is the matrix order and λ max is the largest eigenvalue of A;

[0091] CI = 0 indicates perfect consistency;

[0092] CI close to 0 indicates satisfactory consistency;

[0093] The larger the CI, the more serious the inconsistency.

[0094] Since λ max depends continuously on a ij , then the more λ max exceeds i (matrix order), the more serious the inconsistency of A and the greater the resulting judgment error. Therefore, the magnitude of the value of λ max - i can be used to measure the degree of inconsistency of A.

[0095] Define the consistency ratio:

[0096] where: RI is the random consistency index, generally obtained by looking up a table, as shown in the following table:

[0097] n 1 2 3 4 5 6 7 8 9 RI 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.46

[0098] where n is the matrix order.

[0099] Looking up the table, we can get RI = 0.52.

[0100] When CR < 0.1, it is considered that the degree of inconsistency of A is within the allowable range and passes the one-time test; otherwise, reconstruct the judgment matrix A.

[0101] In one embodiment using the above method, the index layer includes A1, water use efficiency; A2, nitrogen use efficiency; A3, irrigation water amount; A4, nitrogen fertilizer amount; B1, yield; B2, quality; B3, planting area; B4, production sustainability; B5, labor productivity; C1, water leakage; C2, water runoff;

[0102] C3, nitrogen leaching; C4, nitrogen surplus. The criterion layer includes: resource input and utilization efficiency criterion A, yield and quality criterion B, and environmental benefit criterion C.

[0103] Taking the criterion layer as an example below, according to the calculation principle of the analytic hierarchy process and based on the expert scoring results, the criterion layer index judgment matrix (E) is obtained:

[0104]

[0105] The maximum eigenvalue λ of the criterion layer judgment matrix (E) can be calculated max = 3.064, CI = 0.032, where Then it passes the consistency test.

[0106] Calculate the subjective weight. After normalizing matrix E, it is

[0107] The obtained subjective weight values are respectively:[[]]

[0108]

[0109] In some embodiments, in step S5, calculating the objective weight by using the CRITIC weight method includes the following steps:

[0110] Construct the original data matrix; standardize the positive and negative indicators; calculate the information bearing capacity; calculate the objective weight. Using the CRITIC weight method for objective weight analysis and calculation, the CRITIC weight method is an objective weighting method based on data volatility. Its idea lies in two indicators, namely the volatility (contrast intensity) and conflict (correlation) indicators. The contrast intensity is represented by the standard deviation. If the standard deviation of the data is larger, it means the fluctuation is larger and the weight will be higher; the conflict is represented by the correlation coefficient. If the correlation coefficient value between indicators is larger, it means the conflict is smaller, and then its weight will be lower. When calculating the weight, the contrast intensity is multiplied by the conflict indicator and normalized to obtain the final weight.

[0111] The steps of the CRITIC weight method are as follows:

[0112] 1) Normalize each indicator according to the number of each option.

[0113] For positive indicators:

[0114] For negative indicators:

[0115] 2) Calculate the standard deviation to represent the variability of the indicator: In the formula, S j represents the standard deviation of the j-th indicator;

[0116] 3) Calculate the correlation coefficient to represent the conflict of the indicator: In the formula, R j represents the correlation coefficient between evaluation indicators i and j;

[0117] 4) Calculate the information content of the indicator:

[0118] 5) Calculate the objective weights:

[0119] Using the above method, in one embodiment, construct sets for each index in the index layer, give actual data examples, and construct the following sets:

[0120] A1, Water use efficiency; A2, Nitrogen use efficiency; A3, Irrigation water consumption; A4, Nitrogen fertilizer application rate; B1, Yield; B2, Quality; B3, Planting area; B4, Production sustainability; B5, Labor productivity; C1, Water leakage; C2, Water runoff; C3, Nitrogen leaching; C4, Nitrogen surplus.

[0121] After normalizing the data of each index, the following table is obtained:

[0122] A1 A2 A3 A4 B1 B2 B3 B4 B5 C1 C2 C3 C4 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.696 0.814 0.757 0.779 0.731 0.636 0.618 0.809 0.801 0.528 0.625 0.803 0.764 0.403 0.483 0.465 0.443 0.395 0.421 0.366 0.567 0.565 0.434 0.375 0.417 0.457 0.260 0.244 0.264 0.214 0.134 0.221 0.229 0.298 0.317 0.066 0.208 0.205 0.307 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000

[0123] Calculate the standard deviation S of the normalized data j The results are as follows in the table:

[0124] A1 A2 A3 A4 B1 B2 B3 B4 B5 C1 C2 C3 C4 0.388 0.407 0.395 0.407 0.414 0.385 0.384 0.398 0.394 0.403 0.387 0.414 0.390

[0125] Calculate the correlation coefficient between each index:

[0126]

[0127] Calculate the information content C j :

[0128] A1 A2 A3 A4 B1 B2 B3 B4 B5 C1 C2 C3 C4 0.007 0.005 0.003 0.004 0.028 0.020 0.030 0.029 0.029 0.048 0.019 0.029 0.027

[0129] Calculate the weight W of each index j :

[0130] A1 A2 A3 A4 B1 B2 B3 B4 B5 C1 C2 C3 C4 0.386 0.272 0.149 0.192 0.209 0.150 0.218 0.212 0.211 0.385 0.156 0.237 0.222

[0131] The weighted results of each index layer of the finally obtained comprehensive evaluation system for efficient water use of crops are as Figure 3 shown.

[0132] After obtaining the objective weights and subjective weights, in step S5, when calculating the comprehensive level of the efficient water use model of crops, the comprehensive weighting formula is as follows:

[0133] Q i = a×v i +(1 - a)w i ;

[0134] where, Q i is the total weight of the i-th factor, v i is the objective weight of the i-th factor, w iis the subjective weight of the i-th factor, and a is the coefficient of the combined weight.

[0135] Taking the subjective weight obtained by the analytic hierarchy process and the objective weight obtained by the CRITIC weight method as an example above, through the comprehensive weighting formula Q i = a × v i + (1 - a)w i the comprehensive weight is calculated to complete the evaluation of the multi-objective function. The evaluation results of the high-efficiency water use model are obtained. According to the evaluation results, it can be fed back to the crop water irrigation in the actual research area, so as to achieve water conservation and improve the utilization rate of water resources.

[0136] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation of the present invention.

[0137] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0138] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection, an electrical connection or communicable with each other; it can be directly connected, or indirectly connected through an intermediate medium, and can be the internal communication of two elements or the interaction relationship between two elements, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0139] In the present invention, unless otherwise clearly specified or limited, the first feature being "on" or "under" the second feature may mean that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Further, the first feature being "above", "over" and "on top of" the second feature may mean that the first feature is directly above or obliquely above the second feature, or merely indicates that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "below" and "beneath" the second feature may mean that the first feature is directly below or obliquely below the second feature, or merely indicates that the horizontal height of the first feature is less than that of the second feature.

[0140] In the present invention, the terms "an embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without conflicting with each other, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples.

[0141] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods, characterized in that: The following steps are involved: S1. Obtain relevant data in the study area, including meteorological data, soil data, water resources data, and irrigation and fertilization system in the study area; S2. According to the planting scenarios of different crops and the relevant data obtained in the corresponding scenarios, they are input into the crop model for simulation to obtain various indicator parameters that affect the research results of different planting scenarios in the study area; S3, using the various parameter indicators obtained in S2 as predictive variables, constructing sample data, and inputting them into the random forest algorithm to compensate for the deviation caused by unclear information or insufficient knowledge reserve in the crop model, optimize the crop model, and output the optimized various parameter indicators; S4. Use the analytic hierarchy process to establish a crop water efficiency evaluation model, taking the crop water efficiency model as the target layer, the various factors that affect the research results of different planting scenarios in the study area as the criterion layer, and the various optimized index parameters obtained in step S3 as the indicator layer; S5. Calculate and analyze the subjective weight and objective weight of the indicator layer and the criterion layer. Use the analytic hierarchy process to calculate the subjective weight, and use the CRITIC weight method to calculate the objective weight. Perform a weighted calculation again on the subjective weight obtained by the analytic hierarchy process and the objective weight obtained by the CRITIC weight method to finally obtain the comprehensive weight of the criterion layer and the indicator layer. S6, combining steps S4 and S5 to obtain the evaluation results of the crop efficient water use model; The multiple index parameters obtained in step S2 include water utilization rate, crop water productivity, and nitrogen fertilizer utilization efficiency; The various factors affecting the research results of different planting scenarios in the research area described in step S4 include resource input and utilization efficiency, yield and quality, and environmental benefit factors; The optimization of crop models using the random forest algorithm includes the following steps: S31. Crop yield, soil water content, water use efficiency (WUE), crop water productivity (WP), and nitrogen utilization efficiency (NUE) were used as characteristic variables of the random forest algorithm; S32, adjusting and optimizing crop parameters, soil parameters, and irrigation and fertilization parameters according to the random forest algorithm, and obtaining an optimized crop model accordingly; S33, inputting different combinations of meteorological data, soil data, crop yield and irrigation and fertilization system data into the adjusted and optimized crop model for simulation, and outputting optimized simulation values ​​for various index parameters obtained in step S2; S34. The output optimized simulation values ​​are used as the indicator layer of the hierarchical analysis method.

2. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 1, characterized in that: The crop model adopts the DSSAT model.

3. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 1 is characterized in that: In step S3, the regression decision tree of the random forest algorithm is expressed as: Where h(x) is the final prediction result of the random forest algorithm, h(x,θ i ) is the prediction result of a regression decision tree in the random forest algorithm, x is the set of corresponding feature variables used by the decision tree, θ i is an independent and identically distributed random vector, K is the number of decision trees, and N is the number of training sample subsets.

4. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 3 is characterized in that: The corresponding feature variables used in the decision tree include water use efficiency (WUE), crop water productivity (WP), and nitrogen use efficiency (NUE), where: WUE=Y / W Where WUE is water use efficiency; Y is grain yield per unit area; W is water resource input; WP=Y / ET Where WP is crop water productivity; Y is grain yield per unit area; ET is field evapotranspiration; NUE=Y / N Where NUE is nitrogen fertilizer utilization efficiency; Y is grain yield per unit area; N is nitrogen application amount.

5. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 1, characterized in that: In the above S34, the output simulation values ​​include crop yield, simulated crop irrigation water utilization efficiency, simulated crop fertilizer utilization efficiency, and simulated crop soil moisture content.

6. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 1, characterized in that: In step S5, the calculation of subjective weights using the analytic hierarchy process includes the following steps: Construct an expert judgment matrix and perform pairwise comparison for scaling; calculate the judgment matrix weights using the arithmetic mean method; perform consistency checks; and calculate subjective weights.

7. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 1, characterized in that: In step S5, the calculation of objective weights using the CRITIC weight method includes the following steps: Construct the original data matrix; standardize the positive and negative indicators; calculate the information carrying capacity; calculate the objective weight.

8. The crop water efficiency model coupled with multiple evaluation indicators and multiple weighting methods as claimed in claim 1, characterized in that: In step S5, when calculating the comprehensive level of the crop water efficiency model, the comprehensive weighted formula is as follows: Q i =a×v i +(1-a)w i ; Among them, Q i The total weight of the i-th factor, v i is the objective weight of the ith factor, w i is the subjective weight of the ith factor, and a is the coefficient of the combined weight.

Images