Wheat and corn intercropping crop interspecific moisture optimization distribution evaluation method

Abstract

The invention provides a wheat and corn intercropping crop interspecific moisture optimal distribution evaluation method, and relates to the technical field of intercropping plants.The method comprises the steps that related feature data of intercropping crops after moisture optimal distribution is obtained, feature indexes are calculated based on the data, a convolutional neural network model is constructed, and the optimal distribution of moisture in the intercropping crops is evaluated; processing the characteristic index, outputting an interspecific moisture utilization grade index, further obtaining data of a transpiration rate and a dry matter accumulation rate, calculating a moisture utilization correction factor, generating a moisture utilization correction coefficient, establishing an upgrading and degrading mechanism, and comparing the correction coefficient with a preset threshold value, so as to correct the interspecific moisture utilization grade index. And determining a final moisture optimal distribution grade. Through accurate calculation and an intelligent model, efficient allocation of water resources is realized, and the resource utilization efficiency and yield of the intercropping system are improved.

Description

Technical Field

[0001] The invention relates to the technical field of intercropping, and in particular to a method for evaluating optimal water distribution among wheat and corn intercropping crops. Background Art

[0002] Intercropping wheat and corn is a widely used planting model in agricultural production, which can make full use of land resources and improve the efficiency of light and water use. However, due to the difference in water requirements between the two crops during the growth cycle, water competition between them has become a key issue affecting the yield and resource efficiency of the intercropping system. Traditional methods guide production through empirical irrigation and simple water allocation strategies, but they cannot accurately quantify the water requirements of different crops, which can easily lead to resource waste or yield loss.

[0003] At present, with the development of agricultural informatization and intelligence, water optimization allocation methods based on sensors, remote sensing monitoring and mathematical models are gradually emerging. Modern evaluation methods combine crop physiological parameters (such as transpiration rate, dry matter accumulation rate), environmental conditions (such as soil moisture content, climate conditions) and machine learning models (such as neural networks, optimization algorithms) to accurately allocate water between species, thereby improving water resource utilization efficiency and crop productivity. However, existing research still has certain limitations in terms of model complexity, data requirements and adaptability, and further optimization and promotion remain the key directions in the future.

[0004] In the prior art, traditional technical means are mainly operated through empirical methods and simple water allocation strategies. In agricultural production, irrigation management of wheat and corn intercropping systems is usually carried out based on farmers' experience or estimates of crop water requirements. Specifically, the irrigation time and amount of water are determined according to the key stages of the crop growth cycle (such as jointing stage and heading stage), or the same water resources are provided to the two crops through a unified irrigation method. This method is easy to operate, but it cannot accurately consider the physiological differences of crops, soil moisture distribution, and environmental changes, resulting in low water allocation efficiency.

[0005] Some traditional methods use field experiments to assist in the quantitative evaluation of water distribution. By measuring the yield of wheat and corn, changes in soil moisture content and water consumption efficiency under different irrigation modes, appropriate irrigation plans can be derived. However, these methods rely on a large amount of manual monitoring and long-term experiments, and can only provide reference data in specific areas and under specific conditions. They are difficult to be widely applied to planting environments with different climates, soils and crop combinations. In addition, traditional technologies usually ignore key physiological indicators such as crop transpiration rate and growth dynamics, and cannot achieve a true evaluation of optimal water distribution.

[0006] Therefore, it is necessary to provide a method for evaluating optimal water distribution among wheat and corn intercropping crops to solve the problem.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0008] The object of the present invention is to provide a method for evaluating optimal water distribution among wheat and corn intercropping crops to solve the problems raised in the above-mentioned background technology.

[0009] To achieve the above object, the present invention provides the following technical solutions: A method for evaluating optimal water distribution among wheat and corn intercropping crops, comprising the following specific steps: Step 1: Obtain relevant characteristic data of intercropped crops after water optimization distribution, wherein the relevant characteristic data include soil moisture content, crop moisture content, crop root depth, and total crop yield; Step 2: Calculate characteristic indexes for characterizing the production of wheat and corn after optimized interspecific water allocation based on the collected characteristic data, wherein the characteristic indexes include a resource conversion efficiency index, a growth efficiency index, and a yield stability index; Step 3: construct an interspecific water optimization evaluation model, using a convolutional neural network structure, including an input layer, a hidden layer and an output layer, wherein the input layer is used to receive the characteristic index generated by calculation, the hidden layer is used to perform data processing on the characteristic index, and the output layer is used to output the interspecific water utilization level index, and the interspecific water utilization level index includes efficient water utilization level, excellent water utilization level and inefficient water utilization level; Step 4: obtaining relevant crop growth data of the interspecific crops, wherein the relevant growth data include transpiration rate and dry matter accumulation rate, calculating and generating a water use correction factor according to the obtained growth data, and obtaining a characteristic index of the interspecific crops to be evaluated, and calculating a water use correction coefficient using the calculated water use correction factor and the characteristic index of the interspecific crops to be evaluated; Step 5: Establish a promotion and demotion mechanism, compare the water utilization correction coefficient of the interspecific crops to be evaluated with the preset correction threshold range, and correct the interspecific water utilization level index according to the comparison result to determine the final interspecific water utilization level index for the optimal water allocation of the interspecific crops to be evaluated.

[0010] Furthermore, the characteristic index used to characterize the production of wheat and corn after the optimized water distribution among species is calculated based on the collected characteristic data, and the method is based on: The resource conversion efficiency index of crops is calculated based on the total crop yield of wheat and corn, soil moisture and crop moisture content in the collected characteristic data. The formula is: ; in, Represents the resource conversion efficiency index of crops, is the soil moisture content, is the crop moisture content, is the total crop yield; The crop growth efficiency index is calculated based on the total crop yield and crop root depth in the collected characteristic data, and the formula is as follows: ; in, Represents the growth efficiency index of crops, is the crop root depth; According to the total yield of crops, the average yield of crops in a period of time after water distribution and the total yield variance of crops in the same period of time are obtained. The yield stability index of crops is calculated using the average yield and yield variance of crops. The formula is as follows: ; in, Represents the crop yield stability index, is the average crop yield, is the crop yield variance.

[0011] Furthermore, an interspecific water optimization evaluation model was constructed based on the following method: The inter-specific water optimization evaluation model adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is responsible for receiving the generated feature index; the hidden layer is used to extract local and high-level features in the input feature data. By applying multiple convolution kernels, the hidden layer can recognize complex feature patterns. By using the ReLu activation function, nonlinear relationships are introduced so that the model can fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the feature index representation extracted by the hidden layer into the final prediction result, that is, outputting the inter-specific water utilization level index.

[0012] Furthermore, relevant crop growth data of interspecific crops are obtained, and the water utilization correction factor is calculated based on the obtained growth data, and the formula is as follows: The water use correction factor is calculated based on the transpiration rate and dry matter accumulation rate of the crop, and the formula is: ; in, represents the water use correction factor, is the dry matter accumulation rate of the crop, is the transpiration rate of the crop.

[0013] Furthermore, the characteristic index of the interspecific crop to be evaluated is obtained, and the water use correction factor generated by calculation and the characteristic index of the interspecific crop to be evaluated are used to calculate the water use correction coefficient, and the formula based on this is: ; in, represents the water use correction factor, is the water use correction factor.

[0014] Furthermore, the final interspecific water use level index for the optimal water allocation of the interspecific crops to be evaluated is determined based on the following method: Establish a promotion and demotion mechanism. The inter-species water use level indicators include high-efficiency water use level, good water use level and low-efficiency water use level, and preset correction threshold intervals. , the generated water use correction coefficient is compared with the correction threshold interval, combined with the interspecific water use level of the interspecific crops to be evaluated output by the interspecific water optimization evaluation model, when When , the interspecific water utilization grade of the interspecific crops to be evaluated is used as the final interspecific water utilization grade indicator; when When , the interspecific water utilization level of the interspecific crops to be evaluated is increased by one level as the final interspecific water utilization level indicator; when When the interspecific water utilization level of the interspecific crops to be evaluated is output, the interspecific water utilization level will be reduced by one level as the final interspecific water utilization level indicator; when the interspecific water utilization level output by the model belongs to the high-efficiency water utilization level, it is limited that no upgrading operation is required; when the interspecific water utilization level output by the model belongs to the low-efficiency water utilization level, it is limited that no downgrading operation is required.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention effectively improves water use efficiency and crop yield through an interspecific crop production evaluation method with optimized water allocation. The multi-dimensional characteristic index is used to comprehensively evaluate crop performance, so that agricultural managers can fully understand the status of crops in the process of water use and growth. In addition, the intelligent decision-making model based on convolutional neural network can process complex data and provide accurate water use level prediction, thereby supporting precision agricultural decision-making and promoting sustainable agricultural development; The present invention overcomes the limitations of the traditional single-index evaluation method, and can comprehensively consider multiple factors to comprehensively evaluate the growth status of crops. In addition, the flexible upgrade and downgrade mechanism dynamically adjusts the actual performance of different crops, avoiding the inadaptability caused by fixed evaluation standards. In addition, combined with modern data processing technology, it improves the level of intelligent decision-making, solves the inefficiency of relying on experience judgment in the past, and enhances the scientificity and practicality of crop water management; In traditional water allocation methods, water competition among crops is usually not fully considered, resulting in irrational water allocation. The present invention uses a convolutional neural network model to effectively process and mine the potential laws in complex feature data, thereby providing efficient and accurate model predictions for the evaluation of inter-species water utilization levels. This data-driven method can help agricultural managers make more accurate decisions, and the established upgrade and downgrade mechanism can be dynamically adjusted according to the water utilization correction coefficient and the preset correction threshold interval, enhancing the flexibility and adaptability of the system. This mechanism can adjust the water utilization level of crops in a timely manner according to their actual performance to ensure the rational allocation of resources.

[0016] The present invention accurately realizes the optimal allocation of water for intercropping wheat and corn by collecting multi-dimensional crop characteristic data and combining it with a convolutional neural network model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0019] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] Example: See also Figure 1 , a method for evaluating optimal water allocation among wheat and corn intercropping crops, comprising the following specific steps: Step 1: Obtain relevant characteristic data of intercropped crops after water optimization distribution, wherein the relevant characteristic data include soil moisture content, crop moisture content, crop root depth, and total crop yield; Step 2: Calculate characteristic indexes for characterizing the production of wheat and corn after optimized interspecific water allocation based on the collected characteristic data, wherein the characteristic indexes include a resource conversion efficiency index, a growth efficiency index, and a yield stability index; Step 3: construct an interspecific water optimization evaluation model, using a convolutional neural network structure, including an input layer, a hidden layer and an output layer, wherein the input layer is used to receive the characteristic index generated by calculation, the hidden layer is used to perform data processing on the characteristic index, and the output layer is used to output the interspecific water utilization level index, and the interspecific water utilization level index includes efficient water utilization level, excellent water utilization level and inefficient water utilization level; Step 4: obtaining relevant crop growth data of the interspecific crops, wherein the relevant growth data include transpiration rate and dry matter accumulation rate, calculating and generating a water use correction factor according to the obtained growth data, and obtaining a characteristic index of the interspecific crops to be evaluated, and calculating a water use correction coefficient using the calculated water use correction factor and the characteristic index of the interspecific crops to be evaluated; Step 5: Establish a promotion and demotion mechanism, compare the water utilization correction coefficient of the interspecific crops to be evaluated with the preset correction threshold range, and correct the interspecific water utilization level index according to the comparison result to determine the final interspecific water utilization level index for the optimal water allocation of the interspecific crops to be evaluated.

[0021] It should be noted that these characteristic indices can not only quantify the performance of crops in the process of water use and resource conversion, but also provide an in-depth understanding of the adaptability of crops in different growing environments. Through scientific calculation methods, these indices provide agricultural managers with data-based decision-making, helping them optimize water management, increase crop yields and ensure yield stability, thereby achieving the development goal of sustainable agriculture.

[0022] Therefore, it is necessary to calculate the characteristic index to characterize the production of wheat and corn after the optimal distribution of water among species based on the collected characteristic data. The method is as follows: The resource conversion efficiency index of crops is calculated based on the total crop yield of wheat and corn, soil moisture and crop moisture content in the collected characteristic data. The formula is: ; in, Represents the resource conversion efficiency index of crops, is the soil moisture content, is the crop moisture content, is the total crop yield; in the above formula, the total crop yield The higher the resource conversion efficiency index The larger the crop is, the more water it can convert into yield. The increase in indicates that the crop is more efficient in using water; The smaller, The larger it is, the more it means that after water distribution optimization, crops can increase crop yields in a less water environment, indicating that the crop's water utilization efficiency is improved.

[0023] The crop growth efficiency index is calculated based on the total crop yield and crop root depth in the collected characteristic data, and the formula is as follows: ; in, Represents the growth efficiency index of crops, is the crop root depth; in the above formula, the crop root depth The bigger the root, the deeper the root system, and the crops can effectively obtain water and nutrients from deeper layers, which increases the growth rate of crops. Exponential growth; the total yield of the crop at the same root depth and water content Improvement means that crops are more efficient in using resources. The increase in the index indicates that the growth effect of the crop has improved and higher production efficiency can be achieved; Increase, An increase in the index means that the crop is in a better physiological state and can carry out photosynthesis and nutrient synthesis more efficiently.

[0024] According to the total yield of crops, the average yield of crops in a period of time after water distribution and the total yield variance of crops in the same period of time are obtained. The yield stability index of crops is calculated using the average yield and yield variance of crops. The formula is as follows: ; in, Represents the crop yield stability index, is the average crop yield, is the crop yield variance; in the above formula, The bigger, The larger the variance, the higher the average yield, which reflects more efficient resource utilization. In addition, when other conditions remain unchanged, a high average yield usually means that the growth state of crops in different time periods is more consistent, showing better stability. The reason why it is used as the denominator is that the size of the variance can reflect the volatility of crop yield. The smaller it is, the smaller the volatility of crop yield is, which means that the crop shows higher production capacity and better stability during the growth cycle.

[0025] It should be noted that the convolutional structure of the neural network is used because it can improve water use efficiency, automatically extract complex features and capture nonlinear relationships, and enhance the predictive ability of the model. The model provides a scientific basis for agricultural producers to develop more effective water management strategies, thereby increasing crop yields and reducing water waste, and promoting the intelligent and sustainable development of agriculture. In addition, by outputting water use level indicators, it helps support diversified crop planting and promote a healthy agricultural ecosystem.

[0026] Therefore, it is necessary to construct an interspecific water optimization evaluation model based on the following method: The interspecific water optimization evaluation model adopts a neural network convolution structure, including an input layer, a hidden layer, and an output layer. The input layer is responsible for receiving the generated feature index; the hidden layer is used to extract local and high-level features from the input feature data. By applying multiple convolution kernels, the hidden layer can identify complex feature patterns. By using the ReLu activation function, nonlinear relationships are introduced so that the model can fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the feature index representation extracted by the hidden layer into the final prediction result, that is, outputting the interspecific water utilization level index; The relevant characteristic indexes of crops after the previous interspecific water optimization allocation are obtained, and the water utilization degree of crops after the optimized allocation is evaluated by experts, and the water utilization degree of crops is divided into high-efficiency water utilization level, good water utilization level and low-efficiency water utilization level. The relevant characteristic indexes of crops after the previous interspecific water optimization allocation are used as input, and the water utilization level index is used as the output label to train the interspecific water optimization evaluation model. During the training process, the mean square error function is selected as the loss function, and the loss function value is calculated according to the output result and the true label. The gradient is calculated by the back propagation algorithm, and the weight and bias of the neural network are updated. The above operation is repeated until the model reaches the predetermined number of training rounds.

[0027] It should be noted that the calculation of the correction factor can accurately reflect the water use efficiency of crops under specific environmental conditions, and provide a scientific basis for agricultural producers to adjust irrigation strategies and water allocation, thereby achieving effective use of resources and sustainable development, and ultimately improving crop yield and quality.

[0028] Therefore, it is necessary to obtain relevant crop growth data of interspecific crops and calculate the water use correction factor based on the obtained growth data. The formula is: The water use correction factor is calculated based on the transpiration rate and dry matter accumulation rate of the crop, and the formula is: ; in, represents the water use correction factor, is the dry matter accumulation rate of the crop, is the transpiration rate of the crop; in the above formula, The larger the The larger the size, the more biomass the crop can accumulate per unit time. Reduction will also lead to becomes larger, indicating that the biomass consumed per unit time decreases, while The increase indicates that crops are more efficient in obtaining water and converting it into growth, which means that crops can better utilize water resources and improve their growth status and yield.

[0029] It should be noted that by calculating the water use correction factor, agricultural producers can more comprehensively evaluate the water use efficiency of different crops in specific environments, and then formulate more accurate irrigation strategies and water management plans, thereby improving the overall health level and yield of crop growth. This not only helps to improve the utilization efficiency of agricultural resources, but also promotes the development of sustainable agriculture and achieves a win-win situation of economic and ecological benefits.

[0030] Therefore, it is necessary to obtain the characteristic index of the interspecific crops to be evaluated, and use the calculated water use correction factor and the characteristic index of the interspecific crops to be evaluated to calculate the water use correction coefficient. The formula is: ; in, represents the water use correction factor, is the water use correction factor; in the above formula, by establishing a linear cube root relationship, the nonlinear influence of each index on the water use correction coefficient is reflected. The cube root makes the numerical change smoother, avoids excessive amplification of the result when the index value is too large, and helps to mitigate the impact of extreme values; The bigger, The smaller the RCEI is, the introduction of the square of the resource conversion efficiency index is conducive to amplifying the performance of crops in terms of water use efficiency. When the water use efficiency of crops is improved, the value of RCEI will increase significantly, and its influence will be amplified in the form of a square, which means that the improvement of the efficiency of crop resource conversion will have an accelerating effect on the final result, and it has a stronger sensitivity in optimizing resource allocation; By using an exponential function to reflect the nonlinear characteristics of crop growth affected by environmental conditions, especially when resources are abundant, the benefits of crop growth will experience exponential growth. This design makes it easy to identify changes in crop growth potential; The logarithmic function is used to show that as the average yield increases, the impact on the water use correction factor will gradually decrease. This is because under a high level of yield stability, the increased benefit effect will gradually decrease. The introduction of the logarithmic function can better deal with the volatility and stability of yield, emphasizing the importance of water use under high stability conditions; the correction factor The bigger, The smaller it is, the better the crop growth performance is, the higher the water use efficiency is, and the less correction is needed to the model output; therefore The smaller the value, the better, which means the model output is more accurate and can reflect the actual growth status of crops and the degree of water utilization.

[0031] It should be noted that by establishing an upgrade and downgrade mechanism and comparing the water use correction coefficient with the preset correction threshold range, the water use efficiency of crops under different environments can be scientifically evaluated. The classification of efficient, excellent and inefficient water use levels enables agricultural producers to accurately identify the water use performance of crops and formulate targeted irrigation strategies and management plans. When the water use level output by the model is consistent with the preset standard, good management measures can be effectively consolidated. When adjustments are needed, timely upgrades or downgrades can help improve overall water use efficiency, ultimately promoting the development of sustainable agriculture and ensuring a win-win situation for economic and ecological benefits.

[0032] Therefore, it is necessary to determine the final interspecific water use level index for the optimal water allocation of the interspecific crops to be evaluated, based on the following method: Establish a promotion and demotion mechanism. The inter-species water use level indicators include high-efficiency water use level, good water use level and low-efficiency water use level, and preset correction threshold intervals. , the generated water use correction coefficient is compared with the correction threshold interval, combined with the interspecific water use level of the interspecific crops to be evaluated output by the interspecific water optimization evaluation model, when When , the interspecific water utilization grade of the interspecific crops to be evaluated is used as the final interspecific water utilization grade indicator; when When , the interspecific water utilization level of the interspecific crops to be evaluated is increased by one level as the final interspecific water utilization level indicator; when When the interspecific water utilization level of the interspecific crops to be evaluated is output, the interspecific water utilization level will be reduced by one level as the final interspecific water utilization level indicator; when the interspecific water utilization level output by the model belongs to the high-efficiency water utilization level, it is limited that no upgrading operation is required; when the interspecific water utilization level output by the model belongs to the low-efficiency water utilization level, it is limited that no downgrading operation is required.

[0033] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0034] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0035] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0036] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for evaluating optimal water distribution among wheat and corn intercropping crops, characterized in that: The specific steps include: Step 1: Obtain relevant characteristic data of intercropped crops after water optimization distribution, wherein the relevant characteristic data include soil moisture content, crop moisture content, crop root depth, and total crop yield; Step 2: Calculate characteristic indexes for characterizing the production of wheat and corn after optimized interspecific water allocation based on the collected characteristic data, wherein the characteristic indexes include a resource conversion efficiency index, a growth efficiency index, and a yield stability index; Step 3: construct an interspecific water optimization evaluation model, using a convolutional neural network structure, including an input layer, a hidden layer and an output layer, wherein the input layer is used to receive the characteristic index generated by calculation, the hidden layer is used to perform data processing on the characteristic index, and the output layer is used to output the interspecific water utilization level index, and the interspecific water utilization level index includes efficient water utilization level, excellent water utilization level and inefficient water utilization level; Step 4: obtaining relevant crop growth data of the interspecific crops, wherein the relevant growth data include transpiration rate and dry matter accumulation rate, calculating and generating a water use correction factor according to the obtained growth data, and obtaining a characteristic index of the interspecific crops to be evaluated, and calculating a water use correction coefficient using the calculated water use correction factor and the characteristic index of the interspecific crops to be evaluated; Step 5: Establish a promotion and demotion mechanism, compare the water utilization correction coefficient of the interspecific crops to be evaluated with the preset correction threshold range, and correct the interspecific water utilization level index according to the comparison result to determine the final interspecific water utilization level index for the optimal water allocation of the interspecific crops to be evaluated.

2. The method for evaluating optimal water distribution among wheat and corn intercropping crops according to claim 1, characterized in that: The characteristic index used to characterize the production of wheat and corn after the optimal water distribution among species was calculated based on the collected characteristic data. The method is as follows: The resource conversion efficiency index of crops is calculated based on the total crop yield of wheat and corn, soil moisture and crop moisture content in the collected characteristic data. The formula is: ； in, Represents the resource conversion efficiency index of crops, is the soil moisture content, is the crop moisture content, is the total crop yield; The crop growth efficiency index is calculated based on the total crop yield and crop root depth in the collected characteristic data, and the formula is as follows: ； in, Represents the growth efficiency index of crops, is the crop root depth; According to the total yield of crops, the average yield of crops in a period of time after water distribution and the total yield variance of crops in the same period of time are obtained. The yield stability index of crops is calculated using the average yield and yield variance of crops. The formula is as follows: ； in, Represents the crop yield stability index, is the average crop yield, is the crop yield variance.

3. The method for evaluating optimal water distribution among wheat and corn intercropping crops according to claim 1, characterized in that: The interspecific water optimization evaluation model was constructed based on the following method: The inter-specific water optimization evaluation model adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is responsible for receiving the generated feature index; the hidden layer is used to extract local and high-level features in the input feature data. By applying multiple convolution kernels, the hidden layer can recognize complex feature patterns. By using the ReLu activation function, nonlinear relationships are introduced so that the model can fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the feature index representation extracted by the hidden layer into the final prediction result, that is, outputting the inter-specific water utilization level index.

4. The method for evaluating optimal water distribution among wheat and corn intercropping crops according to claim 1, characterized in that: Obtain relevant crop growth data of interspecific crops, and calculate the water use correction factor based on the obtained growth data. The formula is: The water use correction factor is calculated based on the transpiration rate and dry matter accumulation rate of the crop, and the formula is: ； in, represents the water use correction factor, is the dry matter accumulation rate of the crop, is the transpiration rate of the crop.

5. The method for evaluating optimal water distribution among wheat and corn intercropping crops according to claim 2, characterized in that: Obtain the characteristic index of the interspecific crop to be evaluated, and use the calculated water use correction factor and the characteristic index of the interspecific crop to be evaluated to calculate the water use correction coefficient. The formula is: ； in, represents the water use correction factor, is the water use correction factor.

6. The method for evaluating optimal water distribution among wheat and corn intercropping crops according to claim 1, characterized in that: The final interspecific water use level index for optimal water allocation among the crops to be evaluated is determined based on the following method: Establish a promotion and demotion mechanism. The inter-species water use level indicators include high-efficiency water use level, good water use level and low-efficiency water use level, and preset correction threshold intervals. , the generated water use correction coefficient is compared with the correction threshold interval, combined with the interspecific water use level of the interspecific crops to be evaluated output by the interspecific water optimization evaluation model, when When , the interspecific water utilization grade of the interspecific crops to be evaluated is used as the final interspecific water utilization grade indicator; when When , the interspecific water utilization level of the interspecific crops to be evaluated is increased by one level as the final interspecific water utilization level indicator; when When the interspecific water utilization level of the interspecific crops to be evaluated is output, it is reduced by one level as the final interspecific water utilization level indicator; when the interspecific water utilization level output by the model belongs to the high-efficiency water utilization level, it is limited that no upgrading operation is required; when the interspecific water utilization level output by the model belongs to the low-efficiency water utilization level, it is limited that no downgrading operation is required.

Images