Maize irrigation and fertilization decision-making method and system based on future meteorological data

Abstract

The invention discloses a corn irrigation and fertilization decision-making method and system based on future meteorological data, and relates to the technical field of agricultural informatization and intelligent agriculture, and the method comprises the steps: constructing a future meteorological prediction model based on an Informer + TSLANet + TimeBlock combined deep learning network; performing long-time sequence multi-dimensional feature extraction and long-term dependency relationship capture on historical meteorological data by using the model, and predicting to obtain future meteorological data; corn yield prediction is carried out through a DSSAT model, then a Monte Carlo + NSGA-III double-layer combination multi-objective optimization algorithm is utilized to formulate a corn irrigation and fertilization scheme, and an optimal irrigation and fertilization scheme is obtained after optimization. According to the method, the characterization capability of the future meteorological prediction model is enhanced, the accuracy of future meteorological data prediction is improved, and the accuracy and foresight of corn yield prediction and irrigation and fertilization decision prediction are further improved.

Description

Technical Field

[0001] The present application relates to the field of agricultural informatization and intelligent agricultural technology, and in particular to a method and system for making decisions on corn irrigation and fertilization based on future meteorological data. Background Art

[0002] Corn is widely planted in agriculture as an important food and feed crop. It is widely cultivated around the world due to its high yield, wide adaptability and economic value. As one of the crops with the largest planting area and the highest yield in the world, corn not only provides basic food for billions of people around the world, but is also an important industrial raw material and energy crop. Irrigation and fertilization have become key measures to ensure high corn yields. Relatively extensive irrigation methods not only cause waste of water resources, but also increase the risk of soil nitrogen loss. In addition, unreasonable use of nitrogen fertilizers not only has a negative impact on agriculture and soil ecology, but may also lead to excessive nitrate content in groundwater, threatening human health.

[0003] The existing meteorological forecasting process has problems such as poor representation ability and inaccurate forecast results. As a result, most of the existing irrigation and fertilization decisions are analyzed and made based on historical data. The decision-making schemes lack real-time and foresight, and it is difficult to adapt to the impact of climate change on corn planting. In addition, the research on irrigation and fertilization mainly focuses on individual irrigation decisions or individual fertilization decisions, which has certain limitations in practical applications and it is difficult to take into account both water resource utilization efficiency and fertilizer utilization efficiency at the same time. Summary of the invention

[0004] The purpose of this application is to provide a corn irrigation and fertilization decision-making method and system based on future meteorological data, which can enhance the characterization ability of the future meteorological forecast model, improve the accuracy of future meteorological data forecasts, and thus improve the accuracy and foresight of corn yield forecasts and irrigation and fertilization decision forecasts.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In the first aspect, the present application provides a corn irrigation and fertilization decision-making method based on future meteorological data, the method comprising: obtaining historical meteorological data; constructing a future meteorological prediction model based on an Informer+TSLANet+TimesBlock combined deep learning network; using the future meteorological prediction model to extract long-term series multidimensional features of historical meteorological data and capture long-term dependencies to predict future meteorological data; using the DSSAT model to predict corn yield based on future meteorological data to obtain the current season corn yield forecast result; formulating a corn irrigation and fertilization plan based on future meteorological data and the current season corn yield forecast result using a Monte Carlo+NSGA-III two-layer combined multi-objective optimization algorithm, and obtaining the optimal irrigation and fertilization plan after optimization.

[0007] In a second aspect, the present application provides a computer system, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned corn irrigation and fertilization decision-making methods based on future meteorological data.

[0008] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0009] The present application obtains historical meteorological data; constructs a future meteorological prediction model based on the Informer+TSLANet+TimesBlock combined deep learning network; uses the future meteorological prediction model to extract long-term series multidimensional features of historical meteorological data and capture long-term dependencies to predict future meteorological data; by using the TSLANet module to capture the long-term dependencies of long-term series, and using the TimesBlock module to extract the frequency domain features of meteorological data, the Informer model's ability to understand long-term series is further improved, thereby enhancing the representation ability of the future meteorological prediction model and improving the accuracy of future meteorological data prediction; by using the DSSAT model to predict corn yield based on future meteorological data, the prediction result of corn yield in the current season is obtained; based on future meteorological data and the prediction result of corn yield in the current season, the irrigation and fertilization plan of corn is formulated using the Monte Carlo+NSGA-III double-layer combined multi-objective optimization algorithm, and the optimal irrigation and fertilization plan is obtained after optimization; using future meteorological data as input, the corn yield is predicted, and the optimal irrigation and fertilization plan is further obtained, which improves the real-time, accuracy and foresight of corn yield prediction and irrigation and fertilization decision prediction, and takes into account the water resource utilization efficiency and fertilizer utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 A schematic diagram of a corn irrigation and fertilization decision-making method based on future meteorological data provided in an embodiment of the present application Figure 1 .

[0012] Figure 2 A schematic diagram of a corn irrigation and fertilization decision-making method based on future meteorological data provided in an embodiment of the present application Figure 2 .

[0013] Figure 3 A schematic diagram of the flow of the future weather forecast model provided in an embodiment of the present application.

[0014] Figure 4 A schematic diagram of the structure of the Informer+TSLANet+TimesBlock combined deep learning network provided in an embodiment of the present application.

[0015] Figure 5 A schematic diagram of the structure of the TSLANet module provided in an embodiment of the present application.

[0016] Figure 6 A schematic diagram of the structure of the TimesBlock module provided in an embodiment of the present application.

[0017] Figure 7 A schematic diagram of the DSSAT model training process provided in an embodiment of the present application.

[0018] Figure 8 A schematic flow chart of the Monte Carlo and NSGA-III dual-layer combined multi-objective optimization algorithm provided in the embodiments of the present application.

[0019] Fig. 9 This is a graph of the original meteorological combination optimization results for 2018 provided in an embodiment of the present application.

[0020] Fig.10 This is a graph of the original meteorological combination optimization results for 2019 provided in an embodiment of the present application.

[0021] Fig.11 A schematic diagram of the structure of a computer system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0024] Embodiment 1, as Figure 1-Figure 2 As shown, this embodiment provides a corn irrigation and fertilization decision-making method based on future meteorological data, and the method includes the following steps.

[0025] S1. Obtain historical meteorological data.

[0026] Furthermore, the meteorological data specifically include: daily maximum temperature, daily minimum temperature, daily average solar radiation and daily rainfall.

[0027] S2. Construct a future weather forecast model based on the Informer+TSLANet (Time Series Lightweight Adaptive Network)+TimesBlock combined deep learning network.

[0028] Further, Figure 3-Figure 4 As shown, the Informer+TSLANet+TimesBlock combined deep learning network includes a TSLANet module, a TimesBlock module and an Informer model connected in series in sequence.

[0029] In actual application, the Informer+ TSLANet+TimesBlock combined deep learning model is an innovative time series analysis model. By integrating the Informer model, TSLANet and TimesBlock technology, the ability and efficiency of processing time series data are significantly improved, and the advantages of each technology are fully utilized to handle the complexity and dynamics of time series data through a unified architecture. Among them, the Informer model is used to deal with long time series prediction problems. It has an efficient self-attention mechanism, can capture long-term dependencies, build and train the Informer model, and make preliminary predictions on meteorological data. The TSLANet module is added to the Informer model. After embedding encoding, it captures the relationship between the multi-dimensional data of meteorological data and increases data features. After TSLANet, the TimesBlock module further extracts the frequency domain features of meteorological data through multi-dimensional convolution, improving the model's ability to understand time series data.

[0030] First, Figure 5 As shown, the application of TSLANet layer: The present invention first uses TSLANet layer to perform preliminary data processing. The TSLANet layer structure includes an interactive convolution block and an adaptive spectrum block, which are equipped with layer normalization processing, so that the model can effectively identify and analyze periodic and non-periodic patterns in time series data. The design of this layer not only improves the processing ability of local features of data, but also optimizes data flow and information interpretability.

[0031] Specifically, the TSLANet module consists of two main parts: the interactive convolution block (ICB) and the adaptive spectral block (ASB). These two parts are connected and processed through layer normalization. Through the collaborative work of ICB and ASB, TSLANet not only enhances the local feature extraction capability of time series data, but also optimizes the processing capability of global frequency domain features to enhance the feature extraction and processing capabilities of time series data.

[0032] 1) Composition and function of interactive convolutional block (ICB): ICB contains two one-dimensional convolutional layers, which are used to extract local features in time series data. One-dimensional convolutional layers are particularly suitable for processing time series data because they can effectively capture the temporal dependencies in the sequence. In addition, each convolutional layer is followed by a GELU (Gaussian ErrorLinear Unit) activation function, which helps introduce nonlinearity and enables the model to learn more complex data patterns. Finally, the residual connection in ICB (represented by the addition operation of the cross connection) helps to retain the original information of the input signal and reduce the information loss that may occur during training, thereby increasing the training depth of the model without causing performance degradation.

[0033] 2) Composition and function of adaptive spectrum block (ASB): ASB uses Fast Fourier Transform (FFT) and Inverse Fast Fourier Transform (IFFT), which enable the model to analyze and process signals in the frequency domain. Frequency domain analysis is particularly effective for identifying and processing periodic and non-periodic patterns in time series data. At the same time, through adaptive masking technology, ASB can dynamically adjust the importance distribution in the frequency domain, emphasizing important frequency components and suppressing unimportant frequency components. This mechanism improves the model's sensitivity to important features in the signal and enhances the model's prediction accuracy and generalization ability.

[0034] Second, if Figure 6 As shown, the integration of TimesBlock technology: The present invention further integrates the TimesBlock module in the Informer structure to optimize the process of data flowing through the encoder and decoder. The TimesBlock module focuses on processing the time dimension changes in time series data, and through multi-scale analysis of the time dimension, it improves the accuracy and robustness of the model in predicting future trends.

[0035] As a multifunctional time processing unit, TimesBlock not only enhances the time characteristics of the signal through multi-scale analysis, but also optimizes the processing of periodicity and frequency components through FFT and Softmax, thus improving the model's understanding depth and prediction ability of time series data.

[0036] 1) Fast Fourier Transform (FFT) component: This module first uses FFT to convert the input time series data from the time domain to the frequency domain. This step is key to revealing the periodicity and main frequency components of the data, laying the foundation for subsequent data analysis and feature extraction.

[0037] 2) Parameter-efficient Inception block: After FFT, the time series data is fed into a parameter-efficient Inception block. This block is specially designed for feature extraction at different time scales, capturing a wide range of time series dynamics through multi-scale convolution kernels. The high parameter efficiency of this design ensures that the model optimizes the use of computing resources while maintaining high performance.

[0038] 3) Adaptive Masking and Softmax Operation: In order to further emphasize the important frequency components in the data and suppress unimportant information, adaptive masking technology is used to dynamically select key frequencies. Softmax operation is then used to normalize the importance of these frequency components to ensure the reliability and accuracy of the model output.

[0039] 4) Inverse Fast Fourier Transform (IFFT): After the important frequency components are selected and weighted, the processed frequency domain data is converted back to time domain data using IFFT. This reconstruction step is key to ensuring that the model can accurately recover the signal in the time domain.

[0040] 5) Output layer: After the above series of fine processing, the data is finally output for direct use by Informer. This ensures that the data output from TimesBlock maintains a high degree of information integrity and practicality.

[0041] Third, the integration of Informer core technology: the data processed by the TSLANet layer is input into the encoder and decoder of the Informer model. In this part, the present invention adopts a multi-head probabilistic sparse self-attention mechanism, which significantly enhances the model's ability to capture long-term dependencies while maintaining high computational efficiency. This approach ensures the model's high efficiency and powerful performance in processing various complex time series tasks.

[0042] S3. Use the future weather forecast model to extract long-term multi-dimensional features of historical weather data and capture long-term dependencies to predict future weather data.

[0043] Furthermore, step S3 specifically includes the following steps.

[0044] S31. Substitute historical meteorological data into future meteorological prediction models.

[0045] S32. The TSLANet module is used to analyze the periodic and non-periodic patterns in the long time series of historical meteorological data. By processing the local characteristics of the long time series, the historical meteorological data are optimized from the data flow and information representation levels to obtain the optimized historical meteorological data.

[0046] S33. Use the TimesBlock module to perform multi-scale analysis on the optimized historical meteorological data from the time dimension to obtain the historical meteorological data after multi-scale analysis.

[0047] S34. Substitute the historical meteorological data after multi-scale analysis into the Informer model, and use the multi-head probabilistic sparse self-attention mechanism to capture the long-term dependencies of long time series in the historical meteorological data after multi-scale analysis to predict future meteorological data.

[0048] Optionally, the training process of the future weather forecast model is as follows.

[0049] Filter meteorological data at different times as training sets and validation sets.

[0050] The weather data at the previous moment is used as input, and the weather data at the next moment is used as output to train the future weather forecast model.

[0051] Use the validation set to evaluate the prediction performance of the future weather forecast model and adjust the model parameters to improve the prediction accuracy. Deao trained the future weather forecast model.

[0052] S4. Figure 7 As shown in the figure, the DSSAT model is used to predict corn yield based on future meteorological data, and the forecast results of corn yield in the current season are obtained.

[0053] Furthermore, the training process of the DSSAT model is as follows.

[0054] Training data and verification data for corn yield prediction are obtained based on corn planting environment data screening; the corn planting environment data specifically includes: historical meteorological data, historical soil data, corn variety data, farmer planting profile data and crop growth information.

[0055] Based on the training data, the genetic parameters of the DSSAT model are optimized in a fitting and calibrated manner (the growth process of corn in the current season is simulated to generate simulated data at different growth stages). The accuracy and stability of the DSSAT model are evaluated using the validation data, and finally the trained DSSAT model is determined.

[0056] Furthermore, the soil data specifically includes: soil type, soil texture and soil nutrient content; the corn variety data specifically includes: growth cycle of different corn varieties and yield of different corn varieties; the farmer planting profile data specifically includes: planting area, fertilization and irrigation method and planting density; the crop growth information specifically includes: growth stage, growth parameters and yield records.

[0057] In actual application, the construction and verification process of the DSSAT model is as follows.

[0058] 1) Data import: Import the collected corn planting environment data (historical soil data, historical meteorological data, corn variety data, farmer planting profile data and crop growth information) into the DSSAT model.

[0059] 2) Model calibration: The DSSAT model is calibrated using corn planting environment data, and the model parameters are adjusted to fit the historical yield of corn crops. By adjusting the model parameters, the simulated yield output by the model is made close to the actual historical yield, verifying the accuracy of the model.

[0060] 3) Model validation: The model was validated using corn planting environment data that was not calibrated to ensure that the model could accurately predict corn yields under different planting conditions. The accuracy and stability of the model were evaluated by comparing the model predictions with the actual observations.

[0061] S5. Figure 8 As shown in the figure, based on the future meteorological data and the forecast results of corn yield in the current season, the irrigation and fertilization plan of corn is formulated using the Monte Carlo + NSGA-III double-layer combination multi-objective optimization algorithm, and the optimal irrigation and fertilization plan is obtained after optimization.

[0062] Furthermore, step S5 specifically includes the following steps.

[0063] S51. Determine optimization goals; the optimization goals are: maximizing yield, minimizing irrigation amount, and minimizing fertilization amount.

[0064] Optionally, optimization objectives are determined to ensure that corn yields are increased to meet market demand while reducing irrigation water usage and improving water resource utilization efficiency; reducing fertilizer usage and reducing environmental pollution.

[0065] S52. Based on future meteorological data and the forecast results of corn yield in the current season, the Monte Carlo model was used to adopt the method of repeated random sampling, and all possible combinations of irrigation and fertilization dates were randomly generated with potential management strategies as the irrigation and fertilization plan for corn.

[0066] Alternatively, the fertigation scheme for corn is to generate multiple irrigation and fertilization schemes based on random combinations of multiple irrigation and fertilization dates, covering all possible management strategies.

[0067] S53. The irrigation and fertilization scheme of corn is used as the initial population of the NSGA-III multi-objective optimization algorithm. After multiple iterations of optimization, the optimal trade-off solution (Pareto optimal solution) between multiple optimization objectives is obtained as the optimal irrigation and fertilization scheme.

[0068] Furthermore, after multiple iterations of optimization, the optimal trade-off solution between multiple optimization objectives is obtained as the optimal irrigation and fertilization plan, which specifically includes: using the NSGA-III multi-objective optimization algorithm to evaluate the initial population individuals using non-dominated sorting and crowding distance calculation, generating a new generation of solutions through crossover and mutation operations, and using uniformly distributed reference points to maintain the uniformity of the population, and repeatedly executing the algorithm until the preset number of iterations is reached or the solution quality is stable, providing decision makers with the optimal trade-off solution between multiple optimization objectives.

[0069] In actual application, the actual operation process of step S5 is as follows.

[0070] 1) Determine the optimization goal.

[0071] 2) Determine the number of irrigation times X1.

[0072] 3) Determine the number of nitrogen applications X2.

[0073] 4) Repeat.

[0074] 5) Generate X1 random dates for irrigation application.

[0075] 6) Generate X2 random dates for nitrogen fertilizer application.

[0076] 7) Run U-NSGA-III with the given irrigation and nitrogen application rates on the given dates as variables.

[0077] 8) Combine the solution from step 6 with the solutions found in previous iterations.

[0078] 9) Delete non-optimal solutions from the combined solution set.

[0079] The following parts are explained in more detail.

[0080] First, determine the optimization goals: determine the three optimization goals of maximizing yield, minimizing irrigation, and minimizing fertilization, to ensure that corn yields are increased and market demand is met while reducing irrigation water consumption and improving water resource utilization efficiency; reducing fertilizer use and reducing environmental pollution.

[0081] Second, Monte Carlo random irrigation generation: Monte Carlo random algorithm is a computational method based on probability and statistical theory, which aims to solve physical and mathematical problems through repeated random sampling. By randomly generating a series of possible irrigation and fertilization date combinations, these combinations reflect potential management strategies and provide a basis for the next step of optimization.

[0082] Third, NSGA-III multi-objective optimization processing: NSGA-III is a multi-objective optimization algorithm suitable for handling complex optimization problems with three or more objectives. The algorithm starts with a randomly generated population and evaluates individuals through non-dominated sorting and crowding distance calculation to ensure the diversity and quality of solutions. NSGA-III uses crossover and mutation operations to generate a new generation of solutions, while introducing uniformly distributed reference points to maintain the uniformity of the population. The algorithm is repeated until the preset number of iterations is reached or the solution quality is stable, providing decision makers with the optimal trade-off solution between multiple optimization objectives. In this embodiment, the lower layer uses NSGA-III multi-objective optimization to find the Pareto optimal solution set for each Monte Carlo randomly generated irrigation and fertilization date.

[0083] Furthermore, before step S2, the method further includes: preprocessing the historical meteorological data; the preprocessing method is: any one or more of smoothing to fill missing values ​​and filtering to reduce noise.

[0084] Optionally, smoothing and filling missing values ​​(interpolation) is to ensure the integrity of the data by interpolating the missing data; filtering and noise reduction is to remove noise in the data and enhance the data quality by applying filtering technology.

[0085] In actual application, Figure 9-10 As shown in the figure, the global Pareto optimal solution set after screening the original meteorological data in 2018 and 2019 reflects the relationship between irrigation amount, fertilizer amount and crop yield. The following changes can be observed from the figure.

[0086] (1) Yield and irrigation volume: With the increase of irrigation volume, the overall yield also increases, but after reaching a certain irrigation level, the increase in yield tends to slow down or even stagnate. This shows that there is a phenomenon of diminishing marginal returns in the utilization of irrigation resources, and appropriate control of irrigation volume can improve the efficiency of water resource utilization.

[0087] (2) Yield and fertilizer application: Similarly, an increase in fertilizer application can promote an increase in yield, but excessive fertilizer application has limited contribution to yield and may lead to resource waste and environmental problems. Optimizing fertilizer application is crucial to achieving efficient agriculture.

[0088] (3) Trade-off between irrigation and fertilization: In the high-yield solution set, it can be found that the irrigation and fertilization amounts do not increase monotonically, but show a certain complementarity and balance relationship. This shows that when formulating agricultural management strategies, it is necessary to comprehensively consider the synergistic effects of irrigation and fertilization to find the best input combination.

[0089] The technical effects of this application are as follows.

[0090] The present application obtains historical meteorological data; constructs a future meteorological prediction model based on the Informer+TSLANet+TimesBlock combined deep learning network; uses the future meteorological prediction model to extract long-term series multidimensional features of historical meteorological data and capture long-term dependencies to predict future meteorological data; by using the TSLANet module to capture the long-term dependencies of long-term series, and using the TimesBlock module to extract the frequency domain features of meteorological data, the Informer model's ability to understand long-term series is further improved, thereby enhancing the representation ability of the future meteorological prediction model and improving the accuracy of future meteorological data prediction; by using the DSSAT model to predict corn yield based on future meteorological data, the prediction result of corn yield in the current season is obtained; based on future meteorological data and the prediction result of corn yield in the current season, the irrigation and fertilization plan of corn is formulated using the Monte Carlo+NSGA-III double-layer combined multi-objective optimization algorithm, and the optimal irrigation and fertilization plan is obtained after optimization; using future meteorological data as input, the corn yield is predicted, and the optimal irrigation and fertilization plan is further obtained, which improves the real-time, accuracy and foresight of corn yield prediction and irrigation and fertilization decision prediction, and takes into account the water resource utilization efficiency and fertilizer utilization efficiency. This application can not only predict the impact of weather changes on corn growth in advance, but also help farmers and agricultural managers formulate scientific and reasonable planting plans and response measures before the planting season, effectively reduce the uncertainty caused by climate change, and improve the stability and efficiency of agricultural production. Farmers can save water resources and fertilizers to the greatest extent while ensuring high yields, reduce production costs and environmental pollution, promote the sustainable development of agriculture, and improve the economic and environmental benefits of agricultural production.

[0091] Embodiment 2, the present application also provides a computer system, which may be a server or a terminal, and its internal structure diagram may be as follows: Fig.11As shown. The computer system includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer system is used to provide computing and control capabilities. The memory of the computer system includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer system is used to store video tag processing data. The input / output interface of the computer system is used to exchange information between the processor and an external device. The communication interface of the computer system is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a corn irrigation and fertilization decision method based on future meteorological data is implemented.

[0092] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer system to which the scheme of the present application is applied. The specific computer system may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0093] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0094] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A corn irrigation and fertilization decision-making method based on future meteorological data, characterized in that: The corn irrigation and fertilization decision-making method based on future meteorological data includes: Get historical weather data; Build a future weather forecast model based on the Informer+TSLANet+TimesBlock combined deep learning network; Use the future weather forecast model to extract long-term multi-dimensional features of historical weather data and capture long-term dependencies to predict future weather data; Based on future meteorological data, the DSSAT model is used to predict corn yield and obtain the corn yield forecast results for the current season; Based on future meteorological data and the forecast results of corn yield in this season, the irrigation and fertilization plan of corn was formulated using the Monte Carlo + NSGA-III double-layer combination multi-objective optimization algorithm, and the optimal irrigation and fertilization plan was obtained after optimization.

2. The method for corn irrigation and fertilization decision-making based on future meteorological data according to claim 1, characterized in that: The meteorological data specifically include: daily maximum temperature, daily minimum temperature, daily average solar radiation and daily rainfall.

3. The method for corn irrigation and fertilization decision-making based on future meteorological data according to claim 1, characterized in that: The Informer+TSLANet+TimesBlock combined deep learning network includes a TSLANet module, a TimesBlock module and an Informer model connected in series.

4. The method for decision-making on corn irrigation and fertilization based on future meteorological data according to claim 1, characterized in that: The future meteorological forecast model is used to extract long-term multidimensional features of historical meteorological data and capture long-term dependencies, and predict future meteorological data, including: Substitute historical meteorological data into future meteorological prediction models; The TSLANet module is used to analyze the periodic and non-periodic patterns in the long time series of historical meteorological data. By processing the local characteristics of the long time series, the historical meteorological data is optimized from the data flow and information representation levels to obtain the optimized historical meteorological data. The TimesBlock module is used to perform multi-scale analysis on the optimized historical meteorological data from the time dimension to obtain the historical meteorological data after multi-scale analysis; The historical meteorological data after multi-scale analysis is substituted into the Informer model, and the multi-head probabilistic sparse self-attention mechanism is used to capture the long-term dependencies of long time series in the historical meteorological data after multi-scale analysis, and predict future meteorological data.

5. The method for corn irrigation and fertilization decision-making based on future meteorological data according to claim 1, characterized in that: The training process of the DSSAT model is as follows: Training data and verification data for corn yield prediction are obtained based on corn planting environment data; the corn planting environment data specifically includes: historical meteorological data, historical soil data, corn variety data, farmer planting profile data and crop growth information; The genetic parameters of the DSSAT model were optimized by fitting and calibrating the training data, and the accuracy and stability of the DSSAT model were evaluated using the validation data, and finally the trained DSSAT model was determined.

6. The method for decision-making on corn irrigation and fertilization based on future meteorological data according to claim 5, characterized in that: The soil data specifically includes: soil type, soil texture and soil nutrient content; the corn variety data specifically includes: growth cycle of different corn varieties and yield of different corn varieties; the farmer planting profile data specifically includes: planting area, fertilization and irrigation methods and planting density; the crop growth information specifically includes: growth stage, growth parameters and yield records.

7. The method for decision-making on corn irrigation and fertilization based on future meteorological data according to claim 1, characterized in that: Based on future meteorological data and the forecast results of corn yield in the current season, the irrigation and fertilization plan of corn was formulated using the Monte Carlo + NSGA-III double-layer combination multi-objective optimization algorithm, and the optimal irrigation and fertilization plan was obtained after optimization. Determine the optimization goal; the optimization goal is: maximize yield, minimize irrigation amount and minimize fertilization amount; Based on future meteorological data and the forecast results of corn yield in the current season, the Monte Carlo model was used to adopt repeated random sampling method and randomly generate all possible irrigation and fertilization date combinations with potential management strategies as the irrigation and fertilization plan for corn. The irrigation and fertilization scheme of corn is used as the initial population of the NSGA-III multi-objective optimization algorithm. After multiple iterative optimizations, the optimal trade-off solution among multiple optimization objectives is obtained as the optimal irrigation and fertilization scheme.

8. The method for decision-making on corn irrigation and fertilization based on future meteorological data according to claim 7, characterized in that: After multiple iterations of optimization, the optimal trade-off solution among multiple optimization objectives is obtained as the optimal irrigation and fertilization plan, which specifically includes: The NSGA-III multi-objective optimization algorithm is used to evaluate the individuals in the initial population using non-dominated sorting and crowding distance calculation. A new generation of solutions is generated through crossover and mutation operations, and uniformly distributed reference points are used to maintain the uniformity of the population. The algorithm is repeatedly executed until the preset number of iterations is reached or the solution quality is stable, providing decision makers with the optimal trade-off solution between multiple optimization objectives.

9. The method for decision-making on corn irrigation and fertilization based on future meteorological data according to claim 1, characterized in that: Before building a future weather forecast model based on the Informer+TSLANet+TimesBlock combined deep learning network, it also includes: The historical meteorological data is preprocessed; the preprocessing method is: any one or more of smoothing to fill missing values ​​and filtering to reduce noise.

10. A computer system comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the corn irrigation and fertilization decision-making method based on future meteorological data as described in any one of claims 1 to 9.

Images