Crop growth state simulation method and system based on meteorological grid data

Abstract

The crop growth state simulation method and system based on meteorological grid data provided by the embodiments of the present application can accurately predict the growth state of crops by in-depth analysis and simulation of meteorological environmental element variables, and then obtain accurate crop yield prediction results. This prediction not only helps to plan planting in advance, but also provides a scientific basis for agricultural operators to help optimize crop planting structure and resource allocation. The scheme emphasizes the importance of mining the shared cross characteristics between multiple state simulation original data, can better understand how various factors affect crop growth, find the optimal growth conditions, and adjust the meteorological environment parameters accordingly. Adjusting the meteorological environment parameters according to the crop yield prediction results can not only improve the yield of crops, but also improve the efficiency of resource utilization and reduce production costs.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method and system for simulating crop growth status based on meteorological grid data. Background Technology

[0002] With the development of technology, data-driven agricultural forecasting models have gained increasing attention. These models collect and analyze large amounts of data to identify various factors affecting crop growth and yield, in order to provide accurate forecasts for farmers and agricultural operators.

[0003] However, accurately predicting crop growth and yield remains a challenging task. This is mainly because crop growth and yield are influenced by a variety of meteorological environmental factors, including temperature, humidity, wind speed, and rainfall. The relationships between these factors are complex, often requiring in-depth analysis and simulation to obtain accurate prediction results.

[0004] Traditional forecasting methods typically cannot consider all meteorological and environmental factors affecting crop growth, and can only make predictions based on a subset of these factors, thus limiting the accuracy of their forecasts. Furthermore, these methods lack effective tools to process and analyze large amounts of complex meteorological data, further restricting their forecasting capabilities. Summary of the Invention

[0005] To address the aforementioned issues, this application provides a method and system for simulating crop growth status based on meteorological grid data.

[0006] Firstly, a method for simulating crop growth status based on meteorological grid data is provided, applied to a data simulation system. The method includes:

[0007] Obtain meteorological environmental element variables corresponding to meteorological grid monitoring information; wherein, the meteorological environmental element variables are used to simulate crop growth status under several crop growth status labels respectively, and obtain the crop growth status simulation results corresponding to the target agricultural area under the several crop growth status labels respectively;

[0008] When simulating the crop growth state of the meteorological environmental element variables using the growth state simulation algorithms corresponding to the several crop growth state labels, the original state simulation data of the growth state simulation algorithms corresponding to the several crop growth state labels is determined; wherein, the original state simulation data is a description vector to be entered into the growth state simulation algorithm for state simulation.

[0009] Extract the shared cross features between the state feature mapping relationship networks corresponding to several original state simulation data; wherein, the state feature mapping relationship network is obtained by data feature mining of the original state simulation data;

[0010] The original state simulation data are updated using the cross features to obtain updated state simulation data; wherein there is a correspondence between the original state simulation data and the updated state simulation data.

[0011] Based on the aforementioned state simulation update data, crop growth state simulation results corresponding to the target agricultural region under the aforementioned crop growth state labels are generated; wherein, the aforementioned crop growth state simulation results are combined to obtain the crop yield prediction results of the target agricultural region, and the crop yield prediction results are used as guidance for adjusting artificial meteorological environmental parameters.

[0012] In some exemplary technical solutions, the determination of the original state simulation data of the growth state simulation algorithm corresponding to the plurality of crop growth state labels includes:

[0013] Obtain crop growth monitoring information, which is information obtained by monitoring crops in the target agricultural area, and the crop growth monitoring information is used to generate simulation results reflecting the crop growth status in the target agricultural area;

[0014] Using the crop growth monitoring information as a simulation reference, the original data of the state simulation algorithm corresponding to the several crop growth state labels are determined. The simulation reference is used to determine the crop growth trend characteristics when simulating the meteorological environmental element variables.

[0015] In some exemplary technical solutions, obtaining crop growth monitoring information includes:

[0016] At least one dataset obtained from monitoring the target agricultural region is used as the crop growth monitoring information. The dataset is the result of monitoring the target agricultural region based on a set crop growth status label.

[0017] In some exemplary technical solutions, the step of extracting the shared cross features between the state feature mapping relationship networks corresponding to several state simulation original data includes:

[0018] Convolution operations are performed on the several original state simulation data respectively to obtain the state feature mapping relationship network corresponding to the several original state simulation data respectively;

[0019] Local downsampling is performed on several state feature mapping relationship networks to obtain state involvement vectors, which are used to reflect the cross features shared among several state feature mapping relationship networks.

[0020] In some exemplary technical solutions, the step of performing convolution operations on the plurality of original state simulation data to obtain the state feature mapping relationship network corresponding to the plurality of original state simulation data includes:

[0021] Perform convolution operations on the several state simulation raw data respectively to obtain state simulation convolution vectors corresponding to the several crop growth state labels respectively;

[0022] Obtain the sensing and monitoring element vectors corresponding to the several crop growth status labels respectively. The sensing and monitoring element vectors are linear vectors obtained based on the sensor variables corresponding to the crop growth status labels. The sensing and monitoring element vectors are used to reflect the periodic data of the corresponding crop growth status labels. There is a correspondence between the several sensing and monitoring element vectors and several state simulation convolution vectors.

[0023] Based on the correspondence, the state simulation convolution vector and the sensing monitoring element vector under the same crop growth state label are vector integrated to obtain the state feature mapping relationship network corresponding to the several state simulation original data respectively.

[0024] In some exemplary technical solutions, obtaining the sensing and monitoring element vectors corresponding to the plurality of crop growth status tags includes:

[0025] Obtain the sensor variables corresponding to the several crop growth status labels respectively. The sensor variables are used to reflect the sensor distribution characteristics that generate the corresponding crop growth status simulation results. The sensor variables include sensor region labels and sensor category labels. The sensor region labels are used to reflect the distribution of the sensors in the sensing and monitoring feature space relative to the target crop area. The sensor category labels represent the monitoring category of the sensors in the sensing and monitoring feature space relative to the target crop area.

[0026] Several sensor variables are preprocessed to obtain preprocessing results corresponding to the several sensor variables respectively. The preprocessing results are linear vectors obtained by preprocessing the sensor variables in the growth monitoring task.

[0027] By setting a knowledge extraction algorithm to extract knowledge elements from the preprocessing results, the sensor monitoring element vectors corresponding to the several crop growth status labels are obtained.

[0028] In some exemplary technical solutions, the step of locally downsampling several state feature mapping relationship networks to obtain state-related vectors includes:

[0029] The meteorological environment impact feature sets represented by the aforementioned state feature mapping relationship networks are determined respectively. The meteorological environment impact feature sets are used to reflect the set of several meteorological environment impact features in the growth monitoring task when the state feature mapping relationship network is obtained.

[0030] Several meteorological and environmental impact features that are at the same feature position in several sets of meteorological and environmental impact features are focused to obtain several local focus weights;

[0031] The state-related vector is obtained by downsampling the aforementioned local focus weights.

[0032] In some exemplary technical solutions, updating the original data of the plurality of state simulations with the cross features to obtain a plurality of updated state simulation data includes:

[0033] Obtain the state involvement vector representing the cross features;

[0034] Based on the crop growth state labels corresponding to the several state simulation raw data and the state involvement vectors, meteorological environment-related growth description vectors corresponding to the several crop growth state labels are obtained. The meteorological environment-related growth description vectors are used to reflect the contribution of the state involvement vectors to the state simulation raw data at the time-series description level. There is a correspondence between the several meteorological environment-related growth description vectors and the several state simulation raw data.

[0035] Based on the correspondence, the several state simulation update data are obtained by using the meteorological environment-associated growth description vector under the same crop growth state label and the original state simulation data.

[0036] In some exemplary technical solutions, the step of obtaining meteorological environment-related growth description vectors corresponding to the crop growth state labels and the state-related vectors corresponding to the several state simulation raw data respectively includes:

[0037] Determine the sensor monitoring knowledge graphs corresponding to the plurality of crop growth status labels, wherein the sensor monitoring knowledge graphs are generated based on the sensors used when determining the corresponding crop growth status labels;

[0038] Using the sensor monitoring knowledge graph corresponding to the crop growth status label monitoring category as a template, knowledge transfer is performed on the state-related vector to obtain knowledge transfer vectors that represent the crop growth status labels respectively.

[0039] Based on the aforementioned crop growth status labels and corresponding knowledge transfer vectors, the meteorological environment-related growth description vectors corresponding to the aforementioned crop growth status labels in the growth monitoring task are obtained.

[0040] In some exemplary technical solutions, obtaining the meteorological environment-related growth description vectors corresponding to the plurality of crop growth status labels in the growth monitoring task based on the plurality of crop growth status labels and corresponding knowledge transfer vectors includes:

[0041] Obtain the thermal values ​​of crop growth status represented by the several crop growth status tags respectively;

[0042] Under the same crop growth status label, based on the crop growth status thermodynamic value and the knowledge transfer vector, the meteorological environment-related growth description vector corresponding to the several crop growth status labels in the growth monitoring task is obtained.

[0043] In some exemplary technical solutions, the step of obtaining the meteorological environment-related growth description vectors corresponding to the plurality of crop growth status labels in the growth monitoring task, based on the crop growth status thermodynamic values ​​and the knowledge transfer vector under the same crop growth status label, includes:

[0044] A set of meteorological environmental impact features is determined, which is characterized by a state feature mapping relationship network corresponding to several crop growth state labels. The set of meteorological environmental impact features includes several meteorological environmental impact features, and each meteorological environmental impact feature corresponds to a crop growth state thermodynamic value.

[0045] Using the thermal value of crop growth status corresponding to the meteorological environmental impact characteristics as the meteorological environmental impact characteristic value, several meteorological environmental impact characteristics in the meteorological environmental impact characteristic set are derived to obtain a meteorological environmental impact characteristic chain set with the same meteorological environmental impact characteristic value.

[0046] Based on the meteorological environment impact feature chain set and the knowledge transfer vector, the meteorological environment-related growth description vectors corresponding to the several crop growth status labels in the growth monitoring task are obtained.

[0047] In some exemplary technical solutions, obtaining the meteorological environment-related growth description vectors corresponding to the plurality of crop growth status labels in the growth monitoring task based on the meteorological environment impact feature chain set and the knowledge transfer vector includes:

[0048] The meteorological and environmental impact feature chain set is extracted using a deep learning branch to obtain meteorological and environmental impact feature knowledge.

[0049] Under the same crop growth status label, the meteorological environment impact feature knowledge and the knowledge transfer vector are aggregated to obtain the meteorological environment associated growth description vectors corresponding to the several crop growth status labels in the growth monitoring task.

[0050] In some exemplary technical solutions, based on the correspondence, the meteorological environment-related growth description vectors under the same crop growth state label and the original state simulation data are vector-integrated to obtain the plurality of state simulation update data:

[0051] The meteorological environment-related growth description vectors corresponding to several crop growth status labels are mapped to the simulated feature relationship network to obtain the growth environment-related mapping vectors corresponding to several crop growth status labels.

[0052] Under the same crop growth state label, the growth environment association mapping vector and the original state simulation data are vector-integrated to obtain the state simulation update data corresponding to several crop growth state labels respectively.

[0053] In some exemplary technical solutions, each crop growth status label corresponds to x growth status simulation algorithms, where x is a positive integer;

[0054] The step of generating simulation results of crop growth status for the target crop region under the various crop growth status labels based on the simulation update data of the various states includes:

[0055] The state simulation update data of the y-th growth state simulation algorithm corresponding to the plurality of crop growth state labels is used to simulate the crop growth state, so as to obtain the original state simulation data of the (y+1)-th growth state simulation algorithm corresponding to the plurality of crop growth state labels, where y is a positive integer not greater than x.

[0056] In response to the xth growth state simulation algorithm, obtain the state simulation inference vector output by the xth growth state simulation algorithm corresponding to the plurality of crop growth state labels respectively;

[0057] Based on several state simulation inference vectors, the simulation results of the crop growth state corresponding to the target agricultural region under several crop growth state labels are generated.

[0058] In some exemplary technical solutions, generating the crop growth state simulation results corresponding to the target agricultural region under the several crop growth state labels based on several state simulation inference vectors includes:

[0059] Under the several crop growth state labels, the crop growth state simulation is performed cyclically based on the state simulation inference vector until the cyclic condition is met, and then the state simulation decision vector corresponding to the several crop growth state labels is obtained. The state simulation decision vector is used to reflect the linear vector obtained after simulating the crop growth state of the meteorological environmental factor variables.

[0060] Several state simulation decision vectors are passed through simulation output branches to generate simulation results of crop growth status corresponding to the target agricultural area under several crop growth status labels.

[0061] In a second aspect, a data simulation system is provided, comprising a processor and a memory that communicate with each other, the processor being configured to retrieve a computer program from the memory and to implement the method described in the first aspect by running the computer program.

[0062] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, the computer program implementing the method described in the first aspect when it is run.

[0063] The crop growth state simulation method and system based on meteorological grid data provided in this application can accurately predict crop growth status and thus obtain precise crop yield prediction results by deeply analyzing and simulating meteorological environmental variables. This prediction not only helps in advance planting planning but also provides agricultural operators with a scientific basis to help optimize crop planting structure and resource allocation. This approach emphasizes the importance of mining the shared cross-features among the raw data from multiple state simulations, enabling a deeper understanding of how various factors affect crop growth, identifying optimal growth conditions, and adjusting meteorological environmental parameters accordingly. Adjusting meteorological environmental parameters based on crop yield prediction results can not only increase crop yield but also improve resource utilization efficiency and reduce production costs. Attached Figure Description

[0064] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 A flowchart illustrating a method for simulating crop growth status based on meteorological grid data, provided in an embodiment of this application. Detailed Implementation

[0066] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0067] Figure 1 A method for simulating crop growth status based on meteorological grid data is shown and applied to a data simulation system. The method includes the following steps 110-150.

[0068] Step 110: Obtain meteorological environmental element variables corresponding to meteorological grid monitoring information. The meteorological environmental element variables are used to simulate crop growth status under several crop growth status labels to obtain the crop growth status simulation results corresponding to the target agricultural area under the several crop growth status labels.

[0069] Step 120: When simulating the crop growth state of the meteorological environmental element variables using the growth state simulation algorithms corresponding to the several crop growth state labels, determine the original state simulation data of the growth state simulation algorithms corresponding to the several crop growth state labels. The original state simulation data is a description vector to be entered into the growth state simulation algorithm for state simulation.

[0070] Step 130: Extract the shared cross features between the state feature mapping relationship networks corresponding to several state simulation original data respectively, wherein the state feature mapping relationship network is obtained by data feature mining of the state simulation original data.

[0071] Step 140: Update the original state simulation data with the cross features to obtain updated state simulation data, wherein there is a correspondence between the original state simulation data and the updated state simulation data.

[0072] Step 150: Based on the aforementioned state simulation update data, generate crop growth state simulation results corresponding to the target agricultural region under the aforementioned crop growth state labels. The aforementioned crop growth state simulation results are combined to obtain the crop yield prediction results for the target agricultural region. The crop yield prediction results are used as guidance for adjusting artificial meteorological environmental parameters.

[0073] In step 110, the meteorological grid monitoring information consists of a large amount of detailed meteorological data collected by specialized monitoring equipment within a certain geographical area. Each grid represents a specific geographical location, and each location has its own unique meteorological and environmental data.

[0074] Meteorological environmental variables refer to various elements and parameters that describe the meteorological environment, such as temperature, humidity, rainfall, and wind speed. These are used as input variables in models to simulate the growth status of crops.

[0075] Crop growth status tags are classification labels for crop growth stages, such as germination stage, growth stage, flowering stage, and maturity stage. Each tag corresponds to a specific growth stage.

[0076] The target cropping region refers to the crop planting area predicted and simulated by the model. Within this region, meteorological environmental variables are used to simulate the crop growth status.

[0077] The crop growth status simulation results are obtained by simulating meteorological environmental variables and crop growth status labels. It shows the expected conditions of crops at various growth stages under given meteorological conditions. These results can provide a reference for crop planting and management.

[0078] Furthermore, meteorological environmental element variables (or meteorological environmental element characteristics) are data describing climate and weather conditions. They include the following main aspects:

[0079] Temperature: This is one of the most fundamental meteorological elements, directly affecting crop growth. For example, different crops have their suitable temperature ranges for growth;

[0080] Humidity: including relative humidity and absolute humidity, it reflects the amount of moisture in the air and has an important impact on the growth environment of crops and the occurrence of pests and diseases.

[0081] Rainfall: This is an indicator that measures the total amount of precipitation in a region, and it has a direct impact on the irrigation needs of crops and soil moisture conditions.

[0082] Wind speed and wind direction: Excessive wind speed may cause physical damage to crops, while wind direction may affect agricultural activities such as pesticide spraying.

[0083] Sunshine duration and solar radiation: For crops that are closely related to photosynthesis, sunshine duration and solar radiation intensity are important factors affecting their growth.

[0084] Atmospheric pressure: Although it has a relatively small impact on crop growth, it may have some influence under certain conditions.

[0085] These meteorological and environmental variables are important inputs for constructing crop growth simulation models. They can reflect the specific conditions of the crop growth environment and be used to predict the growth status and yield of crops.

[0086] Therefore, when meteorological environmental element variables are represented as feature vectors, each dimension represents a specific meteorological environmental element. In practical applications, these variables may need to undergo preprocessing, such as standardization or normalization, before being input into the model. Below is an example feature vector: Feature vector = [Temperature, Relative Humidity, Absolute Humidity, Rainfall, Wind Speed, Wind Direction, Sunshine Duration, Solar Radiation, Atmospheric Pressure].

[0087] For example, suppose the meteorological data for a certain location at a certain time is: temperature 25℃, relative humidity 60%, absolute humidity 15g / m³. 3 Rainfall 0mm, wind speed 5m / s, easterly wind direction, sunshine duration 10 hours, solar radiation 500W / m² 2 Given an atmospheric pressure of 1013 hPa, the characteristic vector of this meteorological environment can be represented as: [25, 60, 15, 0, 5, 90, 10, 500, 1013]. Wind direction is represented by angles, with easterly winds at 90 degrees. In practical applications, more meteorological environmental factors can be considered, and the data can be preprocessed in other ways according to the model's requirements.

[0088] In other examples, crop growth status labels are used to categorize crops at various stages of their growth cycle. For instance, the growth process of a wheat plant can be divided into several main stages: germination, seedling, jointing, heading, grain-filling, and maturity. Each stage corresponds to a label, such as "germination" or "seedling." The simulation results of crop growth status are calculated by a model using meteorological environmental variables and crop growth status labels, representing the expected growth state of the crop. For example, if a model is given today's meteorological environmental variables, it might predict that wheat will enter the "jointing stage" tomorrow. These simulation results can help understand the possible future growth conditions of wheat and make corresponding agricultural management decisions.

[0089] In step 120, the growth state simulation algorithm is a computational method that takes meteorological environmental variables and crop growth state labels as inputs and outputs a predicted crop growth state. This algorithm may be based on various machine learning or artificial intelligence techniques, such as decision trees, random forests, and neural networks. The raw data for state simulation refers to the data input into the growth state simulation algorithm, including meteorological environmental variables and crop growth state labels. This data is usually processed, such as normalization and encoding, to meet the algorithm's requirements. The description vector is a representation of the input data, integrating multiple related data (such as temperature, humidity, and rainfall) into a single vector. For example, if temperature, humidity, and wind speed are taken as three features, the description vector for a sample point might be [20, 0.8, 5], representing a temperature of 20°C, humidity of 80%, and wind speed of 5 m / s, respectively.

[0090] For example, a decision tree-based crop growth state simulation algorithm is being used. This algorithm uses meteorological environmental variables (such as temperature, humidity, and rainfall) and the current crop growth state label to predict the next crop growth state.

[0091] For example, the following might be an exemplary decision tree:

[0092] If the current state is "germination stage": if the temperature is >15℃ and the rainfall is >10mm, then the next stage is predicted to be "seedling stage"; otherwise, the next stage is predicted to remain "germination stage".

[0093] If the current stage is "seedling stage": If the temperature is >20℃ and the rainfall is <30mm, then the next stage is predicted to be "jointing stage"; otherwise, the next stage is predicted to remain "seedling stage".

[0094] ...

[0095] In practical applications, growth state simulation algorithms typically use more input features and may be based on more complex machine learning models, such as random forests and neural networks. They also take into account more crop growth state labels and the specific circumstances of each growth stage.

[0096] In step 130, the state feature mapping network is a model or structure representing the correlation between data features. For example, in crop growth state simulation, meteorological environmental factors such as temperature, humidity, and rainfall may be closely related to the crop growth state. The state feature mapping network is used to reveal the relationship between these features and growth states. Shared cross features: In multiple different state simulation original datasets, there may be some common features; these are shared cross features. For example, for both wheat and corn, they both require water and sunlight, so "rainfall" and "sunshine duration" may become shared cross features. Data feature mining is a process of extracting useful information or knowledge from raw data. In this process, various statistical methods, machine learning algorithms, and other tools may be used to discover hidden patterns, correlations, trends, etc., in the data. For example, in the state simulation original data, feature mining may reveal that when temperature and humidity reach certain values, the crop growth state changes.

[0097] In the context of state-feature mapping networks, consider a farmland planted with wheat. To simulate the wheat's growth, data on meteorological and environmental factors such as temperature, humidity, and rainfall might be collected. Simultaneously, the wheat's growth status needs to be observed, including its growth rate, color, and the presence of pests and diseases.

[0098] In this process, a state characteristic mapping network can be established, which describes the relationship between various meteorological environmental factors (i.e., state characteristics) and wheat growth status. For example, it might be found that wheat growth is optimal when the temperature is between 20-25℃ and the humidity is between 60-70%. Conversely, if the temperature is too high or too low, or the humidity is insufficient, the wheat growth status may deteriorate. Such relationships can be represented graphically, tabularly, or through algorithms, forming a mapping network.

[0099] Regarding shared characteristics, for example, corn was also planted on the same farmland. Like wheat, the growth of corn is also affected by factors such as temperature, humidity, and rainfall.

[0100] In this context, it can be observed that although wheat and corn are different crops, they are both affected by the same meteorological environmental factors. These meteorological environmental factors affecting the two crops can be considered as shared, overlapping characteristics.

[0101] For example, it might be found that both wheat and corn reach their optimal growth state when the temperature is between 20-25°C and the humidity is between 60-70%. This means that "temperature" and "humidity" are shared cross-features in the simulation of wheat and corn growth states.

[0102] In step 140, after extracting the cross features, these features are used to update the original state simulation data. The update process may involve some adjustments or transformations to the original data to reflect the influence of the cross features. For example, if a shared cross feature (such as temperature) is found to have a significant impact on crop growth status, the weight of this feature may be increased in the simulation data. The data obtained after this update is the "state simulation updated data". Correspondence here refers to a mapping relationship or connection between the original state simulation data and the updated state simulation data. That is, each piece of original state simulation data can be transformed into updated state simulation data in some way (such as adding, deleting, or modifying features). For example, if the weight of the "temperature" feature in the original data is increased by 10%, then there is a correspondence between the original data and the updated data: Updated data = Original data + 10% * Temperature feature.

[0103] In step 150, the crop yield forecast is the expected crop yield obtained by simulating the crop's growth state and combining it with its relationship with meteorological environmental factors. For example, if it is found that a certain crop grows best under certain temperature and humidity conditions, then under these conditions, the crop yield can be predicted to reach its maximum. This expected crop yield is the crop yield forecast result.

[0104] Furthermore, crop yield forecasts serve as a guide for adjusting artificial meteorological environmental parameters. This means that meteorological environmental parameters of farmland can be adjusted based on crop yield forecasts to optimize crop growth conditions and increase crop yields. For example, if a crop's yield is predicted to increase at higher temperatures, the farmland temperature can be adjusted artificially (such as by constructing greenhouses) to approach the predicted optimal temperature. Similarly, if forecasts indicate that rainfall has a significant impact on crop yields, measures such as irrigation can be taken to adjust farmland humidity. Such adjustments are made based on crop yield forecasts with the aim of achieving higher crop yields.

[0105] The above technical solution will be illustrated with a complete example below.

[0106] First, environmental data for a farmland, such as temperature, humidity, and rainfall, are acquired through a meteorological grid monitoring system. Then, using this data, growth simulations are conducted at different wheat growth stages (e.g., seedling stage, jointing stage, heading stage), yielding simulation results for the farmland under these different growth conditions.

[0107] During the simulation process, the original state simulation data corresponding to each growth state label was determined. This original data is a description vector, which will be entered into the growth state simulation algorithm for state simulation.

[0108] Next, the shared cross-features between the state feature mapping networks are extracted from the raw data of these state simulations. This may involve some data analysis and machine learning techniques to discover which features play a key role in all growth state simulations. For example, it may be found that temperature and humidity are very important factors in all growth states.

[0109] Then, these shared cross-features are used to update the original state simulation data, generating updated state simulation data. For example, the weights of temperature and humidity features might be increased, as they have a significant impact on all growth states.

[0110] Finally, based on these state simulation update data, simulation results for the target farmland under different growth conditions can be generated. Combining these simulation results yields a predicted wheat yield. This prediction can then be used to adjust the farmland's meteorological parameters to optimize growth conditions and increase yield. For example, if the prediction shows that higher temperature and humidity lead to better growth and higher yields, the temperature and humidity of the farmland can be artificially adjusted by constructing greenhouses or similar methods.

[0111] In summary, this technical solution, through in-depth analysis and simulation of meteorological environmental variables, can effectively predict crop growth status, thereby helping to obtain more accurate crop yield forecasts. This precise prediction not only helps farmers plan their crop planting in advance but also provides agricultural managers with a scientific basis for optimizing crop planting structures and agricultural resource allocation.

[0112] Furthermore, this technical solution emphasizes the importance of shared cross-features. By mining the shared cross-features among the raw data from multiple state simulations, a deeper understanding can be gained of how various factors affect crop growth. This will help identify optimal crop growth conditions and adjust meteorological environmental parameters for farmland accordingly.

[0113] Finally, adjusting meteorological parameters based on crop yield forecasts can not only increase crop yields but also improve resource utilization efficiency, reduce agricultural production costs, and further increase farmers' income. Overall, this technical solution has significant practical implications and broad application prospects for agricultural production.

[0114] In some possible embodiments, step 120 describes determining the original state simulation data of the growth state simulation algorithm corresponding to the plurality of crop growth state labels, including steps 121-122.

[0115] Step 121: Obtain crop growth monitoring information. The crop growth monitoring information is the information obtained by monitoring crops in the target agricultural area. The crop growth monitoring information is used to generate simulation results reflecting the crop growth status of the target agricultural area.

[0116] Step 122: Using the crop growth monitoring information as a simulation reference, determine the original state simulation data of the growth state simulation algorithm corresponding to the several crop growth state labels respectively. The simulation reference is used to determine the crop growth trend characteristics when simulating the meteorological environmental element variables.

[0117] In this embodiment of the technical solution, step 120 includes steps 121 and 122. Step 121 involves acquiring crop growth monitoring information. This information is obtained through crop monitoring in the target agricultural area and includes various data on crop growth status, such as plant height and leaf area index. This crop growth monitoring information will be used to generate simulation results reflecting the crop growth status of the target agricultural area. Step 122 uses the crop growth monitoring information as a simulation reference to determine the state simulation raw data of the growth status simulation algorithm corresponding to each crop growth status label. "Simulation reference" means using the actually collected crop growth monitoring information as a reference to simulate the growth trend characteristics of crops under different meteorological environmental variables. For example, if the temperature, humidity, and other meteorological conditions of a certain day are known, the growth status of crops can be predicted based on these conditions.

[0118] Thus, by first acquiring crop growth information through on-site monitoring, and then using this as a basis, the raw data for state simulation corresponding to each crop growth status label is determined. This not only more accurately reflects the crop growth status of the target agricultural region, but also allows for the prediction of possible crop growth trends under different meteorological conditions through simulation. This is undoubtedly of great significance for optimizing crop cultivation, increasing crop yields, and improving the efficiency of agricultural resource utilization.

[0119] In some preferred embodiments, obtaining crop growth monitoring information in step 121 includes: obtaining at least one dataset obtained from monitoring the target agricultural area as the crop growth monitoring information, wherein the dataset is the result obtained from monitoring the target agricultural area based on a set crop growth status label.

[0120] In some preferred embodiments, step 121, acquiring crop growth monitoring information, is more specifically defined. This step includes acquiring at least one dataset obtained from monitoring the target crop region as crop growth monitoring information. This "dataset" is the result of monitoring based on predefined crop growth status labels.

[0121] For example, a series of crop growth status labels might be set, such as "germination stage," "tillering stage," and "heading stage." Then, during field monitoring, relevant data would be collected based on these labels. For instance, during the "germination stage," information such as seed germination rate and growth rate might be recorded; during the "tillering stage," the average number of tillers per plant might be observed and recorded. All this information is integrated to form a dataset, which is what is referred to as crop growth monitoring information.

[0122] This method provides highly detailed and accurate information on crop growth, which is extremely helpful for simulating crop growth patterns and predicting yields. Simultaneously, it enables the understanding and mastery of the specific impacts of various meteorological and environmental factors on crop growth, further guiding crop planting and management, optimizing resource allocation, and improving agricultural production efficiency.

[0123] In some alternative embodiments, step 130 includes extracting the shared cross features between the state feature mapping relationship networks corresponding to several state simulation original data, including steps 131-132.

[0124] Step 131: Perform convolution operations on the several original state simulation data respectively to obtain the state feature mapping relationship network corresponding to the several original state simulation data respectively.

[0125] Step 132: Local downsampling is performed on several state feature mapping relationship networks to obtain state involvement vectors. The state involvement vectors are used to reflect the cross features shared among several state feature mapping relationship networks.

[0126] In this alternative embodiment, step 130 includes steps 131 and 132. Step 131 involves performing a convolution operation on several state simulation raw data. "Convolution" is a common signal processing technique used here to extract feature information about crop growth states. This operation yields state feature mapping networks corresponding to each state simulation raw data. These networks reflect how meteorological environmental factors affect crop growth states. Step 132 involves locally downsampling the several state feature mapping networks. "Local downsampling" is a technique for reducing data dimensionality, used to extract key features and reduce computational complexity. This step produces a state involvement vector that reflects the shared cross-features among the several state feature mapping networks.

[0127] Through the two steps described above, key cross-features can be extracted from a large amount of raw state simulation data, and based on these features, more accurate crop growth status predictions can be made. This method effectively utilizes information from various meteorological and environmental factors while avoiding excessive computational complexity, making it a practical and efficient crop growth status prediction technique.

[0128] Under some optional design approaches, step 131 involves performing convolution operations on the several original state simulation data to obtain the state feature mapping relationship network corresponding to the several original state simulation data, including steps 1311-1313.

[0129] Step 1311: Perform convolution operations on the several state simulation original data respectively to obtain state simulation convolution vectors corresponding to the several crop growth state labels respectively.

[0130] Step 1312: Obtain the sensor monitoring element vectors corresponding to the several crop growth status labels respectively. The sensor monitoring element vectors are linear vectors obtained based on the sensor variables corresponding to the crop growth status labels. The sensor monitoring element vectors are used to reflect the periodic data of the corresponding crop growth status labels. There is a correspondence between the several sensor monitoring element vectors and several state simulation convolution vectors.

[0131] Step 1313: Based on the correspondence, perform vector integration on the state simulation convolution vector and the sensing monitoring element vector under the same crop growth state label to obtain the state feature mapping relationship network corresponding to the several state simulation original data respectively.

[0132] Under this optional design approach, step 131 includes steps 1311 to 1313. Step 1311 involves performing convolution operations on several state simulation raw data to obtain state simulation convolution vectors corresponding to each crop growth state label. The "convolution vector" is the feature information extracted from the raw data through the convolution operation, reflecting the influence of various meteorological environmental factors on crop growth status. Step 1312 involves obtaining the sensor monitoring element vectors corresponding to each crop growth state label. The "sensor monitoring element vectors" are linear vectors obtained based on sensor variables corresponding to the crop growth state labels; these vectors reflect the periodic data of the corresponding crop growth state labels. Sensor variables may include temperature, humidity, light intensity, etc., which are environmental parameters collected in real time by monitoring equipment. Step 1313, based on the above correspondence, integrates the state simulation convolution vectors and sensor monitoring element vectors under the same crop growth state label to obtain a state feature mapping network corresponding to each state simulation raw data.

[0133] Thus, through convolution operations and vector ensemble, key features reflecting crop growth status are extracted from the original state simulation data, while also considering the impact of environmental parameters on crop growth. This method can more accurately predict crop growth status and yield, optimize agricultural resource allocation, and improve agricultural production efficiency.

[0134] In some possible embodiments, step 1312, obtaining the sensor monitoring element vectors corresponding to the plurality of crop growth status labels, includes: obtaining sensor variables corresponding to the plurality of crop growth status labels, wherein the sensor variables are used to reflect the sensor distribution characteristics that generate the corresponding crop growth status simulation results, the sensor variables include sensor region labels and sensor category labels, the sensor region labels are used to reflect the distribution of sensors relative to the target crop area in the sensor monitoring feature space, and the sensor category labels represent the monitoring category of sensors relative to the target crop area in the sensor monitoring feature space; preprocessing the plurality of sensor variables to obtain preprocessing results corresponding to the plurality of sensor variables, wherein the preprocessing results are linear vectors obtained by preprocessing the sensor variables in the growth monitoring task stage; and extracting knowledge elements from the preprocessing results by setting a knowledge extraction algorithm to obtain the sensor monitoring element vectors corresponding to the plurality of crop growth status labels.

[0135] In this possible embodiment, step 1312 involves obtaining sensor monitoring element vectors corresponding to several crop growth status labels. This process includes the following sub-steps: First, obtaining the sensor variables corresponding to each crop growth status label. "Sensor variables" reflect the sensor distribution characteristics that generate the corresponding crop growth status simulation results. Sensor variables include "sensor region labels" and "sensor category labels." Sensor region labels reflect the distribution of sensors relative to the target crop area in the sensor monitoring feature space, for example, whether the sensor is located in the center, edge, or corner of the field; while sensor category labels characterize the monitoring category of the sensor relative to the target crop area in the sensor monitoring feature space, for example, whether the sensor is used to monitor temperature, humidity, light intensity, or other meteorological environmental factors. Next, preprocessing is performed on each sensor variable to obtain the preprocessed result corresponding to each sensor variable. Preprocessing typically includes data cleaning, normalization, and other operations, aiming to reduce noise, eliminate outliers, and transform the data into a form suitable for further processing. The preprocessing result is a linear vector obtained by preprocessing the sensor variables within the growth monitoring task stage. Finally, a knowledge extraction algorithm is used to extract knowledge elements from the preprocessed results, resulting in sensor monitoring element vectors corresponding to each crop growth status label. This step extracts useful information from the preprocessed results to facilitate subsequent analysis and simulation.

[0136] Therefore, this technical solution, by acquiring and processing sensor variables, can more accurately reflect the growth status of crops, providing important reference for optimizing crop planting, increasing crop yield, and improving the efficiency of agricultural resource utilization.

[0137] Under some possible design approaches, step 132 involves local downsampling of several state feature mapping relationship networks to obtain state-related vectors, including steps 1321-1323.

[0138] Step 1321: Determine the meteorological and environmental impact feature sets represented by the several state feature mapping relationship networks respectively. The meteorological and environmental impact feature sets are used to reflect the set of several meteorological and environmental impact features in the growth monitoring task link when the state feature mapping relationship network is obtained.

[0139] Step 1322: Focus several meteorological and environmental impact features that are in the same feature position in several sets of meteorological and environmental impact features to obtain several local focus weights.

[0140] Step 1323: Downsample the several local focus weights to obtain the state involvement vector.

[0141] Under this possible design approach, step 132 includes steps 1321 to 1323. Step 1321 first requires determining the meteorological environmental impact feature sets represented by several state feature mapping networks. These meteorological environmental impact feature sets reflect the set of several meteorological environmental impact features within the growth monitoring task when the state feature mapping network is obtained. These features may include meteorological environmental factors affecting crop growth, such as temperature, humidity, and light intensity. Step 1322 focuses several meteorological environmental impact features at the same feature position within the several meteorological environmental impact feature sets, obtaining several local focus weights. Focusing refers to concentrating attention or weights on certain important features while reducing consideration of other less important features. The local focus weights are the weights of each meteorological environmental impact feature obtained through this method. Step 1323 then downsamples the several local focus weights to obtain the state involvement vector. Downsampling is a technique for reducing data volume; it reduces data complexity and speeds up computation by randomly selecting a portion of data from the dataset or by compressing the data in some way. The state-related vector is a vector representing the growth state of crops after downsampling.

[0142] It is evident that by focusing and downsampling the state feature mapping network locally, the most representative and discriminative meteorological environmental impact features can be extracted, thereby more accurately reflecting and predicting the growth status of crops, which helps to improve agricultural production efficiency and agricultural product quality.

[0143] In some other embodiments, step 140 describes updating the original data of the plurality of state simulations with the cross features to obtain a plurality of updated state simulation data, including steps 141-143.

[0144] Step 141: Obtain the state involvement vector representing the cross-feature.

[0145] Step 142: Based on the crop growth state labels corresponding to the several state simulation raw data and the state involvement vectors, obtain the meteorological environment-related growth description vectors corresponding to the several crop growth state labels. The meteorological environment-related growth description vectors are used to reflect the contribution of the state involvement vectors to the state simulation raw data at the time-series description level. There is a correspondence between the several meteorological environment-related growth description vectors and the several state simulation raw data.

[0146] Step 143: Based on the correspondence, obtain the several state simulation update data by using the meteorological environment associated growth description vector under the same crop growth state label and the original state simulation data.

[0147] In these embodiments, step 140 describes updating several state simulation raw data with cross features to obtain several state simulation updated data. This includes the following sub-steps: Step 141 is to obtain state-related vectors representing cross features. Here, cross features refer to the correlation or interaction between meteorological environmental influence features acquired by different types of sensors. The state-related vector is the vector representing the crop growth state obtained after downsampling in the previous step. Step 142 is to obtain meteorological environment-related growth description vectors corresponding to several crop growth state labels based on the crop growth state labels and state-related vectors corresponding to the state simulation raw data. The "meteorological environment-related growth description vector" reflects the contribution of the state-related vector to the state simulation raw data at the time-series description level, that is, it reveals how different meteorological environmental factors affect the crop growth state over time. At the same time, there is a correspondence between each meteorological environment-related growth description vector and the state simulation raw data, which means that each description vector corresponds to one raw data. Step 143, based on this correspondence, obtains several state simulation update data by associating the meteorological environment with the growth description vector and the original state simulation data under the same crop growth state label. In other words, each update data is generated jointly by the corresponding description vector and the original data.

[0148] This design, by introducing cross-features and state-related vectors, can more accurately reflect and predict crop growth status, providing a more scientific and precise basis for agricultural production decisions. Furthermore, this scheme can update simulation data in real time, enabling the model to self-optimize over time, further improving the accuracy and reliability of predictions.

[0149] Further, step 142 describes obtaining meteorological environment-related growth description vectors corresponding to the crop growth state labels and state-related vectors corresponding to the several state simulation original data, including steps 1421-1423.

[0150] Step 1421: Determine the sensor monitoring knowledge graph corresponding to each of the several crop growth status tags. The sensor monitoring knowledge graph is generated based on the sensor used when determining the corresponding crop growth status tag.

[0151] Step 1422: Using the sensor monitoring knowledge graph corresponding to the crop growth status label monitoring category as a template, perform knowledge transfer on the state-related vector to obtain knowledge transfer vectors representing the respective crop growth status labels.

[0152] Step 1423: Based on the several crop growth status labels and the corresponding knowledge transfer vectors, obtain the meteorological environment-related growth description vectors corresponding to the several crop growth status labels in the growth monitoring task.

[0153] In this technical solution, step 142 involves obtaining meteorological environment-related growth description vectors corresponding to several crop growth state labels and state-related vectors, based on the crop growth state labels and state-related vectors corresponding to the original data of several state simulations. This includes the following sub-steps: Step 1421 involves determining the sensor monitoring knowledge graphs corresponding to several crop growth state labels. The "sensor monitoring knowledge graph" is a knowledge graph generated based on the sensors used to determine the corresponding crop growth state labels. A knowledge graph is a structured knowledge representation method that displays entities and the relationships between them in a graph form, facilitating machine understanding and processing. Step 1422 uses the sensor monitoring knowledge graph corresponding to the crop growth state label monitoring category as a template to perform knowledge transfer on the state-related vectors, obtaining knowledge transfer vectors representing the data corresponding to several crop growth state labels. "Knowledge transfer" refers to applying learned knowledge to new scenarios or tasks, and the "knowledge transfer vector" is the vector obtained through knowledge transfer, representing the projection or mapping of the state-related vectors onto the knowledge graph. Step 1423 involves obtaining meteorological environment-related growth description vectors corresponding to several crop growth status labels in the growth monitoring task, based on several crop growth status labels and their corresponding knowledge transfer vectors. In other words, each description vector is generated jointly by the corresponding crop growth status label and the knowledge transfer vector.

[0154] This design, by introducing sensor monitoring knowledge graphs and knowledge transfer technology, can effectively apply existing knowledge to new scenarios or tasks, improving the model's generalization ability. Furthermore, this approach can more accurately reflect and predict crop growth status, providing a more scientific and precise basis for agricultural production decisions.

[0155] In some preferred embodiments, step 1423, which involves obtaining the meteorological environment-related growth description vectors corresponding to the crop growth status labels in the growth monitoring task based on the plurality of crop growth status labels and the corresponding knowledge transfer vectors, includes: obtaining the crop growth status thermodynamic values ​​represented by the plurality of crop growth status labels; and, under the same crop growth status label, obtaining the meteorological environment-related growth description vectors corresponding to the plurality of crop growth status labels in the growth monitoring task based on the crop growth status thermodynamic values ​​and the knowledge transfer vectors.

[0156] In this preferred embodiment, step 1423 is further refined into the following operations: First, it is necessary to obtain the thermal values ​​of crop growth status, represented by several crop growth status labels. "Crop growth status thermal value" is a numerical indicator that measures the intensity or activity of crop growth status. For example, if a status label represents "good growth," its corresponding thermal value may be relatively high; conversely, if a status label represents "slow growth," its corresponding thermal value may be relatively low. Then, under the same crop growth status label, based on the crop growth status thermal value and the knowledge transfer vector, meteorological environment-related growth description vectors corresponding to several crop growth status labels in the growth monitoring task are obtained. This step mainly combines the crop growth status thermal value and the knowledge transfer vector to generate a more comprehensive and accurate description vector.

[0157] Thus, by introducing thermodynamic values ​​of crop growth status, the growth status of crops can be measured and reflected more accurately, improving the predictive accuracy of the model. Furthermore, by combining thermodynamic values ​​and knowledge transfer vectors to generate descriptive vectors, multi-source information can be effectively integrated, further enhancing the model's expressive and generalization abilities. Therefore, this technical solution helps improve agricultural production efficiency, enhance the quality of agricultural products, and provide a more scientific and accurate basis for agricultural production decisions.

[0158] Further, the step of obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth state labels in the growth monitoring task, based on the crop growth state thermodynamic value and the knowledge transfer vector, under the same crop growth state label, includes: determining a set of meteorological environment impact features represented by a state feature mapping relationship network corresponding to several crop growth state labels, wherein the set of meteorological environment impact features includes several meteorological environment impact features, each corresponding to a crop growth state thermodynamic value; using the crop growth state thermodynamic value corresponding to the meteorological environment impact feature as the meteorological environment impact feature value, deriving from several meteorological environment impact features in the set of meteorological environment impact features to obtain a set of meteorological environment impact feature chains with the same meteorological environment impact feature value; and obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth state labels in the growth monitoring task based on the meteorological environment impact feature chain set and the knowledge transfer vector.

[0159] In this technical solution, the process of obtaining meteorological environment-related growth description vectors corresponding to several crop growth state labels in the growth monitoring task, based on crop growth state thermodynamic values ​​and knowledge transfer vectors, is further refined into the following operations: First, a set of meteorological environment impact features, represented by a state feature mapping relationship network corresponding to several crop growth state labels, is determined. These feature sets include several meteorological environment impact features, each corresponding to a crop growth state thermodynamic value. Then, using the crop growth state thermodynamic value corresponding to the meteorological environment impact feature as the feature value, several features in the meteorological environment impact feature set are derived to obtain a set of meteorological environment impact feature chains with the same feature value. A "feature chain set" refers to a set of features with the same feature value, which can better reflect the correlation between different features. Finally, based on the meteorological environment impact feature chain set and the knowledge transfer vector, the meteorological environment-related growth description vectors corresponding to several crop growth state labels in the growth monitoring task are obtained. This step mainly combines the feature chain set and the knowledge transfer vector to generate more comprehensive and accurate description vectors.

[0160] By introducing a state feature mapping network, crop growth state heatmaps, knowledge transfer vectors, and the concept of feature chains, the growth state of crops can be measured and reflected more accurately, improving the model's predictive accuracy. Furthermore, by fusing multiple information sources to generate descriptive vectors, multi-source information can be effectively integrated, further enhancing the model's expressive and generalization abilities. Therefore, this technical solution helps improve agricultural production efficiency, enhance the quality of agricultural products, and provide a more scientific and accurate basis for agricultural production decisions.

[0161] Furthermore, the step of obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth status labels in the growth monitoring task based on the meteorological environment impact feature chain set and the knowledge transfer vector includes: extracting knowledge elements from the meteorological environment impact feature chain set using a deep learning branch to obtain meteorological environment impact feature knowledge; and aggregating the meteorological environment impact feature knowledge and the knowledge transfer vector under the same crop growth status label to obtain the meteorological environment-related growth description vectors corresponding to the several crop growth status labels in the growth monitoring task.

[0162] In this technical solution, the process of obtaining meteorological environment-related growth description vectors corresponding to several crop growth status labels in the growth monitoring task, based on the meteorological environment impact feature chain set and knowledge transfer vectors, is further refined into the following operations: First, knowledge elements are extracted from the meteorological environment impact feature chain set using a deep learning branch to obtain meteorological environment impact feature knowledge. "Deep learning branch" refers to a branch or subsystem utilizing deep learning methods, which can automatically learn and extract the inherent patterns and characteristics of data. "Knowledge element extraction" refers to the important information or knowledge extracted from the meteorological environment impact feature chain set through the deep learning branch, referred to as "meteorological environment impact feature knowledge." Then, under the same crop growth status label, the meteorological environment impact feature knowledge and knowledge transfer vectors are aggregated to obtain meteorological environment-related growth description vectors corresponding to several crop growth status labels in the growth monitoring task. "Aggregation" is the process of merging multiple elements or data into a whole; here, it mainly involves merging the meteorological environment impact feature knowledge and knowledge transfer vectors to generate more comprehensive and accurate description vectors.

[0163] In this way, by extracting knowledge elements through deep learning branches and aggregating them with knowledge transfer vectors, the growth status of crops can be more accurately reflected and predicted. Furthermore, this approach leverages the self-learning and extraction capabilities of deep learning to extract the factors that have the greatest impact on crop growth from a large amount of complex meteorological and environmental data, thereby more accurately predicting the growth status of crops and providing a more scientific and precise basis for agricultural production decisions.

[0164] In other embodiments, based on the correspondence, the meteorological environment-related growth description vectors and the original state simulation data under the same crop growth state label are vector-integrated to obtain the plurality of state simulation update data: the meteorological environment-related growth description vectors corresponding to the plurality of crop growth state labels are mapped to the simulated feature relationship network to obtain the growth environment-related mapping vectors corresponding to the plurality of crop growth state labels; under the same crop growth state label, the growth environment-related mapping vectors and the original state simulation data are vector-integrated to obtain the state simulation update data corresponding to the plurality of crop growth state labels.

[0165] In these embodiments, the process of vector integration of meteorological environment-related growth description vectors and original state simulation data under the same crop growth state label to obtain several state simulation update data includes the following steps: First, the meteorological environment-related growth description vectors corresponding to several crop growth state labels are mapped to a simulated feature relationship network to obtain growth environment-related mapping vectors corresponding to several crop growth state labels. The "simulated feature relationship network" is a network structure that can represent the relationships and interactions between various features, used to simulate complex real-world situations. The "growth environment-related mapping vector" is a vector obtained through mapping operations, reflecting the influence of the growth environment on the crop growth state.

[0166] Then, under the same crop growth state label, the growth environment association mapping vector and the original state simulation data are vector ensembled to obtain state simulation update data corresponding to several crop growth state labels. "Vector ensemble" is a common machine learning technique that generates a new, more comprehensive vector (such as state simulation update data) by integrating information from multiple vectors (such as the growth environment association mapping vector and the original state simulation data).

[0167] This design, by introducing simulated feature networks and vector ensemble techniques, can better integrate various information sources, thereby more accurately reflecting and predicting crop growth status. Furthermore, this scheme can update simulated data in real time, allowing the model to self-optimize over time, further improving the accuracy and reliability of predictions. Therefore, this technical solution helps improve agricultural production efficiency, enhance the quality of agricultural products, and provide a more scientific and precise basis for agricultural production decisions.

[0168] In some examples, each crop growth status label corresponds to x growth status simulation algorithms, where x is a positive integer. Step 150, which describes generating crop growth status simulation results for the target agricultural region under each of the several crop growth status labels based on the updated data from these several status simulations, includes steps 151-153.

[0169] Step 151: Perform crop growth state simulation on the state simulation update data of the y-th growth state simulation algorithm corresponding to the plurality of crop growth state labels, and obtain the original state simulation data of the (y+1)-th growth state simulation algorithm corresponding to the plurality of crop growth state labels, where y is a positive integer not greater than x.

[0170] Step 152: In response to the xth growth state simulation algorithm, obtain the state simulation inference vector output by the xth growth state simulation algorithm corresponding to the plurality of crop growth state labels.

[0171] Step 153: Generate the crop growth state simulation results corresponding to the target agricultural region under the several crop growth state labels based on several state simulation inference vectors.

[0172] In this technical solution, each crop growth status label corresponds to x growth status simulation algorithms, where x is a positive integer. The process of generating crop growth status simulation results for the target crop region under the various crop growth status labels based on several state simulation update data includes the following steps: Step 151 involves simulating crop growth status using the state simulation update data of the y-th growth status simulation algorithm corresponding to each of the several crop growth status labels, obtaining the original state simulation data of the (y+1)-th growth status simulation algorithm corresponding to each of the several crop growth status labels, where y is a positive integer not greater than x; Step 152 involves obtaining the state simulation inference vector output by the x-th growth status simulation algorithm corresponding to each of the several crop growth status labels after processing the x-th growth status simulation algorithm. The "state simulation inference vector" refers to the vector obtained after inferring the state through the simulation algorithm, reflecting the simulation algorithm's understanding and prediction of the crop growth status; Step 153 generates crop growth status simulation results for the target crop region under the various crop growth status labels based on the several state simulation inference vectors. In other words, each simulation result is generated by the corresponding inference vector.

[0173] In summary, the above-described technical solution, by introducing multiple growth state simulation algorithms, can simulate and predict crop growth states from different angles and levels, thereby improving the accuracy and reliability of predictions. Furthermore, this solution can update simulation data in real time and generate simulation results through inference vectors, enabling the model to self-optimize over time, further enhancing the accuracy and reliability of predictions. Therefore, this technical solution helps improve agricultural production efficiency, enhance the quality of agricultural products, and provide a more scientific and precise basis for agricultural production decisions.

[0174] In some optional embodiments, step 153 generates the crop growth state simulation results corresponding to the target agricultural area under the several crop growth state labels based on several state simulation inference vectors, including steps 1531-1533.

[0175] Step 1531: Perform cyclic crop growth state simulation based on the state simulation inference vector under the several crop growth state labels until the cyclic condition is met, and obtain the state simulation decision vector corresponding to the several crop growth state labels respectively. The state simulation decision vector is used to reflect the linear vector obtained after simulating the growth state of crops for the meteorological environmental factor variables.

[0176] Step 1532: Generate the simulation results of crop growth status corresponding to the target agricultural region under the several crop growth status labels by passing several state simulation decision vectors through simulation output branches.

[0177] In these optional embodiments, the process of generating simulation results of crop growth status for a target agricultural region under several crop growth status labels based on several state simulation inference vectors includes the following steps: Step 1531 involves performing cyclic crop growth status simulation based on the state simulation inference vectors under several crop growth status labels until the cyclic condition is met, thereby obtaining state simulation decision vectors corresponding to the several crop growth status labels. The state simulation decision vectors reflect the linear vectors obtained after simulating the crop growth status for meteorological environmental variables. A "linear vector" refers to a vector that can be obtained in vector space through scalar multiplication and vector addition. Step 1532 involves generating simulation results of crop growth status for the target agricultural region under several crop growth status labels by passing the several state simulation decision vectors through simulation output branches. A "simulation output branch" is a system or subsystem that can receive state simulation decision vectors and generate simulation results based on these vectors.

[0178] By introducing cyclic simulation and simulation output branches, this approach can more accurately reflect and predict crop growth status, improving the accuracy and reliability of predictions. Furthermore, this scheme can update simulation data in real time and generate simulation results through state simulation decision vectors, enabling the model to self-optimize over time, further enhancing the accuracy and reliability of predictions. Therefore, this technical solution helps improve agricultural production efficiency, enhance the quality of agricultural products, and provide a more scientific and precise basis for agricultural production decisions.

[0179] Based on the above, a data simulation system is provided, including a processor and a memory that communicate with each other. The processor is used to retrieve a computer program from the memory and implement the above method by running the computer program.

[0180] Based on the above, a computer-readable storage medium is provided, on which a computer program is stored, the computer program implementing the above method when running.

[0181] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for simulating crop growth status based on meteorological grid data, characterized in that, The method, applied to a data simulation system, includes: Obtain meteorological environmental element variables corresponding to meteorological grid monitoring information; wherein, the meteorological environmental element variables are used to simulate crop growth status under several crop growth status labels respectively, and obtain the crop growth status simulation results corresponding to the target agricultural area under the several crop growth status labels respectively; When simulating the crop growth state of the meteorological environmental element variables using the growth state simulation algorithms corresponding to the several crop growth state labels, the original state simulation data of the growth state simulation algorithms corresponding to the several crop growth state labels is determined; wherein, the original state simulation data is a description vector to be entered into the growth state simulation algorithm for state simulation. Extract the shared cross features between the state feature mapping relationship networks corresponding to several original state simulation data; wherein, the state feature mapping relationship network is obtained by data feature mining of the original state simulation data; The original state simulation data are updated using the cross features to obtain updated state simulation data; wherein there is a correspondence between the original state simulation data and the updated state simulation data. Based on the aforementioned state simulation update data, crop growth state simulation results corresponding to the target agricultural region under the aforementioned crop growth state labels are generated; wherein, the aforementioned crop growth state simulation results are combined to obtain the crop yield prediction results of the target agricultural region, and the crop yield prediction results are used as guidance for adjusting artificial meteorological environmental parameters. The step of extracting the shared cross features among the state feature mapping networks corresponding to the several state simulation original data includes: performing convolution operations on the several state simulation original data to obtain the state feature mapping networks corresponding to the several state simulation original data; performing local downsampling on the several state feature mapping networks to obtain state involvement vectors, the state involvement vectors being used to reflect the shared cross features among the several state feature mapping networks; The step of performing convolution operations on the plurality of state-simulated original data to obtain the state feature mapping network corresponding to the plurality of state-simulated original data includes: performing convolution operations on the plurality of state-simulated original data to obtain state-simulated convolution vectors corresponding to the plurality of crop growth state labels; obtaining sensor monitoring element vectors corresponding to the plurality of crop growth state labels, wherein the sensor monitoring element vectors are linear vectors obtained based on sensor variables corresponding to the crop growth state labels, and the sensor monitoring element vectors are used to reflect the periodic data of the corresponding crop growth state labels, wherein there is a correspondence between the plurality of sensor monitoring element vectors and the plurality of state-simulated convolution vectors; and, based on the correspondence, performing vector integration on the state-simulated convolution vectors and the sensor monitoring element vectors under the same crop growth state label to obtain the state feature mapping network corresponding to the plurality of state-simulated original data.

2. The method according to claim 1, characterized in that, The process of determining the original state simulation data for the growth state simulation algorithm corresponding to the plurality of crop growth state labels includes: Obtain crop growth monitoring information, which is information obtained by monitoring crops in the target agricultural area, and the crop growth monitoring information is used to generate simulation results reflecting the crop growth status in the target agricultural area; Using the crop growth monitoring information as a simulation reference, the original data of the state simulation algorithm corresponding to the several crop growth state labels are determined. The simulation reference is used to determine the crop growth trend characteristics when simulating the meteorological environmental element variables. The step of obtaining crop growth monitoring information includes: obtaining at least one dataset obtained from monitoring the target agricultural area as the crop growth monitoring information, wherein the dataset is the result obtained from monitoring the target agricultural area based on a set crop growth status label.

3. The method according to claim 1, characterized in that, The step of obtaining the sensor monitoring element vectors corresponding to the plurality of crop growth status labels includes: Obtain the sensor variables corresponding to the several crop growth status labels respectively. The sensor variables are used to reflect the sensor distribution characteristics that generate the corresponding crop growth status simulation results. The sensor variables include sensor region labels and sensor category labels. The sensor region labels are used to reflect the distribution of the sensors in the sensing and monitoring feature space relative to the target crop area. The sensor category labels represent the monitoring category of the sensors in the sensing and monitoring feature space relative to the target crop area. Several sensor variables are preprocessed to obtain preprocessing results corresponding to the several sensor variables respectively. The preprocessing results are linear vectors obtained by preprocessing the sensor variables in the growth monitoring task. By setting a knowledge extraction algorithm to extract knowledge elements from the preprocessing results, the sensor monitoring element vectors corresponding to the several crop growth status labels are obtained.

4. The method according to claim 1, characterized in that, The step of locally downsampling several state feature mapping relationship networks to obtain state-related vectors includes: The meteorological environment impact feature sets represented by the aforementioned state feature mapping relationship networks are determined respectively. The meteorological environment impact feature sets are used to reflect the set of several meteorological environment impact features in the growth monitoring task when the state feature mapping relationship network is obtained. Several meteorological and environmental impact features that are at the same feature position in several sets of meteorological and environmental impact features are focused to obtain several local focus weights; The state-related vector is obtained by downsampling the aforementioned local focus weights.

5. The method according to claim 1, characterized in that, The step of updating the original state simulation data using the cross features to obtain updated state simulation data includes: Obtain the state-related vector representing the cross-feature; the state-related vector is a vector representing the crop growth state obtained after downsampling; Based on the crop growth state labels corresponding to the several state simulation raw data and the state involvement vectors, meteorological environment-related growth description vectors corresponding to the several crop growth state labels are obtained. The meteorological environment-related growth description vectors are used to reflect the contribution of the state involvement vectors to the state simulation raw data at the time-series description level. There is a correspondence between the several meteorological environment-related growth description vectors and the several state simulation raw data. Based on the correspondence, the several state simulation update data are obtained by using the meteorological environment-associated growth description vector under the same crop growth state label and the original state simulation data.

6. The method according to claim 5, characterized in that, The step of obtaining meteorological environment-related growth description vectors corresponding to the crop growth state labels and state-related vectors corresponding to the several state simulation raw data includes: determining the sensor monitoring knowledge graphs corresponding to the several crop growth state labels, wherein the sensor monitoring knowledge graphs are generated based on the sensors used when determining the corresponding crop growth state labels; using the sensor monitoring knowledge graphs corresponding to the monitoring categories of the crop growth state labels as templates, performing knowledge transfer on the state-related vectors to obtain knowledge transfer vectors representing the several crop growth state labels; and obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth state labels in the growth monitoring task based on the several crop growth state labels and the corresponding knowledge transfer vectors. The step of obtaining the meteorological environment-related growth description vector corresponding to each of the several crop growth status labels and the corresponding knowledge transfer vectors in the growth monitoring task includes: obtaining the crop growth status heat values ​​represented by the several crop growth status labels; and, under the same crop growth status label, obtaining the meteorological environment-related growth description vector corresponding to each of the several crop growth status labels in the growth monitoring task based on the crop growth status heat values ​​and the knowledge transfer vectors; wherein, the crop growth status heat value is a numerical indicator that measures the intensity or activity of crop growth status. The step of obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth state labels in the growth monitoring task, based on the crop growth state thermodynamic value and the knowledge transfer vector, under the same crop growth state label, includes: determining a set of meteorological environment impact features represented by a state feature mapping relationship network corresponding to several crop growth state labels, wherein the set of meteorological environment impact features includes several meteorological environment impact features, each corresponding to a crop growth state thermodynamic value; using the crop growth state thermodynamic value corresponding to the meteorological environment impact feature as the meteorological environment impact feature value, deriving from several meteorological environment impact features in the set of meteorological environment impact features to obtain a set of meteorological environment impact feature chains with the same meteorological environment impact feature value; and obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth state labels in the growth monitoring task based on the meteorological environment impact feature chain set and the knowledge transfer vector. The step of obtaining the meteorological environment-related growth description vectors corresponding to the several crop growth status labels in the growth monitoring task based on the meteorological environment impact feature chain set and the knowledge transfer vector includes: extracting knowledge elements from the meteorological environment impact feature chain set using a deep learning branch to obtain meteorological environment impact feature knowledge; and aggregating the meteorological environment impact feature knowledge and the knowledge transfer vector under the same crop growth status label to obtain the meteorological environment-related growth description vectors corresponding to the several crop growth status labels in the growth monitoring task.

7. The method according to claim 5, characterized in that, Based on the correspondence, the meteorological environment-related growth description vectors and the original state simulation data under the same crop growth state label are vector-integrated to obtain the several state simulation update data: The meteorological environment-related growth description vectors corresponding to several crop growth status labels are mapped to the simulated feature relationship network to obtain the growth environment-related mapping vectors corresponding to several crop growth status labels. Under the same crop growth state label, the growth environment association mapping vector and the original state simulation data are vector-integrated to obtain the state simulation update data corresponding to several crop growth state labels respectively.

8. The method according to claim 1, characterized in that, Each crop growth status label corresponds to x growth status simulation algorithms, where x is a positive integer; The step of generating simulation results of crop growth status for the target crop region under the various crop growth status labels based on the simulation update data of the various states includes: The state simulation update data of the y-th growth state simulation algorithm corresponding to the plurality of crop growth state labels is used to simulate the crop growth state, so as to obtain the original state simulation data of the (y+1)-th growth state simulation algorithm corresponding to the plurality of crop growth state labels, where y is a positive integer not greater than x. In response to the xth growth state simulation algorithm, obtain the state simulation inference vector output by the xth growth state simulation algorithm corresponding to the plurality of crop growth state labels respectively; Based on several state simulation inference vectors, the simulation results of the crop growth state corresponding to the target agricultural area under several crop growth state labels are generated. The step of generating the crop growth state simulation results corresponding to the target agricultural region under the several crop growth state labels based on several state simulation inference vectors includes: performing cyclic crop growth state simulation based on the state simulation inference vectors under the several crop growth state labels until the cyclic condition is met, and obtaining state simulation decision vectors corresponding to the several crop growth state labels respectively. The state simulation decision vectors are used to reflect the linear vectors obtained after simulating the crop growth state of the meteorological environmental factor variables; and generating the crop growth state simulation results corresponding to the target agricultural region under the several crop growth state labels by passing the several state simulation decision vectors through simulation output branches.

9. A data simulation system, characterized in that, The data simulation system includes a processor and a memory that communicate with each other, the processor being configured to retrieve a computer program from the memory and execute the computer program to implement the method of any one of claims 1-8.

Images