Crop growth management method and system based on sky-ground integration

Abstract

The application relates to the technical field of crop growth management, and discloses a crop growth management method and system based on a sky-ground integration, which comprises the following steps: collecting preliminary monitoring data based on a target detection instruction; performing data cleaning and formatting on the preliminary monitoring data to obtain a standard data format, performing space-time alignment on the preliminary monitoring data in the standard data format to obtain stage detection data; constructing a crop growth model, performing fusion processing on the stage detection data based on the crop growth model to obtain a crop growth variable; obtaining a crop growth strategy matched with the crop growth variable based on the crop growth variable; and adjusting the target detection instruction based on the crop growth strategy, and re-collecting the preliminary monitoring data to realize precise irrigation, precise fertilization and precise pest control, reduce resource waste, reduce environmental pollution and improve the sustainability of agricultural production.

Description

Technical Field

[0001] This invention relates to the field of agricultural monitoring technology, and more specifically, to a crop growth management method and system based on an integrated space-air-ground system. Background Technology

[0002] The growth status of crops at different growth stages directly affects the final yield. Traditional monitoring methods are insufficient to comprehensively and timely capture changes in crop growth at each stage, especially in large-scale farmlands, where the limitations of manual monitoring make dynamic management of crop growth difficult. Furthermore, crop yield is influenced by multiple factors, making it difficult to accurately reflect the true growth status and future yield potential of crops in the current season, particularly in the face of abnormal climate or environmental changes, where predictions are often inaccurate.

[0003] For example, application publication number CN118211730A discloses a method for predicting crop yield based on meteorological feature matching and crop growth model. By constructing a method for simulating unknown meteorological data that combines meteorological data matching with yield abundance index, and combining it with crop growth model to predict regional yield, it can make accurate predictions of the yield of different crops and judge the overall supply and demand situation.

[0004] However, the crop growing environment is highly variable during crop cultivation, making yield prediction difficult. Satellite remote sensing, while offering wide coverage, has low resolution and struggles to capture subtle crop changes. While drones offer high resolution, their coverage area is limited and they are heavily influenced by weather conditions. Ground-based sensors provide precise micro-environmental data, but their limited deployment range makes it difficult to reflect the overall situation of large areas of farmland. Individual data points from this system cannot provide comprehensive information on crop growth variables, resulting in insufficient decision-making support for farmland management and an inability to accurately reflect the true condition of the farmland.

[0005] However, integrating data from satellites, drones, and ground sensors often fails to leverage the strengths of each data source through simple overlay analysis, resulting in wasted resources and low management efficiency. Furthermore, in the face of sudden climate change or pest infestations, data analysis from a single source or with delays cannot provide timely and effective response strategies, increasing the risk of crop losses and impacting final yield and quality.

[0006] In view of this, the present invention proposes a crop growth management method and system based on the integration of space, air and ground. Summary of the Invention

[0007] To overcome the shortcomings of existing technologies, this invention provides a crop growth management method and system based on the integration of air, space, and ground, which has the advantage of more precise operation.

[0008] In a first aspect, the present invention provides a crop growth management method based on an integrated space-air-ground system, comprising the following steps:

[0009] Adjust the frequency of data acquisition nodes within a preset period based on the target detection command, and record the timestamps and preliminary monitoring data corresponding to the data acquisition nodes;

[0010] The preliminary monitoring data is cleaned and formatted to obtain a standard data format. The preliminary monitoring data in the standard data format is spatiotemporally aligned within a preset period to obtain stage monitoring data.

[0011] A crop growth model is constructed, and the stage detection data is fused and processed based on the crop growth model to obtain the crop growth variables within a preset period.

[0012] The yield prediction probability distribution is obtained based on crop growth variables, and a list of risk sources corresponding to the current probability distribution is generated. The corresponding crop growth strategy is matched based on the risk source list. The target detection instructions are adjusted through the crop growth strategy, the frequency of data collection nodes within the preset period is adjusted, and the preliminary monitoring data is improved and updated.

[0013] As a preferred technical solution of the first aspect of the present invention, the target detection command is an operation command issued based on different application scenarios during the integrated space-air-ground operation, thereby obtaining different preliminary monitoring data, the preliminary monitoring data including space-based remote sensing data, air-based detection data and ground-based planting data;

[0014] The space-based remote sensing data refers to remote sensing data collected periodically by satellite sensors based on satellite orbits and the geographical location of farmland.

[0015] The airborne detection data refers to local image data of farmland obtained using a drone equipped with imaging equipment;

[0016] The ground-based planting data is crop growth data collected in real time by a ground monitoring network. The ground monitoring network includes soil moisture sensors, temperature sensors, nutrient sensors, and photosynthetically active radiation sensors deployed in the target planting area to monitor planting environment data such as soil moisture, temperature, nutrient content, and meteorological conditions in real time.

[0017] As a preferred technical solution of the first aspect of the present invention, the crop is set up in a process-oriented manner, and different growth cycles are configured for different growth stages and marked as preset cycles; within each preset cycle, the data acquisition nodes are identified by the acquisition timestamp of the space-based remote sensing data, and the preliminary monitoring data acquired between adjacent data acquisition nodes are stored in the same time block, and the current time block is marked by the previous acquisition time node.

[0018] As a preferred embodiment of the first aspect of the present invention, the logic for acquiring the stage detection data is as follows:

[0019] Using the target planting area identified in space-based remote sensing data as a reference, a spatial planting platform is constructed;

[0020] The target planting features identified in the ground-based planting data are marked and matched proportionally to the spatial planting platform through the target planting area to ensure that the geographic space remains consistent.

[0021] The contour lines of the farmland local image data identified in the airborne detection data are overlapped with the target planting area, and local image features are added to the overlapped target planting area.

[0022] The target planting features and local image features are sequentially superimposed on the spatial planting platform according to the time sequence. The spatial planting platform superimposes the detection marker icons collected in the target planting area based on the timestamp to mark the stage detection data of the current time block.

[0023] As a preferred embodiment of the first aspect of this invention, the superposition logic of the spatial planting platform is as follows:

[0024] The space planting platform arbitrarily selects a reference point from the current space-based remote sensing data, uses the reference point as the center coordinate, and constructs a space coordinate system based on the reference point.

[0025] In the spatial coordinate system, reference objects are classified and marked, and the outline of the area corresponding to the crop planting environment is marked as the target planting area;

[0026] The region outline of the target planting area in the airborne detection data and / or ground-based planting data is completely overlapped with the region outline in the spaceborne remote sensing data, and the target planting area corresponding to the ground-based planting data is determined as the three-dimensional coordinate system of the target planting area.

[0027] Extract detection marker icons from different coordinate locations in the airborne detection data and / or ground-based planting data, and characterize the target planting features and local image features based on the detection marker icons;

[0028] All detection marker icons are displayed superimposed on the three-dimensional coordinate system of the target planting area, and the orientation information of the detection marker icons in the target planting area is determined according to the center coordinates.

[0029] As a preferred embodiment of the first aspect of the present invention, the logic for obtaining the crop growth variables is as follows:

[0030] Stage analysis data is obtained by performing stage slice analysis on the stage detection data. The stage analysis data includes target feature data containing various detection marker icons. The target feature data includes reference objects of the target planting area, target planting features, and local image features.

[0031] Semantically align the target feature data, and set a corresponding stacked autoencoder for each target feature data through a multimodal autoencoder network to convert the target feature data into target coded features that can be recognized by the crop growth model;

[0032] The target encoded features are used as input factors for the crop growth model, and the output factor of the crop growth model is the probability of growth abnormality.

[0033] The target coding features and growth anomaly probabilities are reconstructed and marked as a growth trajectory matrix based on the timestamp. Growth anomaly statistics are performed on the growth trajectory matrix. The dimensionality reduction is determined by combining the pre-set reconstruction error threshold corresponding to each target coding feature, and the low-dimensional embedding of the current target coding feature is obtained. The low-dimensional embedding representation is spliced ​​to obtain the crop growth variable.

[0034] As a preferred technical solution of the first aspect of the present invention, a target detection instruction is determined by searching a matching list of risk sources in a priori knowledge base based on crop growth strategies, analyzing the yield impact probability of each crop growth variable in the risk source list based on prior knowledge, and analyzing the yield impact probability threshold based on prior knowledge.

[0035] Secondly, the present invention provides a crop growth management system based on the integration of air, space and ground, which is based on the implementation of the crop growth management method based on the integration of air, space and ground described in the first aspect. It includes a data acquisition module, a data processing module, a crop growth analysis module and a decision feedback module, and the modules are connected to each other by wired or wireless means.

[0036] The data acquisition module adjusts the frequency of data acquisition nodes within a preset period based on the target detection command, records the timestamps and preliminary monitoring data corresponding to the data acquisition nodes, and sends the preliminary monitoring data to the data processing module.

[0037] The data processing module cleans and formats the preliminary monitoring data to obtain a standard data format, aligns the preliminary monitoring data in the standard data format in time and space within a preset period to obtain stage detection data, and sends the stage detection data to the crop growth analysis module.

[0038] The crop growth analysis module constructs a crop growth model, integrates and processes stage detection data based on the crop growth model, and obtains crop growth variables within a preset period; the crop growth variables are then sent to the crop decision feedback module.

[0039] The decision feedback module obtains the probability distribution of yield prediction based on crop growth variables and generates a list of risk sources corresponding to the current probability distribution. It then matches the corresponding crop growth strategy based on the risk source list. By adjusting the target detection instructions through the crop growth strategy, it adjusts the frequency of data collection nodes within a preset period and improves and updates the preliminary monitoring data.

[0040] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0041] The processor executes the crop growth management method based on the integrated space-air-ground system described in the first aspect by calling the computer program stored in the memory.

[0042] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the crop growth management method based on the integrated space-air-ground system described in the first aspect.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] This invention integrates data from satellite remote sensing, UAV monitoring, and ground sensors using a space-air-ground integrated technology, comprehensively covering all aspects of crop growth. It converts data from different modalities into features recognizable by the crop growth model, improving the input quality of the model and ensuring the comprehensiveness and accuracy of the data. This overcomes the shortcomings of single data sources. Through the construction and analysis of the growth trajectory matrix, it can dynamically monitor the crop growth trajectory, promptly identify potential risk sources, take preventative measures to reduce losses, dynamically adjust target detection commands, and re-collect preliminary monitoring data to form a closed-loop feedback mechanism. This enables precision irrigation, precision fertilization, and precision pest and disease control, reducing resource waste, lowering environmental pollution, and improving the sustainability of agricultural production. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the crop growth management system framework of the present invention;

[0046] Figure 2 This is a flowchart of the crop growth management method of the present invention;

[0047] Figure 3 This is a schematic diagram of an electronic device structure according to the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Example 1: As Figure 1 As shown, the present invention provides a crop growth management system based on the integration of air, space and ground, including a data acquisition module 100, a data processing module 200, a crop growth analysis module 300 and a decision feedback module 400, and the modules are connected to each other by wired or wireless means.

[0050] The data acquisition module 100 adjusts the frequency of data acquisition nodes within a preset period based on the target detection command, records the timestamps and preliminary monitoring data corresponding to the data acquisition nodes, and sends the preliminary monitoring data to the data processing module 200.

[0051] Specifically, the target detection command is an operation command issued based on different application scenarios during the integrated space-air-ground operation. Each operation command includes the acquisition frequency of the corresponding data acquisition node. Different data acquisition nodes acquire different preliminary monitoring data, which includes space-based remote sensing data, air-based detection data, and ground-based planting data.

[0052] More specifically, since crop types and planting times are not fixed, when using integrated space-air-ground data monitoring, it is necessary to set up a process for crops, configure different growth cycles for different growth stages, and mark them as preset cycles. Within each preset cycle, the data acquisition nodes are matched with the acquisition timestamps of space-based remote sensing data, and the preliminary monitoring data acquired between adjacent data acquisition nodes are stored in the same time block, and the current time block is marked with the previous acquisition time node.

[0053] More specifically, the space-based remote sensing data refers to remote sensing data collected periodically by satellite sensors based on satellite orbits and the geographical location of farmland, in order to capture dynamic changes in crop growth. The satellite sensors are high-resolution, multispectral, and thermal infrared satellite sensors (such as Landsat, Sentinel-2, MODIS, etc.) that periodically acquire space-based remote sensing data covering large areas of farmland. The space-based remote sensing data includes vegetation cover indices (such as NDVI, DVI, PRI), as well as large-scale environmental variables such as soil moisture, surface temperature, and climate conditions.

[0054] The airborne detection data is obtained by using drones equipped with imaging devices to acquire local image data of farmland. Based on the preliminary analysis results of space-based remote sensing data or the predetermined crop monitoring plan, the drone flight path is planned, and the drone, equipped with high-resolution multispectral cameras, thermal imagers, RGB cameras, and other sensor equipment, acquires detailed image data of local farmland, focusing on abnormal areas or crops in critical growth stages. The airborne detection data includes micro-crop information such as crop canopy height, leaf area index (LAI), vegetation cover, pest and disease status, and water stress. The airborne detection data is transmitted to the data processing center in real time via wireless network, or uploaded in batches after the task is completed.

[0055] The ground-based planting data consists of real-time crop growth data collected by a ground-based monitoring network. This network includes soil moisture sensors, temperature sensors, nutrient sensors, and photosynthetically active radiation sensors deployed within the target planting area. These sensors monitor soil moisture, temperature, nutrient content, and meteorological conditions in real time, providing detailed information on crop growth. The ground sensors typically collect data every few minutes to several hours and transmit it in real-time to the central processing unit via an Internet of Things (IoT) network, ensuring the timeliness and continuity of the data.

[0056] The data processing module 200 cleans and formats the preliminary monitoring data to obtain a standard data format, aligns the preliminary monitoring data in the standard data format in time and space within a preset period to obtain stage detection data, and sends the stage detection data to the crop growth analysis module 300.

[0057] It should be noted that data cleaning involves removing noise, invalid data, and outliers to ensure the quality and reliability of the input data. Algorithms are used to automatically identify and remove outlier data points, such as those caused by sensor malfunctions or data transmission errors.

[0058] Data formatting: Unifying data formats from different sources and converting them into a standard data format suitable for analysis, facilitating subsequent fusion and analysis. This includes rasterization of image data and structured processing of sensor data.

[0059] The logic for obtaining the phase detection data is as follows:

[0060] Using the target planting area identified in space-based remote sensing data as a reference, a spatial planting platform is constructed;

[0061] The target planting features identified in the ground-based planting data are marked and matched proportionally to the spatial planting platform through the target planting area to ensure that the geographic space remains consistent.

[0062] The contour lines of the farmland local image data identified in the airborne detection data are overlapped with the target planting area, and local image features are added to the overlapped target planting area.

[0063] The target planting features and local image features are sequentially superimposed on the spatial planting platform according to the time sequence. The spatial planting platform superimposes the detection marker icons collected in the target planting area based on the timestamp to mark the stage detection data of the current time block.

[0064] To further clarify: the stacking logic of the spatial planting platform is as follows:

[0065] The space planting platform arbitrarily selects a reference point from the current space-based remote sensing data, uses the reference point as the center coordinate, and constructs a space coordinate system based on the reference point.

[0066] In the spatial coordinate system, reference objects are classified and marked, and the outline of the area corresponding to the crop planting environment is marked as the target planting area;

[0067] The region outline of the target planting area in the airborne detection data and / or ground-based planting data is completely overlapped with the region outline in the spaceborne remote sensing data, and the target planting area corresponding to the ground-based planting data is determined as the three-dimensional coordinate system of the target planting area.

[0068] Extract detection marker icons from different coordinate locations in the airborne detection data and / or ground-based planting data, and characterize the target planting features and local image features based on the detection marker icons;

[0069] All detection marker icons are displayed superimposed on the three-dimensional coordinate system of the target planting area, and the orientation information of the detection marker icons in the target planting area is determined according to the center coordinates.

[0070] The crop growth analysis module 300 constructs a crop growth model, integrates and processes stage detection data based on the crop growth model, and obtains crop growth variables within a preset period; the crop growth variables are then sent to the crop decision feedback module 400.

[0071] Specifically, the logic for obtaining the crop growth variables is as follows:

[0072] Stage analysis data is obtained by performing stage slice analysis on the stage detection data. The stage analysis data includes target feature data containing various detection marker icons. The target feature data includes reference objects of the target planting area, target planting features, and local image features.

[0073] Semantically align the target feature data, and set a corresponding stacked autoencoder for each target feature data through a multimodal autoencoder network to convert the target feature data into target coded features that can be recognized by the crop growth model;

[0074] The target encoded features are used as input factors for the crop growth model, and the output factor of the crop growth model is the probability of growth abnormality.

[0075] The target coding features and growth anomaly probabilities are reconstructed and marked as a growth trajectory matrix based on the timestamp. Growth anomaly statistics are performed on the growth trajectory matrix. The dimensionality reduction is determined by combining the pre-set reconstruction error threshold corresponding to each target coding feature, and the low-dimensional embedding of the current target coding feature is obtained. The low-dimensional embedding representation is spliced ​​to obtain the crop growth variable.

[0076] Further explanation: A crop growth model is constructed, using target encoded features as input factors and the probability of growth anomalies as output factors. Historical and current data are used to train the model through various machine learning algorithms, including random forest, logistic regression, and deep learning. The model training process includes feature selection, parameter optimization, and model validation, generating predictive models for different crop types and growth stages.

[0077] Based on real-time data for the current season, the model predicts crop growth, yield, and health status at different growth stages. Model output includes key indicators such as growth level, potential yield, and maturity time. Through model analysis, it identifies anomalies in crop growth, such as pests and diseases, insufficient water, nutrient deficiencies, and environmental stress. Trained on anomalous samples from historical data, it effectively captures anomalous patterns, using the probability of potential growth anomalies as an output factor. Upon detecting anomalies, the system automatically analyzes and obtains crop growth variables, pushing them in real-time to farmers or agricultural managers via mobile devices or management platforms, providing rapid decision support.

[0078] The decision feedback module 400 obtains the yield prediction probability distribution based on crop growth variables and generates a list of risk sources corresponding to the current probability distribution. Based on the risk source list, it matches the corresponding crop growth strategy. Through the crop growth strategy, it adjusts the target detection instructions, adjusts the frequency of data collection nodes within the preset period, and improves and updates the preliminary monitoring data.

[0079] It should be noted that the crop growth strategy includes irrigation strategy, fertilization strategy, and pest and disease control strategy. It optimizes the use of water resources and fertilizers to improve crop yield and quality. The strategy takes into account different growth stages of crops, soil conditions, and environmental factors. In the process of pest and disease control, it provides appropriate pesticide application time, dosage, and methods. By reducing the overuse of pesticides, the system helps to reduce costs and environmental impact. According to the target detection instructions, it controls the drone to conduct targeted inspections according to preset paths and preset times.

[0080] Farmers manage their fields according to the crop growth strategies provided by the system, and the actual data from the management process is then input back into the system to validate and adjust the prediction model. Through iterative optimization, the model gradually improves its prediction accuracy and adaptability.

[0081] By utilizing feedback data and new data sources, model parameters and algorithm structure are continuously adjusted to improve the model's adaptability to different environmental conditions and crop varieties. The model optimization process includes techniques such as cross-validation, incremental learning, and online learning.

[0082] Specifically, based on crop growth strategies, a list of matching risk sources is searched in the prior knowledge base. Based on prior knowledge, the probability of yield impact corresponding to each crop growth variable in the risk source list is analyzed. Based on the analysis threshold of the yield impact probability based on prior knowledge, the target detection instruction is determined.

[0083] Example 2: Based on Example 1, this example demonstrates how the above process enables refined management of crop growth in a smart agriculture project in a certain region. The specific steps are as follows:

[0084] In smart agriculture systems, satellite remote sensing, drones, and ground sensors are used to collect preliminary monitoring data on crops. This preliminary monitoring data includes spectral information, growth height, leaf area index, soil moisture, and meteorological data.

[0085] The collected preliminary monitoring data undergoes data cleaning and formatting. For example, filtering algorithms are used to remove noise, fill in missing values, and convert data from different sources into a unified standard data format. Then, spatiotemporal alignment is performed using Dynamic Time Warping (DTW) to align the time series data, ensuring that data from different time scales are on the same time reference. Spatial alignment is achieved through coordinate system transformation and geometric correction.

[0086] Stage-by-stage segmentation analysis is performed on the phased detection data to extract key features. Then, semantic alignment is performed to ensure semantic comparability of features from different data sources. A crop growth model is used to fuse the multi-source heterogeneous data, generating comprehensive crop growth variables. These variables include crop growth status, health status, and yield prediction.

[0087] A crop growth model, such as WOFOST or CERES, is constructed. Crop growth variables generated by the crop growth analysis module are used as input factors, and the yield prediction probability distribution is used as the output factor. The model analyzes the input environmental data, predicts crop yield in real time, and adjusts planting strategies based on the prediction results. For example, irrigation and fertilization strategies are adjusted based on the predicted yield probability distribution to optimize crop growth conditions. The adjusted target detection instructions are fed back to the data acquisition module, which re-collects preliminary monitoring data, forming a closed-loop feedback mechanism. This not only improves the accuracy of crop yield prediction but also optimizes the utilization of agricultural resources, enhancing the efficiency and sustainability of agricultural production.

[0088] Example 3: Please refer to Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description in Embodiment 1. This embodiment provides a method for monitoring and early warning of crop diseases and pests based on satellite remote sensing and AI algorithms, including the following steps:

[0089] Adjust the frequency of data acquisition nodes within a preset period based on the target detection command, and record the timestamps and preliminary monitoring data corresponding to the data acquisition nodes;

[0090] The preliminary monitoring data is cleaned and formatted to obtain a standard data format. The preliminary monitoring data in the standard data format is spatiotemporally aligned within a preset period to obtain stage monitoring data.

[0091] A crop growth model is constructed, and the stage detection data is fused and processed based on the crop growth model to obtain the crop growth variables within a preset period.

[0092] The yield prediction probability distribution is obtained based on crop growth variables, and a list of risk sources corresponding to the current probability distribution is generated. The corresponding crop growth strategy is matched based on the risk source list. The target detection instructions are adjusted through the crop growth strategy, the frequency of data collection nodes within the preset period is adjusted, and the preliminary monitoring data is improved and updated.

[0093] The target detection command is an operation command issued based on different application scenarios during the integrated space-air-ground operation, thereby obtaining different preliminary monitoring data, including space-based remote sensing data, air-based detection data, and ground-based planting data;

[0094] The space-based remote sensing data refers to remote sensing data collected periodically by satellite sensors based on satellite orbits and the geographical location of farmland.

[0095] The airborne detection data refers to local image data of farmland obtained using a drone equipped with imaging equipment;

[0096] The ground-based planting data is crop growth data collected in real time by a ground monitoring network. The ground monitoring network includes soil moisture sensors, temperature sensors, nutrient sensors, and photosynthetically active radiation sensors deployed in the target planting area to monitor planting environment data such as soil moisture, temperature, nutrient content, and meteorological conditions in real time.

[0097] The acquisition time nodes are divided based on the acquisition timestamps of space-based remote sensing data. The preliminary monitoring data acquired between adjacent acquisition time nodes are stored in the same time block, and the current time block is marked with the previous acquisition time node.

[0098] The logic for obtaining the phase detection data is as follows:

[0099] Using the target planting area identified in space-based remote sensing data as a reference, a spatial planting platform is constructed;

[0100] The target planting features identified in the ground-based planting data are marked and matched proportionally to the spatial planting platform through the target planting area to ensure that the geographic space remains consistent.

[0101] The contour lines of the farmland local image data identified in the airborne detection data are overlapped with the target planting area, and local image features are added to the overlapped target planting area.

[0102] The target planting features and local image features are sequentially superimposed on the spatial planting platform according to the time sequence. The spatial planting platform superimposes the detection marker icons collected in the target planting area based on the timestamp to mark the stage detection data of the current time block.

[0103] The stacking logic of the spatial planting platform is as follows:

[0104] The space planting platform arbitrarily selects a reference point from the current space-based remote sensing data, uses the reference point as the center coordinate, and constructs a space coordinate system based on the reference point.

[0105] In the spatial coordinate system, reference objects are classified and marked, and the outline of the area corresponding to the crop planting environment is marked as the target planting area;

[0106] The region outline of the target planting area in the airborne detection data and / or ground-based planting data is completely overlapped with the region outline in the spaceborne remote sensing data, and the target planting area corresponding to the ground-based planting data is determined as the three-dimensional coordinate system of the target planting area.

[0107] Extract detection marker icons from different coordinate locations in the airborne detection data and / or ground-based planting data, and characterize the target planting features and local image features based on the detection marker icons;

[0108] All detection marker icons are displayed superimposed on the three-dimensional coordinate system of the target planting area, and the orientation information of the detection marker icons in the target planting area is determined according to the center coordinates.

[0109] The logic for obtaining the crop growth variables is as follows:

[0110] Stage analysis data is obtained by performing stage slice analysis on the stage detection data. The stage analysis data includes target feature data containing various detection marker icons. The target feature data includes reference objects of the target planting area, target planting features, and local image features.

[0111] Semantically align the target feature data, and set a corresponding stacked autoencoder for each target feature data through a multimodal autoencoder network to convert the target feature data into target coded features that can be recognized by the crop growth model;

[0112] The target encoded features are used as input factors for the crop growth model, and the output factor of the crop growth model is the probability of growth abnormality.

[0113] The target coding features and growth anomaly probabilities are reconstructed and marked as a growth trajectory matrix based on the timestamp. Growth anomaly statistics are performed on the growth trajectory matrix. The dimensionality reduction is determined by combining the pre-set reconstruction error threshold corresponding to each target coding feature, and the low-dimensional embedding of the current target coding feature is obtained. The low-dimensional embedding representation is spliced ​​to obtain the crop growth variable.

[0114] Based on crop growth strategies, a list of matching risk sources is searched in a prior knowledge base. Based on prior knowledge, the probability of yield impact corresponding to each crop growth variable in the risk source list is analyzed. Based on the threshold analysis of the yield impact probability based on prior knowledge, the target detection instruction is determined.

[0115] Example 4: An electronic device according to an exemplary embodiment includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0116] The processor executes the aforementioned crop growth management method based on the integrated space-air-ground system by calling the computer program stored in the memory.

[0117] Figure 3This is a schematic diagram of an electronic device provided in an embodiment of this application. The electronic device can vary significantly due to differences in configuration or performance. It can include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the integrated space-air-ground crop growth management method provided in the various method embodiments described above. The electronic device can also include other components for implementing device functions; for example, it can have wired or wireless network interfaces and input / output interfaces for input / output. Further details are omitted here.

[0118] Example 5: A computer-readable storage medium according to an exemplary embodiment, wherein an erasable and rewritable computer program is stored thereon;

[0119] When the computer program is run on a computer device, the computer device executes the above-described crop growth management method based on the integration of air, space, and ground.

[0120] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including at least one computer program, which is executable by a processor to perform the integrated space-air-ground crop growth management method described in the above embodiments. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0121] In an exemplary embodiment, a computer program product or computer program is also provided, comprising one or more lines of program code stored in a computer-readable storage medium. One or more processors of an electronic device are capable of reading the one or more lines of program code from the computer-readable storage medium, and the one or more processors execute the one or more lines of program code, enabling the electronic device to perform the aforementioned crop growth management method based on an integrated space-air-ground system.

[0122] It should be understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0123] It should be understood that determining B based on A does not mean determining B solely based on A; it also means determining B based on A and / or other information.

[0124] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0125] The above description is only an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0126] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0127] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0129] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A crop growth management method based on integrated space-air-ground system, characterized by: Includes the following steps: Adjust the frequency of data acquisition nodes within a preset period based on the target detection command, and record the timestamps and preliminary monitoring data corresponding to the data acquisition nodes; The preliminary monitoring data is cleaned and formatted to obtain a standard data format. The preliminary monitoring data in the standard data format is spatiotemporally aligned within a preset period to obtain stage monitoring data. A crop growth model is constructed, and the stage detection data are fused and processed based on the crop growth model to obtain crop growth variables within a preset period; the logic for obtaining the crop growth variables is as follows: Stage analysis data is obtained by performing stage slice analysis on the stage detection data. The stage analysis data includes target feature data containing various detection marker icons. The target feature data includes reference objects of the target planting area, target planting features, and local image features. Semantically align the target feature data, and set a corresponding stacked autoencoder for each target feature data through a multimodal autoencoder network to convert the target feature data into target coded features that can be recognized by the crop growth model; The target encoded features are used as input factors for the crop growth model, and the output factor of the crop growth model is the probability of growth abnormality. The target coding features and growth anomaly probabilities are reconstructed and marked as a growth trajectory matrix based on the timestamp. Growth anomaly statistics are performed on the growth trajectory matrix. The dimensionality reduction is determined by combining the pre-set reconstruction error threshold corresponding to each target coding feature to obtain the low-dimensional embedding of the current target coding feature. The low-dimensional embedding representation is spliced ​​to obtain the crop growth variable. The yield prediction probability distribution is obtained based on crop growth variables, and a list of risk sources corresponding to the current probability distribution is generated. The corresponding crop growth strategy is matched based on the risk source list. The target detection instructions are adjusted through the crop growth strategy, the frequency of data collection nodes within the preset period is adjusted, and the preliminary monitoring data is improved and updated.

2. The crop growth management method based on the integrated space-air-ground system according to claim 1, characterized in that: The target detection command is an operation command issued based on different application scenarios during the integrated space-air-ground operation, thereby obtaining different preliminary monitoring data, including space-based remote sensing data, air-based detection data, and ground-based planting data; The space-based remote sensing data refers to remote sensing data collected periodically by satellite sensors based on satellite orbits and the geographical location of farmland. The airborne detection data refers to local image data of farmland obtained using drones equipped with imaging devices; The ground-based planting data is crop growth data collected in real time by a ground monitoring network. The ground monitoring network includes soil moisture sensors, temperature sensors, nutrient sensors, and photosynthetically active radiation sensors deployed in the target planting area to monitor planting environment data such as soil moisture, temperature, nutrient content, and meteorological conditions in real time.

3. The crop growth management method based on the integrated space-air-ground system according to claim 2, characterized in that: The crop is programmed with a process, and different growth cycles are configured for different growth stages and marked as preset cycles. Within each preset cycle, the data acquisition nodes are matched with the acquisition timestamps of the space-based remote sensing data. The preliminary monitoring data acquired between adjacent data acquisition nodes are stored in the same time block, and the current time block is marked with the previous acquisition time node.

4. The crop growth management method based on the integrated space-air-ground system according to claim 3, characterized in that: The logic for obtaining the phase detection data is as follows: Using the target planting area identified in space-based remote sensing data as a reference, a spatial planting platform is constructed; The target planting features identified in the ground-based planting data are marked and matched proportionally to the spatial planting platform through the target planting area to ensure that the geographic space remains consistent. The contour lines of the farmland local image data identified in the airborne detection data are overlapped with the target planting area, and local image features are added to the overlapped target planting area. The target planting features and local image features are sequentially superimposed on the spatial planting platform according to the time sequence. The spatial planting platform superimposes the detection marker icons collected in the target planting area based on the timestamp to mark the stage detection data of the current time block.

5. The crop growth management method based on the integrated space-air-ground system according to claim 4, characterized in that: The stacking logic of the spatial planting platform is as follows: The space planting platform arbitrarily selects a reference point from the current space-based remote sensing data, uses the reference point as the center coordinate, and constructs a space coordinate system based on the reference point. In the spatial coordinate system, reference objects are classified and marked, and the outline of the area corresponding to the crop planting environment is marked as the target planting area; The region outline of the target planting area in the airborne detection data and / or ground-based planting data is completely overlapped with the region outline in the spaceborne remote sensing data, and the target planting area corresponding to the ground-based planting data is determined as the three-dimensional coordinate system of the target planting area. Extract detection marker icons from different coordinate locations in the airborne detection data and / or ground-based planting data, and characterize the target planting features and local image features based on the detection marker icons; All detection marker icons are displayed superimposed on the three-dimensional coordinate system of the target planting area, and the orientation information of the detection marker icons in the target planting area is determined according to the center coordinates.

6. The crop growth management method based on the integrated space-air-ground system according to claim 5, characterized in that: Based on crop growth strategies, a list of matching risk sources is searched in a prior knowledge base. Based on prior knowledge, the probability of yield impact corresponding to each crop growth variable in the risk source list is analyzed. Based on the threshold analysis of the yield impact probability based on prior knowledge, the target detection instruction is determined.

7. A crop disease and pest monitoring and early warning system based on satellite remote sensing and AI algorithms, implemented based on the integrated space-air-ground crop growth management method described in any one of claims 1-6, characterized in that: It includes a data acquisition module (100), a data processing module (200), a crop growth analysis module (300), and a decision feedback module (400), with each module connected by wired or wireless means; The data acquisition module (100) adjusts the frequency of data acquisition nodes within a preset period based on the target detection command, records the timestamps and preliminary monitoring data corresponding to the data acquisition nodes, and sends the preliminary monitoring data to the data processing module (200). The data processing module (200) cleans and formats the preliminary monitoring data to obtain a standard data format, performs spatiotemporal alignment of the preliminary monitoring data in the standard data format within a preset period to obtain stage detection data, and sends the stage detection data to the crop growth analysis module (300). The crop growth analysis module (300) constructs a crop growth model, and performs fusion processing on the stage detection data based on the crop growth model to obtain crop growth variables within a preset period; the logic for obtaining the crop growth variables is as follows: Stage analysis data is obtained by performing stage slice analysis on the stage detection data. The stage analysis data includes target feature data containing various detection marker icons. The target feature data includes reference objects of the target planting area, target planting features, and local image features. Semantically align the target feature data, and set a corresponding stacked autoencoder for each target feature data through a multimodal autoencoder network to convert the target feature data into target coded features that can be recognized by the crop growth model; The target encoded features are used as input factors for the crop growth model, and the output factor of the crop growth model is the probability of growth abnormality. The target coding features and growth anomaly probabilities are reconstructed and marked as a growth trajectory matrix based on the timestamp. Growth anomaly statistics are performed on the growth trajectory matrix. The dimensionality reduction is determined by combining the pre-set reconstruction error threshold corresponding to each target coding feature to obtain the low-dimensional embedding of the current target coding feature. The low-dimensional embedding representation is concatenated to obtain the crop growth variable. The crop growth variable is sent to the crop decision feedback module (400). The decision feedback module (400) obtains the yield prediction probability distribution based on crop growth variables and generates a list of risk sources corresponding to the current probability distribution. Based on the risk source list, it matches the corresponding crop growth strategy. It adjusts the target detection instructions through the crop growth strategy, adjusts the frequency of data collection nodes within the preset period, and improves and updates the preliminary monitoring data.

8. An electronic device, characterized in that, include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the crop growth management method based on the integrated space-air-ground system as described in any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: The system stores instructions that, when executed on a computer, cause the computer to perform the crop growth management method based on the integrated space-air-ground system as described in any one of claims 1-6.

Images