Field crop growth and production management monitoring method, device, equipment and medium

Abstract

The invention relates to the technical field of field crop monitoring, and discloses a field crop growth and production management monitoring method, device and equipment and a medium, and the method comprises the steps: obtaining the wave band reflectivity of each satellite; based on the waveband data and a trained artificial neural network, predicting a leaf area index to obtain a leaf area index prediction result corresponding to each piece of waveband data; performing reconstruction based on a leaf area index prediction result to obtain a leaf area index time sequence curve; and based on the leaf area index time sequence curve, managing and monitoring growth and production of crops in the field. According to the method, the wave band reflectivity of each satellite platform is integrated, and the leaf area index is predicted and reconstructed based on the wave band reflectivity to obtain the leaf area index time sequence curve, so that the high-precision near-real-time monitoring of the crop growth trend and the field cultivation management measures in the field scale is realized according to the leaf area index time sequence curve.

Description

Technical Field

[0001] The present invention relates to the technical field of field crop monitoring, and in particular to a method, device, equipment and medium for monitoring the growth and production management of field crops. Background Art

[0002] With global climate change, extreme weather and agricultural disasters are frequent, and precise crop monitoring and management technologies are becoming increasingly important for stabilizing agricultural production. Traditional crop growth monitoring methods mainly rely on ground surveys, which have shortcomings such as limited monitoring range, long data acquisition cycle, and poor timeliness. The lag and inaccuracy of this information acquisition seriously affect the timely intervention and effective management of crop growth by agricultural managers. In recent years, satellite remote sensing technology has shown great potential in crop growth monitoring due to its ability to quickly obtain large-area surface information. However, single satellite data often has problems such as insufficient temporal and spatial resolution and is greatly affected by weather, which limits its application effect. In addition, due to the huge challenges in obtaining detailed farmer cultivation management information at the regional scale, it is difficult for existing monitoring and simulation technologies to clearly consider the impact of farmer production management on crop growth, resulting in inaccurate yield prediction results. Therefore, it is of great significance to develop a crop growth and production management monitoring technology that can integrate multi-source satellite remote sensing data.

[0003] At present, the dynamic monitoring of crop growth is mainly concentrated on the kilometer-level (250m-1km) low spatial resolution scale, which makes it difficult to accurately depict the growth and management of crops at the field scale, resulting in limitations in the quantitative monitoring, diagnosis, intervention and yield prediction of field crops. High spatial resolution satellite remote sensing can achieve ten-meter-level precise observation of crop growth at the field scale, but the revisit period of high-resolution satellites is often long (5 days-16 days), and due to the influence of cloudy and rainy weather, a single satellite has few available observations during the crop growth period, and observations during the key growth period are often missing, making it difficult to capture important crop growth dynamics.

[0004] On the other hand, there are large differences in crop cultivation management measures (such as fertilization and irrigation) among different farmers, resulting in great spatial heterogeneity in crop production management at the field scale. However, it is very difficult to collect crop management information (such as application amount, application time, etc.) on a large scale and field by field, and the current monitoring capacity of field production management is relatively weak. Summary of the invention

[0005] Based on this, it is necessary to propose a field crop growth and production management monitoring method, device, computer equipment and storage medium to address the technical problems that existing satellites have few available observations during the crop growth period, often lack observations during the key growth period, and find it difficult to capture important crop growth dynamics.

[0006] In a first aspect, a method for monitoring crop growth and production management in a field is provided, the method comprising:

[0007] Obtain the band reflectivity of each satellite to the field;

[0008] Based on the data of each band and the trained artificial neural network corresponding to each satellite, the leaf area index is predicted to obtain the leaf area index prediction result corresponding to each band data;

[0009] Reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale;

[0010] Based on the leaf area index time series curve, the growth and production of crops in the field are managed and monitored.

[0011] In a second aspect, a field crop growth and production management monitoring device is provided, the device comprising:

[0012] The acquisition module is used to obtain the band reflectivity of each satellite to the field;

[0013] A prediction module, used to predict the leaf area index based on the data of each band and the trained artificial neural network corresponding to each satellite, so as to obtain the prediction result of the leaf area index corresponding to each band data;

[0014] A reconstruction module, used for reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale;

[0015] The monitoring module is used to manage and monitor the growth and production of crops in the field based on the leaf area index time series curve.

[0016] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned field crop growth and production management monitoring method when executing the computer program.

[0017] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned field crop growth and production management monitoring method are implemented.

[0018] The method for managing and monitoring the growth and production of field crops proposed in the present invention obtains the band reflectivity of each satellite for the field, and then predicts the leaf area index based on each of the band data and the trained artificial neural network corresponding to each satellite, and obtains the leaf area index prediction results corresponding to each of the band data, and then reconstructs based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale, and finally manages and monitors the growth and production of field crops based on the leaf area index time series curve. The present invention integrates the band reflectivity of each satellite platform, combines with an advanced crop physiological structure variable inversion algorithm to predict the leaf area index according to the band reflectivity, and reconstructs based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale, thereby realizing high-precision near-real-time monitoring of crop growth dynamics and field cultivation management measures at the field scale based on the leaf area index time series curve. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] in:

[0021] Figure 1 A diagram showing an application environment of a method for monitoring crop growth and production management in a field in an embodiment;

[0022] Figure 2 A flowchart of a method for monitoring crop growth and production management in a field in one embodiment;

[0023] Figure 3 The overall technical roadmap of the field plot crop growth and production management monitoring method of the field plot crop growth and production management monitoring method in one embodiment;

[0024] Figure 4 A schematic diagram of a time series curve of a leaf area index in a method for monitoring crop growth and production management in a field in an embodiment;

[0025] Figure 5 It is a structural block diagram of a field crop growth and production management monitoring device in one embodiment;

[0026] Figure 6 is a structural block diagram of a computer device in one embodiment;

[0027] Figure 7It is a structural block diagram of a computer device in another embodiment. DETAILED DESCRIPTION

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] The crop growth and production management monitoring method provided by the embodiment of the present invention can be applied in the following aspects: Figure 1In the application environment, the client 110 communicates with the server 120 through the network. The server 120 can receive the band reflectivity of each satellite to the field through the client 110, and then predict the leaf area index based on each of the band data and the trained artificial neural network corresponding to each satellite, and obtain the leaf area index prediction results corresponding to each of the band data, and then reconstruct based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale, and finally manage and monitor the growth and production of field crops based on the leaf area index time series curve. The present invention predicts the leaf area index by integrating remote sensing data from various satellite platforms and different spectral bands, combining with advanced crop physiological structure variable inversion algorithms, and reconstructs based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale, thereby realizing high-precision near-real-time monitoring of crop growth dynamics and field cultivation management measures at the field scale according to the leaf area index time series curve. Among them, the client 110 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server 120 can be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0032] See also Figure 2 as well as Figure 3 As shown, Figure 3 This is the overall technical roadmap of the field crop growth and production management monitoring method provided by one embodiment of the present invention. Figure 2 A flow chart of a method for monitoring crop growth and production management in a field provided by an embodiment of the present invention includes the following steps:

[0033] Step S101: obtaining the band reflectivity of each satellite to the field;

[0034] In one embodiment, the satellites include Landsat 8, Landsat 9, Sentinel 2A satellite, and Sentinel 2B satellite.

[0035] As an example, obtain the 30-meter spatial resolution image bands (B2, B3, B4, B5, B6, B7) of the Landsat-8 satellite, and obtain the 10-meter and 20-meter spatial resolution image bands (B2, B3, B4, B5, B6, B7, B8, B8A, B9, B11, B12) of the Sentinel-2A and -2B satellites. The surface reflectivity data of the above different sensors will be used as the input of the trained artificial neural network to invert the crop leaf area index.

[0036] Step S102: predicting the leaf area index based on the band data and the trained artificial neural network corresponding to each satellite, to obtain the leaf area index prediction result corresponding to each band data;

[0037] In one embodiment, the artificial neural network includes two layers of neural networks, the first layer of the neural network is a hidden layer, the hidden layer includes 5 neurons, the second layer of the neural network is an output layer, the output layer includes 1 neuron, the activation function of the hidden layer uses a hyperbolic tangent function, and the output layer uses a linear activation function. The output layer directly maps the nonlinear conversion result of the previous layer to the final LAI (Leaf Area Index) prediction result.

[0038] In one embodiment, before the step of predicting the leaf area index based on the band data and the trained artificial neural network corresponding to each satellite, the step further includes:

[0039] Step S201: Obtain model input variables;

[0040] Step S202: randomly sampling N samples from the prior distribution of the model input variable, inputting the N samples into the leaf radiation transfer model and the canopy radiation transfer model to generate full-wavelength reflectance, where N is an integer greater than 0;

[0041] Step S203: aggregating the simulated full-wavelength reflectivity into the band reflectivity of the target sensor according to the spectral response function, wherein the target sensor is a satellite;

[0042] Step S204: Based on the band reflectance and the leaf area index corresponding to the band reflectance, the initial artificial neural network is trained to obtain a trained artificial neural network.

[0043] In this embodiment, based on the blade radiation transfer model (PROSPECT) and the canopy radiation transfer model (SAILH), a large number of simulated training data sets with broad representation are generated, i.e., the model input variable (V)-simulated reflectivity (R) combination, which is used to train the artificial neural network (ANN) model. Specifically, 10,000 samples are randomly sampled from the prior distribution of the model input variables (Table 1), and the blade radiation transfer model and the canopy radiation transfer model are input to simulate and generate a large number of simulated 400-2500nm full-wavelength reflectivities, and then the simulated full-wavelength reflectivities are aggregated into the band reflectivities of the target sensor (such as Landsat-8) according to the spectral response function, and then the band reflectivities are input and the leaf area index is output to train the initial ANN model. Finally, for Landsat-8, Landsat-9, Sentinel-2a and Sentinel-2b, 4 ANN inversion models are trained.

[0044] Table 1:

[0045]

[0046] Step S103: reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale;

[0047] In this embodiment, since a satellite only makes transit observations on specific dates (such as every 16 days), the leaf area index inverted by the satellite is discontinuous and discrete, and these discrete values ​​are interpolated and reconstructed into a daily continuous leaf area index time series curve.

[0048] In one embodiment, reconstruction is performed based on the Whittaker-Eilers time series smoothing algorithm and each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale.

[0049] As an example, the Whittaker-Eilers time series smoothing algorithm is used to construct the discrete leaf area index prediction results inverted by satellite during the growth period into a continuous time series curve on a daily scale. The core idea of ​​the algorithm is to minimize the following formula to obtain the smoothed data value:

[0050]

[0051] In the formula, y i is the data point of each leaf area index prediction result, is the data point of the daily leaf area index prediction result after smoothing, w iis the data point weight, which can be set according to the credibility or noise level of the data. λ is the smoothing parameter, which is used to control the trade-off between smoothness and fitting accuracy. λ can be set to 25. Figure 4 , Figure 4 It is the discrete leaf area index prediction result of satellite inversion (scattered points in the figure) and the reconstructed daily-scale continuous leaf area index time series curve (curve in the figure).

[0052] In one embodiment, the step of predicting the leaf area index based on the band data and the trained artificial neural network corresponding to each satellite to obtain the leaf area index prediction result corresponding to each band data comprises:

[0053] Step S301: predicting the leaf area index based on the band data of Landsat 8 and the trained artificial neural network corresponding to Landsat 8, to obtain a leaf area index prediction result corresponding to the band data of Landsat 8;

[0054] Step S302: predicting the leaf area index based on the band data of Landsat 9 and the trained artificial neural network corresponding to Landsat 9, to obtain a leaf area index prediction result corresponding to the band data of Landsat 9;

[0055] Step S303: predicting the leaf area index based on the band data of the Sentinel-2A satellite and the trained artificial neural network corresponding to the Sentinel-2A satellite, and obtaining a leaf area index prediction result corresponding to the band data of the Sentinel-2A satellite;

[0056] Step S304: predicting the leaf area index based on the band data of the Sentinel-2B satellite and the trained artificial neural network corresponding to the Sentinel-2B satellite, and obtaining a leaf area index prediction result corresponding to the band data of the Sentinel-2B satellite.

[0057] In one embodiment, the step of reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale includes:

[0058] Step S401: Reconstruct the leaf area index prediction results corresponding to the band data of Landsat 8, the leaf area index prediction results corresponding to the band data of Landsat 9, the leaf area index prediction results corresponding to the band data of Sentinel 2A satellite and the leaf area index prediction results corresponding to the band data of Sentinel 2B satellite to obtain a continuous leaf area index time series curve on a daily scale.

[0059] Step S104: Based on the leaf area index time series curve, manage and monitor the growth and production of crops in the field.

[0060] As an example, the prediction results of crop leaf area index in different locations can be used to monitor the growth dynamics of crops under different fertilization and irrigation levels, as well as the sensitivity of crop growth to management measures such as fertilization and irrigation. Figure 3 As shown in the figure, under irrigation conditions, the leaf area index of crops is generally higher than that of the control group without irrigation, and under the same irrigation conditions, with the increase of nitrogen fertilizer application (N0→N3), the leaf area index of crops increases. To monitor the growth of crops and their response to field management measures (fertilization and irrigation), four nitrogen fertilizer application levels (N0, N1, N2, N3, corresponding to 0, 50, 100 and 150 kg N ha-1 nitrogen fertilizer application, respectively) were set through field control experiments. Nitrogen fertilizer was applied to the sample plots by manual broadcasting at two growth stages: two-thirds at the tillering stage and one-third at the jointing stage. At the same time, there were only two irrigation control groups (W1, no irrigation; W2, 25 mm irrigation at the flowering stage), each combination was repeated 4 times, corresponding to a total of 32 management level sample plots.

[0061] The method for managing and monitoring the growth and production of field crops proposed in the present invention obtains the reflectivity of the bands of each satellite to the field, and then predicts the leaf area index based on the data of each band and the trained artificial neural network corresponding to each satellite, and obtains the leaf area index prediction results corresponding to each band data, and then reconstructs based on each leaf area index prediction result to obtain a continuous leaf area index time series curve on a daily scale, and finally manages and monitors the growth and production of field crops based on the leaf area index time series curve. The present invention predicts the leaf area index by integrating remote sensing data from various satellite platforms and different spectral bands, combined with an advanced crop physiological structure variable inversion algorithm, and reconstructs based on each leaf area index prediction result to obtain a continuous leaf area index time series curve on a daily scale, thereby realizing high-precision near-real-time monitoring of crop growth dynamics and field cultivation management measures at the field scale according to the leaf area index time series curve.

[0062] See also Figure 5 As shown, in one embodiment, a field crop growth and production management monitoring device is provided, the device comprising:

[0063] The acquisition module 10 is used to obtain the band reflectivity of each satellite to the field;

[0064] A prediction module 20 is used to predict the leaf area index based on the band data and the trained artificial neural network corresponding to each satellite, so as to obtain the leaf area index prediction result corresponding to each band data;

[0065] A reconstruction module 30, configured to reconstruct based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale;

[0066] The monitoring module 40 is used to manage and monitor the growth and production of crops in the field based on the leaf area index time series curve.

[0067] The field crop growth and production management monitoring device is also used for:

[0068] Get model input variables;

[0069] Randomly sample N samples from the prior distribution of the model input variables, input the N samples into the leaf radiation transfer model and the canopy radiation transfer model to generate full-wavelength reflectance, where N is an integer greater than 0;

[0070] aggregating the simulated full-wavelength reflectivity into the band reflectivity of the target sensor according to the spectral response function, wherein the target sensor is a satellite;

[0071] Based on the band reflectivity and the leaf area index corresponding to the band reflectivity, the initial artificial neural network is trained to obtain a trained artificial neural network.

[0072] In one embodiment, the artificial neural network includes two layers of neural networks, the first layer of the neural network is a hidden layer, the hidden layer includes 5 neurons, the second layer of the neural network is an output layer, the output layer includes 1 neuron, the activation function of the hidden layer uses a hyperbolic tangent function, and the output layer uses a linear activation function.

[0073] In one embodiment, the satellites include Landsat 8, Landsat 9, Sentinel 2A satellite, and Sentinel 2B satellite.

[0074] In one embodiment, the prediction module 20 is used to:

[0075] Based on the band data of Landsat 8 and the trained artificial neural network corresponding to Landsat 8, the leaf area index is predicted to obtain a leaf area index prediction result corresponding to the band data of Landsat 8;

[0076] Based on the band data of Landsat 9 and the trained artificial neural network corresponding to Landsat 9, the leaf area index is predicted to obtain a leaf area index prediction result corresponding to the band data of Landsat 9;

[0077] Predicting the leaf area index based on the band data of the Sentinel-2A satellite and the trained artificial neural network corresponding to the Sentinel-2A satellite, to obtain a leaf area index prediction result corresponding to the band data of the Sentinel-2A satellite;

[0078] Based on the band data of the Sentinel-2B satellite and the trained artificial neural network corresponding to the Sentinel-2B satellite, the leaf area index is predicted to obtain a leaf area index prediction result corresponding to the band data of the Sentinel-2B satellite.

[0079] In one embodiment, the reconstruction module 30 is also used to reconstruct the leaf area index prediction results corresponding to the band data of Landsat 8, the leaf area index prediction results corresponding to the band data of Landsat 9, the leaf area index prediction results corresponding to the band data of Sentinel 2A satellite, and the leaf area index prediction results corresponding to the band data of Sentinel 2B satellite to obtain a continuous leaf area index time series curve on a daily scale.

[0080] In one embodiment, the reconstruction module 30 is further used to: reconstruct based on the Whittaker-Eilers time series smoothing algorithm and each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale.

[0081] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the service side of a field crop growth and production management monitoring method.

[0082] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, the functions or steps on the client side of a method for managing and monitoring the growth and production of field crops are implemented.

[0083] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0084] Obtain the band reflectivity of each satellite to the field;

[0085] Based on the data of each band and the trained artificial neural network corresponding to each satellite, the leaf area index is predicted to obtain the leaf area index prediction result corresponding to each band data;

[0086] Reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale;

[0087] Based on the leaf area index time series curve, the growth and production of field crops are managed and monitored. In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0088] Obtain the band reflectivity of each satellite to the field;

[0089] Based on the data of each band and the trained artificial neural network corresponding to each satellite, the leaf area index is predicted to obtain the leaf area index prediction result corresponding to each band data;

[0090] Reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale;

[0091] Based on the leaf area index time series curve, the growth and production of crops in the field are managed and monitored.

[0092] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0093] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0094] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0095] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for monitoring crop growth and production management in a field, characterized in that: The field crop growth and production management monitoring method comprises: Obtain the band reflectivity of each satellite to the field; Based on the data of each band and the trained artificial neural network corresponding to each satellite, the leaf area index is predicted to obtain the leaf area index prediction result corresponding to each band data; Reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale; Based on the leaf area index time series curve, the growth and production of crops in the field are managed and monitored.

2. The method for monitoring crop growth and production management in a field according to claim 1, characterized in that: Before the step of predicting the leaf area index based on the band data and the trained artificial neural network corresponding to each satellite, the method further includes: Get model input variables; Randomly sample N samples from the prior distribution of the model input variables, input the N samples into the leaf radiation transfer model and the canopy radiation transfer model to generate full-wavelength reflectance, where N is an integer greater than 0; aggregating the simulated full-wavelength reflectance into the band reflectance of the target sensor according to the spectral response function, wherein the target sensor is a satellite; Based on the band reflectivity and the leaf area index corresponding to the band reflectivity, the initial artificial neural network is trained to obtain a trained artificial neural network.

3. The method for monitoring crop growth and production management in a field according to claim 2, characterized in that: The artificial neural network includes two layers of neural networks, the first layer of the neural network is a hidden layer, the hidden layer contains 5 neurons, the second layer of the neural network is an output layer, the output layer contains 1 neuron, the activation function of the hidden layer uses a hyperbolic tangent function, and the output layer uses a linear activation function.

4. The method for monitoring crop growth and production management in a field according to claim 1, characterized in that: The satellites include Landsat 8, Landsat 9, Sentinel 2A and Sentinel 2B.

5. The method for monitoring crop growth and production management in a field according to claim 4, characterized in that: The step of predicting the leaf area index based on the band data and the trained artificial neural network corresponding to each satellite to obtain the leaf area index prediction result corresponding to each band data comprises: Based on the band data of Landsat 8 and the trained artificial neural network corresponding to Landsat 8, the leaf area index is predicted to obtain a leaf area index prediction result corresponding to the band data of Landsat 8; Based on the band data of Landsat 9 and the trained artificial neural network corresponding to Landsat 9, the leaf area index is predicted to obtain a leaf area index prediction result corresponding to the band data of Landsat 9; Predicting the leaf area index based on the band data of the Sentinel-2A satellite and the trained artificial neural network corresponding to the Sentinel-2A satellite, to obtain a leaf area index prediction result corresponding to the band data of the Sentinel-2A satellite; Based on the band data of the Sentinel-2B satellite and the trained artificial neural network corresponding to the Sentinel-2B satellite, the leaf area index is predicted to obtain a leaf area index prediction result corresponding to the band data of the Sentinel-2B satellite.

6. The method for monitoring crop growth and production management in a field according to claim 5, characterized in that: The step of reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale comprises: The leaf area index prediction results corresponding to the band data of Landsat 8, the leaf area index prediction results corresponding to the band data of Landsat 9, the leaf area index prediction results corresponding to the band data of Sentinel 2A satellite and the leaf area index prediction results corresponding to the band data of Sentinel 2B satellite are reconstructed to obtain a continuous leaf area index time series curve on a daily scale.

7. The method for monitoring crop growth and production management in a field according to any one of claims 1 to 6, characterized in that: The step of reconstructing based on each leaf area index prediction result to obtain a continuous leaf area index time series curve on a daily scale comprises: Reconstruction is performed based on the Whittaker-Eilers time series smoothing algorithm and each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale.

8. A field crop growth and production management monitoring device, characterized in that: The field crop growth and production management monitoring device comprises: The acquisition module is used to obtain the band reflectivity of each satellite to the field; A prediction module, used to predict the leaf area index based on the data of each band and the trained artificial neural network corresponding to each satellite, so as to obtain the prediction result of the leaf area index corresponding to each band data; A reconstruction module, used for reconstructing based on each of the leaf area index prediction results to obtain a continuous leaf area index time series curve on a daily scale; The monitoring module is used to manage and monitor the growth and production of crops in the field based on the leaf area index time series curve.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the field crop growth and production management monitoring method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the field crop growth and production management monitoring method as described in any one of claims 1 to 7 are implemented.

Images