CN115511224B - Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment - Google Patents

Abstract

The invention belongs to the field of remote sensing technology, and relates to an intelligent crop growth monitoring method, device and electronic equipment integrated with space and ground. The method includes: acquiring satellite time-series remote sensing data, and constructing a first crop growth evaluation index; acquiring continuous near-ground observation data, Construct the second crop growth evaluation index; based on the second crop growth evaluation index, supplement the missing value of the first crop growth evaluation index to construct a model label; continuously interpolate the first crop growth evaluation index to obtain the reconstructed crop growth data; use The label trains the neural network to obtain the index mapping model; corrects the reconstructed crop growth data to obtain the target crop growth evaluation data. The present invention realizes the purpose of comprehensively using spaceflight remote sensing data and near-ground data to monitor the growth of crops, and solves the problem of insufficient accuracy and time density of spaceflight remote sensing data used in existing methods and the existence of near-ground observation data with small data range and low precision. Discontinuous problem.

Description

Crop growth intelligent monitoring method, device and electronic equipment integrated with space and ground

technical field

The invention belongs to the technical field of remote sensing, and in particular relates to a method, a device and an electronic device for intelligent monitoring of crop growth status integrated with space and ground.

Background technique

The agricultural ecosystem is a typical artificial ecosystem, and the active management activities of human beings play an important role in improving the quality of agricultural products, increasing production, and reducing disaster losses. At present, problems such as population increase and ecological environment deterioration have put forward higher requirements for food production and safety. Accurate crop growth parameter information can reflect the resource utilization in the agricultural production process, and is an important data support for crop yield prediction and agricultural planting structure adjustment.

In the application of agricultural management, although remote sensing technology has been widely used in crop type identification and moisture monitoring, it is difficult to overcome the large-scale and precise observation of crop growth because most research and applications still use aerospace remote sensing platforms. , real-time conflicting dilemma. In addition, due to the influence of interference factors such as atmospheric absorption and radiation, satellite remote sensing inversion cannot accurately obtain crop parameters, so it only characterizes the relative differences in growth status between different types of crops; The results of the near-ground agricultural monitoring method have high accuracy, but it is difficult to avoid the problem of small monitoring area.

Contents of the invention

In view of the inaccurate absolute value of the crop growth parameters obtained by the aerospace remote sensing platform, the untimely data acquisition, and the small observation range of near-ground data, a crop growth parameter inversion method based on the coordination of space and ground multi-platform is provided, that is, through the synchronization relationship between data, Convert the large-scale space remote sensing calculation of crop growth parameters to high-precision, high-continuous crop growth parameters near the ground, so as to realize large-scale, high-precision, high-continuous crop growth monitoring.

In the first aspect, the present disclosure provides an intelligent monitoring method of crop growth integrated with space and ground, including:

Collect remote sensing satellite data and obtain satellite time series remote sensing data in the target area;

Calculate crop growth state parameters and crop stress state parameters according to the satellite time-series remote sensing data;

Using the crop growth state parameters and the crop stress state parameters to construct a first crop growth assessment index based on satellite time-series remote sensing data; the first crop growth assessment index is used to characterize the relationship between the crop growth state and the crop growth background ;

Collect growth data of the target crop, and obtain near-ground observation data including the daily growth index data of the target crop;

Using the growth index data based on a statistical model to construct a second crop growth assessment index based on the near-ground observation data;

Based on the near-surface observation data, the missing value of the first crop growth assessment index at the same position and at the same time in the remote sensing satellite data is supplemented to obtain the first crop growth assessment index model and the The mapping model training label of the second crop growth evaluation index;

performing continuous interpolation on the first crop growth assessment index by means of average interpolation to obtain reconstructed continuous crop growth data;

Constructing a neural network model, using the mapping model training label to train the neural network model to obtain a crop growth data mapping model;

Using the crop growth data mapping model to correct the reconstructed continuous crop growth data to obtain target crop growth evaluation data.

In the second aspect, the present disclosure provides a space-ground integrated crop growth intelligent monitoring device, including a first acquisition unit, a first processing unit, a first construction unit, a second acquisition unit, a second construction unit, a second processing unit, a heavy structural unit, network model unit and correction unit;

The first acquiring unit is configured to collect remote sensing satellite data, and acquire satellite time-series remote sensing data in the target area;

The first processing unit is configured to calculate crop growth state parameters and crop stress state parameters according to the satellite time-series remote sensing data;

The first construction unit is configured to use the crop growth state parameters and the crop stress state parameters to construct a first crop growth assessment index based on satellite time-series remote sensing data; the first crop growth assessment index is used to characterize The relationship between crop growth status and crop growth background;

The second acquisition unit is configured to collect growth data of the target crop, and obtain near-ground observation data including the daily growth index data of the target crop;

The second construction unit is configured to use the growth index data based on a statistical model to construct a second crop growth assessment index based on the near-ground observation data;

The second processing unit is configured to supplement the missing value of the first crop growth assessment index at the same position and at the same time in the remote sensing satellite data based on the near-ground observation data, to obtain the first A crop growth assessment index model and a mapping model training label of the second crop growth assessment index;

The reconstruction unit is configured to continuously interpolate the first crop growth assessment index by means of average interpolation to obtain reconstructed continuous crop growth data;

The network model unit is used to construct a neural network model, and uses the mapping model training label to train the neural network model to obtain a crop growth data mapping model;

The correction unit is configured to use the crop growth data mapping model to correct the reconstructed continuous crop growth data to obtain target crop growth evaluation data.

In a third aspect, the present disclosure provides an electronic device, including:

processor and memory;

The memory is used to store computer operation instructions;

The processor is configured to execute the method for intelligent monitoring of crop growth status integrated with space and ground by invoking the computer operation instructions.

The beneficial effects of the present invention are: the present invention realizes the purpose of comprehensively using spaceflight remote sensing data and near-ground observation data to monitor the growth of crops, and solves the lack of accuracy and time density of spaceflight remote sensing data and the existence of near-ground observation data in existing methods. The problem of small data range, low precision, and discontinuity.

On the basis of the above technical solutions, the present invention can also be improved as follows.

Further, collecting remote sensing satellite data and obtaining satellite time-series remote sensing data in the target area includes: collecting remote sensing satellite data, performing radiometric correction and geometric registration on the remote sensing satellite data, and resampling all data to the same spatial resolution rate to obtain satellite time-series remote sensing data in the target area.

Further, using the crop growth state parameters and the crop stress state parameters, the first crop growth evaluation index based on satellite time-series remote sensing data is constructed by linear regression.

Further, the crop growth state parameters include normalized normalized vegetation index, enhanced vegetation index and greenness index; the crop stress state parameters include red edge index and soil vegetation index.

Further, the growth state parameters of the target crops are collected, and near-ground observation data containing the daily growth index data of the target crops are obtained, including:

Real-time observation of the growth state parameters of the target crops using sensors set up in the farmland;

performing statistics on the observed growth state parameters to obtain the growth index data;

The growth state parameters include plant height, stem diameter, leaf density and pest density of the crop; the growth index data include the daily average plant height index and average leaf density index of the target crop.

Further, based on the near-ground observation data, the missing value of the first crop growth assessment index at the same position and at the same time in the remote sensing satellite data is supplemented to obtain the first crop growth assessment index model and The mapping model training label of the second crop growth evaluation index includes:

Define the point in the remote sensing satellite data that is consistent with the geographical location of the ground observation as a reference point, obtain a number of satellite data sequence point values before and after the reference point, and define the satellite data sequence point of the reference point and the reference point The ground observation sequence value corresponding to the satellite data sequence point of the preceding and following points;

Using the method of derivation, obtain the derivatives used to characterize the change of the point value of the adjacent satellite data sequence, and determine the point value of the satellite data sequence of the reference point and the satellite data sequence of points before and after the reference point The relationship between point values, construct a fitting equation:

If the signs of all the derivatives in the fitting equation are consistent, or the signs of the derivatives in the fitting equation are different and the positions where the signs of the derivatives are different are located at points other than the reference point, then directly carry out quadratic function fitting to described fitting equation;

If the position where the sign of the derivative in the fitting equation differs is located at the reference point, use two sets of point values of the satellite data sequence at points other than the reference point and the satellite The data group composed of the ground observation values corresponding to the data sequence point values is fitted with a quadratic function segmentally, using the two groups of data groups to calculate the satellite data values of the two groups of reference points respectively, and taking the two groups of reference points The average value of the satellite data value of the point obtains the target satellite data sequence point value of the reference point, and the ground observation value corresponding to the target satellite data sequence point value, the target satellite data sequence point value, the The satellite data sequence point value of the reference point and the ground observation value corresponding to the reference point are combined to obtain the training label.

Description of drawings

Fig. 1 is the schematic diagram of the intelligent monitoring method for crop growth condition integrated with space and ground in Embodiment 1 of the present invention;

Fig. 2 is the schematic diagram of the intelligent crop growth monitoring device integrated with space and ground in Embodiment 2 of the present invention;

FIG. 3 is a schematic diagram of an electronic device provided in Embodiment 3 of the present invention.

Icons: 30-electronic device; 310-processor; 320-bus; 330-memory; 340-transceiver.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations.

Example 1

As an embodiment, as shown in accompanying drawing 1, in order to solve the above-mentioned technical problems, this embodiment provides an intelligent monitoring method for the growth of crops integrated with space and ground, which specifically includes the following processes:

Collect remote sensing satellite data and obtain satellite time-series remote sensing data in the target area; specifically, collect multi-source remote sensing satellite data. The data with the widest coverage and the most frequency in the source remote sensing satellite data set is used as the benchmark, and radiometric correction and geometric registration are performed on the remaining data, and all the data are resampled to the same spatial resolution to obtain the time series satellites in the target area. Remote sensing data; in the actual application process, first obtain the data source of the target area and construct the time-series characteristics of crops, make statistics on the collected satellite remote sensing data, select the data source as the benchmark data; use this as the benchmark to register other data, this paper The embodiment collects the data of Sentinel 2 satellite, Landsat8 satellite and Gaofen 1 satellite, wherein the data of Sentinel 2 satellite guarantees coverage at least once a month, and the data of Landsat8 satellite and Gaofen 1 satellite are used as interpolation data Encrypt data from Sentinel-2 satellites.

According to satellite time-series remote sensing data, calculate crop growth state parameters and crop stress state parameters; specifically, use time-series satellite remote sensing data to calculate normalized difference vegetation index NDVI, enhanced vegetation index EVI, and greenness index related to crop growth state GNDVI, vegetation index such as red edge index REIP and soil vegetation index SAVI related to crop growth environment, crop growth state parameters include normalized difference vegetation index NDVI, enhanced vegetation index EVI, greenness index GNDVI, used to characterize the growth of crops State, crop stress state parameters include red edge index REIP and soil vegetation index SAVI, which are used to characterize the stress state of crops.

Optionally, the first crop growth assessment index based on satellite time-series remote sensing data is constructed by using the crop growth state parameters and the crop stress state parameters in a linear regression manner. The first satellite-based crop growth index (Satellite-based Crop Growing Index, CGI_S) is constructed by linear regression, which is usually constructed using a linear relationship to describe the relationship between crop growth status and crop growth background ; The crop growth background refers to the state of the farmland where the crop grows, including the soil texture of the farmland where the crop is located, the irrigation level of the crop, and the sunshine level.

Optionally, the crop growth state parameters include normalized difference vegetation index, enhanced vegetation index and greenness index; the crop stress state parameters include red edge index and soil vegetation index. Let w ₀ be the weight of the normalized difference vegetation index NDVI, w ₁ be the weight of the enhanced vegetation index EVI, w ₂ be the weight of the greenness index GNDVI, w ₃ be the weight of the red edge index REIP, w ₄ be the soil vegetation index The weight of SAVI, the first crop growth assessment index CGI_S is:

CGI_S=( w ₀ *NDVI+w ₁ *EVI+w ₂ *GNDVI)/w ₃ *REIP+w ₄ *SAVI+a ₁ ).

Among them, the weights w ₀ , w ₁ , w ₂ , w ₃ , and w ₄ can be dynamically adjusted according to the monitored crop types, and a ₁ is an optional parameter, which is used to prevent the invalidation of the equation caused by the parameter REIP and SAVI being 0 .

Using crop growth state parameters and crop stress state parameters, construct the first crop growth evaluation index based on satellite time series remote sensing data; the first crop growth evaluation index is used to characterize the relationship between crop growth state and crop growth background;

Collect the growth data of the target crops, and obtain the near-ground observation data including the daily growth index data of the target crops; specifically, use the sensors set up in the farmland to observe the growth status of the target crops in real time. The observed parameters include plant height, stem diameter , leaf density, pest density, etc., and perform statistics on the data to obtain the daily average plant height, average leaf density and other indexes of the target crop;

Use the growth index data based on the statistical model to construct the growth evaluation index of the second crop based on the near-ground observation data; specifically, use the daily average plant height and average leaf density of the target crop based on the statistical model to construct the second crop growth near the ground State Evaluation Index (Ground-based Crop Growing Index, CGI_G);

Let H be plant height, D be stem diameter, LD be leaf density, PD be pest density, w ₅ be the weight of plant height, w ₆ be the weight of stem diameter, w ₇ be the weight of leaf density, w ₈ be the weight of disease and pest The weight of insect density, the second crop growth status evaluation index CGI_G characterizes the correlation between crop growth status (positive) and disaster status (negative) obtained by using near-ground observation data, then:

CGI_G=( w ₅ * H + w ₆ * D + w ₇ * LD )/( w ₈ * PD+a ₂ ).

Among them, the weights w ₅ , w ₆ , w ₇ , and w ₈ can be dynamically adjusted according to the monitored crop types, and a ₂ is an optional parameter, which is used to prevent the parameter PD from being 0 and causing the equation to be invalid.

Based on the near-surface observation data, the missing values of the first crop growth evaluation index at the same position and at the same time in the remote sensing satellite data are supplemented, and the mapping model training labels of the first crop growth evaluation index model and the second crop growth evaluation index are obtained ,include:

Define the point in the remote sensing satellite data that is consistent with the geographical location of the ground observation as the reference point, obtain the satellite data sequence point values before and after several reference points, define the satellite data sequence point of the reference point and the satellite data sequence point of the points before and after the reference point The ground observation sequence value corresponding to the bit;

Using the method of derivation, the derivatives used to characterize the change of the adjacent satellite data sequence point values are respectively obtained, and the difference between the point value of the satellite data sequence of the reference point and the point value of the satellite data sequence of points before and after the reference point is determined. relationship, construct the fitting equation:

If the signs of all derivatives in the fitting equation are the same, or if there are differences in the signs of the derivatives in the fitting equation and the positions where the signs of the derivatives are different are located at points other than the reference point, then directly perform quadratic function fitting on the fitting equation;

If the position where the sign of the derivative in the fitting equation is different is located at the reference point, use two groups of ground observation values corresponding to the point value of the satellite data sequence at points other than the reference point and the point value of the satellite data sequence The data group segmentally fits the quadratic function, respectively uses two groups of data groups to calculate the satellite data values of two groups of reference points, takes the average value of the satellite data values of the two groups of reference points to obtain the point value of the target satellite data sequence of the reference points, The training label is obtained by combining the point value of the target satellite data sequence, the ground observation value corresponding to the point value of the target satellite data sequence, the point value of the satellite data sequence of the reference point, and the ground observation value corresponding to the reference point.

Specifically, the process of obtaining the training label of the mapping model is as follows: on the basis of obtaining the ground observation data (position p , time t ), define the point in the satellite data sequence consistent with the geographical location of the ground observation as y ₃ , then the point The value of the previous sequence point is defined as y ₁ and y ₂ , the value of the sequence point after this point is defined as y ₄ and y ₅ , and the corresponding ground observation sequence values are x ₁ , x ₂ , x ₃ , x4 _and x5 _;

Judge the relative relationship of y ₁ , y ₂ , y ₄ , and y ₅ by means of derivation, obtain the three derivatives k _i between y ₁ and y ₂ , y ₂ and y ₄ , and y ₄ and y ₅ respectively, so as to judge Whether the 5 values are increasing/decreasing, or whether there is an inflection point in the fitting curve of the 5 values, and further determine the position and shape of the inflection point, and construct the fitting equation:

y = a ₀ + a ₁ * ( x _i - x ₃ ) + a ₂ * ( x _i - x ₃ ) ² ;

Among them, x _i needs to be selected according to the value _of ki . If the signs of all ki remain the same, only ordinary quadratic function fitting is performed; if the _{sign of ki} changes , the position of the slope sign _change is further judged. The position where the sign of k _i changes is located in y ₂ or y ₄ , then only the ordinary quadratic function is still used for fitting, if the changed position is located in y ₃ , it is necessary to use ( x ₁ , y ₁ ), ( x ₂ , y ₂ ) to perform Fitting, and ( x ₄ , y ₄ ), ( x ₅ , y ₅ ) for fitting, to obtain the satellite data value y ₃ ' of the two reference points, and then take the satellite data value y ₃ ' of the two reference points The point value p of the target satellite data sequence of the reference point is obtained by means of the average value, and the point value p of the target satellite data sequence, the ground observation value t corresponding to the point value of the target satellite data sequence, and the point value of the satellite data sequence of the reference point x ₃ and the ground observation value y ₃ corresponding to the reference point are combined to obtain the training label, thereby constructing a set of training labels ( p , t , x ₃ , y ₃ ), and realizing the second crop growth status evaluation index CGI_G at this point to the first 1. Conversion of crop growth assessment index CGI_S.

Continuously interpolating the first crop growth assessment index by means of average interpolation to obtain reconstructed crop growth data;

Construct the neural network model, use the mapping model training label to train the neural network model, and obtain the crop growth data mapping model; specifically, the attention mechanism of the neural network mapping model can be expressed by the following formula:

E =( w *( s _t-1 , h ₁ ), …, w *( s _t-1 , h _t ));

Among them, w is the weight coefficient, h ₁ ... h _t represents the hidden neuron, s _t represents the sequence value representing the length of the time-series feature of the crop, and the encoder uses the form of dot product to represent the aforementioned y ₃ and the reconstructed crop The matching degree of the corresponding position value in the growth data.

Optionally, the network used by the neural network mapping model belongs to RNNs but is not limited to RNNs, the basic unit is not limited to the attention unit (attention unit), and the length of the near-ground sequence used covers the growth period of the crop (February to November ), the training environment of the neural network mapping model is not limited to Tensorflow.

The crop growth data mapping model is used to correct the reconstructed continuous crop growth data, obtain continuous daily, full-coverage crop growth evaluation values, and obtain target crop growth evaluation data.

The invention realizes the purpose of comprehensively using spaceflight remote sensing data and near-surface observation data to monitor crop growth, and solves the problems of insufficient accuracy and time density of spaceflight remote sensing data and small data range of near-surface observation data in existing methods.

Example 2

Based on the same principle as the method shown in Embodiment 1 of the present invention, as shown in Figure 3, an intelligent crop growth monitoring system integrating space and ground is also provided in the embodiment of the present invention, including a first acquisition unit, a second A processing unit, a first construction unit, a second acquisition unit, a second construction unit, a second processing unit, a reconstruction unit, a network model unit and a correction unit;

The first acquisition unit is used to collect remote sensing satellite data and obtain satellite time series remote sensing data in the target area;

The first processing unit is used to calculate crop growth state parameters and crop stress state parameters according to satellite time-series remote sensing data;

The first construction unit is used to construct the first crop growth evaluation index based on satellite time series remote sensing data by using the crop growth state parameters and the crop stress state parameters; the first crop growth evaluation index is used to characterize the relationship between the crop growth state and the crop growth background relation;

The second acquisition unit is used to collect the growth data of the target crop, and obtain near-ground observation data including the daily growth index data of the target crop;

The second construction unit is used to use the growth index data based on a statistical model to construct a second crop growth evaluation index based on near-surface observation data;

The second processing unit is used to supplement the missing value of the first crop growth assessment index at the same position and at the same time in the remote sensing satellite data based on the near-ground observation data, and obtain the first crop growth assessment index model and the second crop growth condition Mapping model training labels for evaluation indices;

The reconstruction unit is used to continuously interpolate the first crop growth assessment index by means of average interpolation to obtain reconstructed continuous crop growth data;

The network model unit is used to train the neural network model by using the mapping model training label to obtain the crop growth data mapping model;

The correction unit is used to correct the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain target crop growth evaluation data.

Optionally, the first acquisition unit is used to collect remote sensing satellite data and obtain satellite time series remote sensing data in the target area, including: collecting remote sensing satellite data, performing radiometric correction and geometric registration on the remote sensing satellite data, and reconstructing all data Sampling to the same spatial resolution to obtain satellite time-series remote sensing data in the target area.

Optionally, the first construction unit constructs the first crop growth assessment index based on satellite time-series remote sensing data by using the crop growth state parameters and the crop stress state parameters in a linear regression manner.

Optionally, the crop growth state parameters include normalized difference vegetation index, enhanced vegetation index and greenness index; the crop stress state parameters include red edge index and soil vegetation index.

Optionally, the second acquisition unit uses sensors installed in the farmland to observe the growth state parameters of the target crops in real time; perform statistics on the observed growth state parameters to obtain growth index data, including:

Real-time observation of the growth data of the target crops using the sensors set up in the farmland;

Perform statistics on the observed growth data to obtain the growth index data;

The growth data includes plant height, stem diameter, leaf density and pest density of the crop; the growth index data includes the daily average plant height index and average leaf density index of the target crop.

Growth state parameters include plant height, stem diameter, leaf density and pest density of crops; growth index data include daily average plant height index and average leaf density index of the target crop.

Optionally, the second processing unit takes the near-surface observation data as a benchmark, supplements the missing values of the satellite time-series remote sensing data at the same position and at the same time in the remote sensing satellite data, and obtains the first crop growth evaluation index model and the second crop growth evaluation index model Index mapping model training labels, including a second processing subunit, a first determination unit and a second determination unit;

The second processing subunit is used to define the point in the remote sensing satellite data that is consistent with the geographical location of the ground observation as the reference point, obtain the satellite data sequence points of points before and after the reference point, and define the satellite data sequence point and reference point of the reference point The ground observation sequence value corresponding to the satellite data sequence point of the preceding and following points, and obtain its value;

The first determination unit is used to define the point in the remote sensing satellite data that is consistent with the geographical location of the ground observation as the reference point, obtain the satellite data sequence point values before and after several reference points, and define the satellite data sequence point of the reference point and the reference point before and after The ground observation sequence value corresponding to the satellite data sequence point of the point;

Using the method of derivation, the derivatives used to characterize the change of the adjacent satellite data sequence point values are respectively obtained, and the difference between the point value of the satellite data sequence of the reference point and the point value of the satellite data sequence of points before and after the reference point is determined. relationship, construct the fitting equation:

If the signs of all derivatives in the fitting equation are the same, or if there are differences in the signs of the derivatives in the fitting equation and the positions where the signs of the derivatives are different are located at points other than the reference point, then directly perform quadratic function fitting on the fitting equation;

If the position where the sign of the derivative in the fitting equation is different is located at the reference point, use two groups of ground observation values corresponding to the point value of the satellite data sequence at points other than the reference point and the point value of the satellite data sequence The data group segmentally fits the quadratic function, respectively uses two groups of data groups to calculate the satellite data values of two groups of reference points, takes the average value of the satellite data values of the two groups of reference points to obtain the point value of the target satellite data sequence of the reference points, The training label is obtained by combining the point value of the target satellite data sequence, the ground observation value corresponding to the point value of the target satellite data sequence, the point value of the satellite data sequence of the reference point, and the ground observation value corresponding to the reference point.

Example 3

Based on the same principle as the method shown in the embodiment of the present invention, an electronic device is also provided in the embodiment of the present invention, as shown in Figure 3, the electronic device may include but not limited to: a processor and a memory The memory is used to store the computer program; the processor is used to execute the method for intelligent monitoring of crop growth status integrated with space and ground shown in any embodiment of the present invention by calling the computer program.

An electronic device is provided in an optional embodiment, and the electronic device 30 shown in FIG. 3 includes: a processor 310 and a memory 330 . Wherein, the processor 310 is connected to the memory 330 , such as through a bus 320 .

Optionally, the electronic device 30 may further include a transceiver 340, and the transceiver 340 may be used for data interaction between the electronic device and other electronic devices, such as sending and/or receiving data. It should be noted that, in practical applications, the transceiver 340 is not limited to one, and the structure of the electronic device 30 does not limit the embodiment of the present invention.

The processor 310 may be a CPU central processing unit, a general purpose processor, a DSP data signal processor, an ASIC application specific integrated circuit, an FPGA field programmable gate array or other programmable logic devices, hardware components or any combination thereof. The processor 310 may also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

Bus 320 may include a path for communicating information between the components described above. The bus 320 may be a PCI peripheral component interconnect standard bus or an EISA extended industry standard architecture bus or the like. The bus 320 can be divided into a control bus, a data bus, an address bus, and the like. For ease of representation, only one thick line is used in FIG. 3 , but it does not mean that there is only one bus or one type of bus.

The memory 330 can be a ROM read-only memory or other types of static storage devices that can store static information and instructions, a RAM random access memory or other types of dynamic storage devices that can store information and instructions, or an EEPROM electrically erasable programmable memory device. Read-only memory, CD-ROM or other optical disc storage, optical disc storage (including optical discs, laser discs, compact discs, digital versatile discs, etc.), magnetic disk storage media, or capable of carrying or storing information in the form of instructions or data structures desired program code and any other medium that can be accessed by a computer, but not limited thereto.

The memory 330 is used to store application program codes (computer programs) for implementing the solutions of the present invention, and the execution is controlled by the processor 310 . The processor 310 is configured to execute the application program code stored in the memory 330, so as to implement the contents shown in the foregoing method embodiments.

The above are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (6)

1. The intelligent monitoring method of crop growth condition integrated with space and ground, characterized in that it includes: Collect remote sensing satellite data and obtain satellite time series remote sensing data in the target area; Calculate crop growth state parameters and crop stress state parameters according to the satellite time-series remote sensing data; Using the crop growth state parameters and the crop stress state parameters, construct the first crop growth assessment index based on satellite time-series remote sensing data; the crop growth state parameters include normalized normalized vegetation index, enhanced vegetation index and greenness Index; the crop stress state parameters include red edge index and soil vegetation index; the first crop growth assessment index is used to characterize the relationship between crop growth state and crop growth background; Collect growth data of the target crop, and obtain near-ground observation data including the daily growth index data of the target crop; Using the growth index data based on a statistical model to construct a second crop growth assessment index based on the near-ground observation data; Based on the near-surface observation data, the missing value of the first crop growth assessment index at the same position and at the same time in the remote sensing satellite data is supplemented to obtain the first crop growth assessment index model and the The mapping model training label of the second crop growth assessment index includes: defining the point in the remote sensing satellite data that is consistent with the geographical location of the ground observation as a reference point, obtaining a number of satellite data sequence point values before and after the reference point, and defining the points The satellite data sequence point position of the reference point and the ground observation sequence value corresponding to the satellite data sequence point position of the points before and after the reference point; using the method of derivation, respectively obtain the satellite data sequence points used to characterize the adjacent The derivative of the position value change determines the relationship between the satellite data sequence point value of the reference point and the satellite data sequence point value of the points before and after the reference point, and constructs a fitting equation: if in the fitting equation The signs of all the derivatives are the same, or there are differences in the signs of the derivatives in the fitting equation and the positions where the signs of the derivatives are different are located at points other than the reference point, then directly adjust the fitting equation Carry out quadratic function fitting; if the position where the signs of the derivatives in the fitting equation differ is located at the reference point, then use two groups of satellite data sequence points from points other than the reference point The data group piecewise fitting quadratic function that the digit value and the ground observation value corresponding to the said satellite data sequence point value is composed of, uses two groups of said data groups to calculate the satellite data value of two groups of said reference points respectively, takes The average value of the satellite data values of the two groups of reference points obtains the target satellite data sequence point value of the reference point, and the ground corresponding to the target satellite data sequence point value and the target satellite data sequence point value The training label is obtained by combining the observation value, the satellite data sequence point value of the reference point, and the ground observation value corresponding to the reference point; performing continuous interpolation on the first crop growth assessment index by means of average interpolation to obtain reconstructed continuous crop growth data; Constructing a neural network model, using the mapping model training label to train the neural network model to obtain a crop growth data mapping model; Using the crop growth data mapping model to correct the reconstructed continuous crop growth data to obtain target crop growth evaluation data. 2. according to claim 1, the integrated crop growth intelligent monitoring method is characterized in that collecting remote sensing satellite data and obtaining satellite time-series remote sensing data in the target area comprises: collecting remote sensing satellite data, and analyzing the remote sensing satellite data Carry out radiometric correction and geometric registration, and resample all data to the same spatial resolution to obtain satellite time series remote sensing data in the target area. 3. according to the intelligent monitoring method of the crop growth state of claim 1, it is characterized in that, utilize described crop growth state parameter and described crop stress state parameter, adopt the mode of linear regression to construct the time-series remote sensing data based on satellite. The first crop growth assessment index. 4. according to the intelligent monitoring method of the crop growth state of claim 1, it is characterized in that, collect the growth data of target crop, obtain the near ground observation data that comprises the growth index data of described target crop every day, comprising: Real-time observation of the growth data of the target crops using sensors set up in the farmland; performing statistics on the observed growth data to obtain the growth index data; The growth data includes plant height, stem diameter, leaf density and pest density of the crop; the growth index data includes the daily average plant height index and average leaf density index of the target crop. 5. An intelligent crop growth monitoring device integrated with space and ground, characterized in that it includes a first acquisition unit, a first processing unit, a first construction unit, a second acquisition unit, a second construction unit, a second processing unit, and a reconstruction unit , network model unit and correction unit; The first acquiring unit is configured to collect remote sensing satellite data, and acquire satellite time-series remote sensing data in the target area; The first processing unit is used to calculate crop growth state parameters and crop stress state parameters according to the satellite time-series remote sensing data; the crop growth state parameters include normalized normalized vegetation index, enhanced vegetation index and greenness index ; The crop stress state parameters include red edge index and soil vegetation index; The first construction unit is configured to use the crop growth state parameters and the crop stress state parameters to construct a first crop growth assessment index based on satellite time-series remote sensing data; the first crop growth assessment index is used to characterize The relationship between crop growth status and crop growth background; The second acquisition unit is configured to collect growth data of the target crop, and obtain near-ground observation data including the daily growth index data of the target crop; The second construction unit is configured to use the growth index data based on a statistical model to construct a second crop growth assessment index based on the near-ground observation data; The second processing unit is configured to supplement the missing value of the first crop growth assessment index at the same position and at the same time in the remote sensing satellite data based on the near-ground observation data, to obtain the first A crop growth assessment index model and the mapping model training label of the second crop growth assessment index, including: defining a point in the remote sensing satellite data that is consistent with the geographical location of ground observation as a reference point, and obtaining a number of points before and after the reference point The satellite data sequence point value defines the satellite data sequence point of the reference point and the ground observation sequence value corresponding to the satellite data sequence point of the points before and after the reference point; using the method of derivation, respectively obtain the points used for characterization Derivatives of changes in adjacent satellite data sequence point values, determine the relationship between the satellite data sequence point values of the reference point and the satellite data sequence point values of points before and after the reference point, and construct a fitting Equation: if the signs of all the derivatives in the fitting equation are the same, or the signs of the derivatives in the fitting equation are different and the positions where the signs of the derivatives are different are located at points other than the reference point , then directly carry out quadratic function fitting to described fitting equation; The data group segmental fitting quadratic function composed of the satellite data sequence point value of the point and the ground observation value corresponding to the satellite data sequence point value, using two groups of the data groups to calculate the two groups The satellite data value of the reference point, the average value of the satellite data value of the two groups of the reference point is taken to obtain the target satellite data sequence point value of the reference point, and the target satellite data sequence point value, the target The ground observation value corresponding to the satellite data sequence point value, the satellite data sequence point value of the reference point, and the ground observation value corresponding to the reference point are combined to obtain the training label; The reconstruction unit is configured to continuously interpolate the first crop growth assessment index by means of average interpolation to obtain reconstructed continuous crop growth data; The network model unit is used to construct a neural network model, and uses the mapping model training label to train the neural network model to obtain a crop growth data mapping model; The correction unit is configured to use the crop growth data mapping model to correct the reconstructed continuous crop growth data to obtain target crop growth evaluation data. 6. An electronic device, characterized in that it comprises: processor and memory; The memory is used to store computer operation instructions; The processor is configured to execute the space-ground integrated intelligent monitoring method for crop growth according to any one of claims 1 to 4 by invoking the computer operation instructions.

Images