Crop growth index prediction method, device, equipment and medium

Abstract

The invention provides a crop growth index prediction method and device, equipment and a medium, and relates to the technical field of image data processing, and the method comprises the steps: determining a vegetation index according to a satellite remote sensing image corresponding to a to-be-detected crop; and inputting the vegetation index into a growth index prediction model to obtain a crop growth index output by the growth index prediction model, the growth index prediction model being constructed based on a vegetation index sample and a crop growth index sample, the crop growth index samples are determined based on agricultural parameters of crop samples. According to the method, a growth vigor index prediction model with high accuracy and comprehensiveness is constructed through a vegetation index sample and a crop growth vigor index sample in combination with agronomic parameters of ground investigation, so that the crop growth vigor index with high accuracy, comprehensiveness and reliability is obtained, and the crop growth condition is accurately monitored and predicted in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a method, device, equipment and medium for predicting crop growth index. Background Art

[0002] The dynamic changes in the growth of crops during the production process are closely related to the final yield and quality. Based on this, dynamic monitoring of the growth of crops is of great value and significance. Remote sensing observation has the advantages of wide coverage and high efficiency, overcoming many problems brought about by ground sampling observation, such as time-consuming, high cost, and destructiveness.

[0003] There are two main methods for monitoring crop growth based on remote sensing observations: relying on a single normalized vegetation index to predict crop growth, and using chlorophyll and nitrogen content monitoring models to monitor crop growth. However, the former does not take into account other factors that may affect crop growth, while the latter focuses too much on the monitoring of chlorophyll and nitrogen content, and neither can accurately and real-time monitor and predict crop growth. Summary of the invention

[0004] The present invention provides a crop growth index prediction method, device, equipment and medium, which are used to solve the defect that the existing technology cannot accurately and real-time monitor and predict the growth status of crops, and realize the construction of a growth index prediction model with high accuracy and comprehensiveness through vegetation index samples and crop growth index samples, combined with agronomic parameters of ground survey, so as to obtain a crop growth index with high accuracy, comprehensiveness and reliability, so as to accurately and real-time monitor and predict the growth status of crops.

[0005] The invention provides a method for predicting a crop growth index, comprising the following steps.

[0006] The vegetation index is determined based on the satellite remote sensing images corresponding to the crops to be tested.

[0007] The vegetation index is input into a growth index prediction model to obtain a crop growth index output by the growth index prediction model. The growth index prediction model is constructed based on vegetation index samples and crop growth index samples, and the crop growth index samples are determined based on agronomic parameters of the crop samples.

[0008] According to a crop growth index prediction method provided by the present invention, the growth index prediction model is constructed based on the following steps: determining the vegetation index sample according to the satellite remote sensing image sample corresponding to the crop sample; determining the crop growth index sample according to the agronomic parameters of the crop sample; taking the crop growth index sample as the dependent variable and the vegetation index sample as the independent variable, and combining with the initial growth index prediction model, determining multiple groups of fitting parameters; constructing the growth index prediction model according to the multiple groups of fitting parameters and the dependent variable and independent variable in the initial growth index prediction model.

[0009] According to a crop growth index prediction method provided by the present invention, the agronomic parameters include multiple sub-agronomic parameters; the determining the crop growth index sample based on the agronomic parameters of the crop sample includes: when the number of the multiple sub-agronomic parameters is only two, determining the crop growth index sample based on two sub-agronomic parameters; when the number of the multiple sub-agronomic parameters is at least three, determining multiple data combinations based on at least three sub-agronomic parameters, each data combination includes any two parameters of the at least three sub-agronomic parameters, and the multiple data combinations are all different; determining the growth ground index corresponding to each of the multiple data combinations, and determining the multiple growth ground indices as the crop growth index sample.

[0010] According to a crop growth index prediction method provided by the present invention, the vegetation index sample is determined based on the satellite remote sensing image sample corresponding to the crop sample, including: obtaining the satellite remote sensing image sample corresponding to the longitude and latitude position of the crop sample; and determining the vegetation index sample based on the multispectral data of the satellite remote sensing image sample.

[0011] According to a crop growth index prediction method provided by the present invention, the crop growth index sample is determined based on the two sub-agronomic parameters, including: taking the square root of the product of the two sub-agronomic parameters and determining the crop growth index sample as the calculation result.

[0012] According to a crop growth index prediction method provided by the present invention, the growth index prediction model is constructed according to the multiple groups of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model, including: using a cross-validation algorithm to determine the target fitting parameters from the multiple groups of fitting parameters; constructing the growth index prediction model according to the target fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0013] According to a crop growth index prediction method provided by the present invention, the growth index prediction model is constructed according to the multiple groups of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model, including: determining the growth index prediction accuracy according to the first-level results corresponding to the crop growth index samples and the second-level results corresponding to the crop growth index; determining the root mean square error according to the crop growth index samples and the crop growth index; and constructing the growth index prediction model according to the growth index prediction accuracy and the root mean square error, in combination with the multiple groups of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0014] The present invention also provides a crop growth index prediction device, comprising the following modules.

[0015] The data processing module is used to determine the vegetation index based on the satellite remote sensing images corresponding to the crops to be tested.

[0016] The index prediction module is used to input the vegetation index into the growth index prediction model to obtain the crop growth index output by the growth index prediction model. The growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample, and the crop growth index sample is determined based on the agronomic parameters of the crop sample.

[0017] The present invention also provides an electronic device, 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, any of the above-mentioned crop growth index prediction methods is implemented.

[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for predicting the growth index of crops as described in any one of the above is implemented.

[0019] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned crop growth index prediction methods.

[0020] The crop growth index prediction method, device, equipment and medium provided by the present invention determine the vegetation index according to the satellite remote sensing image corresponding to the crop to be tested; input the vegetation index into the growth index prediction model to obtain the crop growth index output by the growth index prediction model, the growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample, and the crop growth index sample is determined based on the agronomic parameters of the crop sample. The method constructs a growth index prediction model with high accuracy and comprehensiveness through the vegetation index sample and the crop growth index sample, combined with the agronomic parameters of the ground survey, and then obtains the crop growth index with high accuracy, comprehensiveness and reliability, so as to accurately and in real time monitor and predict the growth status of crops. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0022] Figure 1 It is a schematic flow chart of the crop growth index prediction method provided by the present invention.

[0023] Figure 2 It is a schematic diagram of the thematic monitoring map provided by the present invention.

[0024] Figure 3 It is a structural schematic diagram of the crop growth index prediction device provided by the present invention.

[0025] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0027] It should be noted that the execution subject involved in the embodiment of the present invention can be a crop growth index prediction device or an electronic device. Optionally, the electronic device can include: a computer, a mobile terminal, a wearable device, etc.

[0028] The embodiment of the present invention is further described below by taking an electronic device as an example.

[0029] Figure 1 FIG. 1 is a flow chart of the crop growth index prediction method provided by the present invention, such as Figure 1 As shown, the method may include the following steps 101-102.

[0030] Step 101: Determine a vegetation index based on satellite remote sensing images corresponding to the crop to be tested.

[0031] The crops to be tested refer to the types of crops that need to be evaluated and monitored. Optionally, the crops to be tested may include at least one of wheat, corn, rice, and soybeans.

[0032] Satellite remote sensing images are images formed by processing electromagnetic wave signals reflected or emitted from the earth's surface captured by satellite sensors. Optionally, the satellite remote sensing image is a Landsat8 satellite image, wherein the Landsat8 satellite image contains 7 bands, namely, Blue Band, Green Band, Red Band, Near Infrared Band, Shortwave Infrared 1 Band (SWIR 1 Band), Shortwave Infrared 2 Band and Panchromatic Band (Pan Band).

[0033] Vegetation index is a mathematical formula calculated by the reflectivity or emissivity of a specific band of satellite remote sensing images, which is used to quantify the growth characteristics of the crops to be tested. Optionally, vegetation index may include: Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Ratio Vegetation Index (RVI), Difference Vegetation Index (DVI), Enhanced Vegetation Index 2 (EVI2), etc.

[0034] Optionally, the reflectance corresponding to the i-th band among the seven bands may be calculated using a reflectance formula: Reflectance=Bandi×gain+bias.

[0035] Among them, Bandi represents the i-th band; Reflectance represents the reflectivity corresponding to the i-th band; gain represents the reflectivity amplification factor; bias represents the reflectivity offset.

[0036] Optionally, the electronic device determines the vegetation index based on the satellite remote sensing image corresponding to the crop to be tested, which may include: the electronic device obtains the satellite remote sensing image corresponding to the longitude and latitude position of the crop to be tested; the electronic device determines the vegetation index based on multispectral data of the satellite remote sensing image.

[0037] In the process of determining the vegetation index, the electronic device can first determine the crop to be tested, and use the geographic information system to determine the longitude and latitude position of the crop to be tested, and the accuracy of the longitude and latitude position is relatively high; then, the electronic device collects satellite remote sensing images of the area where the longitude and latitude position is located, and extracts multispectral data from the satellite remote sensing image, and then calculates the multispectral data to obtain the vegetation index corresponding to the crop to be tested, thereby providing data support for the subsequent determination of the crop growth index of the crop to be tested.

[0038] Specifically, the normalized difference vegetation index NDVI is calculated using the first formula: NDVI=(NIR-RED) / (NIR+RED).

[0039] Among them, NIR represents the reflectivity of the near-infrared band; RED represents the reflectivity of the red light band.

[0040] Specifically, the green normalized vegetation index GNDVI is calculated using the second formula: GNDVI=(NIR-GREEN) / (NIR+GREEN).

[0041] Among them, GREEN represents the reflectivity of the green light band.

[0042] Specifically, the ratio vegetation index RVI is calculated using the third formula: RVI=NIR / RED.

[0043] Specifically, the difference vegetation index DVI is calculated using the fourth formula: DVI=NIR-RED.

[0044] Specifically, the enhanced vegetation index EVI2 is calculated using the fifth formula: EVI2=α(NIR-RED) / (NIR+RED+β).

[0045] Among them, α represents the first constant, which is usually 2.4; β represents the second constant, which is usually 1.

[0046] It should be noted that the above remote sensing images are acquired in real time, so they can be processed in real time to provide data support for subsequent monitoring and prediction of crop growth conditions. It also helps farmers and agricultural managers to understand the growth conditions of crops in a timely manner and take corresponding management measures.

[0047] Step 102: Input the vegetation index into the growth index prediction model to obtain the crop growth index output by the growth index prediction model. The growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample. The crop growth index sample is determined based on the agronomic parameters of the crop sample.

[0048] Among them, the crop growth index is a prediction result used to comprehensively reflect the growth status of the crops to be tested.

[0049] After constructing a growth index prediction model with high accuracy and comprehensiveness through vegetation index samples and crop growth index samples combined with agronomic parameters from ground surveys, the growth index prediction model can comprehensively consider various factors affecting crop growth, thereby improving the accuracy, comprehensiveness and reliability of the prediction results, so as to accurately and real-time monitor and predict crop growth conditions.

[0050] In some embodiments, the growth index prediction model is constructed based on the following steps: determining vegetation index samples based on satellite remote sensing image samples corresponding to crop samples; determining crop growth index samples based on agronomic parameters of crop samples; using crop growth index samples as dependent variables and vegetation index samples as independent variables, combined with an initial growth index prediction model, to determine multiple sets of fitting parameters; constructing a growth index prediction model based on multiple sets of fitting parameters and the dependent and independent variables in the initial growth index prediction model.

[0051] Among them, agronomic parameters are used to characterize the growth status characteristics of crop samples.

[0052] Optionally, each group of fitting parameters may include: a first fitting parameter and a second fitting parameter, which together determine the specific form and prediction ability of the growth index prediction model.

[0053] After obtaining the satellite remote sensing image samples corresponding to the crop samples and the agronomic parameters of the crop samples, the satellite remote sensing image samples can be analyzed to obtain vegetation index samples, and the agronomic parameters can be analyzed to obtain crop growth index samples; since there is a linear relationship between the vegetation index samples and the crop growth index samples, the initial growth index prediction model is constructed with the crop growth index samples as the dependent variable and the vegetation index samples as the independent variable to obtain multiple sets of fitting parameters, and then the growth index prediction model is constructed by combining the dependent variable and the independent variable in the initial growth index prediction model.

[0054] Optionally, the growth index prediction model can be represented by the target formula: CGI=a+b×VI.

[0055] Among them, CGI represents the dependent variable, that is, the prediction result, and its value range is (0,1); a represents the first fitting parameter; b represents the second fitting parameter; VI represents the independent variable, that is, the vegetation index, and its value range is (0,1).

[0056] In some embodiments, determining vegetation index samples based on satellite remote sensing image samples corresponding to crop samples may include: obtaining satellite remote sensing image samples corresponding to the longitude and latitude positions of the crop samples; and determining vegetation index samples based on multispectral data of the satellite remote sensing image samples.

[0057] In some embodiments, the agronomic parameters may include multiple sub-agronomic parameters; determining the crop growth index sample based on the agronomic parameters of the crop sample may include one of the following implementation methods.

[0058] Implementation method 1: When the number of the multiple sub-agronomic parameters is only two, a sample of the crop growth index is determined according to the two sub-agronomic parameters.

[0059] In some embodiments, determining the crop growth index sample according to the two sub-agronomic parameters may include: taking the square root of the product of the two sub-agronomic parameters and determining the result as the crop growth index sample.

[0060] Optionally, the crop growth index sample can use the target calculation formula: Calculated.

[0061] Among them, CGIg represents the crop growth index sample, and the value range is (0,1); A represents the first sub-agronomic parameter; B represents the second sub-agronomic parameter; A×B represents the product of the two sub-agronomic parameters.

[0062] Optionally, the first sub-agronomic parameter is the Clumping Index (CI) of the coverage of the crop samples, and the value range is (0,1); the second sub-agronomic parameter is the Greenness Index (GI) of the crop samples, and the value range is (0,1).

[0063] Implementation method 2: When the number of multiple sub-agronomic parameters is at least three, multiple data combinations are determined based on the at least three sub-agronomic parameters, each data combination may include any two parameters of the at least three sub-agronomic parameters, and the multiple data combinations are different; determine the growth ground index corresponding to each of the multiple data combinations, and determine the multiple growth ground indices as crop growth index samples.

[0064] When the number of multiple sub-agronomic parameters is at least three, two parameters can be randomly selected from the at least three sub-agronomic parameters for combination to obtain a data combination, and then two new parameters can be randomly selected from the at least three sub-agronomic parameters for combination to obtain a data combination. At this time, this data combination is different from the previous data combination. The difference here means that there is at most one identical sub-agronomic parameter in the two data combinations. Based on this, the above-mentioned at least three sub-agronomic parameters are traversed to obtain multiple data combinations. Then, the above-mentioned target calculation formula can be used to calculate the growth ground index corresponding to each of the multiple data combinations, and then all the growth ground indexes are determined as crop growth index samples.

[0065] Optionally, the multiple sub-agronomic parameters may include, in addition to coverage and greenness, plant height (cm), stem diameter (cm), biomass (g), and another coverage CI2.

[0066] Among them, the coverage CI2 can be calculated using the coverage formula: CI2= (NDVI-NDVI min ) / (NDVI max -NDVI min ) is calculated.

[0067] NDVI min Indicates the minimum value of the Normalized Difference Vegetation Index; NDVI max Indicates the maximum value of the Normalized Difference Vegetation Index.

[0068] Optionally, after determining the crop growth index sample according to the agronomic parameters of the crop sample, the method may further include: normalizing the crop growth index sample to obtain a target crop growth index sample.

[0069] After determining the crop growth index sample according to the agronomic parameters of the crop sample, the determined crop growth index sample is different due to different data combinations. In order to simplify the complexity of subsequent data calculation, the crop growth index sample can be normalized to obtain the target crop growth index sample.

[0070] Optionally, the target crop growth index sample can be normalized using the formula: NCGIg = (CGIg-CGI min ) / (CGI max -CGI min ) is calculated.

[0071] Among them, NCGIg represents the target crop growth index sample, with a value range of (0,1); CGI min Indicates the minimum value of the crop growth index sample; CGI maxIndicates the maximum value of the crop growth index samples.

[0072] It should be noted that CGI min and CGI max All can be obtained based on historical observations.

[0073] In some embodiments, constructing a growth index prediction model according to multiple sets of fitting parameters and dependent variables and independent variables in the initial growth index prediction model may include at least one of the following implementation methods.

[0074] Implementation method 1: Use a cross-validation algorithm to determine the target fitting parameters from multiple groups of fitting parameters; construct a growth index prediction model based on the target fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0075] Among them, the cross-validation algorithm refers to dividing the data set into smaller subsets and using these subsets to train and verify the model, so as to reduce overfitting and improve the generalization ability of the model, so as to reduce the performance fluctuations caused by different data division methods, such as the k-fold cross-validation algorithm. Usually, the value of k is 5.

[0076] The cross-validation algorithm is used to effectively evaluate the performance of different fitting parameter combinations by splitting the data set multiple times and performing training and testing, so as to select the optimal model configuration, that is, to select the optimal target fitting parameters, and then to initialize the dependent and independent variables in the growth index prediction model to construct the growth index prediction model. This method not only reduces the risk of overfitting, but also improves the generalization ability and prediction accuracy of the growth index prediction model.

[0077] Implementation method 2: Determine the growth index prediction accuracy based on the first-level results corresponding to the crop growth index samples and the second-level results corresponding to the crop growth index; determine the root mean square error based on the crop growth index samples and the crop growth index; construct a growth index prediction model based on the growth index prediction accuracy and the root mean square error, combined with multiple sets of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0078] Optionally, the crop growth index samples in implementation method 2 may be replaced by target crop growth index samples.

[0079] After determining the crop growth index samples and the crop growth index, the following Table 1 can be used to classify the crop growth index samples to obtain the first-level results, and Table 1 can be used to classify the crop growth index to obtain the second-level results; then, the growth level is used for accuracy verification, specifically, the image elements that are consistent with the first-level results and the second-level results are determined, and the growth index prediction accuracy is calculated; at the same time, the growth index is used for accuracy verification, specifically, the crop growth index samples and the crop growth index are calculated to obtain the root mean square error, and then the growth index prediction accuracy, multiple sets of fitting parameters, and the dependent variables and independent variables in the initial growth index prediction model are combined to construct a growth index prediction model. The entire process can ensure the reliability of subsequent prediction results (i.e., crop growth index) through accuracy verification, providing strong technical support for agricultural production.

[0080] Table 1:

[0081] As can be seen from Table 1, the grade results are divided into five levels, namely: level 5, level 4, level 3, level 2 and level 1, and these five levels are from low to high.

[0082] Optionally, the above growth index prediction accuracy can be calculated using the accuracy prediction formula: OA=(C1+…+Ci+…+Ck) / K×100%.

[0083] Among them, OA represents the prediction accuracy of the growth index; K represents the total number of image elements (including consistent image elements and inconsistent image elements), K≥2; usually, k is taken as 5, and C1~C5 represent the number of pixels whose crop growth grade obtained from the ground survey is consistent with the corresponding predicted crop growth grade.

[0084] It should be noted that when OA is greater than the first preset threshold (such as 85%), it means that the crop growth index is qualified data. At this time, the vegetation index type of the qualified data and the corresponding crop growth ground index type are recorded.

[0085] Optionally, the above root mean square error can be calculated using the error calculation formula: Calculated.

[0086] Among them, RMSE represents the root mean square error; N represents the number of verification samples of crop growth index; represents the target crop growth index sample corresponding to the i-th verification sample; Represents the crop growth index corresponding to the i-th verification sample.

[0087] Exemplarily, as shown in Table 2, the model accuracy statistics provided by the embodiment of the present invention are shown.

[0088] Table 2:

[0089] Table 2 records the two sub-agronomic parameters used by the crop growth index, and the types of vegetation indices (such as NDVI, GNDVI, RVI, DVI and EVI2) used to predict the crop growth index CGI. As can be seen from Table 2, the RMSE is small, and the OA corresponding to other types except GNDVI is high.

[0090] Optionally, after step 102, the method may further include: the electronic device generates a special monitoring map of crop growth according to the crop growth index (such as Figure 2 Specifically, the crop growth index is written into the first band of the monitoring map.

[0091] In this way, through real-time monitoring and thematic monitoring maps, intuitive and scientific monitoring and evaluation tools are provided for agricultural production, as well as intelligent and refined management methods, thereby improving the yield and quality of the crops to be tested and providing strong technical support for agricultural production.

[0092] In an embodiment of the present invention, the vegetation index is determined according to the satellite remote sensing image corresponding to the crop to be tested; the vegetation index is input into the growth index prediction model to obtain the crop growth index output by the growth index prediction model, the growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample, and the crop growth index sample is determined based on the agronomic parameters of the crop sample. The method constructs a growth index prediction model with high accuracy and comprehensiveness through the vegetation index sample and the crop growth index sample, combined with the agronomic parameters of the ground survey, and then obtains the crop growth index with high accuracy, comprehensiveness and reliability, so as to accurately and in real time monitor and predict the growth status of crops.

[0093] The crop growth index prediction device provided by the present invention is described below. The crop growth index prediction device described below and the crop growth index prediction method described above can be referenced to each other.

[0094] Figure 3 Schematic diagram of the structure of the crop growth index prediction device provided by the present invention. Figure 3 As shown, the device includes the following data processing module 301 and index prediction module 302.

[0095] The data processing module 301 is used to determine the vegetation index according to the satellite remote sensing image corresponding to the crop to be tested.

[0096] The index prediction module 302 is used to input the vegetation index into the growth index prediction model to obtain the crop growth index output by the growth index prediction model. The growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample, and the crop growth index sample is determined based on the agronomic parameters of the crop sample.

[0097] Optionally, the device also includes a model construction module; the model construction module is used to determine the vegetation index sample based on the satellite remote sensing image sample corresponding to the crop sample; determine the crop growth index sample based on the agronomic parameters of the crop sample; use the crop growth index sample as the dependent variable, and the vegetation index sample as the independent variable, combined with the initial growth index prediction model, to determine multiple sets of fitting parameters; construct the growth index prediction model based on the multiple sets of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0098] Optionally, the agronomic parameter includes multiple sub-agronomic parameters; the model building module is specifically used to determine the crop growth index sample based on the two sub-agronomic parameters when the number of the multiple sub-agronomic parameters is only two; when the number of the multiple sub-agronomic parameters is at least three, determine multiple data combinations based on the at least three sub-agronomic parameters, each data combination includes any two parameters of the at least three sub-agronomic parameters, and the multiple data combinations are all different; determine the growth ground index corresponding to each of the multiple data combinations, and determine the multiple growth ground indices as the crop growth index sample.

[0099] Optionally, the model building module is specifically used to obtain a satellite remote sensing image sample corresponding to the longitude and latitude position of the crop sample; and determine the vegetation index sample based on the multispectral data of the satellite remote sensing image sample.

[0100] Optionally, the model building module is specifically used to calculate the square root of the product of the two sub-agronomic parameters and determine it as the crop growth index sample.

[0101] Optionally, the model building module is specifically used to adopt a cross-validation algorithm to determine the target fitting parameters from the multiple groups of fitting parameters; and to construct the growth index prediction model based on the target fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0102] Optionally, the model construction module is specifically used to determine the growth index prediction accuracy based on the first-level results corresponding to the crop growth index sample and the second-level results corresponding to the crop growth index; determine the root mean square error based on the crop growth index sample and the crop growth index; and construct the growth index prediction model based on the growth index prediction accuracy and the root mean square error, combined with the multiple sets of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

[0103] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the crop growth index prediction method, which includes: determining the vegetation index according to the satellite remote sensing image corresponding to the crop to be tested; inputting the vegetation index into the growth index prediction model to obtain the crop growth index output by the growth index prediction model, wherein the growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample, and the crop growth index sample is determined based on the agronomic parameters of the crop sample.

[0104] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0105] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the crop growth index prediction method provided by the above-mentioned methods, the method including: determining the vegetation index according to the satellite remote sensing image corresponding to the crop to be tested; inputting the vegetation index into a growth index prediction model to obtain the crop growth index output by the growth index prediction model, the growth index prediction model is constructed based on vegetation index samples and crop growth index samples, and the crop growth index samples are determined based on the agronomic parameters of the crop samples.

[0106] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the crop growth index prediction method provided by the above-mentioned methods, the method comprising: determining a vegetation index based on a satellite remote sensing image corresponding to the crop to be tested; inputting the vegetation index into a growth index prediction model to obtain the crop growth index output by the growth index prediction model, the growth index prediction model being constructed based on vegetation index samples and crop growth index samples, and the crop growth index samples being determined based on agronomic parameters of the crop samples.

[0107] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0108] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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.

Claims

1. A method for predicting crop growth index, characterized in that: include: Determine the vegetation index based on the satellite remote sensing images corresponding to the crops to be tested; The vegetation index is input into a growth index prediction model to obtain a crop growth index output by the growth index prediction model. The growth index prediction model is constructed based on vegetation index samples and crop growth index samples. The crop growth index samples are determined based on agronomic parameters of the crop samples.

2. The crop growth index prediction method according to claim 1, characterized in that: The growth index prediction model is constructed based on the following steps: Determining the vegetation index sample according to the satellite remote sensing image sample corresponding to the crop sample; Determining the crop growth index sample according to the agronomic parameters of the crop sample; Taking the crop growth index samples as dependent variables and the vegetation index samples as independent variables, combined with the initial growth index prediction model, to determine multiple groups of fitting parameters; The growth index prediction model is constructed according to the multiple groups of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

3. The crop growth index prediction method according to claim 2, characterized in that: The agronomic parameter includes a plurality of sub-agronomic parameters; and determining the crop growth index sample according to the agronomic parameter of the crop sample includes: In the case where the number of the plurality of sub-agronomic parameters is only two, determining the crop growth index sample according to the two sub-agronomic parameters; When the number of the multiple sub-agronomic parameters is at least three, multiple data combinations are determined based on the at least three sub-agronomic parameters, each data combination includes any two parameters of the at least three sub-agronomic parameters, and the multiple data combinations are different; the growth ground index corresponding to each of the multiple data combinations is determined, and the multiple growth ground indices are determined as the crop growth index samples.

4. The crop growth index prediction method according to claim 2, characterized in that: The step of determining the vegetation index sample according to the satellite remote sensing image sample corresponding to the crop sample comprises: Obtaining satellite remote sensing image samples corresponding to the latitude and longitude positions of the crop samples; The vegetation index sample is determined according to the multispectral data of the satellite remote sensing image sample.

5. The crop growth index prediction method according to claim 3, characterized in that: Determining the crop growth index sample according to the two sub-agronomic parameters includes: The square root of the product of the two sub-agronomic parameters is calculated to determine the crop growth index sample.

6. The crop growth index prediction method according to claim 2, characterized in that: The step of constructing the growth index prediction model according to the multiple sets of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model comprises: Using a cross-validation algorithm, determine a target fitting parameter from the multiple groups of fitting parameters; The growth index prediction model is constructed according to the target fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

7. The crop growth index prediction method according to any one of claims 2 to 6, characterized in that: The step of constructing the growth index prediction model according to the multiple sets of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model comprises: Determining the growth index prediction accuracy rate according to the first level result corresponding to the crop growth index sample and the second level result corresponding to the crop growth index; Determining a root mean square error according to the crop growth index sample and the crop growth index; The growth index prediction model is constructed according to the growth index prediction accuracy and the root mean square error, combined with the multiple groups of fitting parameters and the dependent variables and independent variables in the initial growth index prediction model.

8. A crop growth index prediction device, characterized in that: include: A data processing module is used to determine the vegetation index based on the satellite remote sensing images corresponding to the crops to be tested; The index prediction module is used to input the vegetation index into the growth index prediction model to obtain the crop growth index output by the growth index prediction model. The growth index prediction model is constructed based on the vegetation index sample and the crop growth index sample, and the crop growth index sample is determined based on the agronomic parameters of the crop sample.

9. An electronic device 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 crop growth index prediction method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the crop growth index prediction method according to any one of claims 1 to 7 is implemented.

Images