CN115983503A - Crop maturity prediction method, equipment and storage medium - Google Patents
Crop maturity prediction method, equipment and storage medium Download PDFInfo
- Publication number
- CN115983503A CN115983503A CN202310263635.XA CN202310263635A CN115983503A CN 115983503 A CN115983503 A CN 115983503A CN 202310263635 A CN202310263635 A CN 202310263635A CN 115983503 A CN115983503 A CN 115983503A
- Authority
- CN
- China
- Prior art keywords
- biochemical parameter
- data
- image data
- biochemical
- change curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 108
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000002310 reflectometry Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 7
- 230000005855 radiation Effects 0.000 claims description 7
- 238000012952 Resampling Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000007499 fusion processing Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 93
- 229930002875 chlorophyll Natural products 0.000 description 53
- 235000019804 chlorophyll Nutrition 0.000 description 53
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 53
- 230000035508 accumulation Effects 0.000 description 28
- 238000009825 accumulation Methods 0.000 description 28
- 230000008569 process Effects 0.000 description 24
- 208000037516 chromosome inversion disease Diseases 0.000 description 23
- 235000002595 Solanum tuberosum Nutrition 0.000 description 15
- 244000061456 Solanum tuberosum Species 0.000 description 15
- 235000012015 potatoes Nutrition 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000010276 construction Methods 0.000 description 6
- 230000003595 spectral effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000009331 sowing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000003306 harvesting Methods 0.000 description 3
- 230000010198 maturation time Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000005070 ripening Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000001058 brown pigment Substances 0.000 description 1
- 235000021466 carotenoid Nutrition 0.000 description 1
- 150000001747 carotenoids Chemical class 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application provides a crop maturity prediction method, equipment and a storage medium, wherein the method comprises the following steps: acquiring remote sensing image data, and carrying out image preprocessing on the remote sensing image data to obtain an actual reflectance value; carrying out biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve; acquiring second biochemical parameter data, performing time sequence harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage. By adopting two kinds of data of the sentinel No. 2 image and the terrestrial satellite No. 8 image, high space and high time resolution are better considered; the prediction can be carried out without depending on the remote sensing data of the past year and the continuous cultivation data of the same plot.
Description
Technical Field
The present application relates to the field of remote sensing image processing technologies, and in particular, to a crop maturity prediction method, a device, and a computer-readable storage medium.
Background
The precision agriculture is an agricultural operation management system which is based on the space difference of farmland crops and the environment, obtains farmland information of different units in a farmland through various technical means, performs farmland optimization management by using a variable technology and realizes refinement and accuracy of a production process. The remote sensing information provides an important technical means for quickly, accurately and dynamically acquiring the spatial variation parameters required by the precise agriculture. With the development of remote sensing technology, the remote sensing technology plays an increasingly important role in the field of precision agriculture. The method is characterized in that crop maturity information is obtained based on remote sensing data, a harvesting sequence is formulated, and the method is an important application field of remote sensing in precision agriculture. The method reasonably predicts the crop harvesting time, avoids the influence of adverse factors, is helpful for improving the quality and yield of agricultural products, and can guide agricultural machinery to carry out reasonable scheduling arrangement, thereby having important significance for mechanized harvesting in large-scale crop planting areas.
The traditional method is mainly used for judging the maturity of crops by subjectively interpreting the crop characteristics such as the color, the structure, the canopy structure and the like of leaves, cannot be applied in a large range, and is easy to introduce errors of subjective judgment. Some crop maturity prediction methods are gradually researched, and currently, the existing researches can be roughly divided into the following three categories: firstly, the crop maturity period prediction based on meteorological statistics is simple and easy to use, the prediction can be carried out only by less meteorological data (such as temperature, precipitation and the like), but the method has the defect that field scale fine estimation cannot be carried out, and meanwhile, the established statistical model is usually difficult to popularize among areas; secondly, the crop maturity stage prediction based on a crop growth model is that the model is generally high in precision for a single-point region, but the huge workload is caused by relevant parameter information such as soil, crops and weather required in the simulation process, so that the application and the popularization of the model in the region are limited; the existing model of the method has higher requirements on the space-time resolution of remote sensing data, most of used data are time sequence vegetation index data with medium-low resolution, the effect of the method is usually difficult to meet the actual requirements, and most of researches have high requirements on the integrity of the time sequence data, so that the prediction result of the method often has 'after the fact' property.
Disclosure of Invention
The main purpose of the application is to provide a crop maturity stage prediction method, equipment and a computer readable storage medium, aiming at constructing a crop standard biochemical parameter change curve reference library to select an optimal reference curve, and predicting the crop maturity stage without relying on past year remote sensing data and continuous cultivation data of the same plot.
In a first aspect, the present application provides a method for predicting the maturity of a crop, comprising the steps of:
acquiring remote sensing image data, and performing image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data;
carrying out biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve;
acquiring second biochemical parameter data, performing time sequence harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage.
In a second aspect, the present application provides a crop maturity prediction apparatus comprising:
a preprocessing module: the remote sensing image data acquisition module is used for acquiring remote sensing image data, carrying out image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data;
an inversion analysis module: the system is used for carrying out biochemical parameter inversion according to the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve;
a reference prediction module: the system is used for acquiring second biochemical parameter data, performing time sequence harmonic analysis on the second biochemical parameter data to obtain a biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the range of the biochemical parameter change curve reference library to predict the maturity stage of crops.
In a third aspect, the present application further provides a computer device, which includes a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the crop maturity prediction method as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, having a computer program stored thereon, where the computer program, when executed by a processor, implements the steps of the crop maturity prediction method as described above.
The application provides a crop maturity prediction method, equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring remote sensing image data, and performing image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data; carrying out biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve; acquiring second biochemical parameter data, performing time series harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage. According to the method, two kinds of data, namely the sentinel No. 2 image and the terrestrial satellite 8 image with similar spatial resolution and spectral characteristics are adopted, and additional time-space fusion is not needed, so that a huge error caused by a large scale difference is avoided, and high spatial resolution and high time resolution are better considered; a standard biochemical parameter change curve reference library is established through a time series harmonic analysis method and is matched with an optimal reference curve to predict the crop maturity, the crop maturity can be predicted without depending on the remote sensing data of the past year and the continuous cultivation data of the same plot, and the prediction precision is higher as the maturity is closer, so that the dynamic prediction process is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for predicting the maturity of a crop according to an embodiment of the present disclosure;
FIG. 2 is a graph of spectral characteristics of a blade according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a biochemical parameter variation curve matching provided in an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating an accumulation amount of a biochemical parameter of a crop and a reference accumulation amount according to an embodiment of the present application;
FIG. 5 is a schematic flow chart of a method for predicting the maturity of potatoes provided in the embodiments of the present application;
fig. 6 is a schematic structural diagram of a device for predicting the maturity of a crop according to an embodiment of the present disclosure;
fig. 7 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
The flowcharts shown in the figures are illustrative only and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1 to 4, fig. 1 is a schematic flow chart illustrating a method for predicting a maturity stage of a crop according to an embodiment of the present application; FIG. 2 is a graph of spectral characteristics of a blade according to an embodiment of the present disclosure; FIG. 3 is a schematic diagram of biochemical parameter variation curve matching provided in an embodiment of the present application; fig. 4 is a schematic diagram of an accumulation amount of a biochemical parameter of a crop and a reference accumulation amount according to an embodiment of the present application.
As shown in fig. 1, the method for predicting the maturity of a crop includes steps S110 to S130.
S110, remote sensing image data are obtained, image preprocessing is carried out on the remote sensing image data, and an actual reflectance value is obtained, wherein the remote sensing image data comprise the sentinel No. 2 image data and the land satellite 8 image data.
In some embodiments, obtaining remote sensing image data, performing image preprocessing on the remote sensing image data to obtain an actual reflectance value, where the remote sensing image data includes sentinel No. 2 image data and terrestrial satellite 8 image data, and includes: acquiring remote sensing image data, wherein the remote sensing image data comprises sentry No. 2 image data and land satellite 8 image data; and performing space-time screening, radiation correction and cloud removal on the remote sensing image data, and performing panchromatic-multispectral fusion processing on the terrestrial satellite 8 image data to obtain an actual reflectance value.
And (3) screening the remote sensing image data according to the distribution area of the crops to obtain the Sentinel-2 (Sentinel No. 2) images and Landsat-8 (land satellite 8) images which can be obtained in the growth cycle of the crops in the year. And performing radiation correction (radiometric calibration, atmospheric correction and the like) on the two data to enable an original DN value (pixel brightness value of the remote sensing image) to represent a surface reflectance value, and masking a cloud layer coverage area by utilizing a cloud mask band, wherein for the Landsat-8 data, a panchromatic band and a multispectral band are further fused to improve the spatial resolution of the multispectral band. The obtained remote sensing image data is subjected to the preprocessing operation, and the surface reflectance value, namely the actual reflectance value, is obtained preliminarily so as to perform the subsequent biochemical parameter inversion operation.
Illustratively, the panchromatic wave band and the multispectral wave band of the Landsat-8 image data are fused, and the spatial resolution of the multispectral wave band can be improved to 15m. The image fusion refers to a process of generating a new image from the multi-source remote sensing image in a specified geographic coordinate system according to a certain algorithm. The panchromatic image generally has higher spatial resolution, the multispectral image spectral information is richer, and in order to improve the spatial resolution of the multispectral image, the panchromatic image can be fused into the multispectral image, so that the spatial resolution of the multispectral image is improved, and the multispectral characteristic of the multispectral image is reserved.
Illustratively, the above process may be implemented in SNAP software or ENVI software, etc.
S120, performing biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and performing time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve.
In some embodiments, the biochemical parameters include chlorophyll content and leaf water content. As shown in fig. 2, chlorophyll content and water content change the spectral characteristics of the blade by affecting the scattering and absorption of photons within the blade. Chlorophyll content and water content generally cannot be resolved by a forward process, but the content can be obtained by coupling a leaf model with a canopy model and then inverting the reflectivity data of the canopy.
In some embodiments, performing biochemical parametric inversion based on the actual reflectance value to obtain first biochemical parametric data comprises: acquiring ground observation data, and respectively constructing a simulation reflectance value lookup table based on biochemical parameters at each time phase according to the ground observation data; comparing each analog reflectivity value in the lookup table with the actual reflectivity value at the same time phase to obtain a reflectivity difference value; and selecting the first x minimum reflectivity difference values from the lookup table, and averaging the corresponding x groups of biochemical parameter data to serve as inverted first biochemical parameter data, wherein x is a positive integer not less than 1.
The construction of the analog reflectivity value lookup table based on each biochemical parameter is realized by adopting a radiation transmission model or a geometric optical model, such as a PROSAIL physical model or a linear regression model. The PROSAIL physical model has good stability on remote sensing images with different spatial resolutions. The PROSAIL model is a model formed by coupling a PROSPECT model and a SAIL model, and therefore, the characteristics of crops can be described from the leaf scale and the canopy scale at the same time.
In this embodiment, a simulated reflectance value lookup table is constructed by using a PROSAIL model. For each stage of inversion, in actual operation, a plurality of parameters required in model construction can be obtained through different instruments, wherein a vegetation canopy analyzer is used for measuring a leaf area index LAI and an average leaf inclination angle ALIA, a chlorophyll content determinator is used for measuring a chlorophyll content LCC, a portable spectrometer is used for collecting a canopy spectrum Rp and a soil reflectivity Rs of crops from the ground, a leaf water content measurer is used for measuring a leaf water content Cw, in addition, each sampling point position is positioned through an RTK measuring system and centimeter-level differential positioning service, the maximum possible collection time is ensured to be synchronous with transit time of Sentel-2 and Landsat-8 satellites, so that parameters required by the model, namely a sun zenith angle SZA, an observation zenith angle OZA and a relative azimuth angle rAA, can be obtained through a head file of satellite data, and other parameters, including a brown pigment Cb, a carotenoid Car, a dry matter content Cm, a Hot spot and a leaf structure parameter N, set a certain gradient value according to prior knowledge and related documents. And then, taking the parameters as input parameters of a PROSAIL model, and constructing a lookup table of the corresponding relation among the water content, the chlorophyll content and the reflectivity, namely a simulated reflectivity value lookup table.
After the analog reflectivity value lookup table is constructed, the difference between the analog reflectivity value and the actual reflectivity value (obtained in step S110) is compared, and the smaller the difference is, the closer the corresponding biochemical parameter data in the lookup table is to the real value is. And finally, selecting the biochemical parameter data corresponding to the partial data with the minimum difference to calculate an average value as an inversion result of the current time phase. And finally, carrying out inversion to obtain biochemical parameter data of different time phases.
Illustratively, the difference between the simulated reflectance value and the actual reflectance value is characterized by a square function Y of the difference, which is expressed as follows:
wherein, the first and the second end of the pipe are connected with each other,
represents the analog reflectivity value in the wavelength n>
And representing the actual image reflectance value at the wavelength n, selecting the average value of the biochemical parameter data corresponding to the first x minimum Y values as an inversion result, and verifying through the actual measurement result.
In some embodiments, performing time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter variation curve includes: uniformly resampling the first biochemical parameter data of each time phase, and stacking the data according to a time sequence to obtain time sequence biochemical parameter data; and performing time series harmonic analysis processing on the time series biochemical parameter data to obtain continuous time series biochemical parameter data and a biochemical parameter change curve.
Previous researches show that the apparent reflectivities of Landsat-8 data and Sentinal-2 data are very similar on the whole, and the difference is smaller when the earth surface covers a single area, so that the corresponding wave bands of the two data do not need to be converted under normal conditions, and the spatial resolutions of the two data are similar, thereby avoiding a huge error caused by a large scale difference between the data.
Illustratively, the biochemical parameter data of different phases of the inversion are uniformly resampled to a spatial resolution of 15m. The Sentinel-2 data are complemented by two stars, the time resolution can reach 5 days, and the Landsat-8 data time resolution is 16 days. And uniformly resampling the biochemical parameter data of different time phases obtained by Landsat-8 and Sentinel-2 data inversion to 15m spatial resolution, and respectively stacking the biochemical parameter layers according to the time sequence so as to further improve the time resolution.
Illustratively, the HLS (harmnized Landsat Sentinel-2) dataset, published by NASA/USGS in 2020, was processed on the basis of Landsat-8 and Sentinel-2 data with time resolution increased to 2-3 days.
In some embodiments, the time series harmonic analysis comprises: generating a least square fitting curve according to the discrete time sequence biochemical parameter data, comparing the time sequence biochemical parameter data with the fitting curve, and rejecting the biochemical parameter data with deviation exceeding a preset threshold value; based on the rest biochemical parameter data, repeating the steps of generating a least square fitting curve and removing the biochemical parameter data with deviation exceeding a preset threshold value until all the biochemical parameter data values and the deviation of the fitting curve do not exceed a threshold value range, and obtaining a biochemical parameter change curve; and acquiring continuous time sequence biochemical parameter data with specific time resolution according to the biochemical parameter change curve.
The Time Series Harmonic Analysis (Harmonic Analysis of Time Series, HANTS) is the synthesis of two methods of smoothing and filtering, and can fully utilize the characteristics of timeliness and spatiality of the remote sensing image to link the distribution rule in space with the change rule in Time. When the time series harmonic analysis method is used for image reconstruction, the dual characteristics of vegetation growth period and data are fully considered, the time series image can be reconstructed by using vegetation frequency curves representing different growth periods, and the periodic change rule of vegetation is truly reflected. The core algorithms are fourier transform and least squares fitting, but the requirements for time series images are not as strict as Fast Fourier Transform (FFT), which can be images of unequal time intervals. Thus HANTS has greater flexibility in the choice of frequency and time series length.
In actual operation, due to interference of the cloud, the biochemical parameter data after data stacking has a certain data hole, and the time resolution of 2-3 days still needs to be further improved so as to meet the requirement of more refined maturity prediction. Through the HANTS method, firstly, a least square fitting curve is generated by all discrete data quantities, then each data value is checked and compared with the curve, wherein the point with the maximum deviation quantity exceeding the threshold value is firstly removed, then, the fitting curve is regenerated according to the rest sampling points, then, each data value is checked, the point with the deviation curve value exceeding the threshold value is removed, and the process is repeatedly circulated until all the points do not exceed the threshold value range.
Illustratively, continuous time sequence biochemical parameter data with the time resolution of n days are finally obtained by setting the time interval parameter to be n days; typically, the time interval parameter is set to 1 day, and finally continuous chlorophyll content and water content time sequence data with the time resolution of 1 day are obtained, namely a chlorophyll content change curve s _ chl and a water content change curve s _ water at the corresponding position of each pixel point.
S130, obtaining second biochemical parameter data, performing time series harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage.
In some embodiments, obtaining second biochemical parameter data, performing time series harmonic analysis on the second biochemical parameter data to obtain a reference library of standard biochemical parameter variation curves, comprises: acquiring second biochemical parameter data observed on the ground, wherein the second biochemical parameter data comprises a plurality of groups of time sequence biochemical parameter data with different growth cycles; respectively carrying out time sequence harmonic analysis processing on each group of time sequence biochemical parameter data to obtain a standard biochemical parameter change curve of each growth cycle; and summarizing the standard biochemical parameter change curves of all growth periods to obtain a standard biochemical parameter change curve reference library.
Through continuous observation of a ground instrument for many years, ground observation data of chlorophyll content and water content of crops in different growth periods from sowing to the mature process are obtained, then time sequence observation data of the chlorophyll content and the water content are processed through an HANTS method, standard chlorophyll content and water content change curves in the crop growth process are obtained, then crop chlorophyll content and water content change curves of different observation points in different years are summarized, and a chlorophyll content change curve reference library LS _ chl and a water content change curve reference library LS _ water for predicting the mature period of the crops are formed respectively.
Illustratively, the time series harmonic analysis includes: generating a least square fitting curve according to the discrete time sequence biochemical parameter data, comparing the time sequence biochemical parameter data with the fitting curve, and rejecting the biochemical parameter data with deviation exceeding a preset threshold value; based on the remaining biochemical parameter data, repeating the steps of generating a least square fitting curve and removing the biochemical parameter data with deviation exceeding a preset threshold value until all biochemical parameter data values and the deviation of the fitting curve do not exceed a threshold value range, so as to obtain a biochemical parameter change curve; and acquiring continuous time sequence biochemical parameter data with specific time resolution according to the biochemical parameter change curve. And setting time interval parameters to be n days according to the biochemical parameter change curve so as to obtain continuous time sequence biochemical parameter data with the time resolution of n days, wherein n is a positive integer not less than 1. Preferably, n is set to 1 day.
In some embodiments, selecting an optimal reference curve matching the biochemical parameter variation curve within the standard biochemical parameter variation curve reference library range to predict the maturity stage of the crop comprises: selecting an optimal reference curve with the highest similarity from the biochemical parameter change curve reference library according to the biochemical parameter change curve, and calculating the reference cumulant of the biochemical parameter according to the optimal reference curve; and calculating the current biochemical parameter cumulant of the crops according to the biochemical parameter change curve, and calculating the time required by the biochemical parameter cumulant to reach the reference cumulant level so as to predict the maturity stage of the crops.
Because the crops have a difference in phenology in the growth process of different years, a great error is bound to be generated when the maturity stage of the crop in the current year is predicted by directly referring to the time sequence characteristics (such as the chlorophyll content in the time sequence of the previous year) in the growth process of the crop in the previous year. In order to reduce such errors and improve the accuracy of the crop maturity prediction, in this embodiment, the time series warping method (DTW) is adopted to match the chlorophyll content variation curve S _ chl and the water content variation curve S _ water obtained by the above processing with the variation curves in the chlorophyll content variation curve reference library LS _ chl and the water content variation curve reference library LS _ water one by one, so as to obtain the reference variation curves with the highest similarity measurement results with S _ chl and S _ water as the optimal reference curves S _ chl and S _ water. The biochemical parameter variation curve is matched and shown in figure 3.
As shown in fig. 4, according to the optimum reference curves S _ chl and S _ water obtained by matching, the total chlorophyll accumulation SUM _ chl and the total water content accumulation SUM _ water to be reached in the whole growth process of the crop from sowing to ripening can be calculated by integration as reference accumulations; meanwhile, the actual chlorophyll accumulation sum _ chl and the actual water content accumulation sum-water in the crop growth process up to the current moment can be obtained by performing integral calculation on the s _ chl and the s _ water; therefore, the residual chlorophyll accumulation rem _ chl and the residual water content rem _ water required by s _ chl and s _ water from the current time to the maturation time can be expressed as:
when the chlorophyll accumulation amount and the water content accumulation amount of the crops simultaneously reach the reference level, the maturity period is reached. Since the optimal reference curves S _ chl and S _ water with the highest similarity have been matched for S _ chl and S _ water in the above process, respectively, and therefore the trends of the changes between S _ chl and S _ chl, and between S _ water and S _ water are very similar, it is only necessary to judge the time required for the chlorophyll accumulation amount of S _ chl and the water content accumulation amount of S _ water to reach the SUM _ chl and SUM _ water levels from the current time levels SUM _ chl and SUM-water, that is, the time required for S _ chl and S _ water to both achieve the remaining accumulation amounts of rem _ chl and rem _ water, starting from the cut-off times of SUM _ chl and SUM-water levels.
Assuming that the times at which the chlorophyll content and the water content on S _ chl reach the same level as the actual chlorophyll accumulation amount sum _ chl and the actual water content accumulation amount sum-water at the present time are t1 and t2, respectively, the dates after the chlorophyll content and the water content of the crop reach the accumulation amounts on S _ chl and S _ water, respectively, to rem _ chl and rem _ water from the times t1 and t2 may be regarded as the maturity dates of the crop. Specifically, the following formula can be expressed as follows:
wherein the content of the first and second substances,
and &>
Indicates the chlorophyll content and the water content at time i on S _ chl and S _ water, respectively, and ` H `>
And &>
Respectively representing the time when the chlorophyll content cumulant and the water content cumulant of the crops reach the maturity standard, and T is the maturity date of the crops.
In actual operation, the biochemical parameter data of different growth cycles of crops are obtained through years of observation data of a ground instrument, the time sequence observation data of the biochemical parameter data are processed through an HANTS method, a standard biochemical parameter change curve in the growth process of the crops is obtained, a standard biochemical parameter change curve reference library of each growth cycle is established and used as a reference for predicting the maturity of the crops through a time sequence remote sensing image, and the maturity is reached when the biological biochemical parameter accumulation reaches a reference level at the same time. The mode does not depend on the remote sensing data of the past year, and the same crop is not required to be continuously cultivated in the same land.
By inverting the continuous time sequence biochemical parameter data of the current year, the optimal reference curve is matched in the range of the established standard biochemical parameter change curve reference library, and when the biochemical parameter data of the current year reaches the reference level, the maturity stage is reached, so that the purpose of predicting the maturity stage is achieved. The closer the mode is to the mature period (the more the instant sequence data is finished), the higher the prediction precision is, and therefore the dynamic prediction process is realized.
According to the method, two kinds of data, namely the sentinel No. 2 image and the land satellite 8 image with similar spatial resolution and spectral characteristics, are adopted, and extra time-space fusion is not needed, so that a huge error caused by a large scale difference is avoided, and high spatial resolution and high time resolution are better considered; a standard biochemical parameter change curve reference library is established through a time series harmonic analysis method and an optimal reference curve is matched to predict the maturity stage of the crop, the maturity stage of the crop can be predicted without depending on past year remote sensing data and continuous cultivation data of the same plot, and the prediction precision is higher as the maturity stage is closer, so that the process of dynamic prediction is realized.
Referring to fig. 5, fig. 5 is a schematic flow chart of a method for predicting the maturity of potatoes according to an embodiment of the present disclosure.
As shown in FIG. 5, the method for predicting the maturity of potato comprises the following steps.
And screening all the available Sentinel-2 images and Landsat-8 images in the growth cycle of the potatoes in the year according to the distribution area and the growth cycle of the potatoes. And performing radiation correction on the two data to enable the pixel value to represent the earth surface reflectance value, and masking the cloud covering region by using a cloud mask wave band, wherein for the Landsat-8 data, the panchromatic wave band and the multispectral wave band are further fused, so that the multispectral wave band spatial resolution is improved to 15m.
A lookup table based on the water content and the chlorophyll content of the leaves is built through a PROSAIL model, then the difference between the simulated reflectance value and the actual reflectance value is compared, and the smaller the difference is, the closer the corresponding chlorophyll content and the water content of the leaves are to the true value is shown. This difference is characterized here by its squared function Y of the difference, which is given by the following formula:
wherein the content of the first and second substances,
represents a simulated reflectance value in the wavelength n>
The actual reflectance value of the image at wavelength n is shown. And finally, selecting the average value of the chlorophyll content and the leaf water content corresponding to the previous x minimum Y values as an inversion result, and verifying through an actual measurement result.
And uniformly resampling the chlorophyll content and the leaf water content data of different time phases of Landsat-8 and Sentinel-2 data inversion to 15m spatial resolution, and respectively performing data stacking on a chlorophyll content layer and a leaf water content layer according to a time sequence so as to further improve the time resolution.
The chlorophyll content data and leaf water content data after data stacking are firstly generated into a least square fitting curve by all discrete data amounts through a HANTS method, and then each data value is checked and compared with the curve. The points with the maximum deviation exceeding the threshold are removed firstly, then a fitting curve is regenerated according to the remaining sampling points, each data value is checked, and the points with the deviation curve value exceeding the threshold are removed. And repeating the steps until all the points do not exceed the threshold range to obtain the biochemical parameter change curve. And setting the time interval parameter to be 1 day, and finally acquiring continuous chlorophyll content and water content time sequence data with the time resolution of 1 day, namely a chlorophyll content change curve and a water content change curve of the corresponding position of each pixel point.
Through years of continuous observation of a ground instrument, ground observation data of chlorophyll content and water content of potatoes in different growth periods from sowing to maturing are obtained, then time sequence observation data of the chlorophyll content and the water content are processed through an HANTS method, standard change curves of chlorophyll content and water content of potatoes in a growth process are obtained, further, change curves of chlorophyll content and water content of potatoes at different observation points in different years are summarized, and a chlorophyll content change curve reference library and a water content change curve reference library for predicting the maturity period of the potatoes are formed respectively.
And matching the chlorophyll content change curve S _ chl and the water content change curve S _ water obtained by the treatment with the change curves in the chlorophyll content change curve reference library and the water content change curve reference library one by adopting a time series normalization method to obtain a reference change curve with the highest similarity measurement result with the S _ chl and the S _ water respectively as an optimal reference curve, namely an optimal reference curve S _ chl of the chlorophyll content change curve and an optimal reference curve S _ water of the water content change curve.
Calculating according to the optimal reference curves S _ chl and S _ water to obtain the total chlorophyll accumulation SUM _ chl and total water content accumulation SUM _ water required by the potato in the whole growth process from sowing to ripening; meanwhile, performing integral calculation on the s _ chl and the s _ water to obtain the actual chlorophyll cumulative amount sum _ chl and the actual water content cumulative amount sum-water in the potato growth process at the current moment; therefore, the residual chlorophyll accumulation rem _ chl and the residual water content rem _ water required by s _ chl and s _ water from the current time to the maturation time can be expressed as:
assuming that the times at which the chlorophyll content and the water content at S _ water at S _ chl reach the same level as the actual chlorophyll accumulation sum _ chl and the actual water content accumulation sum-water at the present time are t1 and t2, respectively, the dates corresponding to the respective accumulated amounts of chlorophyll content and water content at S _ chl and S _ water at S _ water reaching rem _ chl and rem _ water from the times t1 and t2 can be regarded as the ripening dates of the potatoes. Specifically, the following formula can be expressed as follows:
wherein the content of the first and second substances,
and &>
Indicates the chlorophyll content and the water content at time i on S _ chl and S _ water, respectively, and ` H `>
And &>
Respectively representing the corresponding time when the chlorophyll content accumulation and the water content accumulation of the potato reach the maturation standard, and T is the maturation time of the potato.
Thus, after the time T, the chlorophyll accumulation amount and the water content accumulation amount of the potatoes simultaneously reach the reference level, namely the mature period is reached.
According to the method, the chlorophyll content and the water content of existing time sequence data in the year are inverted, continuous time sequence data are obtained through harmonic analysis, a change curve reference library of standard chlorophyll content and water content is established through ground observation data, an optimal reference curve is matched, and the purpose of predicting the maturity is achieved. The closer the approach to the maturity stage (the more complete the instant sequence data) the higher the prediction precision, thereby realizing dynamic prediction.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a crop maturity prediction apparatus according to an embodiment of the present disclosure.
As shown in fig. 6, the crop maturity prediction apparatus includes a preprocessing module 10, an inversion analysis module 20, and a reference prediction module 30.
The preprocessing module 10: the remote sensing image data acquisition module is used for acquiring remote sensing image data, carrying out image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data;
the inversion analysis module 20: the system is used for carrying out biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve;
the reference prediction module 30: the system is used for acquiring second biochemical parameter data, performing time series harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage.
In some embodiments, the pre-processing module 10 comprises:
an image acquisition unit: the remote sensing image data acquisition device is used for acquiring remote sensing image data, wherein the remote sensing image data comprises sentry No. 2 image data and land satellite 8 image data;
an image processing unit: the system is used for carrying out space-time screening, radiation correction and cloud removal processing on the remote sensing image data and carrying out panchromatic-multispectral fusion processing on the terrestrial satellite 8 image data to obtain an actual reflectance value.
In some embodiments, the inversion analysis module 20 includes:
a lookup table construction unit: the system comprises a data acquisition module, a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring ground observation data and respectively constructing a simulation reflectance value lookup table based on biochemical parameters under each time phase according to the ground observation data;
a difference value construction unit: the system is used for comparing each simulation reflectivity value in the lookup table with the actual reflectivity value in the same time phase to obtain a reflectivity difference value;
an inversion subunit: and the method is used for selecting the first x minimum reflectivity difference values from the lookup table, averaging the corresponding x groups of biochemical parameter data, and taking the average value as inverted first biochemical parameter data, wherein x is a positive integer not less than 1.
In some embodiments, the inversion analysis module 20 further comprises:
a data processing unit: the time sequence biochemical parameter data acquisition module is used for uniformly resampling the first biochemical parameter data of each time phase and stacking the data according to a time sequence to obtain time sequence biochemical parameter data;
a timing analysis unit: and the time sequence harmonic analysis processing module is used for carrying out time sequence harmonic analysis processing on the time sequence biochemical parameter data to obtain continuous time sequence biochemical parameter data and a biochemical parameter change curve.
In some embodiments, the reference prediction module 30 includes:
a data acquisition unit: the system comprises a first biochemical parameter data acquisition unit, a second biochemical parameter data acquisition unit, a data acquisition unit and a data processing unit, wherein the first biochemical parameter data acquisition unit is used for acquiring first biochemical parameter data observed on the ground, and the first biochemical parameter data comprises a plurality of groups of time sequence biochemical parameter data of different growth cycles;
a timing analysis unit: the time sequence harmonic analysis processing module is used for respectively carrying out time sequence harmonic analysis processing on each group of time sequence biochemical parameter data to obtain a standard biochemical parameter change curve of each growth cycle;
a reference library construction unit: and the standard biochemical parameter change curve is used for summarizing the standard biochemical parameter change curves of all growth periods to obtain a standard biochemical parameter change curve reference library.
In some embodiments, the reference prediction module 30 further comprises:
a reference matching unit: the biochemical parameter storage unit is used for storing biochemical parameters of the biochemical system, and storing the biochemical parameters in a biochemical parameter storage unit;
maturity prediction unit: and the device is used for calculating the current biochemical parameter cumulant of the crops according to the biochemical parameter change curve and calculating the time required by the biochemical parameter cumulant to reach the reference cumulant level so as to predict the maturity period of the crops.
In some embodiments, the timing analysis unit comprises:
a data fitting unit: the time sequence biochemical parameter data processing device is used for generating a least square fitting curve according to the dispersed time sequence biochemical parameter data, comparing the time sequence biochemical parameter data with the fitting curve and eliminating the biochemical parameter data with deviation exceeding a preset threshold value;
a threshold monitoring unit: the step of generating a least squares fitting curve and removing the biochemical parameter data with deviation exceeding a preset threshold value is repeated based on the remaining biochemical parameter data until all the biochemical parameter data values and the deviation of the fitting curve do not exceed a threshold value range, so as to obtain a biochemical parameter change curve;
an individual rate setting unit: and the time sequence biochemical parameter data acquisition module is used for acquiring continuous time sequence biochemical parameter data with a specific time resolution according to the biochemical parameter change curve.
It is understood that the crop maturity prediction apparatus implements the aforementioned crop maturity prediction method during operation.
The crop maturity prediction device does not need to additionally perform space-time fusion on the acquired image data, avoids huge errors caused by large scale difference, and gives consideration to high space and high time resolution; a standard crop maturity prediction integral model is established through a time sequence construction module, and the crop maturity can be predicted without depending on the remote sensing data of the past year and the continuous cultivation data of the same land parcel.
Referring to fig. 7, fig. 7 is a schematic block diagram illustrating a structure of a computer device according to an embodiment of the present disclosure. The computer device may be a server or a terminal.
As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a storage medium and an internal memory.
The storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of the crop maturity prediction methods.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for the execution of a computer program on a storage medium, which when executed by the processor, causes the processor to perform any one of the crop maturity prediction methods.
The network interface is used for network communication, such as sending assigned tasks and the like. It will be appreciated by those skilled in the art that the configuration shown in fig. 4 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
acquiring remote sensing image data, and performing image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data;
carrying out biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve;
acquiring second biochemical parameter data, performing time sequence harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage.
The method comprises the following steps of obtaining remote sensing image data, carrying out image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprise sentinel No. 2 image data and land satellite 8 image data, and the method comprises the following steps:
acquiring remote sensing image data, wherein the remote sensing image data comprises sentry No. 2 image data and land satellite 8 image data;
and performing space-time screening, radiation correction and cloud removal on the remote sensing image data, and performing panchromatic-multispectral fusion processing on the terrestrial satellite 8 image data to obtain an actual reflectance value.
Performing biochemical parameter inversion according to the actual reflectance value to obtain first biochemical parameter data, wherein the acquiring comprises:
acquiring ground observation data, and respectively constructing a simulation reflectance value lookup table based on biochemical parameters at each time phase according to the ground observation data;
comparing each analog reflectivity value in the lookup table with the actual reflectivity value at the same time phase to obtain a reflectivity difference value;
and selecting the first x minimum reflectivity difference values from the lookup table, and averaging the corresponding x groups of biochemical parameter data to serve as inverted first biochemical parameter data, wherein x is a positive integer not less than 1.
Wherein, the time-series harmonic analysis is performed on the first biochemical parameter data to obtain a biochemical parameter change curve, and the method comprises the following steps:
uniformly resampling the first biochemical parameter data of each time phase, and stacking the data according to a time sequence to obtain time sequence biochemical parameter data;
and performing time series harmonic analysis processing on the time series biochemical parameter data to obtain continuous time series biochemical parameter data and a biochemical parameter change curve.
Wherein, the obtaining of the second biochemical parameter data and the time-series harmonic analysis of the second biochemical parameter data to obtain the reference library of the standard biochemical parameter variation curve comprise:
acquiring second biochemical parameter data observed on the ground, wherein the second biochemical parameter data comprises a plurality of groups of time sequence biochemical parameter data with different growth periods;
respectively carrying out time sequence harmonic analysis processing on each group of time sequence biochemical parameter data to obtain a standard biochemical parameter change curve of each growth cycle;
and summarizing the standard biochemical parameter change curves of all growth periods to obtain a standard biochemical parameter change curve reference library.
Wherein, the optimal reference curve matched with the biochemical parameter change curve is selected in the standard biochemical parameter change curve reference library range to predict the crop maturity period, and the method comprises the following steps:
selecting an optimal reference curve with the highest similarity from the biochemical parameter change curve reference library according to the biochemical parameter change curve, and calculating the reference cumulant of the biochemical parameters according to the optimal reference curve;
and calculating the current biochemical parameter cumulant of the crops according to the biochemical parameter change curve, and calculating the time required by the biochemical parameter cumulant to reach the reference cumulant level so as to predict the maturity stage of the crops.
Wherein the time series harmonic analysis comprises:
generating a least square fitting curve according to the discrete time sequence biochemical parameter data, comparing the time sequence biochemical parameter data with the fitting curve, and rejecting the biochemical parameter data with deviation exceeding a preset threshold value;
based on the remaining biochemical parameter data, repeating the steps of generating a least square fitting curve and removing the biochemical parameter data with deviation exceeding a preset threshold value until all biochemical parameter data values and the deviation of the fitting curve do not exceed a threshold value range, so as to obtain a biochemical parameter change curve;
and acquiring continuous time sequence biochemical parameter data with specific time resolution according to the biochemical parameter change curve.
It should be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the crop maturity prediction may refer to the corresponding process in the foregoing embodiment of the crop maturity prediction method, and will not be described herein again.
Embodiments of the present application also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed, a method implemented by the computer program instructions may refer to various embodiments of the crop maturity prediction method of the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for predicting the maturity of a crop, comprising:
acquiring remote sensing image data, and performing image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data;
carrying out biochemical parameter inversion on the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve;
acquiring second biochemical parameter data, performing time series harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage.
2. The crop maturity prediction method of claim 1, wherein the obtaining of remote sensing image data, the image preprocessing of the remote sensing image data to obtain an actual reflectance value, the remote sensing image data including sentinel No. 2 image data and land satellite 8 image data, comprises:
acquiring remote sensing image data, wherein the remote sensing image data comprises sentry No. 2 image data and land satellite 8 image data;
and performing space-time screening, radiation correction and cloud removal on the remote sensing image data, and performing panchromatic-multispectral fusion processing on the terrestrial satellite 8 image data to obtain an actual reflectance value.
3. The method for predicting the maturity of crops according to claim 1, wherein the performing biochemical parameter inversion according to the actual reflectance value to obtain a first biochemical parameter data comprises:
acquiring ground observation data, and respectively constructing a simulation reflectance value lookup table based on biochemical parameters at each time phase according to the ground observation data;
comparing each analog reflectivity value in the lookup table with the actual reflectivity value at the same time phase to obtain a reflectivity difference value;
and selecting the first x minimum reflectivity difference values from the lookup table, and averaging the corresponding x groups of biochemical parameter data to obtain first inverted biochemical parameter data, wherein x is a positive integer not less than 1.
4. The method for predicting the maturity of crops as claimed in claim 3, wherein the time series harmonic analysis of the first biochemical parameter data to obtain the biochemical parameter variation curve comprises:
uniformly resampling the first biochemical parameter data of each time phase, and stacking the data according to a time sequence to obtain time sequence biochemical parameter data;
and performing time series harmonic analysis processing on the time series biochemical parameter data to obtain continuous time series biochemical parameter data and a biochemical parameter change curve.
5. The method for predicting the maturity of crops according to claim 4, wherein the obtaining of the second biochemical parameter data and the time-series harmonic analysis of the second biochemical parameter data to obtain the standard biochemical parameter variation curve reference library comprises:
acquiring second biochemical parameter data observed on the ground, wherein the second biochemical parameter data comprises a plurality of groups of time sequence biochemical parameter data with different growth periods;
respectively carrying out time sequence harmonic analysis processing on the biochemical parameter data of each group of time sequences to obtain a standard biochemical parameter change curve of each growth period;
and summarizing the standard biochemical parameter change curves of all growth periods to obtain a standard biochemical parameter change curve reference library.
6. The method of claim 5, wherein the selecting an optimal reference curve matching the biochemical parameter variation curve within the standard biochemical parameter variation curve reference library to predict the maturity of the crop comprises:
selecting an optimal reference curve with the highest similarity from the biochemical parameter change curve reference library according to the biochemical parameter change curve, and calculating the reference cumulant of the biochemical parameter according to the optimal reference curve;
and calculating the current biochemical parameter cumulant of the crops according to the biochemical parameter change curve, and calculating the time required by the biochemical parameter cumulant to reach the reference cumulant level so as to predict the maturity stage of the crops.
7. The method of crop maturity prediction of claim 5, wherein the time series harmonic analysis comprises:
generating a least square fitting curve according to the discrete time sequence biochemical parameter data, comparing the time sequence biochemical parameter data with the fitting curve, and eliminating the biochemical parameter data with the deviation exceeding a preset threshold value;
based on the remaining biochemical parameter data, repeating the steps of generating a least square fitting curve and removing the biochemical parameter data with deviation exceeding a preset threshold value until all biochemical parameter data values and the deviation of the fitting curve do not exceed a threshold value range, so as to obtain a biochemical parameter change curve;
and acquiring continuous time sequence biochemical parameter data with specific time resolution according to the biochemical parameter change curve.
8. A crop maturity prediction apparatus, comprising:
a preprocessing module: the remote sensing image data acquisition module is used for acquiring remote sensing image data, carrying out image preprocessing on the remote sensing image data to obtain an actual reflectance value, wherein the remote sensing image data comprises sentinel No. 2 image data and land satellite 8 image data;
an inversion analysis module: the system is used for carrying out biochemical parameter inversion according to the actual reflectance value to obtain first biochemical parameter data, and carrying out time series harmonic analysis on the first biochemical parameter data to obtain a biochemical parameter change curve;
a reference prediction module: the system is used for acquiring second biochemical parameter data, performing time series harmonic analysis on the second biochemical parameter data to obtain a standard biochemical parameter change curve reference library, and selecting an optimal reference curve matched with the biochemical parameter change curve in the standard biochemical parameter change curve reference library range to predict the crop maturity stage.
9. An electronic device comprising a memory and a processor, the memory storing one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement a method of crop maturity prediction as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of crop maturity prediction according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310263635.XA CN115983503A (en) | 2023-03-18 | 2023-03-18 | Crop maturity prediction method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310263635.XA CN115983503A (en) | 2023-03-18 | 2023-03-18 | Crop maturity prediction method, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115983503A true CN115983503A (en) | 2023-04-18 |
Family
ID=85968493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310263635.XA Pending CN115983503A (en) | 2023-03-18 | 2023-03-18 | Crop maturity prediction method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983503A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008079549A (en) * | 2006-09-28 | 2008-04-10 | Mitsubishi Paper Mills Ltd | Method for evaluating tree growth |
| CN102878957A (en) * | 2012-09-26 | 2013-01-16 | 安徽大学 | Leaf area index and chlorophyll content inversion method based on remote sensing image optimization PROSAIL model parameters |
| CN103345707A (en) * | 2013-06-04 | 2013-10-09 | 中国科学院遥感与数字地球研究所 | Crop maturation stage remote sensing prediction method based on multi-source remote sensing data |
| CN110390287A (en) * | 2019-07-17 | 2019-10-29 | 中科光启空间信息技术有限公司 | A kind of crop maturity phase prediction technique based on satellite remote sensing |
| CN111582554A (en) * | 2020-04-17 | 2020-08-25 | 北京农业信息技术研究中心 | Crop growth prediction method and system |
| CN111931988A (en) * | 2020-07-09 | 2020-11-13 | 黑龙江省农业科学院农业遥感与信息研究所 | Rice maturity period prediction method combining remote sensing image, crop model and weather forecast |
| CN112101681A (en) * | 2020-09-25 | 2020-12-18 | 北京师范大学 | Method for monitoring winter wheat dry and hot wind disasters based on remote sensing NDPI time sequence |
| CN113673366A (en) * | 2021-07-29 | 2021-11-19 | 长光卫星技术有限公司 | Crop growth monitoring method based on remote sensing inversion |
| CN113850139A (en) * | 2021-08-25 | 2021-12-28 | 南京林业大学 | Multi-source remote sensing-based forest annual phenological monitoring method |
| CN114663489A (en) * | 2022-03-24 | 2022-06-24 | 广州大学 | Crop leaf area index remote sensing inversion method and system under constraint of space-time characteristics of land blocks |
| CN114973012A (en) * | 2022-05-20 | 2022-08-30 | 四川航天神坤科技有限公司 | Cultivated land identification method and system of medium-low resolution remote sensing data |
| CN115062863A (en) * | 2022-07-13 | 2022-09-16 | 中国农业科学院农业资源与农业区划研究所 | Apple flowering phase prediction method based on crop reference curve and accumulated temperature correction |
-
2023
- 2023-03-18 CN CN202310263635.XA patent/CN115983503A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008079549A (en) * | 2006-09-28 | 2008-04-10 | Mitsubishi Paper Mills Ltd | Method for evaluating tree growth |
| CN102878957A (en) * | 2012-09-26 | 2013-01-16 | 安徽大学 | Leaf area index and chlorophyll content inversion method based on remote sensing image optimization PROSAIL model parameters |
| CN103345707A (en) * | 2013-06-04 | 2013-10-09 | 中国科学院遥感与数字地球研究所 | Crop maturation stage remote sensing prediction method based on multi-source remote sensing data |
| CN110390287A (en) * | 2019-07-17 | 2019-10-29 | 中科光启空间信息技术有限公司 | A kind of crop maturity phase prediction technique based on satellite remote sensing |
| CN111582554A (en) * | 2020-04-17 | 2020-08-25 | 北京农业信息技术研究中心 | Crop growth prediction method and system |
| CN111931988A (en) * | 2020-07-09 | 2020-11-13 | 黑龙江省农业科学院农业遥感与信息研究所 | Rice maturity period prediction method combining remote sensing image, crop model and weather forecast |
| CN112101681A (en) * | 2020-09-25 | 2020-12-18 | 北京师范大学 | Method for monitoring winter wheat dry and hot wind disasters based on remote sensing NDPI time sequence |
| CN113673366A (en) * | 2021-07-29 | 2021-11-19 | 长光卫星技术有限公司 | Crop growth monitoring method based on remote sensing inversion |
| CN113850139A (en) * | 2021-08-25 | 2021-12-28 | 南京林业大学 | Multi-source remote sensing-based forest annual phenological monitoring method |
| CN114663489A (en) * | 2022-03-24 | 2022-06-24 | 广州大学 | Crop leaf area index remote sensing inversion method and system under constraint of space-time characteristics of land blocks |
| CN114973012A (en) * | 2022-05-20 | 2022-08-30 | 四川航天神坤科技有限公司 | Cultivated land identification method and system of medium-low resolution remote sensing data |
| CN115062863A (en) * | 2022-07-13 | 2022-09-16 | 中国农业科学院农业资源与农业区划研究所 | Apple flowering phase prediction method based on crop reference curve and accumulated temperature correction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luo et al. | ChinaCropPhen1km: a high-resolution crop phenological dataset for three staple crops in China during 2000–2015 based on leaf area index (LAI) products | |
| CN111598019B (en) | Crop type and planting mode identification method based on multi-source remote sensing data | |
| Huang et al. | Assimilating a synthetic Kalman filter leaf area index series into the WOFOST model to improve regional winter wheat yield estimation | |
| Meng et al. | Generation of high spatial and temporal resolution NDVI and its application in crop biomass estimation | |
| Waldner et al. | High temporal resolution of leaf area data improves empirical estimation of grain yield | |
| CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
| Choudhary et al. | Agriculture phenology monitoring using NDVI time series based on remote sensing satellites: a case study of Guangdong, China | |
| Zhang et al. | Estimating wheat yield by integrating the WheatGrow and PROSAIL models | |
| CN110687053B (en) | Regional organic matter content estimation method and device based on hyperspectral image | |
| CN109711102A (en) | A kind of crop casualty loss fast evaluation method | |
| CN109211791B (en) | Crop growth monitoring method and system | |
| CN111829957A (en) | System and method for inverting moisture content of winter wheat plants based on multispectral remote sensing of unmanned aerial vehicle | |
| CN107122739A (en) | The agricultural output assessment model of VI time-serial positions is reconstructed based on Extreme mathematical modelings | |
| Wenwen et al. | High spatial-and temporal-resolution NDVI produced by the assimilation of MODIS and HJ-1 data | |
| Li et al. | Precise identification of maize in the North China Plain based on Sentinel-1A SAR time series data | |
| Qiao et al. | Estimating maize LAI by exploring deep features of vegetation index map from UAV multispectral images | |
| Pang et al. | Pixel-level rice planting information monitoring in Fujin City based on time-series SAR imagery | |
| CN114882359B (en) | Soybean planting area extraction method and system based on vegetation index time series spectrum characteristics | |
| CN113534083B (en) | SAR-based corn stubble mode identification method, device and medium | |
| Zahran et al. | Remote sensing based water resources and agriculture spatial indicators system | |
| Hu et al. | Detecting regional GPP variations with statistically downscaled solar-induced chlorophyll fluorescence (SIF) based on GOME-2 and MODIS data | |
| Zhao et al. | Should phenological information be applied to predict agronomic traits across growth stages of winter wheat? | |
| Eugene et al. | Rice modeling using long time series of high temporal resolution vegetation indices in Nepal | |
| CN115983503A (en) | Crop maturity prediction method, equipment and storage medium | |
| CN115496999A (en) | Method and device for estimating field straw yield |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230418 |