CN115018105A - Winter wheat meteorological yield prediction method and system - Google Patents
Winter wheat meteorological yield prediction method and system Download PDFInfo
- Publication number
- CN115018105A CN115018105A CN202110237189.6A CN202110237189A CN115018105A CN 115018105 A CN115018105 A CN 115018105A CN 202110237189 A CN202110237189 A CN 202110237189A CN 115018105 A CN115018105 A CN 115018105A
- Authority
- CN
- China
- Prior art keywords
- winter wheat
- meteorological
- wofost
- remote sensing
- yield
- 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
- 241000209140 Triticum Species 0.000 title claims abstract description 187
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000011160 research Methods 0.000 claims abstract description 47
- 230000007613 environmental effect Effects 0.000 claims abstract description 23
- 238000007726 management method Methods 0.000 claims description 24
- 238000004519 manufacturing process Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 14
- 230000004069 differentiation Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 101000583150 Homo sapiens Membrane-associated phosphatidylinositol transfer protein 3 Proteins 0.000 claims description 9
- 102100030351 Membrane-associated phosphatidylinositol transfer protein 3 Human genes 0.000 claims description 9
- DZSYJVXGONVNKA-UHFFFAOYSA-L NIR-1 dye Chemical compound [K+].[K+].C1=CC2=C(S([O-])(=O)=O)C=C(S([O-])(=O)=O)C=C2C(C2(C)C)=C1[N+](CC)=C2C=CC=CC=CC=C1C(C)(C)C2=CC(C(O)=O)=CC=C2N1CCCCS([O-])(=O)=O DZSYJVXGONVNKA-UHFFFAOYSA-L 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 101000583145 Homo sapiens Membrane-associated phosphatidylinositol transfer protein 1 Proteins 0.000 claims description 6
- 102100030353 Membrane-associated phosphatidylinositol transfer protein 1 Human genes 0.000 claims description 6
- AUQMGYLQQPSCNH-UHFFFAOYSA-L NIR-2 dye Chemical compound [K+].[K+].C1=CC2=C(S([O-])(=O)=O)C=C(S([O-])(=O)=O)C=C2C(C2(C)C)=C1[N+](CC)=C2C=CC=CC=C1C(C)(C)C2=CC(C(O)=O)=CC=C2N1CCCCS([O-])(=O)=O AUQMGYLQQPSCNH-UHFFFAOYSA-L 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 230000007787 long-term memory Effects 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 4
- 230000004807 localization Effects 0.000 claims description 4
- 230000006403 short-term memory Effects 0.000 claims description 4
- 238000013277 forecasting method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 11
- 238000012795 verification Methods 0.000 description 8
- 230000001766 physiological effect Effects 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 239000002689 soil Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- 208000036855 Left sided atrial isomerism Diseases 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004069 plant analysis Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Mining & Mineral Resources (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Marine Sciences & Fisheries (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for predicting meteorological output of winter wheat, wherein the method comprises the following steps: performing band operation on the winter wheat MODIS remote sensing data based on a preset time sequence to obtain the MODIS remote sensing information characteristics of a winter wheat target research area; dividing time periods according to a preset time sequence, collecting environmental data and management data of the winter wheat target research area, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods; and inputting the MODIS remote sensing data and the WOFOST analog quantity characteristics into a trained winter wheat meteorological output prediction model to obtain a winter wheat meteorological output prediction result. According to the method, the analog quantity from the node-elongation period to the heading period of the WOFOST crop model is added, the yield prediction model fusing WOFOST and LSTM is constructed, and the yield prediction effect is improved.
Description
Technical Field
The invention relates to the technical field of agricultural remote sensing, in particular to a winter wheat meteorological output prediction method and system.
Background
In recent years, the wheat yield problem is widely concerned by society, the growth process information of wheat is effectively grasped, the yield is predicted, and the method has important significance for adjusting the wheat planting structure and making agricultural decisions of relevant departments.
The remote sensing data has the advantages of high resolution, low cost, wide area coverage and the like, and is applied to yield prediction research, and many researches resample the remote sensing data to a monthly scale and adopt different types of remote sensing data to predict crop yield. In addition, deep learning occupies an important role in artificial intelligence, and the method has high feature analysis capability by setting a complex network, is high in speed and precision, and has obvious advantages in processing multidimensional features.
With the continuous development of remote sensing data and deep learning, researchers at home and abroad can predict the crop yield by combining the remote sensing data and the deep learning. Many researches bring remote sensing data of different crop growth periods, different growth period combinations, histograms and other modes into a deep learning yield prediction model, however, the deep learning effect depends on characteristic samples, and the characteristic samples are easily influenced by the growth environments of crops in different periods, so that the prediction effect on the crop yield is not accurate enough. Therefore, there is a need for a method and system for predicting meteorological output of winter wheat to solve the above problems.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for predicting meteorological output of winter wheat.
The invention provides a winter wheat meteorological output prediction method, which comprises the following steps:
performing band operation on the winter wheat MODIS remote sensing data based on a preset time sequence to obtain the MODIS remote sensing information characteristics of a winter wheat target research area;
dividing time periods according to the preset time sequence, collecting environmental data and management data of the winter wheat target research area, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods;
and inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a yield prediction result of the winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through sample MODIS remote sensing information characteristics, sample WOFOST analog quantity characteristics and sample meteorological yield characteristics.
According to the winter wheat meteorological output prediction method provided by the invention, the trained winter wheat meteorological output prediction model is obtained by training through the following steps:
performing band operation on MODIS remote sensing data based on a preset time sequence to obtain a normalized vegetation index and a normalized vegetation moisture index, drawing a frequency histogram, obtaining a frequency value of the frequency histogram, and constructing a sample MODIS remote sensing information characteristic;
dividing time periods according to the preset time sequence, extracting and obtaining the WOFOST analog quantity of each ear differentiation period from the elongation to the heading period of the winter wheat corresponding to each time period, and constructing sample WOFOST analog quantity characteristics, wherein the sample WOFOST analog quantity characteristics comprise crop growth process, leaf area index, dry matter quantity and physiological action characteristics;
constructing sample meteorological output characteristics according to the meteorological output data;
inputting the sample MODIS remote sensing information characteristics, the sample WOFOST analog quantity characteristics and the sample meteorological output characteristics into a winter wheat meteorological output prediction model for training to obtain a trained winter wheat meteorological output prediction model.
According to the winter wheat meteorological output forecasting method provided by the invention, the sample meteorological output characteristics are constructed according to the meteorological output data, and the method comprises the following steps:
according to a 5a moving average method, trend removing processing is carried out on the actual single-yield sample data of the winter wheat to obtain a trend yield;
and acquiring meteorological yield data according to the difference between the actual single-yield sample data and the trend yield, and constructing sample meteorological yield characteristics.
According to the winter wheat meteorological output prediction method provided by the invention, before the time periods are divided according to the preset time sequence, the environmental data and the management data of the target research area of the winter wheat are collected and input into the WOFOST model, and the WOFOST analog quantity characteristics of the growth period of the winter wheat in different time periods are acquired, the method further comprises the following steps: and carrying out localization calibration on the WOFOST model.
According to the method for predicting the meteorological yield of the winter wheat, the long and short term memory neural network comprises 1 input layer, 5 hidden layers, 1 full-connection layer and 1 output layer, wherein the input layer is used for standardizing data through centralization and converting the data into standard normal distribution.
According to the method for predicting the meteorological output of the winter wheat, provided by the invention, before the band operation is carried out on the MODIS remote sensing data of the winter wheat based on the preset time sequence, the method further comprises the following steps:
and carrying out mosaic, projection and cutting processing on the winter wheat MODIS remote sensing data based on the preset time sequence.
According to the winter wheat meteorological output prediction method provided by the invention, the band operation is carried out on MODIS remote sensing data based on a preset time sequence to obtain a normalized vegetation index and a normalized vegetation moisture index, and the method comprises the following steps:
obtaining a normalized vegetation index according to a pixel value of a near infrared band 1 and a pixel value of a red light band in MOD09A1, wherein the formula is as follows:
NDVI＝(NIR1-R)/(NIR1+R)；
obtaining a normalized vegetation moisture index according to a pixel value of a near infrared waveband 1 and a pixel value of a near red waveband 2 in MOD09A1, wherein the formula is as follows:
NDWI＝(NIR1-NIR2)/(NIR1+NIR2)；
wherein NDVI represents a normalized vegetation index and NDWI represents a normalized vegetation moisture index; r represents the pixel value of the red light wave band and corresponds to the 1 st wave band original effective value of MOD09A 1; NIR1 represents the pixel value of the near infrared band 1, corresponding to the original effective value of MOD09a1 band 2; NIR2 represents the pixel value of the near infrared band 2, corresponding to the original valid value of MOD09a1 band 5.
The invention also provides a winter wheat meteorological output prediction system, which comprises:
the remote sensing information characteristic acquisition module is used for carrying out band operation on winter wheat MODIS remote sensing data based on a preset time sequence to acquire MODIS remote sensing information characteristics of a winter wheat target research area;
the analog quantity characteristic acquisition module is used for dividing time periods according to the preset time sequence, acquiring environmental data and management data of the target research area of the winter wheat, inputting the environmental data and the management data into a WOFOST model and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods;
and the meteorological yield prediction module is used for inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a yield prediction result of the winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through sample MODIS remote sensing information characteristics, sample WOFOST analog quantity characteristics and sample meteorological yield characteristics.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the method for predicting the meteorological yield of the winter wheat.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for winter wheat meteorological production prediction as described in any one of the above.
According to the method and the system for predicting the meteorological yield of the winter wheat, MODIS remote sensing information characteristics of a target research area of the winter wheat are obtained by performing band operation on MODIS remote sensing data of the winter wheat, WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods are obtained by utilizing a WOFOST model, then the MODIS remote sensing data and the WOFOST analog quantity characteristics are input into a trained winter wheat meteorological yield prediction model, and a meteorological yield prediction result of the target research area of the winter wheat is obtained.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a winter wheat meteorological output prediction method provided by the invention;
FIG. 2 is a schematic diagram of a prediction result of a winter wheat meteorological output prediction model provided by the invention, in which a combination of a crop growth process, a total dry matter weight and a physiological effect analog quantity is used as a characteristic variable;
FIG. 3 is a schematic diagram showing the comparison of the results of the winter wheat meteorological output prediction model provided by the invention in different temperature ranges and without adding WOFOST analog quantity;
FIG. 4 is a schematic diagram of an LSTM structure in a winter wheat meteorological yield prediction model provided by the invention;
FIG. 5 is a schematic diagram of a winter wheat meteorological output prediction system according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow diagram of a winter wheat meteorological yield prediction method provided by the present invention, and as shown in fig. 1, the present invention provides a winter wheat meteorological yield prediction method, which includes:
step 101, performing band operation on winter wheat MODIS remote sensing data based on a preset time sequence to obtain MODIS remote sensing information characteristics of a winter wheat target research area;
In the invention, in step 101, remote sensing data of a resolution Imaging spectrometer (MODIS) in the winter wheat at different growth stages are obtained, band operation is carried out on the MODIS remote sensing data of the winter wheat according to a time sequence order to obtain a required Normalized Vegetation Index (NDVI) and a required Normalized Vegetation Water Index (NDWI), and a frequency histogram is drawn to obtain MODIS remote sensing information characteristics of a target research area of the winter wheat. Optionally, the order according to the time sequence is that according to the growth stage of the winter wheat from the jointing stage to the heading stage, the MODIS remote sensing data synthesized in 8 days are arranged in sequence according to time.
Further, in step 102, the preset time sequence is divided into a plurality of time periods, each time period corresponds to each ear differentiation period of the winter wheat, crop, soil, weather and management data are used as input data of a World Food research (wobest) crop model, and wobest analog quantity characteristics of the winter wheat in growth periods in different time periods are obtained.
The system comprises a plurality of sets of soil data, a plurality of sets of simulation data and a plurality of sets of weather data, wherein the crop data comprise selected simulated crop varieties, the soil data comprise soil types and set related soil hydrological characteristics, and the weather data comprise data such as weather data formats, available sites, rainfall, temperature and the like; the management data is the starting time of the crop simulation, the ending time of the crop simulation, and the maximum duration of the crop cycle.
Further, in step 103, combining the image histogram frequency value of the MODIS remote sensing information features and the WOFOST multi-type analog quantity features, inputting the combined value as a feature variable into a winter wheat meteorological output prediction model, and predicting through the trained winter wheat meteorological output prediction model to obtain an output prediction result of the winter wheat target research area. The winter wheat meteorological yield prediction model is a Long Short-term Memory network (LSTM) model.
The winter wheat meteorological yield prediction method provided by the invention comprises the steps of carrying out wave band operation on winter wheat MODIS remote sensing data to obtain MODIS remote sensing information characteristics of a winter wheat target research area, obtaining WOFOST analog quantity characteristics of winter wheat growth periods in different time periods by utilizing a WOFOST model, inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a meteorological yield prediction result of the winter wheat target research area.
On the basis of the embodiment, the trained winter wheat meteorological output prediction model is obtained by training through the following steps:
step 202, dividing time periods according to the preset time sequence, extracting and obtaining WOFOST analog quantity of each ear differentiation period from the elongation to the heading of the winter wheat corresponding to each time period, and constructing sample WOFOST analog quantity characteristics, wherein the sample WOFOST analog quantity characteristics comprise crop growth process, leaf area index, dry matter quantity and physiological action characteristics;
step 203, constructing sample meteorological output characteristics according to the meteorological output data;
and 204, inputting the sample MODIS remote sensing information characteristics, the sample WOFOST analog quantity characteristics and the sample meteorological yield characteristics into a winter wheat meteorological yield prediction model for training to obtain a trained winter wheat meteorological yield prediction model.
In the invention, in step 201, MOD09A1 product with the resolution of 500m, which is obtained from LAADS Web, is obtained to synthesize MODIS remote sensing data in 8 days from the joint in 2017 to the heading date. The method comprises the following steps of carrying out band operation on MODIS remote sensing data synthesized in 8 days from the jointing stage to the heading stage of winter wheat to obtain a normalized vegetation index and a normalized vegetation moisture index, and specifically comprises the following steps:
obtaining a normalized vegetation index according to the pixel value of the near-infrared band 1 and the pixel value of the red light band in MOD09A1, wherein the formula is as follows:
NDVI＝(NIR1-R)/(NIR1+R)；
obtaining a normalized vegetation moisture index according to a pixel value of a near infrared waveband 1 and a pixel value of a near red waveband 2 in MOD09A1, wherein the formula is as follows:
NDWI＝(NIR1-NIR2)/(NIR1+NIR2)；
wherein NDVI represents a normalized vegetation index and NDWI represents a normalized vegetation moisture index; MOD09A1 represents a data product providing a 500m resolution of 8 days synthesis of bands 1-7 for estimating surface spectral reflectance of the area of interest; r represents the pixel value of the red light wave band and corresponds to the 1 st wave band original effective value of MOD09A 1; NIR1 denotes a pixel value of the near infrared band 1, corresponding to the 2 nd band raw effective value of MOD09a 1; NIR2 denotes a pixel value of the near infrared band 2, corresponding to the original valid value of MOD09a1 at 5 th band.
Furthermore, in order to solve the problem that the shapes and the ranges of winter wheat planting areas in different counties are inconsistent, the pixel values of remote sensing images in the counties are counted in a frequency histogram mode. Statistics shows that the NDVI is between 0 and 1, the NDWI is between-0.25 and 0.25, the NDVI in 7 time periods from the jointing stage to the heading stage is divided into 5 intervals according to 0.2, the NDWI is divided into 5 intervals according to 0.1, frequency values of the intervals generated by each image histogram are selected as characteristic values, 70 characteristic variables are counted, and the construction of the MODIS remote sensing information sample characteristics is completed.
In the invention, in step 202, in order to match with MODIS remote sensing data synthesized in 8 days, 8 days obtained in the step S1 from the heading to heading stage are divided into 7 time periods, each time period corresponds to each ear differentiation stage, and wopit analog quantities of each ear differentiation stage from the heading to heading stage are extracted, which are mainly divided into four aspects: and (4) completing construction of WOFOST simulation information sample characteristics by crop growth process, leaf area index, dry matter weight and physiological action.
Wherein, the average stage from the jointing stage to the heading stage of winter wheat which is easy to be frosted later in Henan province from 3 months 14 to 5 months 8 days is selected, the stage from the jointing stage to the heading stage is divided into 7 time periods by taking 8 days as a unit, and each time period corresponds to each heading differentiation stage, as shown in Table 1:
TABLE 1
| Time period | Date | Stage of ear differentiation |
| 1 | 3/14-3/21 | Early stage of floret differentiation |
| 2 | 3/22-3/29 | Late stage of floret differentiation |
| 3 | 3/30-4/6 | Differentiation stage of male and female stamens |
| 4 | 4/7-4/14 | At the early stage of drug septum |
| 5 | 4/15-4/22 | Late stage of drug compartment |
| 6 | 4/23-4/30 | Tetrad period |
| 7 | 5/1-5/8 | Heading and flowering period |
In the present invention, the yield of the crop is formed under the combined influence of various natural and unnatural factors, and the actual yield of the crop is generally decomposed into a trend yield, a meteorological yield and a random yield in step 203. The corresponding yield component is called meteorological yield, due to fluctuations in crop yield caused by inter-annual meteorological conditions. And selecting meteorological output data of 2004-2017 for a plurality of years to construct sample meteorological output characteristics.
In the invention, in step 204, the frequency values of the image histogram obtained in step 201 are respectively used as characteristic variables with the crop growth process, leaf area index, dry matter weight and physiological action related variables of 7 ear differentiation periods obtained in step 202, the meteorological output obtained in step 203 is used as a target variable, an LSTM meteorological output prediction model is constructed, and the LSTM meteorological output prediction model is compared with the result only using remote sensing information.
Wherein, the model takes 2004-2014 as training data and 2015-2017 as verification data. By the use of R 2 And 3 indexes of RMSE and MAE are used as evaluation indexes of the meteorological yield prediction accuracy of the winter wheat in Henan: 1) r2 is used as a criterion for evaluating the correlation between predicted and measured values of a model, R 2 The closer to 1, the better the independent variable in the model is interpreted to the dependent variable; 2) the RMSE is used for evaluating the concentration degree of the samples, and the closer the RMSE is to 0, the higher the concentration degree of the samples is; 3) the MAE is used as a criterion for evaluating the error between the predicted value and the measured value, and the more the MAE is close to 0, the higher the accuracy of the estimation result is. The specific formula is as follows:
wherein X i Is a measured value of Y i In order to predict the value of the target,
is the measured average value of the measured values,
to predict the mean, N is the number of observed samples.
The WOFOST analog partitioning and accuracy comparison are shown in the attached table 2:
TABLE 2
As can be seen from table 2, the model constructed using the combination of DVS, total dry matter weight, and physiological effect analog was the most accurate. Model R using only remote sensing information 2 Reaching 0.707, RMSE reaching 765.452kg/ha, MAE reaching 588.977 kg/ha; model R constructed using DVS 2 Reaching 0.758, RMSE reaching 702.565kg/ha, MAE reaching 537.788 kg/ha; model R reconstructed using Total Dry matter 2 Reaching 0.754, RMSE reaching 743.953kg/ha, MAE reaching 553.239 kg/ha; model R constructed using a combination of physiological effect analog quantities 2 To 0.762, RMSE to 706.099kg/ha and MAE to 529.092 kg/ha.
Further, a multi-type analog quantity combination composed of a crop growth process with high precision, the total dry matter weight and the physiological effect analog quantity combination is selected as a characteristic variable, the frequency value of an image histogram is combined, the meteorological output is used as a target variable, an LSTM meteorological output prediction model is constructed, and comparison is carried out with comparison only by using remote sensing information. The model takes 2004-2014 as training data and 2015-2017 as verification data. By the use of R 2 RMSE and MAE were precision rated.
FIG. 2 is a diagram showing the prediction results of a winter wheat meteorological output prediction model provided by the invention, in which a multi-type analog quantity combination composed of a crop growth process, a total dry matter weight and a physiological effect analog quantity combination is used as a characteristic variable. As shown in (a) of FIG. 2, a model R of a combination of multiple types of analog quantities 2 Reaches 0.773, RMSE reaches 709.278kg/ha, MAE reaches 531.324kg/ha, and compared with the R in figure 2 (b), which only uses RS as the characteristic variable and adopts a plurality of types of analog quantity combinations consisting of the combinations of the growth process of the crops, the total dry matter weight and the physiological effect analog quantity as the characteristic variable 2 The method has the advantages that both the RMSE and the MAE are improved, and accordingly the prediction accuracy of the winter wheat meteorological output prediction model is improved.
Further, based on the above accuracyThe high multi-type analog quantity combined model is used for analyzing the capability of predicting the yield of the winter wheat in different lowest temperature intervals, comparing the capability with the result only using remote sensing data, and adopting R 2 RMSE and MAE were precision rated. The specific method comprises the following steps:
and extracting 300 verification samples in total in 2015-2017 from an LSTM yield model constructed by fusing frequency values of the multi-type analog quantity combination and the image histogram. The lowest air temperature from the average jointing to the heading stage in Henan province is taken as an index, and the lowest air temperature is divided into 3 intervals according to the index of frost damage level of winter wheat in crop frost damage levels (QX/T88-2008) in the meteorological industry standard of the people's republic of China and in consideration of the balance of distribution of verification samples: and (3) less than-1 ℃, less than (-1 ℃, 0 ℃) and less than (0 ℃, 2 ℃), wherein the total number of 120 verification samples in the range of less than-1 ℃, the total number of 94 verification samples in the range of (-1 ℃, 0 ℃), and the total number of 86 verification samples in the range of (0 ℃, 2 ℃), and the accuracy of the winter wheat meteorological yield prediction model for yield prediction under the influence of late frost freezing is evaluated according to the verification samples in different ranges, and is compared with the result without WOFOST analog quantity.
FIG. 3 is a schematic diagram showing the comparison of the results of the winter wheat meteorological yield prediction model provided by the invention in different temperature ranges and without adding WOFOST analog quantity. As shown in FIG. 3, R of the model added with WOFOST analog in the range of less than-1 deg.C 2 Reaching 0.839, RMSE reaching 626.013kg/ha, MAE reaching 450.124 kg/ha; at (-1 deg.C, 0 deg.C)]Model R of 2 Reaching 0.717, RMSE reaching 767.957kg/ha, MAE reaching 554.500 kg/ha; at (0 ℃, 2℃)]Model R of 2 Reaching 0.722, RMSE reaching 750.645kg/ha, MAE reaching 619.295 kg/ha; model R at a temperature of less than-1 deg.C 2 The yield prediction accuracy of the model is higher and the sensitivity is stronger in the range of less than-1 ℃, and the meteorological yield prediction model of the winter wheat can effectively monitor the yield of the winter wheat under the influence of late frost.
On the basis of the above embodiment, the constructing the sample meteorological production characteristics according to the meteorological production data includes:
according to a 5a moving average method, trend removing processing is carried out on the actual single-yield sample data of the winter wheat to obtain a trend yield;
and acquiring meteorological yield data according to the difference between the actual single-yield sample data and the trend yield, and constructing sample meteorological yield characteristics.
In particular, the actual yield per unit of a crop includes meteorological yield, trending yield, and random yield. The weather yield refers to the yield influenced by the change of weather and climate and has the characteristic of pulsation; the trend yield represents the yield caused by social development and technological innovation; random yield refers to yield changes due to random factors of earthquakes and social transformations. The method adopts a 5a moving average method to perform trend removing processing on actual single-yield sample data to obtain the trend yield, and obtains the meteorological yield according to a yield calculation formula. The specific formula is as follows:
y＝y t +y c +e；
wherein y is the actual yield, y t To trend yield, y c For meteorological production, e is random production.
Random yield is not included in the equation because random yield is essentially irregular, and is ignored in the present invention. Therefore, the difference between the actual single-yield sample data and the trend yield is calculated, and the meteorological yield data can be obtained.
On the basis of the above embodiment, before the time slots are divided according to the preset time sequence, the environmental data and the management data of the target research area of the winter wheat are collected and input into the wobest model, and the wobest analog quantity characteristics of the growth period of the winter wheat in different time slots are acquired, the method further comprises: and carrying out localization calibration on the WOFOST model.
In the invention, crop, soil, weather and management data in 2017 of 2004-plus in a winter wheat research area are collected as input data of a WOFOST model, and the weather data in 2017 of 2004-plus are acquired from an NASA (national institute of advanced technology for plant analysis) website and comprise the lowest air temperature, total radiation, the highest air temperature, wind speed, water vapor pressure and precipitation. In order to achieve better simulation effect, the model is locally calibrated, and the WOFOST model is simulated.
The parameters TSUMEM, TSUM1 and TSUM2 in the WOFOST model are calculated according to the data of the multiple-year development period of each site and the data of the air temperature and are obtained by model calibration and adjustment; LAIEM and SPAN affect the initial growth and progression of LAI, and thus the light interception rate, as determined by reviewing the literature and through model calibration, and the final localization parameter values for TSUMEM, TSUM1, TSUM2, LAIEM, and SPAN are 120.5 (c. ad-1), 1480.3 (c. ad-1), 704.2 (c. ad-1), 0.131, and 35.0(d), respectively.
By carrying out localized calibration on the WOFOST model, the model is more suitable for the local climatic environment situation, thereby better realizing the effect of dynamically simulating the growth and development process of crops.
On the basis of the above embodiment, the long and short term memory neural network includes 1 input layer, 5 hidden layers, 1 fully-connected layer, and 1 output layer, where the input layer normalizes data by centralization, and converts the data into standard normal distribution.
FIG. 4 is a schematic diagram of an LSTM structure in the winter wheat meteorological yield prediction model provided by the invention. As shown in FIG. 4, in the present invention, LSTM was chosen to build a winter wheat meteorological yield prediction model. The structure includes: 1 input layer, 5 hidden layers, 1 fully connected layer and 1 output layer. The input layer mainly comprises two parts of remote sensing information and WOFOST simulation information, because input data are more and complicated, standardization processing is needed, and the data are converted into standard normal distribution in a centralized mode to avoid the influence of abnormal values on the model. The specific formula is as follows:
where μ denotes the mean of the training samples and s denotes the standard deviation.
A hidden layer is connected behind the input layer, so that the time sequence information from the jointing of the winter wheat to the heading stage can be learned, and Dropout for removing the network unit according to the ratio is added in the hidden layer to avoid overfitting; finally, combining the learned information characteristics through a full connection layer and outputting the combined information characteristics to a 1-dimensional space to obtain a prediction result of an output layer; in order to increase the convergence rate of the model, the model is optimized by using a Stochastic Gradient Descent (SGD) method. According to multiple tests and tuning, the final super-parameters of the model are set as follows: the number of samples taken for one training is 50, the ratio of neural network elements removed is 0.2, the learning rate is 0.01, and the number of single training iterations for all batches in the forward and backward propagation is 700.
The input remote sensing information characteristics and WOFOST analog quantity characteristics are processed and analyzed through the LSTM model, the speed of processing the multidimensional characteristics is increased, the model is optimized according to a random gradient descent method, the convergence speed of the winter wheat meteorological output prediction model can be increased, and therefore the prediction accuracy of the winter wheat meteorological output prediction model is effectively improved.
On the basis of the above embodiment, before performing the band operation on the winter wheat MODIS remote sensing data based on the preset time sequence, the method further includes:
and carrying out mosaic, projection and cutting processing on the winter wheat MODIS remote sensing data based on the preset time sequence.
In the invention, the remote sensing data of the winter wheat MODIS are subjected to mosaic processing, images of more than two scenes are seamlessly spliced to form a complete target area, and the transparency and the feathering radius of the remote sensing data image are changed, so that the mosaic places of the images are better fused;
carrying out projection processing on the winter wheat MODIS remote sensing data, carrying out self-defined projection setting according to the remote sensing data requirements, or converting the remote sensing data into required projection information according to application requirements;
and cutting the MODIS remote sensing data of the winter wheat, reserving an image of a target research area of the winter wheat, and ensuring that the information of a cut part is rich.
By carrying out the preprocessing on the winter wheat MODIS remote sensing data, the geometric distortion and the information error of the remote sensing image caused by the factors such as the change of the attitude, the height, the speed, the atmospheric interference and the like in the remote sensing imaging process are corrected.
Fig. 5 is a schematic structural diagram of a winter wheat meteorological production prediction system provided by the present invention, and as shown in fig. 5, the present invention provides a winter wheat meteorological production prediction system, which includes a remote sensing information characteristic obtaining module 501, an analog quantity characteristic obtaining module 502, and an meteorological production prediction module 503, wherein the remote sensing information characteristic obtaining module 501 is configured to perform a band operation on winter wheat MODIS remote sensing data based on a preset time sequence, so as to obtain an MODIS remote sensing information characteristic of a winter wheat target research area; the analog quantity characteristic acquisition module 502 is used for dividing time periods according to the preset time sequence, acquiring environmental data and management data of the target research area of the winter wheat, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods; the weather yield prediction module 503 is configured to input the MODIS remote sensing information features and the WOFOST analog quantity features into a trained winter wheat weather yield prediction model, and obtain a weather yield prediction result of the winter wheat target research area, where the trained winter wheat weather yield prediction model is obtained by training a long-term memory neural network through the sample MODIS remote sensing information features, the sample WOFOST analog quantity features and the sample weather yield features.
According to the winter wheat meteorological yield prediction system, the MODIS remote sensing information characteristics of a winter wheat target research area are obtained by performing band operation on the winter wheat MODIS remote sensing data, the WOFOST analog quantity characteristics of winter wheat in the growth period in different time periods are obtained by using a WOFOST model, then the MODIS remote sensing data and the WOFOST analog quantity characteristics are input into a trained winter wheat meteorological yield prediction model, and the meteorological yield prediction result of the winter wheat target research area is obtained.
In the invention, the remote sensing information characteristic obtaining module 501 can process the historical retained data to obtain the remote sensing information characteristic variable, and can also obtain the remote sensing information characteristic variable of the research area on line in real time.
Further, the analog feature obtaining module 502 may output a single analog to the weather production prediction module 503, or may output a combination of multiple types of analog with higher precision to the weather production prediction module 503.
Furthermore, the meteorological output prediction system can also be applied to crops such as rice, corn, soybean and the like.
The system provided by the present invention is used for executing the above method embodiments, and for the specific processes and details, reference is made to the above embodiments, which are not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 6, the electronic device may include: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a winter wheat meteorological production prediction method comprising: carrying out band operation on winter wheat MODIS remote sensing data based on a preset time sequence to obtain MODIS remote sensing information characteristics of a winter wheat target research area; dividing time periods according to the preset time sequence, collecting environmental data and management data of the winter wheat target research area, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods; and inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a yield prediction result of the winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through sample MODIS remote sensing information characteristics, sample WOFOST analog quantity characteristics and sample meteorological yield characteristics.
In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method for predicting the meteorological production of winter wheat provided by the above methods, the method comprising: performing band operation on the winter wheat MODIS remote sensing data based on a preset time sequence to obtain the MODIS remote sensing information characteristics of a winter wheat target research area; dividing time periods according to the preset time sequence, collecting environmental data and management data of the winter wheat target research area, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods; and inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a yield prediction result of the winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through sample MODIS remote sensing information characteristics, sample WOFOST analog quantity characteristics and sample meteorological yield characteristics.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the above-provided weather-related winter wheat yield prediction methods, the method comprising: performing band operation on the winter wheat MODIS remote sensing data based on a preset time sequence to obtain the MODIS remote sensing information characteristics of a winter wheat target research area; dividing time periods according to the preset time sequence, collecting environmental data and management data of the winter wheat target research area, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods; and inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a yield prediction result of the winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through sample MODIS remote sensing information characteristics, sample WOFOST analog quantity characteristics and sample meteorological yield characteristics.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A winter wheat meteorological yield prediction method is characterized by comprising the following steps:
performing band operation on the winter wheat MODIS remote sensing data based on a preset time sequence to obtain the MODIS remote sensing information characteristics of a winter wheat target research area;
dividing time periods according to the preset time sequence, collecting environmental data and management data of the winter wheat target research area, inputting the environmental data and the management data into a WOFOST model, and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods;
and inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a meteorological yield prediction result of a winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through the sample MODIS remote sensing information characteristics, the sample WOFOST analog quantity characteristics and the sample meteorological yield characteristics.
2. The method for predicting meteorological yield of winter wheat as claimed in claim 1, wherein the trained meteorological yield model of winter wheat is trained by the following steps:
performing band operation on MODIS remote sensing data based on a preset time sequence to obtain a normalized vegetation index and a normalized vegetation moisture index, drawing a frequency histogram, obtaining a frequency value of the frequency histogram, and constructing a sample MODIS remote sensing information characteristic;
dividing time periods according to the preset time sequence, extracting and obtaining WOFOST analog quantity of each ear differentiation period from the elongation of the winter wheat corresponding to each time period to the heading period, and constructing sample WOFOST analog quantity characteristics, wherein the sample WOFOST analog quantity characteristics comprise crop growth process, leaf area index, dry matter quantity and physiological action characteristics;
constructing sample meteorological output characteristics according to the meteorological output data;
and inputting the sample MODIS remote sensing information characteristics, the sample WOFOST analog quantity characteristics and the sample meteorological output characteristics into a long-time memory neural network for training to obtain a trained winter wheat meteorological output prediction model.
3. The weather-meteorological production forecasting method for winter wheat as claimed in claim 2, wherein the constructing the sample weather-meteorological production characteristics according to the weather-meteorological production data comprises:
according to a 5a moving average method, trend removing processing is carried out on the actual single-yield sample data of the winter wheat to obtain a trend yield;
and acquiring meteorological yield data according to the difference between the actual single-yield sample data and the trend yield, and constructing sample meteorological yield characteristics.
4. The method for predicting meteorological production of winter wheat as claimed in claim 1, wherein before the time periods are divided according to the preset time sequence, the environmental data and the management data of the target research area of the winter wheat are collected and input into a WOFOST model, and the WOFOST analog quantity characteristics of the growth period of the winter wheat in different time periods are acquired, the method further comprises: and carrying out localization calibration on the WOFOST model.
5. The method for predicting meteorological production of winter wheat, according to claim 1, wherein the long and short term memory neural network comprises 1 input layer, 5 hidden layers, 1 fully-connected layer and 1 output layer, wherein the input layer normalizes data through centralization, and converts the data into standard normal distribution.
6. The method for predicting meteorological yield of winter wheat according to claim 1, wherein before performing band operation on winter wheat MODIS remote sensing data based on a preset time sequence, the method further comprises:
and carrying out mosaic, projection and cutting processing on the winter wheat MODIS remote sensing data based on the preset time sequence.
7. The method for predicting meteorological output of winter wheat according to claim 1, wherein the band operation is performed on MODIS remote sensing data based on a preset time sequence to obtain a normalized vegetation index and a normalized vegetation moisture index, and the method comprises the following steps:
obtaining a normalized vegetation index according to a pixel value of a near-infrared band 1 and a pixel value of a red light band in MOD09A1, wherein the formula is as follows:
NDVI＝(NIR1-R)/(NIR1+R)；
obtaining a normalized vegetation moisture index according to a pixel value of a near-infrared waveband 1 and a pixel value of a near-red waveband 2 in MOD09A1, wherein the formula is as follows:
NDWI＝(NIR1-NIR2)/(NIR1+NIR2)；
wherein NDVI represents a normalized vegetation index and NDWI represents a normalized vegetation moisture index; r represents the pixel value of the red wave band, and corresponds to the 1 st wave band original effective value of MOD09A 1; NIR1 represents the pixel value of the near infrared band 1, corresponding to the original effective value of MOD09a1 band 2; NIR2 represents the pixel value of the near infrared band 2, corresponding to the original valid value of MOD09a1 band 5.
8. A winter wheat meteorological production prediction system is characterized by comprising:
the remote sensing information characteristic acquisition module is used for carrying out band operation on winter wheat MODIS remote sensing data based on a preset time sequence to acquire MODIS remote sensing information characteristics of a winter wheat target research area;
the analog quantity characteristic acquisition module is used for dividing time periods according to the preset time sequence, acquiring environmental data and management data of the target research area of the winter wheat, inputting the environmental data and the management data into a WOFOST model and acquiring WOFOST analog quantity characteristics of the winter wheat in growth periods in different time periods;
and the meteorological yield prediction module is used for inputting the MODIS remote sensing information characteristics and the WOFOST analog quantity characteristics into a trained winter wheat meteorological yield prediction model to obtain a meteorological yield prediction result of a winter wheat target research area, wherein the trained winter wheat meteorological yield prediction model is obtained by training a long-time memory neural network through sample MODIS remote sensing information characteristics, sample WOFOST analog quantity characteristics and sample meteorological yield characteristics.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the winter wheat weather production prediction method of any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the winter wheat meteorological production prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110237189.6A CN115018105A (en) | 2021-03-03 | 2021-03-03 | Winter wheat meteorological yield prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110237189.6A CN115018105A (en) | 2021-03-03 | 2021-03-03 | Winter wheat meteorological yield prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115018105A true CN115018105A (en) | 2022-09-06 |
Family
ID=83064482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110237189.6A Pending CN115018105A (en) | 2021-03-03 | 2021-03-03 | Winter wheat meteorological yield prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115018105A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115578637A (en) * | 2022-10-17 | 2023-01-06 | 中国科学院空天信息创新研究院 | Winter wheat yield estimation analysis method and system based on long-term and short-term memory network |
| CN115830442A (en) * | 2022-11-11 | 2023-03-21 | 中国科学院空天信息创新研究院 | Machine learning-based remote sensing estimation method and system for wheat tiller density |
| CN116151445A (en) * | 2023-01-31 | 2023-05-23 | 南京信息工程大学 | Initial flowering phase prediction method and system based on LSTM neural network model |
| CN118364975A (en) * | 2024-06-19 | 2024-07-19 | 北京市农林科学院智能装备技术研究中心 | Wheat yield prediction method of multi-source data-driven hybrid mechanism learning model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2697608A1 (en) * | 2010-03-23 | 2011-09-23 | Dennis Bulani | Method of predicting crop yield |
| CN102651096A (en) * | 2012-04-28 | 2012-08-29 | 中国农业大学 | Method for estimating yield of winter wheat by assimilating characteristics of leaf area index time-sequence curve |
| CN104134095A (en) * | 2014-04-17 | 2014-11-05 | 中国农业大学 | Crop yield estimation method based on scale transformation and data assimilation |
| CN109754125A (en) * | 2019-01-18 | 2019-05-14 | 中国农业大学 | Crop yield forecast method based on crop modeling, history and meteorological forecast data |
| US20200342226A1 (en) * | 2019-04-23 | 2020-10-29 | Farmers Edge Inc. | Yield forecasting using crop specific features and growth stages |
-
2021
- 2021-03-03 CN CN202110237189.6A patent/CN115018105A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2697608A1 (en) * | 2010-03-23 | 2011-09-23 | Dennis Bulani | Method of predicting crop yield |
| CN102651096A (en) * | 2012-04-28 | 2012-08-29 | 中国农业大学 | Method for estimating yield of winter wheat by assimilating characteristics of leaf area index time-sequence curve |
| CN104134095A (en) * | 2014-04-17 | 2014-11-05 | 中国农业大学 | Crop yield estimation method based on scale transformation and data assimilation |
| CN109754125A (en) * | 2019-01-18 | 2019-05-14 | 中国农业大学 | Crop yield forecast method based on crop modeling, history and meteorological forecast data |
| US20200342226A1 (en) * | 2019-04-23 | 2020-10-29 | Farmers Edge Inc. | Yield forecasting using crop specific features and growth stages |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115578637A (en) * | 2022-10-17 | 2023-01-06 | 中国科学院空天信息创新研究院 | Winter wheat yield estimation analysis method and system based on long-term and short-term memory network |
| CN115830442A (en) * | 2022-11-11 | 2023-03-21 | 中国科学院空天信息创新研究院 | Machine learning-based remote sensing estimation method and system for wheat tiller density |
| CN115830442B (en) * | 2022-11-11 | 2023-08-04 | 中国科学院空天信息创新研究院 | Remote sensing estimation method and system for wheat stem tiller density based on machine learning |
| CN116151445A (en) * | 2023-01-31 | 2023-05-23 | 南京信息工程大学 | Initial flowering phase prediction method and system based on LSTM neural network model |
| CN118364975A (en) * | 2024-06-19 | 2024-07-19 | 北京市农林科学院智能装备技术研究中心 | Wheat yield prediction method of multi-source data-driven hybrid mechanism learning model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287944B (en) | Crop pest monitoring method based on multispectral remote sensing image of deep learning | |
| CN115018105A (en) | Winter wheat meteorological yield prediction method and system | |
| CN110309985A (en) | A kind of crop yield prediction technique and system | |
| CN112348812B (en) | Forest stand age information measurement method and device | |
| CN110909933B (en) | Agricultural drought rapid diagnosis and evaluation method coupling crop model and machine learning language | |
| CN113192026A (en) | Walnut maturity detection and prediction method based on visible light image | |
| CN113553697B (en) | Long-time-sequence multi-source data-based vegetation disturbance analysis method for coal mining | |
| CN108805079B (en) | Winter wheat identification method and device | |
| CN115222100A (en) | Crop yield prediction method based on three-dimensional cyclic convolution neural network and multi-temporal remote sensing image | |
| CN110321774B (en) | Crop disaster situation evaluation method, device, equipment and computer readable storage medium | |
| CN112861712B (en) | Agricultural pest and disease monitoring method based on artificial intelligence and multi-temporal remote sensing | |
| CN116227758B (en) | Agricultural product maturity prediction method and system based on remote sensing technology and deep learning | |
| CN113063739A (en) | Rice canopy nitrogen content monitoring method based on airborne hyperspectral sensor | |
| CN118072178B (en) | Corn yield estimation method and system based on classified percentage data assimilation | |
| CN114529097A (en) | Multi-scale crop phenological period remote sensing dimensionality reduction prediction method | |
| CN115661674A (en) | Crop irrigation information extraction method based on multisource satellite soil humidity data | |
| Bao et al. | Forecasting spring maize yield using vegetation indices and crop phenology metrics from UAV observations | |
| Wu et al. | Evaluating the accuracy of ARMA and multi‐index methods for predicting winter wheat maturity date | |
| CN116579521B (en) | Yield prediction time window determining method, device, equipment and readable storage medium | |
| CN117074340A (en) | Wheat nitrogen content measuring and calculating method based on hyperspectral remote sensing image of unmanned aerial vehicle | |
| CN116151454A (en) | Method and system for predicting yield of short-forest linalool essential oil by multispectral unmanned aerial vehicle | |
| CN114359725B (en) | Crop growth condition remote sensing monitoring system and method based on crop model and assimilation technology | |
| CN115496999A (en) | Method and device for estimating field straw yield | |
| CN114923908A (en) | Multi-source data-based field rice bacterial leaf blight monitoring method and system | |
| Shakir | Optimal Deep Learning Driven Smart Sugarcane Crop Monitoring on Remote Sensing Images |
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 |