CN110927082A - Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing - Google Patents
Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing Download PDFInfo
- Publication number
- CN110927082A CN110927082A CN201911167291.2A CN201911167291A CN110927082A CN 110927082 A CN110927082 A CN 110927082A CN 201911167291 A CN201911167291 A CN 201911167291A CN 110927082 A CN110927082 A CN 110927082A
- Authority
- CN
- China
- Prior art keywords
- yield prediction
- aerial vehicle
- unmanned aerial
- prediction method
- winter wheat
- 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 68
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003384 imaging method Methods 0.000 title claims abstract description 13
- 230000012010 growth Effects 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 17
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 88
- 229910052757 nitrogen Inorganic materials 0.000 claims description 44
- 238000012937 correction Methods 0.000 claims description 14
- 238000002310 reflectometry Methods 0.000 claims description 14
- 239000002689 soil Substances 0.000 claims description 14
- 239000013067 intermediate product Substances 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000002262 irrigation Effects 0.000 claims description 6
- 238000003973 irrigation Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 230000004720 fertilization Effects 0.000 claims description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 description 19
- 230000008901 benefit Effects 0.000 description 7
- 238000000701 chemical imaging Methods 0.000 description 7
- 230000003595 spectral effect Effects 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 235000013339 cereals Nutrition 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010219 correlation analysis Methods 0.000 description 3
- 239000003337 fertilizer Substances 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001808 coupling effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000618 nitrogen fertilizer Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000001850 reproductive effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009105 vegetative growth Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The invention provides a winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing, which comprises the following steps of: and (3) carrying out hyperspectral image processing on the unmanned aerial vehicle, then carrying out growth parameter inversion on crops, constructing a winter wheat yield prediction model, and finally verifying the yield prediction precision. The prediction method provided by the invention comprehensively considers the wheat growth information obtained by the hyperspectral remote sensing of the unmanned aerial vehicle in a plurality of growth periods, and simultaneously introduces the crop growth priori knowledge provided by the crop growth model to predict the wheat yield.
Description
Technical Field
The invention relates to the technical field of farmland quantitative remote sensing monitoring, in particular to a method for predicting crop yield by utilizing a hyperspectral remote sensing technology.
Background
Grain is an important strategic material for the economic safety of the county citizens and the countries, and the grain safety is closely related to the development of economy and the harmony of society. Water resource shortage, land degradation, frequent natural disasters and increasingly serious agricultural environment pollution seriously affect the stable development and the improvement of the quality of grain production. Winter wheat is one of main grains in China, the yield of the winter wheat can be predicted accurately in time, powerful support can be provided for agricultural decision making and operation management, and the method is an urgent need for developing accurate agriculture and walking sustainable development roads.
Satellite remote sensing is widely applied to large-scale crop estimation at present, has important significance for decision on a macro scale, but has little auxiliary effect on actual operation management of agricultural operators due to the problems of long revisit period, low image resolution, mixed pixels, meteorological condition limitation and the like of satellite images. The unmanned aerial vehicle remote sensing has the advantages of high space-time resolution, low operation cost, flexibility, repeatability and the like, can quickly and efficiently acquire a farmland remote sensing image with a large area and high precision, and can effectively assist agricultural operators in regulation and control and decision making.
The unmanned aerial vehicle remote sensing estimation mainly refers to a satellite remote sensing estimation method, but because the aspects of a remote sensing platform, image spatial resolution and the like are obviously different from the satellite remote sensing, whether the method is suitable for unmanned aerial vehicle remote sensing research or not is yet researched. The remote sensing data is used for predicting the yield of regional crops, and at present, the regional crop yield can be mainly divided into an empirical model and a physical model. The yield prediction method is based on remote sensing spectral information, and a yield prediction result is obtained by establishing a regression relation between vegetation indexes and yield in multiple periods. The latter is mainly based on a crop growth model, can better simulate the crop growth condition, but has a plurality of model parameters and a more complex method.
Disclosure of Invention
Based on the technical background, the inventor of the invention has conducted keen research to overcome the defects of the existing winter wheat remote sensing yield prediction method, and provides a winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing.
The invention provides a winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing, which comprises the following steps of:
(1) processing hyperspectral images of the unmanned aerial vehicle;
(2) inversion of crop growth parameters;
(3) constructing a winter wheat yield prediction model;
(4) and verifying the yield prediction precision.
The winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing provided by the invention has the following advantages:
according to the method for predicting the yield of the winter wheat, the hyperspectral remote sensing information and the crop growth information of the unmanned aerial vehicle are comprehensively considered, and the crop growth model is introduced, so that the method has the advantages that the coupling action mechanism of various influence factors such as soil, climate, precipitation and the like in the growth process of the wheat is considered, the calculation of the prediction model is simple and convenient to operate, and the result is accurate to the greatest extent.
Drawings
FIG. 1 is a diagram illustrating steps of hyperspectral image processing of an unmanned aerial vehicle;
FIG. 2-a shows an unmanned aerial vehicle true color synthetic remote sensing image after the winter wheat jointing stage is processed;
FIG. 2-b shows a real-color synthetic remote sensing image of the unmanned aerial vehicle after the winter wheat heading period is processed;
FIG. 3-a shows the inversion result of leaf area index at the jointing stage of winter wheat;
FIG. 3-b shows the inversion results of the leaf area index at heading stage of winter wheat;
FIG. 4-a shows the inversion results of nitrogen content of leaves during the jointing stage of winter wheat;
FIG. 4-b shows the inversion results of leaf nitrogen content during heading of winter wheat;
FIG. 5 shows a winter wheat test field spatial profile;
FIG. 6-a shows the comparison result of the inversion value and the measured value of the leaf area index of winter wheat at the jointing stage;
6-b shows the comparison result of the inversion value and the measured value of the leaf area index of the winter wheat at the heading stage;
FIG. 7-a shows the comparison result of the inversion value and the measured value of the nitrogen content of the leaves in the jointing stage of the winter wheat;
7-b show the comparison result of the inversion value and the measured value of the leaf nitrogen content of winter wheat at heading stage;
FIG. 8 shows measured yield versus predicted yield results;
FIG. 9 shows a step diagram of a winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing.
Detailed Description
The present invention will be described in detail below, and features and advantages of the present invention will become more apparent and apparent with reference to the following description.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The invention provides a winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing, which comprises the following steps of:
(1) processing hyperspectral images of the unmanned aerial vehicle;
(2) inversion of crop growth parameters;
(3) constructing a winter wheat yield prediction model;
(4) and verifying the yield prediction precision.
This step is specifically described and illustrated below.
And (1) processing hyperspectral images of the unmanned aerial vehicle.
In the invention, the unmanned aerial vehicle carries a hyperspectral sensor to image a target area, and the period of collecting the image is the growth period of winter wheat, preferably the emergence period, the reversion period, the jointing period, the booting period, the heading period, the flowering period and the filling period, and more preferably the jointing period and the heading period. The analysis shows that the jointing stage and the heading stage are the growth stage with the highest correlation with yield.
Spectral imaging techniques are classified according to the spectral resolution of the sensor, and can be generally classified into multispectral imaging, hyperspectral imaging, and hyperspectral imaging. Multispectral means that the spectral resolution is on the order of 0.1mm, and such sensors typically have only a few bands in the visible and near infrared regions. The hyperspectral sensor has spectral resolution of 0.01mm magnitude order, the sensor has dozens of to hundreds of wave bands in visible light and near infrared regions, the spectral resolution can reach nm level, the sensor can capture the fine position and depth difference of characteristic absorption peaks and reflection valleys of plant reflection spectrum curves caused by the change of biochemical components of plants, can invert vegetation biochemical parameters more accurately, and has the unique advantages of high spectral resolution and integrated atlas. In the hyperspectral imaging, compared with multispectral imaging, a hyperspectral image obtained by the hyperspectral imaging method has richer image and spectral information.
In the step (1), the unmanned aerial vehicle is operated on the day to ensure that the sky is clear and cloudless, and the operation time is preferably 10: 00-14: 00. And the acquired image is ensured to be clear.
The unmanned aerial vehicle is selected from the group consisting of MavicAir, M600 Pro, unmanned aerial vehicle, Habersen H501A and UDrone idea unmanned aerial vehicle, preferably Mavic Air and M600 Pro, and more preferably M600 Pro.
The flight height of the unmanned aerial vehicle is 50-150 m, preferably 70-120 m, more preferably 100m, and the flight speed is 1-6 m/s, preferably 2-4 m/s, more preferably 3 m/s.
The hyperspectral sensor is selected from SOC750HB, a middary and near-infrared hyperspectral spectrometer, an Isoplane spectrometer and a Pika L hyperspectral imager, and is preferably a Pika L hyperspectral imager. The hyperspectral sensor is imaged in a push-broom mode.
Before an unmanned aerial vehicle carries a hyperspectral sensor to image a target area, a standard white board or a standard reflectivity target needs to be laid on the ground of the target area for radiation correction.
Preferably, the unmanned aerial vehicle is further required to carry a common camera to image the target area, and a multispectral image is generated for orthorectification.
The specific process of the orthorectification comprises the following steps: firstly, performing radiation correction and coarse geometric correction on an original hyperspectral image to generate an intermediate product, performing space-three processing on a multispectral image generated by imaging of a common camera to generate an orthoimage, and performing orthorectification on the intermediate product by using the orthoimage.
The whole process of hyperspectral image processing is shown in fig. 1. Firstly, performing radiation correction and coarse geometric correction on the hyperspectral image of the unmanned aerial vehicle to generate an intermediate product, then performing space-three processing on the multispectral image imaged by a camera to generate an orthoimage, then performing orthorectification on the generated intermediate product and the orthoimage, and finally performing image splicing to generate a complete hyperspectral image of the unmanned aerial vehicle.
The radiation correction is to convert the DN value of an original image of the unmanned aerial vehicle into radiance by utilizing a hyperspectral sensor calibration file, and then convert the radiance image of the unmanned aerial vehicle into a reflectivity image by utilizing the relationship between the radiance of a standard white board or a standard reflectivity target on the image and a reflectivity spectrum measured in a laboratory.
The geometric correction of the invention is to use unmanned aerial vehicle GPS file information to carry out primary geometric correction processing on the reflectivity image to generate an intermediate product.
In the orthographic correction, multispectral images are subjected to space-three processing, the space-three processing refers to space triangulation, and the method is a measurement method for conducting indoor control point encryption according to a small number of field control points in stereo photogrammetry to obtain the elevation and the plane position of an encrypted point. The method comprises the following specific steps: dense point clouds are built for the multispectral images, grids are generated, textures are generated, and finally orthoscopic images are generated. By selecting the control points of the orthoimage and the intermediate product, the orthorectification is realized. And finally, splicing the images to finally obtain a complete high-reflectivity high-spectral image map, wherein the spatial resolution of the image is 0.1 m.
And (2) inverting the crop growth parameters.
The crop growth parameters include leaf area index and leaf nitrogen content. In the present invention, the leaf area index is obtained by directional second order differential inversion.
The directional second order differential is an algorithm which can eliminate soil background information and effectively invert leaf area indexes, and the spectral analysis of leaves and soil shows that the quotient rho' of the second order differential of the leaves is at the wave bands of 0.68-0.71 mu m and 0.73-0.75 mu mvIs far greater than the second order differential quotient rho ″ of soilgThe hyperspectral data can be used for selectively establishing a second order differential quotient rho' at a certain wavelengthvAnd an empirical relation with the leaf area index, and inverting the leaf area index according to the relation.
The reflectivity of the pixel target in the invention can be determined by a contribution term rho' of primary scattering1And the contribution term p "of multiple scatteringmIs represented by the sum of. At the wavelength band of 0.68-0.71 μm, the multiple scattering term can be completely ignored, and assuming observation from the hot spot direction, the formula can be simplified as follows:
in the formula (1), ρ 'represents a second order differential, ρ', of the target pixelvThe second order differential of the representative pure vegetation pixel is obtained by constructing a remote sensing image red and near infrared reflectivity characteristic space and selecting the pure vegetation pixel, LAI represents a leaf area index, b is a parameter related to vegetation type, observation zenith angle and the like, and can be approximately 0.5 for farmland.
In step (2) of the invention, the nitrogen content of the leaves is obtained by AIVI index inversion. The AIVI index is a vegetation index which is insensitive to angle and has strong correlation with the nitrogen concentration of winter wheat leaves. The vegetation index is based on the reflectivity of blue, green wave bands and red edges, and has the advantage of being more stable and accurate than other vegetation index models. The expression is as follows:
in the formula (2), RiRepresents the reflectance of the pixel at the i (unit: nm) wavelength band;
according to the method, wave bands with wavelengths of 445nm, 573nm, 720nm and 735nm are selected, the AIVI of the winter wheat is obtained by using the formula (2), and then the nitrogen content of the leaves of the winter wheat is obtained by inversion according to an empirical linear relation between the AIVI and the nitrogen content of the leaves of the winter wheat in the formula (5).
AIVI ═ 0.353LNC +0.397 formula (5)
In formula (5), LNC represents the percentage of the leaf nitrogen content. The empirical linear relation between the AIVI index and the nitrogen content of the winter wheat leaves is obtained by combining the measured value of the nitrogen content of the winter wheat leaves and then establishing by using a least square method.
And (3) constructing a winter wheat yield prediction model.
The winter wheat yield prediction model is constructed based on a random forest algorithm. The random forest is a machine learning algorithm based on a decision tree and is a natural nonlinear modeling tool. The algorithm randomly and repeatedly selects samples, randomly selects branch nodes, and constructs a large number of non-repetitive decision trees for decision summarization, so that the generalization capability and the prediction precision of the model are improved.
According to a preferred embodiment of the present invention, the training samples of the yield prediction model are from simulation results of a CERES-Wheat growth model. The CERES-Wheat model is one of the most widely used crop growth model systems at present, can simulate the basic physiological and ecological processes of vegetative growth, reproductive growth and development process, crop photosynthesis, respiration, dry matter distribution, plant growth, aging and the like of crops, and finally realizes the simulation of the crop yield.
The CERES-wheel model input parameters comprise meteorological parameters, soil data, variety information and field management data. The meteorological data comprise the highest temperature, the lowest temperature, precipitation and the like, the soil data comprise soil texture, capacity, pH value, soil moisture characteristics and the like, the variety information needs to be debugged for many times, the data which best meet the experimental variety are selected, and the field management data comprise irrigation information, fertilization information, planting information and the like.
The output data of the CERES-wheel model comprises daily change data of parameters such as leaf area index and leaf nitrogen content, yield data after crops are mature and the like. The growth period with the highest correlation with the yield can be found through correlation analysis, the inventor sets 4 winter Wheat variety parameters in a CERES-Wheat model respectively, 12 nitrogen fertilizer management parameters with nitrogen application levels from N0 to N22 at intervals of 30kg/ha, 5 water management parameters with water irrigation amount from 0mm to 60mm at intervals of 15mm, and 3 fertilization and irrigation dates to simulate 720 groups of winter Wheat growth parameters in total, and correlation between leaf area indexes and leaf nitrogen content in the jointing stage and the heading stage and the yield is found to be highest through correlation analysis. Therefore, the selected acquisition imaging period is the jointing period and the heading period of the winter wheat.
According to a further preferred embodiment of the present invention, five sixths of the simulation result data of the CERES-Wheat growth model is used as a training sample of the model, and the remaining one sixth is used as a test sample. Then, random modeling is carried out by utilizing R language, the algorithm mainly determines two parameters, one is the number of random features input when each node of the decision tree is split, and the other parameter is the number of the constructed decision tree. Through training and testing, the fitting precision and the prediction precision of the model can reach more than 0.9.
And (4) verifying the yield prediction precision.
And (4) bringing the leaf area index and leaf nitrogen content obtained by inversion into the winter wheat yield prediction model constructed in the step (3), so as to obtain a yield prediction value of each cell of the test field.
In the invention, the yield prediction precision verification comprises the precision verification of the inverted leaf area index, the leaf nitrogen content and the predicted yield.
The precision verification comprises two verification indexes, preferably a root mean square error RMSE and an average relative error absolute value MAPE, and the calculation formulas are respectively as follows:
in the formula (I), the compound is shown in the specification,
representing the predicted value, y representing the measured value, and m representing the number of samples participating in the statistics.
The invention has the following beneficial effects:
(1) according to the method for predicting the yield of the winter wheat, a hyperspectral remote sensing technology is combined with an unmanned aerial vehicle, and the advantages of high space-time resolution, low operation cost, flexibility, repeatability and the like of unmanned aerial vehicle remote sensing are utilized, so that the method for predicting the yield of the winter wheat can quickly and efficiently acquire farmland remote sensing images with large areas and high accuracy, and can effectively assist agricultural operators in regulation and control and decision making;
(2) according to the method for predicting the yield of the winter wheat, the hyperspectral remote sensing information and the crop growth information of the unmanned aerial vehicle are comprehensively considered, and meanwhile, the crop growth model is introduced, so that the crop growth condition is well simulated, and the method for predicting the yield of the winter wheat is more scientific and accurate;
(3) the method for predicting the yield of the winter wheat comprehensively considers the coupling action mechanism of various influence factors such as soil, climate and the like in the growth process of the winter wheat, and achieves the effects of simple and convenient calculation of a prediction model and accurate calculation result.
(4) According to the winter wheat yield prediction method, the fitting precision and the prediction precision of the built yield prediction model can reach more than 0.9.
(5) The winter wheat yield prediction method disclosed by the invention is universal from a remote sensing mechanism, and provides a new idea and a new method for accurately predicting the crop yield.
Examples
The invention is further illustrated by the following specific examples, which are intended to be illustrative only and not limiting to the scope of the invention.
Take the example of the production base of high-quality wheat in urban country level 37118of Henan province in 2019. The sensor Pika L hyperspectral imager is carried by a Xinjiang M600 Pro unmanned aerial vehicle platform, the number of wave bands is 300, the range of the wave bands is 400 nm-1000 nm, and the sensor adopts a push-broom mode for imaging. The flying height of the unmanned aerial vehicle is set as 100m, and the flying speed is 3 m/s. A standard white board and four standard reflectance targets with reflectance of 1.2m × 1.2m size of 5%, 20%, 40% and 60%, respectively, are laid on the ground. Carrying out radiometric calibration and coarse geometric correction processing on the original hyperspectral image of the unmanned aerial vehicle by using Resonon software to generate an intermediate product, carrying out space three processing on the multispectral image by using Agisoft Photoscan software to generate an orthoscopic image, carrying out orthoscopic correction on the intermediate product by using the orthoscopic image, and finally carrying out image splicing to obtain the orthoscopic hyperspectral image with the spatial resolution of 0.1 m. Fig. 2-a is a true color synthetic image of the unmanned aerial vehicle in the jointing stage after image processing, fig. 2-b is a true color synthetic image of the unmanned aerial vehicle in the heading stage after image processing, and from fig. 2-a and 2-b, it can be seen that the winter wheat planting test area is divided into a plurality of cells, 4 in each row, and 10 rows in total.
The leaf area index is obtained by directional second order differential inversion. Selecting the target pixel reflectivity rho 'at a 701nm waveband for calculation, and selecting the second-order differential quotient rho' of the bladevThe average value is obtained by averaging the reflectivity of pure vegetation pixels on the remote sensing image at 701 nm. The pure vegetation pixels are selected by constructing a red and near infrared reflectivity characteristic space of a remote sensing image and retrieving all the pixels which are considered as pure vegetation in the characteristic space on the remote sensing image. After the soil background is eliminated by using the second-order differential quotient, leaf area index inversion is carried out on the whole image by using the formula (1). The inversion results of the leaf area indexes of the winter wheat in the jointing stage and the heading stage are respectively shown in fig. 3-a and fig. 3-b, and the inversion results of all cells can be seen in the images.
The leaf nitrogen content was obtained by inversion using the AIVI index. Selecting wave bands with wavelengths of 445nm, 573nm, 720nm and 735nm, and obtaining the AIVI index of winter wheat by using the formula (2). And then, obtaining the leaf nitrogen content by inversion according to an empirical linear relation (5) of the AIVI index and the leaf nitrogen content of the winter wheat. The inversion results of the leaf nitrogen content of the winter wheat in the jointing stage and the heading stage are respectively shown in figures 4-a and 4-b, and the inversion results of all cells in the test area are clearly shown in the figures.
The varieties tested were dwarf antibody 58(AK58), Zhoumai 27(ZM27), Xinong 509(XN509) and Yumai 49-198(YM49-198), corresponding to A1, A2, A3 and A4 in the table below and FIG. 5, respectively. The test was conducted with 4 nitrogen levels of 0kg/ha (N0), 120kg/ha (N1), 225kg/ha (N2) and 330kg/ha (N3), 50% being a base fertilizer and 50% being a topdressing during the jointing stage. The test adopts a random block design, N0 only performs one group of tests, and the cell area is 100m2And N1, N2 and N3 were repeated three times, and the cell area was 130m2. The test area has 40 cells, and the spatial distribution is shown in figure 5. FIG. 5 shows the spatial distribution of 40 test areas, which is divided into 4 columns and 10 rows, wherein the block design of the test areas is random, and for the sake of understanding, the nomenclature of each test area is now illustrated, A1N0 indicates that the test area is planted with dwarf 58(A1) and no fertilizer, IIIA 4N1 indicates that the test area is planted with dwarf 49-198(A4) and fertilizer is applied at 120kg/ha, and the third time is repeated.
Taking the cells as scale units, respectively averaging the leaf area index and leaf nitrogen content of the pixel inversion of each cell in the jointing stage and heading stage to obtain the average leaf area index and average leaf nitrogen content of each cell, as shown in table 1. Table 1 shows leaf area index and leaf nitrogen content at the jointing stage and heading stage of each cell obtained by inversion of 40 experimental zones.
TABLE 1 average leaf area index and average leaf nitrogen content for each cell
4 winter Wheat variety parameters corresponding to local varieties are respectively set in a CERES-Wheat model, 12 nitrogen fertilizer management parameters of nitrogen application levels from N0 to N22 are set at intervals of 30kg/ha, 5 water management parameters of water irrigation amounts from 0mm to 60mm are set at intervals of 15mm, 3 fertilization and irrigation dates are set, 720 groups of winter Wheat growth parameters are simulated in total, and correlation analysis shows that the leaf area index LAI and the leaf nitrogen content LNC in the jointing stage and the heading stage have the highest correlation with yield. In the random forest model, five sixths of simulation data is used as a training sample, and the rest one sixth of simulation data is used as a test sample. The random forest modeling is carried out by utilizing R language, the algorithm mainly determines two parameters, one parameter is the number of random features input when each node of the decision tree is split, and the other parameter is the number of the decision tree. Through training and testing, the fitting precision and the prediction precision of the model can reach more than 0.9.
The specific comparison results of the leaf area indexes of the jointing stage and the heading stage obtained by inversion and the actually measured leaf area indexes are shown in fig. 6-a and fig. 6-b, fig. 6-a is a schematic diagram of the comparison result of the leaf area indexes of the jointing stage of the winter wheat and the actually measured leaf area indexes, and it can be seen from the diagram that the root mean square error of the leaf area indexes of the jointing stage obtained by inversion by the method of the invention and the actually measured leaf area indexes is only 0.082; FIG. 6-b is a schematic diagram showing the comparison result between the winter wheat heading stage leaf area index and the actually measured leaf area index, and it can be seen from the diagram that the root mean square error between the heading stage leaf area index obtained by inversion by the method of the present invention and the actually measured leaf area index is 0.093, and therefore, the accuracy of inversion by the method of the present invention can be seen.
The specific comparison results of the leaf nitrogen content at the jointing stage and heading stage obtained by inversion and the actually measured leaf nitrogen content are shown in fig. 7-a and fig. 7-b. FIG. 7-a is the root mean square error of the nitrogen content of the leaves in the jointing stage of the winter wheat and the measured nitrogen content of the leaves, and it can be seen from the figure that the root mean square error of the nitrogen content of the leaves in the jointing stage of the winter wheat and the measured nitrogen content of the leaves is 0.149; FIG. 7-b is the root mean square error between the nitrogen content of the leaves in the heading stage of the winter wheat and the actually measured nitrogen content of the leaves, and it can be seen that the root mean square error between the nitrogen content of the leaves in the heading stage and the actually measured nitrogen content of the leaves is 0.168.
Table 2 shows the predicted yield and the actual measured yield of winter wheat by the method of the present invention, showing the yield prediction and the actual yield measurement for each test area, and the calculation of the relative error for each test area. The values in Table 2 were plotted to obtain FIG. 8, where FIG. 8 is a comparison graph of actual yield versus predicted yield, and it can be seen from the graph that the root mean square error RMSE between the predicted yield and the actual measured yield by the yield prediction method of the present invention is 933.14kg/ha, and the average relative error absolute MAPE between the predicted yield and the actual measured yield of the present invention is 8.39%.
TABLE 2 Absolute value of mean relative error between yield prediction and measured yield
The invention has been described in detail with reference to specific embodiments and illustrative examples, but the description is not intended to be construed in a limiting sense. Those skilled in the art will appreciate that various equivalent substitutions, modifications or improvements may be made to the technical solution of the present invention and its embodiments without departing from the spirit and scope of the present invention, which fall within the scope of the present invention. The scope of the invention is defined by the appended claims.
Claims (10)
1. A winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing is characterized by comprising the following steps:
(1) processing hyperspectral images of the unmanned aerial vehicle;
(2) inversion of crop growth parameters;
(3) constructing a winter wheat yield prediction model;
(4) and verifying the yield prediction precision.
2. The yield prediction method according to claim 1, wherein, in step (1),
the unmanned aerial vehicle carries out imaging on a target area by carrying out hyperspectral sensor, and winter wheat in the target area is in a growth period, preferably in a seedling emergence period, a green turning period, an elongation period, a booting period, a heading period, a flowering period and a filling period, and more preferably in the elongation period and the heading period.
3. The yield prediction method according to claim 2, wherein, in the step (1),
before an unmanned aerial vehicle carries a hyperspectral sensor to image a target area, a standard white board or a standard reflectivity target is laid on the ground of the target area for radiation correction;
preferably, a common camera is mounted on the unmanned aerial vehicle to image the target area for orthorectification.
4. The yield prediction method of claim 3, wherein, in step (1),
the orthorectification is performed as follows: performing radiation correction and coarse geometric correction on the original hyperspectral image to generate an intermediate product, performing space-three processing on the multispectral image to generate an orthoimage, and performing orthorectification on the intermediate product by using the orthoimage;
and finally, carrying out image splicing to generate a complete hyperspectral image of the unmanned aerial vehicle.
5. The yield prediction method of claim 1, wherein, in step (2),
the crop growth parameters comprise a leaf area index and leaf nitrogen content, the leaf area index is obtained by directional second order differential inversion, and the relationship between a target pixel second order differential and the leaf area index is as follows:
in the formula (I), the compound is shown in the specification,
ρ "represents the second order differential of the target pixel,
ρ″vrepresents the second order differential of the pure vegetation pixel,
LAI represents the leaf area index,
b is a parameter related to vegetation type, observed zenith angle.
6. The yield prediction method of claim 5, wherein, in step (2),
the nitrogen content of the leaves is obtained by AIVI index inversion, and the AIVI expression is as follows:
in the formula, RiRepresenting the reflectivity of the picture element at the i-wave band;
the empirical linear relation between the AIVI index and the nitrogen content of the winter wheat leaves is as follows:
AIVI ═ 0.353LNC +0.397 formula (5)
Wherein LNC represents the percentage of leaf nitrogen content.
7. The yield prediction method of claim 1, wherein, in step (3),
the yield prediction model is a nonlinear regression model constructed based on a random forest algorithm, and preferably, a training sample of the yield prediction model is from a simulation result of a CERES-Wheat growth model;
the CERES-wheel model input parameters comprise meteorological data, soil data, variety information and field management data;
the CERES-Wheat model output data comprises leaf area index, daily variation data of leaf nitrogen content and yield data after crop maturity.
8. The yield prediction method of claim 7, wherein, in step (3),
the meteorological data comprise a highest air temperature, a lowest air temperature and precipitation;
the soil data includes soil texture, capacity, PH and soil moisture characteristics;
the variety information needs to be debugged for multiple times, and data which best accords with the experimental variety is selected;
the field management data includes irrigation information, fertilization information, and planting information.
9. The yield prediction method of claim 1, wherein, in step (4),
the yield prediction precision verification comprises precision verification of inverted leaf area indexes, leaf nitrogen content and predicted yield.
10. The yield prediction method of claim 9, wherein, in step (4),
the precision verification comprises two verification indexes, preferably a root mean square error RMSE and an average relative error absolute value MAPE, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
representing the predicted value, y representing the measured value, and m representing the number of samples participating in the statistics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911167291.2A CN110927082A (en) | 2019-11-25 | 2019-11-25 | Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911167291.2A CN110927082A (en) | 2019-11-25 | 2019-11-25 | Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110927082A true CN110927082A (en) | 2020-03-27 |
Family
ID=69851051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911167291.2A Pending CN110927082A (en) | 2019-11-25 | 2019-11-25 | Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110927082A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798327A (en) * | 2020-06-24 | 2020-10-20 | 安徽大学 | Construction method and application of wheat yield calculation model based on hyperspectral image |
| CN111798326A (en) * | 2020-06-24 | 2020-10-20 | 安徽大学 | Construction method and application of wheat yield calculation model based on visible light image |
| CN111815014A (en) * | 2020-05-18 | 2020-10-23 | 浙江大学 | Crop yield prediction method and system based on unmanned aerial vehicle low-altitude remote sensing information |
| CN112161938A (en) * | 2020-11-05 | 2021-01-01 | 江西省农业科学院作物研究所 | Method for measuring rape yield based on hyperspectral technology |
| CN112667955A (en) * | 2020-12-24 | 2021-04-16 | 青岛大学 | Method for estimating regional scale corn potential yield and yield difference based on remote sensing and application |
| CN112949179A (en) * | 2021-03-01 | 2021-06-11 | 中国农业科学院农业信息研究所 | Winter wheat growth simulation method and system under application of resin coated nitrogen fertilizer |
| CN113030903A (en) * | 2021-03-05 | 2021-06-25 | 深圳大学 | Hatch nutrition level inversion method based on unmanned aerial vehicle hyperspectrum and laser radar |
| CN113705937A (en) * | 2021-10-27 | 2021-11-26 | 武汉大学 | Crop yield estimation method combining machine vision and crop model |
| CN114062282A (en) * | 2022-01-12 | 2022-02-18 | 中国农业科学院农业资源与农业区划研究所 | Method and device for rapidly judging dry matters of fruits on trees |
| CN115797812A (en) * | 2023-02-09 | 2023-03-14 | 北京和颐林生物科技有限公司 | Method for controlling symbiotic liquid in high SOD content wheat production process for improving sleep |
| CN116187100A (en) * | 2023-04-25 | 2023-05-30 | 吉林大学 | Method for estimating corn kernel protein content by combining crop growth model |
| CN116297243A (en) * | 2023-02-28 | 2023-06-23 | 北京市农林科学院信息技术研究中心 | Method and device for estimating dressing amount of flue-cured tobacco nitrogenous fertilizer, electronic equipment and storage medium |
| CN117391472A (en) * | 2023-10-26 | 2024-01-12 | 北京麦麦趣耕科技有限公司 | Device and method for predicting growth period of wheat and application of device and method |
| CN117592604A (en) * | 2023-11-22 | 2024-02-23 | 河北省农林科学院旱作农业研究所 | Unmanned aerial vehicle-mounted remote sensing identification method for water-efficient wheat varieties |
| WO2024077760A1 (en) * | 2022-10-12 | 2024-04-18 | 安徽科技学院 | Unmanned aerial vehicle accurate variable-rate fertilization method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105675549A (en) * | 2016-01-11 | 2016-06-15 | 武汉大学 | Portable crop parameter measurement and growth vigor intelligent analysis device and method |
| CN107314759A (en) * | 2017-06-05 | 2017-11-03 | 江苏大学 | Wheatland yield method of estimation and device based on unmanned plane multi-angled shooting |
| CN107798668A (en) * | 2017-11-23 | 2018-03-13 | 北京依锐思遥感技术有限公司 | The method and system of unmanned plane imaging EO-1 hyperion geometric correction based on RGB images |
| CN108898070A (en) * | 2018-06-07 | 2018-11-27 | 湖南中科星图信息技术有限公司 | A kind of high-spectrum remote-sensing extraction Mikania micrantha device and method based on unmanned aerial vehicle platform |
| CN108917722A (en) * | 2018-08-01 | 2018-11-30 | 北斗导航位置服务（北京）有限公司 | Vegetation coverage calculation method and device |
| CN109459392A (en) * | 2018-11-06 | 2019-03-12 | 南京农业大学 | A kind of rice the upperground part biomass estimating and measuring method based on unmanned plane multispectral image |
| CN110245589A (en) * | 2019-05-30 | 2019-09-17 | 农业农村部农业生态与资源保护总站 | A kind of the Northwest's mulch information comprehensive analysis method based on high score remote sensing image |
| CN110376167A (en) * | 2019-07-29 | 2019-10-25 | 北京麦飞科技有限公司 | Rice leaf nitrogen content monitoring method based on unmanned plane EO-1 hyperion |
-
2019
- 2019-11-25 CN CN201911167291.2A patent/CN110927082A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105675549A (en) * | 2016-01-11 | 2016-06-15 | 武汉大学 | Portable crop parameter measurement and growth vigor intelligent analysis device and method |
| CN107314759A (en) * | 2017-06-05 | 2017-11-03 | 江苏大学 | Wheatland yield method of estimation and device based on unmanned plane multi-angled shooting |
| CN107798668A (en) * | 2017-11-23 | 2018-03-13 | 北京依锐思遥感技术有限公司 | The method and system of unmanned plane imaging EO-1 hyperion geometric correction based on RGB images |
| CN108898070A (en) * | 2018-06-07 | 2018-11-27 | 湖南中科星图信息技术有限公司 | A kind of high-spectrum remote-sensing extraction Mikania micrantha device and method based on unmanned aerial vehicle platform |
| CN108917722A (en) * | 2018-08-01 | 2018-11-30 | 北斗导航位置服务（北京）有限公司 | Vegetation coverage calculation method and device |
| CN109459392A (en) * | 2018-11-06 | 2019-03-12 | 南京农业大学 | A kind of rice the upperground part biomass estimating and measuring method based on unmanned plane multispectral image |
| CN110245589A (en) * | 2019-05-30 | 2019-09-17 | 农业农村部农业生态与资源保护总站 | A kind of the Northwest's mulch information comprehensive analysis method based on high score remote sensing image |
| CN110376167A (en) * | 2019-07-29 | 2019-10-25 | 北京麦飞科技有限公司 | Rice leaf nitrogen content monitoring method based on unmanned plane EO-1 hyperion |
Non-Patent Citations (12)
| Title |
|---|
| HE LI等: "Improved remote sensing of leaf nitrogen concentration in winter wheat using multi-angular hyperspectral data", 《REMOTE SENSING OF ENVIRONMENT》 * |
| HUANG LINSHENG等: "The Estimation of Winter Wheat Yield Based on MODIS Remote Sensing Data", 《INTERNATIONAL FEDERATION FOR INFORMATION PROCESSING 2012》 * |
| KANNING MARTIN等: "High-Resolution UAV-Based Hyperspectral Imagery for LAI and Chlorophyll Estimations from Wheat for Yield Prediction", 《RENOTE SENSING》 * |
| YANG SIQI等: "Estimation Model of Winter Wheat Yield Based on Uav Hyperspectral Data", 《IGARSS 2019-2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM》 * |
| 任建强等: "基于叶面积指数反演的区域冬小麦单产遥感估测", 《应用生态学报》 * |
| 何卫平等: "《统计学》", 31 December 2008, 北京交通大学出版社 * |
| 冯美臣: "《黄土高原水旱地冬小麦长势动态监测及产量品质遥感估测》", 31 October 2015, 中国农业大学出版社 * |
| 卢小平等: "《遥感原理与方法》", 31 August 2012, 测绘出版社 * |
| 朱婉雪等: "基于无人机遥感植被指数优选的田块尺度冬小麦估产", 《农业工程学报》 * |
| 李舰等: "《数据科学中的R语言》", 31 July 2015, 西安交通大学出版社 * |
| 郑丽敏等: "《农业信息***原理及其应用》", 31 March 2006, 化学工业出版社 * |
| 鞠建华等: "《遥感技术在土地管理中的应用》", 30 April 2009, 地质出版社 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815014A (en) * | 2020-05-18 | 2020-10-23 | 浙江大学 | Crop yield prediction method and system based on unmanned aerial vehicle low-altitude remote sensing information |
| CN111815014B (en) * | 2020-05-18 | 2023-10-10 | 浙江大学 | Crop yield prediction method and system based on unmanned aerial vehicle low-altitude remote sensing information |
| CN111798326A (en) * | 2020-06-24 | 2020-10-20 | 安徽大学 | Construction method and application of wheat yield calculation model based on visible light image |
| CN111798327A (en) * | 2020-06-24 | 2020-10-20 | 安徽大学 | Construction method and application of wheat yield calculation model based on hyperspectral image |
| CN112161938A (en) * | 2020-11-05 | 2021-01-01 | 江西省农业科学院作物研究所 | Method for measuring rape yield based on hyperspectral technology |
| CN112667955A (en) * | 2020-12-24 | 2021-04-16 | 青岛大学 | Method for estimating regional scale corn potential yield and yield difference based on remote sensing and application |
| CN112667955B (en) * | 2020-12-24 | 2022-05-24 | 青岛大学 | Method for estimating regional scale corn potential yield and yield difference based on remote sensing and application |
| CN112949179A (en) * | 2021-03-01 | 2021-06-11 | 中国农业科学院农业信息研究所 | Winter wheat growth simulation method and system under application of resin coated nitrogen fertilizer |
| CN112949179B (en) * | 2021-03-01 | 2023-05-12 | 中国农业科学院农业信息研究所 | Winter wheat growth simulation method and system under application of resin coated nitrogenous fertilizer |
| CN113030903B (en) * | 2021-03-05 | 2023-08-29 | 深圳大学 | Seaweed nutrition level inversion method based on unmanned aerial vehicle hyperspectrum and laser radar |
| CN113030903A (en) * | 2021-03-05 | 2021-06-25 | 深圳大学 | Hatch nutrition level inversion method based on unmanned aerial vehicle hyperspectrum and laser radar |
| CN113705937A (en) * | 2021-10-27 | 2021-11-26 | 武汉大学 | Crop yield estimation method combining machine vision and crop model |
| CN114062282B (en) * | 2022-01-12 | 2023-09-22 | 中国农业科学院农业资源与农业区划研究所 | Method and device for rapidly judging dry matters of fruits on tree |
| CN114062282A (en) * | 2022-01-12 | 2022-02-18 | 中国农业科学院农业资源与农业区划研究所 | Method and device for rapidly judging dry matters of fruits on trees |
| WO2024077760A1 (en) * | 2022-10-12 | 2024-04-18 | 安徽科技学院 | Unmanned aerial vehicle accurate variable-rate fertilization method and system |
| CN115797812A (en) * | 2023-02-09 | 2023-03-14 | 北京和颐林生物科技有限公司 | Method for controlling symbiotic liquid in high SOD content wheat production process for improving sleep |
| CN116297243A (en) * | 2023-02-28 | 2023-06-23 | 北京市农林科学院信息技术研究中心 | Method and device for estimating dressing amount of flue-cured tobacco nitrogenous fertilizer, electronic equipment and storage medium |
| CN116297243B (en) * | 2023-02-28 | 2024-02-02 | 北京市农林科学院信息技术研究中心 | Method and device for estimating dressing amount of flue-cured tobacco nitrogenous fertilizer, electronic equipment and storage medium |
| CN116187100A (en) * | 2023-04-25 | 2023-05-30 | 吉林大学 | Method for estimating corn kernel protein content by combining crop growth model |
| CN117391472A (en) * | 2023-10-26 | 2024-01-12 | 北京麦麦趣耕科技有限公司 | Device and method for predicting growth period of wheat and application of device and method |
| CN117391472B (en) * | 2023-10-26 | 2024-02-13 | 北京麦麦趣耕科技有限公司 | Device and method for predicting growth period of wheat and application of device and method |
| CN117592604A (en) * | 2023-11-22 | 2024-02-23 | 河北省农林科学院旱作农业研究所 | Unmanned aerial vehicle-mounted remote sensing identification method for water-efficient wheat varieties |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110927082A (en) | Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing | |
| Qiu et al. | Estimation of nitrogen nutrition index in rice from UAV RGB images coupled with machine learning algorithms | |
| Zheng et al. | Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery | |
| Jin et al. | Estimation of maize yield by assimilating biomass and canopy cover derived from hyperspectral data into the AquaCrop model | |
| Battude et al. | Estimating maize biomass and yield over large areas using high spatial and temporal resolution Sentinel-2 like remote sensing data | |
| Sun et al. | Retrieval of rapeseed leaf area index using the PROSAIL model with canopy coverage derived from UAV images as a correction parameter | |
| CN106372592B (en) | A kind of winter wheat planting area calculation method based on winter wheat area index | |
| CN111241912A (en) | Multi-vegetation index rice yield estimation method based on machine learning algorithm | |
| AU2020101095A4 (en) | A Satellite Remote Sensing Monitoring Method for the Content of Chlorophyll A in the Canopy of Jujube Trees | |
| CN112287892B (en) | Arbor biomass measurement and calculation method based on unmanned aerial vehicle hyperspectral and machine learning algorithm | |
| Zhang et al. | Estimating wheat yield by integrating the WheatGrow and PROSAIL models | |
| Kaivosoja et al. | A case study of a precision fertilizer application task generation for wheat based on classified hyperspectral data from UAV combined with farm history data | |
| Lu et al. | Estimation of rice plant potassium accumulation based on non-negative matrix factorization using hyperspectral reflectance | |
| Jeong et al. | Application of an unmanned aerial system for monitoring paddy productivity using the GRAMI-rice model | |
| Huang et al. | Assimilating remotely sensed information with the wheatgrow model based on the ensemble square root filter for improving regional wheat yield forecasts | |
| CN106501255B (en) | A kind of satellite remote-sensing monitoring method of jujube tree canopy Chlorophyll content | |
| CN115128013A (en) | Soil organic matter content space prediction evaluation method based on partition algorithm | |
| Guo et al. | Inversion of maize leaf area index from UAV hyperspectral and multispectral imagery | |
| Ge et al. | Estimating rice yield by assimilating UAV-derived plant nitrogen concentration into the DSSAT model: Evaluation at different assimilation time Windows | |
| Adeluyi et al. | Exploiting centimetre resolution of drone-mounted sensors for estimating mid-late season above ground biomass in rice | |
| CN115759524A (en) | Soil productivity grade identification method based on remote sensing image vegetation index | |
| CN106504240A (en) | A kind of satellite remote-sensing monitoring method of jujube tree canopy Chlorophyll-a Content | |
| CN106501454B (en) | A kind of satellite remote-sensing monitoring method of jujube tree canopy content of chlorophyll b | |
| Zhu et al. | Mapping crop leaf area index from multi-spectral imagery onboard an unmanned aerial vehicle | |
| Yu et al. | UAV hyperspectral inversion modeling of rice nitrogen content based on WOA-ELM |
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: 20200327 |