CN109614891A - Crop identification method based on phenology and remote sensing - Google Patents
Crop identification method based on phenology and remote sensing Download PDFInfo
- Publication number
- CN109614891A CN109614891A CN201811427585.XA CN201811427585A CN109614891A CN 109614891 A CN109614891 A CN 109614891A CN 201811427585 A CN201811427585 A CN 201811427585A CN 109614891 A CN109614891 A CN 109614891A
- Authority
- CN
- China
- Prior art keywords
- ndvi
- crop
- rice
- target area
- growth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000012010 growth Effects 0.000 claims abstract description 49
- 230000003595 spectral effect Effects 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 240000008042 Zea mays Species 0.000 claims description 61
- 235000002017 Zea mays subsp mays Nutrition 0.000 claims description 61
- 241000209094 Oryza Species 0.000 claims description 60
- 235000007164 Oryza sativa Nutrition 0.000 claims description 60
- 235000009566 rice Nutrition 0.000 claims description 60
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 claims description 52
- 235000005822 corn Nutrition 0.000 claims description 52
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims description 9
- 235000009973 maize Nutrition 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 230000009605 growth rhythm Effects 0.000 abstract description 2
- 238000009395 breeding Methods 0.000 description 15
- 230000001488 breeding effect Effects 0.000 description 15
- 238000012544 monitoring process Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 235000015097 nutrients Nutrition 0.000 description 6
- 238000001228 spectrum Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 235000013339 cereals Nutrition 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 241000196324 Embryophyta Species 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000003973 irrigation Methods 0.000 description 3
- 230000002262 irrigation Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 3
- 230000001850 reproductive effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 229930002875 chlorophyll Natural products 0.000 description 2
- 235000019804 chlorophyll Nutrition 0.000 description 2
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003651 drinking water Substances 0.000 description 2
- 235000020188 drinking water Nutrition 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 230000008635 plant growth Effects 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000833020 Padilla Species 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012272 crop production Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000005070 ripening Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000009331 sowing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000000179 transient infrared spectroscopy Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present invention proposes a kind of crops recognition methods based on phenology and remote sensing, comprising: is analyzed the phenological period of objective crop to obtain objective crop in growth conditions in different time periods；According to the growth rhythm of objective crop, determines the phenological calendar of the growth of objective crop, and the 4th red spectral band band4 and the 5th infrared band band5 of remotely-sensed data, calculate the vegetation index NDVI of objective crop；According to objective crop in growth conditions in different time periods and corresponding NDVI value, the NDVI sequence for extracting the entire growth period of objective crop is generated；Using classification tree algorithm, crops and background are identified according to NDVI value.
Description
Technical field
The present invention relates to data analysis technique fields, are known more particularly, to a kind of based on the crops of phenology and remote sensing
Other method.
Background technique
Farmland information extraction is one of the difficult point of remote sensing Extracting Thematic Information, this is because arable land is with background atural object in sky
Between on inlay, therefore plough for remote sensing picture being interlaced between background atural object and constitute complicated mixture.
When bored, arable land to plough spectrum between internal different land types because of the difference of the crop of plantation, irrigation method and soil attribute
The separability very little of feature.
Summary of the invention
For the current defect for lacking arable land remote sensing recognition technology, the embodiment of the present invention proposes a kind of based on phenology
Learn the crops recognition methods with remote sensing, at least part of solution problems of the prior art.
To achieve the goals above, it is identified the embodiment of the invention provides a kind of based on the crops of phenology and remote sensing
Method, comprising:
Step 1 is analyzed the phenological period of objective crop to obtain objective crop in growth in different time periods
State；
Step 2, the growth rhythm according to objective crop determine the phenological calendar of the growth of objective crop, and remote sensing number
According to the 4th red spectral band band4 and the 5th infrared band band5, calculate the vegetation index NDVI of objective crop,
NDVI=(band5-band4)/(band5+band4)；
Step 3, according to objective crop in growth conditions in different time periods and corresponding NDVI value, generate and extract mesh
Mark the NDVI sequence in the entire growth period of crops；
Step 4, using classification tree algorithm, crops and background are identified according to NDVI value.
Wherein, the step 4 specifically includes:
The NDVI value of target area is obtained, and judges whether NDVI≤0.15 is true, if it is the target area is water
Body, if it is not, then the NDVI curve according to the NDVI value of target area and objective crop in growth period matches, to distinguish
Target area is agricultural land or non-agricultural land.
Wherein, the method also includes:
Step 5, using Remote Spectra information inverting vegetation index NDVI, and establish the relationship mould of vegetation index and yield
Type is with forecast production.
Wherein, the step 5 specifically includes:
The NDVI for obtaining each pixel of Monitoring of Paddy Rice Plant Area of target area under different growing stage in preset time period is equal
Yield per unit area in value and preset time period；
Multivariate regression models as shown in formula 1 is established, rice specific yield is subjected to estimation compared with actual value, choosing
It takes equation model related coefficient index and calculates the correlativity between reality, evaluation analysis is carried out to multivariate regression models；
Y=2116.8X1+9338.4X2+3351.4X3+13829.7X4–17930.9X5- 2300.4 (formula 1)
Wherein, X1For the NDVI mean value of the target area rice at initial stage in tillering stage；X2For the target area of tillering stage mid-term
The NDVI mean value of rice；X3For the NDVI mean value of the target area rice in later period in tillering stage；X4For the target area of early stage at heading stage
The NDVI mean value of domain rice；X5For the NDVI mean value of the target area rice in advanced stage at heading stage；
It is estimated with rice specific yield of the equation of calibration to predeterminable area.
Wherein, the step 5 specifically includes:
The NDVI for obtaining each pixel of maize sown area of target area under different growing stage in preset time period is equal
Yield per unit area in value and preset time period；
Corn specific yield is carried out estimation compared with actual value, chooses equation by the multivariate regression models for establishing formula 2
Fitting correlation coefficient index simultaneously calculates the correlativity between reality, carries out evaluation analysis to multivariate regression models；
Y=4639-108574X1+46498X2+19556X3+191661X4-158471X5
(formula 2)
Wherein, X1Indicate the NDVI mean value of the target area corn of jointing stage；X2It is beautiful for the target area of early stage at heading stage
The NDVI mean value of rice；X3For the NDVI mean value of the target area corn in advanced stage at heading stage；X4For the target area of early stage dough stage
The NDVI mean value of corn；X5For the NDVI mean value of the target area corn in advanced stage dough stage；
It is estimated with corn specific yield of the equation of calibration to predeterminable area.
Technical solution of the present invention has the advantage that
Above scheme proposes a kind of crops recognition methods based on phenology and remote sensing, benefit that can be more accurate
Crops are identified with phenology and remote sensing technology, and further the yield of crops can be estimated, with reality
Existing more scientific effective crops monitoring management.
Detailed description of the invention
Pass through the description carried out with reference to the accompanying drawing to a preferred embodiment of the present invention, technical solution of the present invention
And its technical effect will become clearer, and more easily understand.Wherein:
Fig. 1 is the corn and the NDVI sequence diagram in rice entire growth period of the embodiment of the present invention；
Fig. 2 is the flow diagram that classification tree identifies crops；
Fig. 3 is the relational graph that the rice obtained using the technical solution of the embodiment of the present invention calculates response with real response；
Fig. 4 is the relational graph that the corn obtained using the technical solution of the embodiment of the present invention calculates response with real response.
Specific embodiment
A preferred embodiment of the present invention is described below with reference to appended attached drawing.
Farmland information extraction is one of the difficult point of remote sensing Extracting Thematic Information, because arable land and background atural object are spatially
It inlays, mixture that is interlaced and constituting complexity.When bored, plough because of the crop of plantation, irrigation method and soil attribute
Difference to plough the separability very little of spectral signature between internal different land types.
1, remotely-sensed data source
On 2 11st, 2013, NASA (NASA) succeeded in sending up Landsat-8 satellite.Landsat-8 is defended
Two sensors are carried on star, are that the land OLI imager (Operational Land Imager) and TIRS thermal infrared pass respectively
Sensor (Thermal Infrared Sensor).Landsat-8 spatial resolution and in terms of and Landsat
1-7 maintains almost the same, and satellite one shares 11 wave bands, and the spatial resolution of wave band 1~7,9~11 is 30 meters, wave band 8
For the panchromatic wave-band of 15 meters of resolution ratio, a Global coverage may be implemented within satellite every 16 days.The land OLI imager has 9 waves
Section, imaging wide cut are 185x185km.Compared with the ETM sensor on Landsat-7, the land OLI imager has been done to lower
Whole: the wavelength band of Band 5 is adjusted to 0.845~0.885 μm, eliminates the influence of water vapor absorption at 0.825 μm；Band 8
Panchromatic wave-band range is relatively narrow, so as to more preferably distinguish vegetation and nonvegetated area domain；Increase two wave bands newly.The blue wave of Band 1
Section (0.433~0.453 μm) is mainly used in littoral zone observation, and 9 short infrared wave band of Band (1.360~1.390 μm) is answered
For cloud detection.
The full name of MODIS is Moderate Imaging Spectroradiomete (moderate-resolution imaging
Spectroradio meter), it is an important sensor being mounted on terra and aqua satellite, is unique on satellite
Real-time observed data is directly broadcasted by x wave band to the whole world, and can freely receive the spaceborne instrument of data and use without compensation
Device, many countries and regions in the whole world are all receiving and are using MODIS data.
MODIS product has 44 kinds, can be divided into atmosphere, land, ice and snow, the thematic data product of ocean four, wherein
MOD13Q1 belongs to the product of land special topic, and full name is MODIS/Terra Vegetation Indices 16-Day L3
Global 250m SIN Grid., referred to as: MOD13Q1.
The MOD13Q1 data in the whole world are 3 grades of grid data products using Sinusoidal projection pattern, are had
250 meters of spatial resolution provided primary every 16 days.When lacking the blue wave band of 250 meters of resolution ratio, evi algorithm is used
The remaining atmospheric effect of the blue wave band correction of 500 meters of resolution ratio.
Vegetation index is used to reflect global vegetation environmental condition monitoring and display land cover pattern and land cover pattern variation, this
A little data can be used as the input number of simulation of global biogeochemical process, hydrologic process and the whole world or regional climate
According to, it can also be used to land surface bio-physical property and process, including primary production and windy and sandy soil conversion are described.
NDVI (Normalized Difference Vegetation Index, normalized site attenuation, below
It is referred to as vegetation index) it is a kind of effective land use covering monitoring, density of cover evaluation, crop identification and crop
The technology of yield forecast.Crop has different physiological characteristics in various seasons, different growing, and in some aspects
(such as population characteristic) is reflected by NDVI.Therefore the time changing curve of multidate NDVI data can be showed sufficiently same
Crop different growing and Different Crop same breeding time difference.
It is illustrated for Chinese medicine of embodiment of the present invention corn and rice.Multidate is utilized in the embodiment of the present invention
Landsat-8 satellite phase remote sensing image more than 2015 generates NDVI and its characteristic wave bands, imitates in conjunction with the time change of object spectrum
It should be classified with Spatial Variation information using Decision Tree Algorithm, reach the mesh that high-precision identifies Crop Group
's.
2, the phenology feature of crops:
Phenology be mainly study the plant (including crops) of nature, animal and environmental condition (weather, the hydrology, on
Earth condition) mechanical periodicity and its between correlation science, be the side between climatology, agricultural meteorology and ecology
Edge subject.Influence of the external environment to crop growth and development is an extremely complex process.In general, we use instrument
Certain individual factors of prevailing circumstances condition can be carried out with detection record, and phenological phenomenon can be by the past and now each
Kind environmental factor carries out concentrated expression.
Therefore, phenological phenomenon can be used to the general effect that evaluation environment influences crops, can also be used as simultaneously
The index that integrated environment factor influences.The phenological calendar of the growth of research area's corn and rice is shown in Table 1, and is arrived using in March, 2015
October, more scape Landsat Landsat-8 data, calculated corresponding NDVI value, and NDVI value passes through the 4th of landsat8- product
A red spectral band (band4) calculates with the 5th infrared band (band5) and obtains, and calculation formula is NDVI=(band5-
Band4)/(band5+band4) is calculated using the spatial Analyst-Raster Calculator in Arcgis
(Float (band5)-Float (band4)/Float (band5)+Float (band4)) value, as a result output are that a width NDVI schemes
As, and the point of combined ground observation rice and corn, the NDVI sequence of corn and rice entire growth period is extracted respectively, is seen
Shown in Fig. 1.
The phenological calendar of table 1 corn and rice
The phenological period of corn is analyzed, the first tenday period of a month in May to the middle ten days seeding corn；Late May is to early June maize seed
Sub- endosperm nutrient exhausts substantially, and seedling starts to adopt from soil interior suction point, and corn turns to heterotrophism from autotrophy life and lives；June
The internode of the middle ten days and the last ten days to early July Maize Stem extends rapidly upwards, and plant strain growth is fast at this time, needs large quantity of moisture, nutriment,
NDVI gradually rises；Mid or late July to early or mid August is the heading stage of corn, indicate corn by nutrient growth (root and stem,
The growth of leaf etc.) reproductive growth (blooming, result) is turned to, that is, nutrient growth and reproductive growth is vigorous goes forward side by side the stage,
This is to determine corn yield most critical period, this period is also that growth and development is most fast in life for corn, to nutrient, moisture, temperature
Degree, illumination require most periods, therefore are to be reached most using the critical period of irrigation, ear manuer top dressing in this period NDVI
Big value；Late August starts to step into the maturity period, hereafter gradualling mature with corn, and the chlorophyll content in blade is gradually
It reduces, NDVI is gradually reduced again.With the sowing of corn, growth, heading, maturation, reflect the NDVI value of vegetation growth status
Also there is apparent fluctuation pattern.
The phenological period of rice is analyzed, May to early June sows rice；Mid or late June starts to transplant；July is to 8
The first tenday period of a month in middle of the month rice enters tillering stage, and the solid tiller that can ear born in early days is known as effective tillering, and what advanced stage bore cannot
Heading is eared and acarpous referred to as ineffective tillering；The middle ten days and the last ten days in August to early September is the heading stage of rice, indicates rice
It goes forward side by side the stage into nutrient growth and reproductive growth are vigorous, this is to determine corn yield most critical period, in this period
NDVI reaches maximum value；Start mid-September to step into the maturity period, hereafter gradualling mature with rice, the leaf in blade
Chlorophyll contents are reduced gradually, and NDVI is gradually reduced again.Compare the difference in the phenological period of corn and rice, it can be seen that rice
Heading stage and maturity period integrally lag behind the heading stage and maturity period of corn, and wherein heading stage NDVI reaches maximum value, are reflected in
In NDVI time series, the NDVI peak value of rice shifts to an earlier date than the peak value of corn, and NDVI starts after then respectively coming to the ripening period
Decline.
3, classification tree identifies crops
Due to the presence of corn and rice phenological period difference, this research uses classification tree, using remotely-sensed data to agriculture
Agrotype is classified, and then extracts crop area.Remotely-sensed data has been selected with higher spatial resolution and spectrum point
Four scape Landsat Landsat-8 data of resolution, time are respectively on June 16th, 2015,18 days, 2015 July in 2015
September 4 days, on September 20th, 2015, spatial resolution 30m.Classification tree identification crops process is shown in Fig. 2.September 4 in 2015
The NDVI that date remote sensing images calculate is boundary with 0.15, is considered water body less than 0.15, what it is greater than 0.15 is non-water body.
Further classified to non-water body again, by phenological calendar and the NDVI curve of crops it is found that July and August are important crop
The peak period of growth period and NDVI, therefore the region of crops is planted, the NDVI of mid-June should be less than mid-July, and 9
The NDVI at the beginning of the month should be greater than September end, distinguish agricultural land and non-agricultural land for this as condition.By NDVI peak of curve
Difference compares September in 2015 4, two phase remote sensing satellite data on July 18th, 2015, and the peak value of rice is and beautiful at September 4th
Thus the peak value of rice identified corn and rice, and extract crop acreage July 18.
It is cultivated according to total area under cultivation, rice cultivation area, corn that result is assured that out in identification region is extracted
Area.
4, Remote Sensing Yield Estimation model is established
Traditional Crop Estimation, mainly uses manual area investigation method, and speed is slow, heavy workload, at high cost,
And it is difficult to meet the required precision of crop production forecast.Remote sensing technology have the characteristics that it is macroscopical, objective, quick, inexpensive, can
To overcome the limitation of traditional yield estimation method, and the emerging skill of Crop Estimation in recent decades and Growing state survey has been increasingly becoming it
Art.
Develop on a large scale very much currently, Crop Yield Estimation by Remote has achieved, be summed up, there are mainly three types of types: the first is
Remote Sensing Yield Estimation model based on agronomy mechanism mainly utilizes water, nitrogen needed for the spectral information inverting vegetation growth of remote sensing image
Equal nutrients information, and then vegetation growing way situation is obtained, obtain final grain yield.Such as Feng Wei is contained by measuring plant nitrogen
Amount, weight and leaf area index and maturity period grain yield, the phase of quantitative analysis wheat grain yield and Canop hyperspectrum parameter
Mutual relation, and establish the crop kernel Production Forecast Models based on EO-1 hyperion parameter.Second is based on remote sensing and crop
The Yield Estimation Model of growth model mainly utilizes Remote Spectra information reciprocal portions plant growth parameter, and and crop growth model
In conjunction with establishing plant growth Remote Sensing Yield Estimation model.Such as Padilla is using GRAMI model and TM remote sensing image to Spain south
Area crops production in portion's is monitored, and achieves more satisfied estimation result.
The third is the Remote Sensing Yield Estimation model based on vegetation index, mainly utilizes Remote Spectra information inverting vegetation index,
And the relational model of vegetation index and yield is established, obtain final grain yield.Normalized differential vegetation index NDVI is as a kind of
One of common vegetation index, is more used to study crop condition monitoring and Granule weight.Normalized differential vegetation index is not only
Reflect vegetation growth status, productivity and other biophysics, chemical feature, can also eliminate with solar elevation,
The influence of shape, shade and atmospheric conditions to satellite sounding spectral information, variation and crop growth conditions, developmental stage relationship
Closely.Therefore, NDVI is widely used in terms of crop biomass, leaf area, crop yield.
Moriondo etc. establishes crop yield appraising model using NDVI data set, and to model accuracy carried out verifying on the spot and
Assessment.This research just uses the third Remote Sensing Yield Estimation model, establishes the relationship of vegetation index NDVI and yield.
4.1, the Yield Estimation Model of rice
It can be seen that from each key developmental stages of paddy growth, the NDVI value of paddy growth early period can reflect rice shoot battalion
The case where feeding quality, mid-term can reflect the growth change of rice shoot to spike of rice growth change, whether the later period can reflect rice
The case where green stalk yellow maturity or lodging, it all cannot accurately estimate very much the yield of rice.When comparing single breeding time, heading
The indices of phase are more excellent with respect to other single breeding times, and after being primarily due to Rice Heading, growth change is larger, variation
The intensity of direction and variation has key effect to the height of rice yield, and will determine rice whether early ageing, green stalk
Yellow maturity, remaining green when it is due to become yellow and ripe excessive growth even lodge.The composite model that Crop growing stage is combined and the independent model phase of corresponding breeding time
Than multiple breeding time combinations can more reflect the prolonged NDVI value variation of rice from mechanism, be able to reflect in entire breeding time
The variation of rice growing way, reduces the error between independent breeding time and yield.
Use 8 years 2003-2010 years Tieling rice data for sample point, in conjunction with 3 breeding time (tillers of rice
Phase, heading stage, maturity period) in 5 phase MODIS-NDVI image datas (see Fig. 4, early July, mid-July, early August, 9
The first tenday period of a month moon and mid-September).
The NDVI for establishing Monitoring of Paddy Rice Plant Area each pixel in Tieling under 8 years 2003-2010 years different growing stages is equal
Value and the 8 years yield per unit area in Tieling establish multivariate regression models (see formula 4-1), estimate to rice specific yield
It calculates compared with actual value, the correlativity chosen between equation model related coefficient index, calculating and reality is shown in Fig. 3, to polynary
Regression model carries out evaluation analysis.
Y=2116.8X1+9338.4X2+3351.4X3+13829.7X4–17930.9X5 -2300.4
Wherein, X1Indicate the NDVI mean value of the first tenday period of a month in July Tieling rice；X2Indicate mid-July Tieling rice
NDVI mean value；X3Indicate the NDVI mean value of early August Tieling rice；X4Indicate that the NDVI of the first tenday period of a month in September Tieling rice is equal
Value；X5Indicate the NDVI mean value of mid-September Tieling rice.R2=0.637.
It is carried out with 2015 rice specific yield of the equation of calibration to bavin River Reservoir drinking water source area second protection zone
Estimation.Estimation result is shown in Table 2.Interpretation result of the Monitoring of Paddy Rice Plant Area result in remote sensing difference one section of agrotype.
Rice total output is 1925.8 tons.
2 rice yield estimation by remote sensing result of table
4.2, the Yield Estimation Model of corn
It can be seen that from each key developmental stages of corn growth, the NDVI value of corn growth early period can reflect rice shoot battalion
Feeding quality, mid-term can reflect the growth change of rice shoot to the case where corn growth variation, and whether the later period can reflect corn
The case where green stalk yellow maturity or lodging, it all cannot accurately estimate very much the yield of corn.When comparing single breeding time, heading
The indices of phase are more excellent with respect to other single breeding times, and after being primarily due to corn heading, growth change is larger, variation
The intensity of direction and variation has key effect to the height of corn yield, and will determine corn whether early ageing, green stalk
Yellow maturity, remaining green when it is due to become yellow and ripe excessive growth even lodge.The composite model that Crop growing stage is combined and the independent model phase of corresponding breeding time
Than multiple breeding time combinations can more reflect the prolonged NDVI value variation of corn from mechanism, be able to reflect in entire breeding time
The variation of corn growing way, reduces the error between independent breeding time and yield.
Use 8 years 2003-2010 years Tieling corn data for sample point, in conjunction with 3 breeding time (jointing of corn
Phase, heading stage, dough stage) in 5 image data (the first tenday period of a month in July, mid-July, early August, early Septembers phase MODIS-NDVI
And mid-September).Establish the NDVI of maize sown area each pixel in Tieling under 8 years 2003-2010 years different growing stages
Mean value and the 8 years yield per unit area in Tieling establish multivariate regression models (see formula 2), estimate to corn specific yield
It calculates compared with actual value, the correlativity figure (see Fig. 4) chosen between equation model related coefficient index, estimation and reality is right
Multivariate regression models carries out evaluation analysis.
Y=4639-108574X1+46498X2+19556X3+191661X4-158471X5
Wherein, X1Indicate the NDVI mean value of the first tenday period of a month in July Tieling corn；X2Indicate mid-July Tieling corn
NDVI mean value；X3Indicate the NDVI mean value of early August Tieling corn；X4Indicate that the NDVI of the first tenday period of a month in September Tieling corn is equal
Value；X5Indicate the NDVI mean value of mid-September Tieling corn.R2=0.914.
It is carried out with 2015 corn specific yield of the equation of calibration to bavin River Reservoir drinking water source area second protection zone
Estimation.Estimation result is shown in Table 3.Interpretation result of the maize sown area result in remote sensing difference one section of agrotype.
Corn total output is 73204.7 tons.
3 Remote Sensing in maize yield estimation result of table
For person of ordinary skill in the field, with the development of technology, present inventive concept can be in different ways
It realizes.Embodiments of the present invention are not limited in embodiments described above, and can carry out within the scope of the claims
Variation.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811427585.XA CN109614891A (en) | 2018-11-27 | 2018-11-27 | Crop identification method based on phenology and remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811427585.XA CN109614891A (en) | 2018-11-27 | 2018-11-27 | Crop identification method based on phenology and remote sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109614891A true CN109614891A (en) | 2019-04-12 |
Family
ID=66005299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811427585.XA Pending CN109614891A (en) | 2018-11-27 | 2018-11-27 | Crop identification method based on phenology and remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109614891A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163138A (en) * | 2019-05-13 | 2019-08-23 | 河南科技大学 | A kind of wheat tillering density measuring method based on unmanned plane multi-spectral remote sensing image |
| CN110243406A (en) * | 2019-06-21 | 2019-09-17 | 武汉思众空间信息科技有限公司 | Crop Yield Estimation Method, Device, Electronic Equipment and Storage Medium |
| CN110399860A (en) * | 2019-08-02 | 2019-11-01 | 吉林高分遥感应用研究院有限公司 | A kind of corn damage caused by waterlogging monitoring method and system |
| CN111142106A (en) * | 2020-02-26 | 2020-05-12 | 北京师范大学 | Automatic rice identification method based on synthetic aperture radar time sequence data |
| CN111310639A (en) * | 2020-02-11 | 2020-06-19 | 中国气象科学研究院 | Remote sensing identification method of evergreen plantation forest and remote sensing monitoring method of evergreen plantation growth |
| CN111507303A (en) * | 2020-04-28 | 2020-08-07 | 同济大学 | A kind of detection method of wetland plant species |
| CN112215090A (en) * | 2020-09-21 | 2021-01-12 | 首都师范大学 | Remote sensing rice mapping method based on phenological knowledge and its application |
| CN112580491A (en) * | 2020-12-15 | 2021-03-30 | 广州极飞科技有限公司 | Method and device for determining growth stage of crop and nonvolatile storage device |
| CN112712208A (en) * | 2020-12-31 | 2021-04-27 | 航天信息股份有限公司 | Method and system for predicting yield of rice in key growth period |
| CN114332546A (en) * | 2022-03-17 | 2022-04-12 | 北京艾尔思时代科技有限公司 | Large-scale migration learning crop classification method and system based on phenological matching strategy |
| CN114529097A (en) * | 2022-02-26 | 2022-05-24 | 黑龙江八一农垦大学 | Multi-scale crop phenological period remote sensing dimensionality reduction prediction method |
| CN114548812A (en) * | 2022-03-01 | 2022-05-27 | 武汉鸟瞰天下科技有限公司 | Forest and grassland fire risk prediction decision method, device and computer equipment |
| CN114782832A (en) * | 2022-06-24 | 2022-07-22 | 中国农业科学院农业资源与农业区划研究所 | Crop extraction method and device, readable storage medium and electronic equipment |
| CN114782816A (en) * | 2022-04-28 | 2022-07-22 | 天津大学 | Remote sensing extraction method for crop multiple cropping index |
| CN115004213A (en) * | 2020-02-03 | 2022-09-02 | 国际商业机器公司 | Estimation of crop type and/or sowing date |
| CN115936917A (en) * | 2023-03-09 | 2023-04-07 | 中化现代农业有限公司 | Yield estimation method and device for whole crop, electronic equipment and storage medium |
| CN116542403A (en) * | 2023-07-06 | 2023-08-04 | 航天宏图信息技术股份有限公司 | Crop yield prediction method, device, electronic equipment and readable storage medium |
| CN117788200A (en) * | 2024-02-28 | 2024-03-29 | 杨凌职业技术学院 | Agricultural product maturity prediction system based on multisource remote sensing data |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363949A (en) * | 2017-12-27 | 2018-08-03 | 二十世纪空间技术应用股份有限公司 | A kind of cotton remote-sensing monitoring method based on phenology analysis |
-
2018
- 2018-11-27 CN CN201811427585.XA patent/CN109614891A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363949A (en) * | 2017-12-27 | 2018-08-03 | 二十世纪空间技术应用股份有限公司 | A kind of cotton remote-sensing monitoring method based on phenology analysis |
Non-Patent Citations (1)
| Title |
|---|
| 李嘉薇等: ""基于遥感的饮用水源地农业面源污染负荷估算"", 《生态学杂志》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163138A (en) * | 2019-05-13 | 2019-08-23 | 河南科技大学 | A kind of wheat tillering density measuring method based on unmanned plane multi-spectral remote sensing image |
| CN110163138B (en) * | 2019-05-13 | 2022-03-11 | 河南科技大学 | Method for measuring and calculating wheat tillering density based on multispectral remote sensing image of unmanned aerial vehicle |
| CN110243406A (en) * | 2019-06-21 | 2019-09-17 | 武汉思众空间信息科技有限公司 | Crop Yield Estimation Method, Device, Electronic Equipment and Storage Medium |
| CN110243406B (en) * | 2019-06-21 | 2021-06-15 | 武汉思众空间信息科技有限公司 | Crop yield estimation method, device, electronic device and storage medium |
| CN110399860B (en) * | 2019-08-02 | 2021-04-09 | 吉林高分遥感应用研究院有限公司 | Corn flood monitoring method and system |
| CN110399860A (en) * | 2019-08-02 | 2019-11-01 | 吉林高分遥感应用研究院有限公司 | A kind of corn damage caused by waterlogging monitoring method and system |
| CN115004213A (en) * | 2020-02-03 | 2022-09-02 | 国际商业机器公司 | Estimation of crop type and/or sowing date |
| CN111310639A (en) * | 2020-02-11 | 2020-06-19 | 中国气象科学研究院 | Remote sensing identification method of evergreen plantation forest and remote sensing monitoring method of evergreen plantation growth |
| CN111310639B (en) * | 2020-02-11 | 2020-10-23 | 中国气象科学研究院 | Evergreen artificial forest remote sensing identification method and evergreen artificial forest growth remote sensing monitoring method |
| CN111142106B (en) * | 2020-02-26 | 2021-12-03 | 北京师范大学 | Automatic rice identification method based on synthetic aperture radar time sequence data |
| CN111142106A (en) * | 2020-02-26 | 2020-05-12 | 北京师范大学 | Automatic rice identification method based on synthetic aperture radar time sequence data |
| CN111507303A (en) * | 2020-04-28 | 2020-08-07 | 同济大学 | A kind of detection method of wetland plant species |
| CN112215090A (en) * | 2020-09-21 | 2021-01-12 | 首都师范大学 | Remote sensing rice mapping method based on phenological knowledge and its application |
| CN112215090B (en) * | 2020-09-21 | 2023-05-02 | 北京航天绘景科技有限公司 | Remote sensing rice mapping method fusing knowledge of weather and application thereof |
| CN112580491A (en) * | 2020-12-15 | 2021-03-30 | 广州极飞科技有限公司 | Method and device for determining growth stage of crop and nonvolatile storage device |
| CN112712208A (en) * | 2020-12-31 | 2021-04-27 | 航天信息股份有限公司 | Method and system for predicting yield of rice in key growth period |
| CN114529097A (en) * | 2022-02-26 | 2022-05-24 | 黑龙江八一农垦大学 | Multi-scale crop phenological period remote sensing dimensionality reduction prediction method |
| CN114529097B (en) * | 2022-02-26 | 2023-01-24 | 黑龙江八一农垦大学 | Multi-scale crop phenological period remote sensing dimensionality reduction prediction method |
| CN114548812A (en) * | 2022-03-01 | 2022-05-27 | 武汉鸟瞰天下科技有限公司 | Forest and grassland fire risk prediction decision method, device and computer equipment |
| CN114332546A (en) * | 2022-03-17 | 2022-04-12 | 北京艾尔思时代科技有限公司 | Large-scale migration learning crop classification method and system based on phenological matching strategy |
| CN114782816A (en) * | 2022-04-28 | 2022-07-22 | 天津大学 | Remote sensing extraction method for crop multiple cropping index |
| CN114782816B (en) * | 2022-04-28 | 2023-03-24 | 天津大学 | A Remote Sensing Extraction Method for Multiple Crop Index |
| CN114782832A (en) * | 2022-06-24 | 2022-07-22 | 中国农业科学院农业资源与农业区划研究所 | Crop extraction method and device, readable storage medium and electronic equipment |
| CN115936917A (en) * | 2023-03-09 | 2023-04-07 | 中化现代农业有限公司 | Yield estimation method and device for whole crop, electronic equipment and storage medium |
| CN115936917B (en) * | 2023-03-09 | 2023-08-08 | 中化现代农业有限公司 | Yield estimation method and device for whole crop, electronic equipment and storage medium |
| CN116542403A (en) * | 2023-07-06 | 2023-08-04 | 航天宏图信息技术股份有限公司 | Crop yield prediction method, device, electronic equipment and readable storage medium |
| CN116542403B (en) * | 2023-07-06 | 2023-10-20 | 航天宏图信息技术股份有限公司 | Crop yield prediction method, device, electronic equipment and readable storage medium |
| CN117788200A (en) * | 2024-02-28 | 2024-03-29 | 杨凌职业技术学院 | Agricultural product maturity prediction system based on multisource remote sensing data |
| CN117788200B (en) * | 2024-02-28 | 2024-05-10 | 杨凌职业技术学院 | Agricultural product maturity prediction system based on multisource remote sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109614891A (en) | Crop identification method based on phenology and remote sensing | |
| US10028426B2 (en) | Agronomic systems, methods and apparatuses | |
| Huang et al. | Improving winter wheat yield estimation by assimilation of the leaf area index from Landsat TM and MODIS data into the WOFOST model | |
| Jongschaap | Run-time calibration of simulation models by integrating remote sensing estimates of leaf area index and canopy nitrogen | |
| Xiao et al. | Quantitative relationships between field-measured leaf area index and vegetation index derived from VEGETATION images for paddy rice fields | |
| CN109829234A (en) | A kind of across scale Dynamic High-accuracy crop condition monitoring and yield estimation method based on high-definition remote sensing data and crop modeling | |
| US20180014452A1 (en) | Agronomic systems, methods and apparatuses | |
| CN106600434A (en) | Remote crop growth status monitoring method based on crop model and assimilation technology | |
| Wang et al. | Large-area rice yield forecasting using satellite imageries | |
| Bai et al. | Jujube yield prediction method combining Landsat 8 Vegetation Index and the phenological length | |
| CN107273820A (en) | A kind of Land Cover Classification method and system | |
| Bai et al. | Growth simulation and yield prediction for perennial jujube fruit tree by integrating age into the WOFOST model | |
| Caturegli et al. | GeoEye-1 satellite versus ground-based multispectral data for estimating nitrogen status of turfgrasses | |
| Amankulova et al. | Time-series analysis of Sentinel-2 satellite images for sunflower yield estimation | |
| CN107941713A (en) | A kind of rice yield estimation method based on coupling crop modeling assimilation spectral reflectivity | |
| Ge et al. | Estimating rice yield by assimilating UAV-derived plant nitrogen concentration into the DSSAT model: Evaluation at different assimilation time windows | |
| Liu et al. | Influences of agricultural phenology dynamic on land surface biophysical process and climate feedback | |
| Ranđelović et al. | High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data | |
| Song et al. | Evaluation of Landsat 8 time series image stacks for predicitng yield and yield components of winter wheat | |
| Ali et al. | Broad Scope of Site‐Specific Crop Management and Specific Role of Remote Sensing Technologies Within It—A Review | |
| Hu et al. | Retrieval of photosynthetic capability for yield gap attribution in maize via model-data fusion | |
| Yamanura et al. | NDVI derived LAI model: a novel tool for crop monitoring. | |
| Fan et al. | Sent2Agri System Based Crop Type Mapping in Yellow River Irrigation Area | |
| Stoyanova et al. | Unmanned drone multispectral imaging for assessment of wheat and oilseed rape habitus. | |
| Patel et al. | Precision nutrient management |
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 |
Application publication date: 20190412 |
|
| RJ01 | Rejection of invention patent application after publication |