CN114299393A - Tobacco and rice planting mode identification method based on optical and radar time sequence data - Google Patents
Tobacco and rice planting mode identification method based on optical and radar time sequence data Download PDFInfo
- Publication number
- CN114299393A CN114299393A CN202111637590.5A CN202111637590A CN114299393A CN 114299393 A CN114299393 A CN 114299393A CN 202111637590 A CN202111637590 A CN 202111637590A CN 114299393 A CN114299393 A CN 114299393A
- Authority
- CN
- China
- Prior art keywords
- index
- tobacco
- time sequence
- pixel
- vegetation
- 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
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 68
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 57
- 235000009566 rice Nutrition 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000003287 optical effect Effects 0.000 title claims abstract description 19
- 244000061176 Nicotiana tabacum Species 0.000 title 1
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000208125 Nicotiana Species 0.000 claims abstract description 67
- 241000209094 Oryza Species 0.000 claims abstract description 56
- 230000010287 polarization Effects 0.000 claims abstract description 42
- 239000000049 pigment Substances 0.000 claims abstract description 27
- 238000011160 research Methods 0.000 claims abstract description 27
- 229930002877 anthocyanin Natural products 0.000 claims abstract description 24
- 235000010208 anthocyanin Nutrition 0.000 claims abstract description 24
- 239000004410 anthocyanin Substances 0.000 claims abstract description 24
- 150000004636 anthocyanins Chemical class 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 11
- 101001057166 Homo sapiens Protein EVI2A Proteins 0.000 claims description 16
- 102100027246 Protein EVI2A Human genes 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010168 coupling process Methods 0.000 claims description 9
- 238000005859 coupling reaction Methods 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 6
- 238000012567 pattern recognition method Methods 0.000 claims description 6
- 238000002310 reflectometry Methods 0.000 claims description 6
- 238000003909 pattern recognition Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000010899 nucleation Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 2
- 238000013507 mapping Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 241000209140 Triticum Species 0.000 description 4
- 235000021307 Triticum Nutrition 0.000 description 4
- 240000008042 Zea mays Species 0.000 description 4
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 4
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 4
- 235000005822 corn Nutrition 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000009336 multiple cropping Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000013339 cereals Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013074 reference sample Substances 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a tobacco and rice planting mode identification method based on optical and radar time sequence data, which comprises the following steps: step S01: establishing a time sequence data set of a vegetation index and an anthocyanin index in a research area; step S02: establishing a VV polarization signal time sequence data set of a research area; step S03: designing a vegetation-pigment high-high overlapping degree index; step S04: dividing the growth periods of the front and rear crops; step S05: designing VV amplitude variation indexes of the previous stubble and the next stubble; step S06: designing a VH valley bottom curvature index; step S07: establishing a tobacco and rice planting mode identification technical process; step S08: and obtaining a tobacco and rice planting mode space distribution map of a research area. The method has strong interpretability, simplicity and feasibility, good robustness and large-scale multi-year automatic application and popularization capability without depending on training sample data.
Description
Technical Field
The invention belongs to the technical field of crop remote sensing, and particularly relates to a tobacco and rice planting mode identification method based on optical and radar time sequence data.
Background
China, as the largest tobacco producing and consuming nation in the world, dominates the tobacco industry all over the world. On one hand, smoking damages health, and on the other hand, the flue-cured tobacco industry plays an important role in the development of socioeconomic performance as the supporting industry of provinces such as Yunnan in south China. The method has the advantages that the distribution information of the planting area of the flue-cured tobacco is accurately acquired in a high-aging mode, and the method is very important for ensuring the stable development of the flue-cured tobacco industry. Traditional manual investigation of crop collection is very costly to distribute and has limited coverage. The time sequence remote sensing image data with higher time, space and spectral resolution provides an uncommon opportunity for crop distribution mapping, but also provides higher requirements for remote sensing feature extraction and classification algorithms.
The remote sensing index can effectively monitor corresponding ground feature characteristics by carrying out combined operation on the ground feature spectral channels. Common remote sensing indexes include vegetation indexes, water indexes, building indexes, soil indexes and the like. In recent years, some agricultural remote sensing scholars successively put forward remote sensing indexes respectively aiming at bulk crops such as rice, winter wheat and corn. The crop remote sensing indexes are designed by fully excavating the unique change characteristics of a certain crop in the key phenological period of the crop, so that the crop can be effectively distinguished, and a certain effect is achieved in the application of agricultural remote sensing technology. For example, based on the characteristic that rice needs to be transplanted and irrigated, the rice index is designed by integrating the relative variability characteristics of the vegetation index and the water body index from the tillering stage to the heading stage, and the method can be used for large-area rice distribution mapping.
At present, related crop remote sensing indexes are only limited to main grain crops, a few oil crops and the like, and no crop remote sensing index specially aiming at flue-cured tobacco exists. Compared with other crops, the remote sensing monitoring technology for flue-cured tobacco has relatively few researches. The main reasons for this are: on one hand, the flue-cured tobacco planting is scattered relatively sporadically and is mixed with other crops, so that the difficulty is brought to remote sensing mapping of the flue-cured tobacco; on the other hand, flue-cured tobacco in China is mostly distributed in a southern humid area, and due to the fact that the flue-cured tobacco is cloudy and rainy all the year round, the data availability of optical remote sensing images is generally influenced, so that the crop mapping precision based on optical remote sensing data is reduced to a great extent, and the industrial application requirements are generally difficult to meet.
At present, on the basis of obtaining a farmland multiple cropping index, crop planting times and a corresponding growing period of crops in one year are determined, and then time sequence remote sensing image features are extracted in the growing period of the crops to identify different crop types. The problem faced by the research scheme is that the cultivated land multiple cropping index is usually based on vegetation index time sequence curve characteristics, and the data precision of the southern cloudy and rainy region in China is difficult to guarantee. The method is expected to effectively solve the problem by directly carrying out remote sensing monitoring on the crop planting mode through a research scheme implemented by jumping out the farmland multiple cropping index-crop type identification step by step.
The Sentinel-2 MSI time sequence remote sensing data has ideal time, space and spectral resolution, and three unique red light edge wave bands, so that a good opportunity is brought to crop remote sensing mapping. The Sentinel-1 radar time sequence data is beneficial to effectively making up the loss of the time sequence data in the cloudy and rainy region so as to improve the mapping precision of crops. The tobacco and rice planting mode can not only ensure the safe supply of grains, but also effectively increase the income of farmers, thereby being widely popularized and applied in the southern provinces of China.
Disclosure of Invention
The invention aims to provide a tobacco and rice planting mode identification method based on optical and radar time sequence data, which has strong interpretability, is simple and feasible, has good robustness, and has large-scale multi-year automatic application and popularization capability under the condition of not depending on training sample data.
In order to achieve the purpose, the invention adopts the technical scheme that: a tobacco and rice planting pattern recognition method based on optical and radar time sequence data comprises the following steps:
step S01: establishing a time sequence data set of a vegetation index and an anthocyanin index in a research area;
step S02: establishing a VV polarization signal time sequence data set of a research area;
step S03: designing a vegetation-pigment high-high overlapping degree index;
step S04: dividing the growth periods of the front and rear crops;
step S05: designing VV amplitude variation indexes of the previous stubble and the next stubble;
step S06: designing a VH valley bottom curvature index;
step S07: establishing a tobacco and rice planting mode identification technical process;
step S08: and obtaining a tobacco and rice planting mode space distribution map of a research area.
Further, in the step S01, based on the red light and near-infrared band reflectivity data of Sentinel-2, calculating vegetation indexes EVI2 pixel by pixel and period by period, respectively, so as to obtain an EVI2 time-series data set of the year of the research area; similarly, on the basis of green light and first red side band reflectivity data of Sentinel-2, respectively calculating anthocyanin indexes (ARI) pixel by pixel and period by period, thereby obtaining an ARI time sequence data set of the year in the research area; according to the cloud coverage condition, eliminating observation records with clouds; the sequential data sets of EVI2 and ARI indexes which are continuously and smoothly performed day by day are constructed by adopting a Whittaker smooth data smoothing method on the basis of the effective observation sequential data sets of the EVI2 and the ARI indexes on the basis of cloudless days by pixel.
Further, in step S02, based on the 10-day Sentinel-1 VV and VH polarization data of the GEE cloud platform, a year-by-year VV polarization signal timing data set of the pixel is obtained by a pixel-by-pixel linear interpolation method.
Further, in the step S03, the median M of the annual daily vegetation index time series data is extracted pixel by pixelEVI2Will be greater than the median MEVI2The numerical range of (1) is called a vegetation index high value range EVI 2-H; similarly, the median M of day-to-day anthocyanin index time sequence data in the year is extracted pixel by pixelARIWill be greater than the median MARIThe numerical range of (a) is called an anthocyanin index high value range ARI-H; on the basis of obtaining the vegetation index and anthocyanin index high-value intervals, further calculating the intersection of the vegetation index and the anthocyanin index, namely a set of the vegetation index and the anthocyanin index which are both in the high-value intervals, and defining the set as a vegetation-pigment high-high coupling interval; defining the number No-HH of observed data in the vegetation-pigment high-high coupling interval as the percentage of half of the number No-Year of the observed data in the whole Year, and the calculation formula is as follows:
HHR=2×(No-HH/No-Year) ×100%
wherein HHR represents the vegetation-pigment high overlapping degree, No-HH represents the number of observed data in the vegetation-pigment high-coupling interval, and No-Yeast represents the number of observed data in the whole Year.
Further, in the step S04, the cultivation and seeding habit and the crop season in the tobacco and rice planting mode are divided into the preceding and following crop growth periods; sequentially determining the time of the first half year and the time of the second half year as the growth periods of the previous crops and the next crops; the specific strategy is that the 1 st to 182 th days are divided into the growth period of the previous crops; and the 183-.
Further, in step S05, the annual time series data sets of VV polarization signals are sorted pixel by pixel, and the minimum VV values are recorded in sequence and recorded respectivelyminFirst quantile VVq1VV of the third quantile q3And maximum value VVmax(ii) a Within the VV polarization signal annual time series data set, calculating VV greater than or equal to a third quantile q3The mean of all data, recorded as VVMeanTopThe VV high value interval mean value is represented; then, within the time-series data set of the VV polarization signal year, a VV less than or equal to the first quantile is calculatedq1Is recorded as VVMeandownThe average value of the VV low value interval is shown; defining the difference between the high-value interval mean value and the low-value interval mean value of the VV polarization signal as a previous and next VV amplitude variation index VVC; the VV amplitude variation index VVC of the previous and next stubbles has the calculation formula as follows:
VVC=VVMeanTop-VVMeandown
wherein VVC represents the variable amplitude index of VV of the succeeding crop, VVMeanTopRepresents the mean value, VVM mean, of all data in the time sequence data set greater than or equal to the third quantile within the VV year of the pixeldownRepresenting the mean of all data in the time series data set less than or equal to the first quantile over the VV year.
Further, in step S06, the minimum VH of the annual time series data set of VH polarization signals is searchedminRecording the time as Tmin; from Tmin, search for VH polarization signal time sequence in yearThe curve is obtained by counting the continuous increase of VH in 60 days and recording the result as VHAP(ii) a In the above search process, if the previous day VH polarization signal value VH is encounteredt-1Less than the current day's VH polarization signal value VHtIf so, stopping searching; designing a VH valley bottom curvature index VHR, wherein the calculation formula is as follows:
VHR=VHAP*( VHAP /(VHmax-VHmin))
wherein VHR represents a VH valley bottom curvature index, VHminRepresenting the minimum of the annual time series data set of the VH polarization signal, VHAPIndicates the continuous increase of VH within 60 days before the Tmin.
Further, in the step S07, establishing a tobacco and rice planting pattern recognition technical process according to three indexes of VV amplitude VVC, VH valley bottom curvature VHR and vegetation-pigment high-high overlapping degree HHR of the previous and subsequent crops; the specific judgment rule is as follows:
if VVC is satisfied at the same time>θ 1、VHR>θ 2、HHR>θ 3If not, the pixel is in a tobacco and rice planting mode, otherwise, the pixel is in other crop planting modes.
Compared with the prior art, the invention has the following beneficial effects:
(1) the method has good robustness, and can be popularized and applied in large scale for many years without adjusting according to additional reference sample data.
(2) The method is simple and easy to implement, and can realize automatic identification of the tobacco and rice planting mode through simple decision rules according to the three designed time sequence indexes.
(3) The interpretability is strong, three time sequence indexes based on domain knowledge are designed from the aspects of VV, VH and vegetation-pigment spectral index time sequence characteristics by analyzing the growth characteristics of tobacco leaves and rice, namely the characteristics of the tobacco leaves and the rice that the leaves are tall and the rice needs to be harvested instead of fruits and rice in the flood irrigation and drought rotation planting mode, so that the interpretability and the automatic drawing capability of the method are ensured.
(4) The requirement on time sequence remote sensing data is not high, open free Sentinel-1 radar time sequence data is fully utilized, interference caused by optical data deletion in cloudy and rainy areas is avoided, and the application and popularization capability of the method in tobacco planting main production areas in south China is ensured.
(5) The time sequence index is designed based on the overall distribution characteristics of the radar time sequence signal or the spectrum index time sequence data, so that the interference of data noise on the designed time sequence index is effectively avoided, and the robustness and the application popularization capability of the method are further improved.
Drawings
Fig. 1 is a flow chart of an implementation of the embodiment of the present invention.
FIG. 2 is a diagram of EVI2 and ARI timing signals of tobacco rice, winter wheat and corn in the embodiment of the invention.
FIG. 3 is a diagram of EVI2 and VV timing signals of tobacco rice, winter wheat and corn in the embodiment of the invention.
FIG. 4 is a diagram of the EVI2 and VH time sequence signals of tobacco rice, winter wheat and corn in the example of the invention.
FIG. 5 shows the vegetation-pigment high degree of overlap of the tobacco and rice planting patterns of the present invention.
FIG. 6 shows the vegetation-pigment high overlap for the winter wheat-corn mode of the present invention.
FIG. 7 is a flow chart of a tobacco and rice planting pattern recognition technique according to an embodiment of the present invention.
FIG. 8 is a spatial distribution diagram of tobacco and rice planting patterns in a study area according to an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the embodiment provides a tobacco planting pattern recognition method based on optical and radar time sequence data, which includes the following steps:
step S01: establishing a time sequence data set of a vegetation index and an anthocyanin index in a research area;
step S02: establishing a VV polarization signal time sequence data set of a research area;
step S03: designing a vegetation-pigment high-high overlapping degree index;
step S04: dividing the growth periods of the front and rear crops;
step S05: designing VV amplitude variation indexes of the previous stubble and the next stubble;
step S06: designing a VH valley bottom curvature index;
step S07: establishing a tobacco and rice planting mode identification technical process;
step S08: and obtaining a tobacco and rice planting mode space distribution map of a research area.
Step S01: establishing a time sequence data set of vegetation index and anthocyanin index in a research area
Based on the red light and near infrared band reflectivity data of Sentinel Sentinel-2, the vegetation index EVI2 is calculated pixel by pixel and period by period, and accordingly an EVI2 time sequence data set of the year in the research area is obtained. Similarly, on the basis of the green light and first red side band reflectivity data of the Sentinel-2, the anthocyanin index ARI is calculated pixel by pixel and period by period respectively, so that an ARI time sequence data set of the year in the research area is obtained. And according to the cloud coverage condition, removing the observation records with the cloud. The sequential data sets of EVI2 and ARI indexes which are continuously and smoothly performed day by day are constructed by adopting a Whittaker smooth data smoothing method on the basis of the effective observation sequential data sets of the EVI2 and the ARI indexes on the basis of cloudless days by pixel. The constructed time sequence signal diagram of the EVI2 and ARI indexes of the tobacco rice and the winter wheat-corn is shown in figure 2.
Step S02: establishing a VV and VH polarization signal timing data set of a research region
Based on 10-day Sentinel-1 VV and VH polarization data of the GEE cloud platform, a pixel-by-pixel day-by-day VV polarization signal time sequence data set of the pixel is obtained based on a linear interpolation method. Based on the annual time sequence data set of the day-by-day VV polarization signal in the research area, the created VV time sequence graph of the planting modes of different crops such as tobacco rice, winter wheat-corn and the like is shown in fig. 3. Based on the annual time series data set of daily VH polarization signals in the research area, the established VH time series curve graph of the tobacco rice and the winter wheat-corn is shown in FIG. 4.
Step S03: design of high degree of vegetation-pigment overlap
Median M for extracting day-to-day vegetation index time sequence data in year in pixel-by-pixel mannerEVI2Will be greater than the median MEVI2The numerical interval of (2) is called a vegetation index high value interval EVI 2-H. Similarly, the median M of day-to-day anthocyanin index time sequence data in the year is extracted pixel by pixelARIWill be greater than the median MARIThe interval of values of (a) is called the anthocyanin index high value interval ARI-H. On the basis of obtaining the high value intervals of the vegetation index and the anthocyanin index, further calculating the intersection of the vegetation index and the anthocyanin index, namely a set of the vegetation index and the anthocyanin index which are both in the high value intervals, and defining the set as a vegetation-pigment high-high coupling interval. And defining the number (No-HH) of observed data in the vegetation-pigment high-high coupling interval as the percentage of half of the number (No-Yeast) of observed data in the whole Year as the vegetation-pigment high-overlapping HHR. The calculation formula is as follows:
HHR=2×(No-HH/No-Year) ×100%
wherein HHR represents the vegetation-pigment high overlapping degree, No-HH represents the number of observed data in the vegetation-pigment high-coupling interval, and No-Yeast represents the number of observed data in the whole Year.
The vegetation-pigment high-overlapping degree of the two designed planting modes of the tobacco rice and the winter wheat-corn are respectively shown in fig. 5 and fig. 6.
Step S04: dividing the front and rear crop growth periods
The tobacco and rice planting mode, the growing period of tobacco and rice, is usually mainly in the first and second half years, respectively. Therefore, the cultivation and seeding habits and the crop phenological period according to the tobacco and rice planting mode are divided into the front and rear crop growth periods. The first half year and the second half year are determined as the growth period of the previous crop and the next crop in turn. The specific strategy is that the 1 st to 182 th days are divided into the growth period of the previous crops; and the 183-.
Step S05: VV amplitude variation index of stubbles before and after design
Sequencing time sequence data sets of VV polarization signals in year by pixel, and sequentially and respectively recording minimum VVminFirst quantile VVq1VV of the third quantile q3And maximum value VVmax. Calculating a third fractional number (VV) or greater within the time-series data set of the VV polarization signal year q3) The mean of all data, recorded as VVMeanTopThe VV mean value of the high interval is shown. Then, within the time-series data set of the VV polarization signal year, a first quantile (VV) or less is calculatedq1) Is recorded as VVMeandownThe average value of the VV low interval is shown. And defining the difference between the high-value interval mean value and the low-value interval mean value of the VV polarization signal as a previous and next VV amplitude variation index VVC. The VV amplitude variation index VVC of the previous and next stubbles has the calculation formula as follows:
VVC=VVMeanTop-VVMeandown
wherein VVC represents the variable amplitude index of VV of the succeeding crop, VVMeanTopRepresents the mean value, VVM mean, of all data in the time sequence data set greater than or equal to the third quantile within the VV year of the pixeldownRepresenting the mean of all data in the time series data set less than or equal to the first quantile over the VV year.
Step S06: design of VH valley bottom curvature index
Search for the minimum VH of a set of annual time series data of VH polarization signalsminThe time is recorded as Tmin. Searching a VH polarization signal time sequence curve in year from Tmin, counting the continuous increase of VH in 60 days, and accumulating and recording the continuous increase as VHAP. In the above search process, if the previous day VH polarization signal value VH is encounteredt-1Less than the current day's VH polarization signal value VHtWill stop the search. Designing a VH valley bottom curvature index VHR, wherein the calculation formula is as follows:
VHR=VHAP*( VHAP /(VHmax-VHmin))
wherein VHR represents a VH valley bottom curvature index, VHminRepresenting the minimum of the annual time series data set of the VH polarization signal, VHAPIndicates the continuous increase of VH within 60 days before the Tmin.
Step S07: technical process for establishing tobacco and rice planting mode recognition
In a tobacco and rice planting mode, in the first-season crop growth prime period, tobacco leaves are upright in plant type, flourishing in plants and large in leaves, and VV and VH polarization signals are strong; in the second crop rice, because flood irrigation is needed in the transplanting period, the ground surface is basically covered by water, and the VV and VH polarization signals are weak. Therefore, compared with other crop planting modes, the tobacco and rice planting mode has the characteristics of large VV amplitude index and large VH valley bottom curvature index of the front and the back crops. In the growing period of the tobacco leaves, the vegetation index and the anthocyanin show the homodromous change characteristic, namely, a large intersection exists in a vegetation-pigment high-value interval, and the characteristic of high vegetation-pigment overlapping degree is shown. Therefore, the tobacco and rice planting pattern recognition technical process can be established according to three indexes of VV amplitude variation (VVC) of previous and subsequent crops, VH valley bottom curvature (VHR) and vegetation-pigment high-overlapping degree (HHR). The specific judgment rule is as follows:
if VVC is satisfied at the same time>θ 1、VHR>θ 2、HHR>θ 3If not, the pixel is in a tobacco and rice planting mode, otherwise, the pixel is in other crop planting modes. In the present embodiment, it is preferred that,θ 1、θ 2、θ 3the values are respectively theta1=4, θ2=4.8, θ3=48%。
The invention establishes a tobacco planting mode identification method flow based on optical and radar time sequence data, as shown in figure 7.
Step S8: obtaining the tobacco and rice planting mode space distribution map of the research area
Taking the example of the sharp town in summer in san ming city, san ming, of fujian province, according to the flow method provided by this embodiment, the spatial distribution map of flue-cured tobacco in the research area is obtained, as shown in fig. 8.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (8)
1. A tobacco and rice planting pattern recognition method based on optical and radar time sequence data is characterized by comprising the following steps:
step S01: establishing a time sequence data set of a vegetation index and an anthocyanin index in a research area;
step S02: establishing a VV polarization signal time sequence data set of a research area;
step S03: designing a vegetation-pigment high-high overlapping degree index;
step S04: dividing the growth periods of the front and rear crops;
step S05: designing VV amplitude variation indexes of the previous stubble and the next stubble;
step S06: designing a VH valley bottom curvature index;
step S07: establishing a tobacco and rice planting mode identification technical process;
step S08: and obtaining a tobacco and rice planting mode space distribution map of a research area.
2. The tobacco and rice planting pattern recognition method based on optical and radar time sequence data as claimed in claim 1, wherein in step S01, based on the reflectivity data of red light and near infrared bands of Sentinel-2, vegetation indexes EVI2 are calculated respectively pixel by pixel and period by period, so as to obtain EVI2 time sequence data set of the year of the research area; similarly, on the basis of green light and first red side band reflectivity data of Sentinel-2, respectively calculating anthocyanin indexes (ARI) pixel by pixel and period by period, thereby obtaining an ARI time sequence data set of the year in the research area; according to the cloud coverage condition, eliminating observation records with clouds; the sequential data sets of EVI2 and ARI indexes which are continuously and smoothly performed day by day are constructed by adopting a Whittaker smooth data smoothing method on the basis of the effective observation sequential data sets of the EVI2 and the ARI indexes on the basis of cloudless days by pixel.
3. The tobacco and rice planting pattern recognition method based on optical and radar time sequence data as claimed in claim 1, wherein in step S02, based on 10-day Sentinel-1 VV and VH polarization data of the GEE cloud platform, a pixel-by-pixel day-by-day VV polarization signal time sequence data set of the pixel is obtained based on a linear interpolation method.
4. The method for recognizing tobacco and rice planting patterns based on optical and radar time sequence data as claimed in claim 1, wherein in step S03, the median M of the day-by-day vegetation index time sequence data in the year is extracted pixel by pixelEVI2Will be greater than the median MEVI2The numerical range of (1) is called a vegetation index high value range EVI 2-H; similarly, the median M of day-to-day anthocyanin index time sequence data in the year is extracted pixel by pixelARIWill be greater than the median MARIThe numerical range of (a) is called an anthocyanin index high value range ARI-H; on the basis of obtaining the vegetation index and anthocyanin index high-value intervals, further calculating the intersection of the vegetation index and the anthocyanin index, namely a set of the vegetation index and the anthocyanin index which are both in the high-value intervals, and defining the set as a vegetation-pigment high-high coupling interval; defining the number No-HH of observed data in the vegetation-pigment high-high coupling interval as the percentage of half of the number No-Year of the observed data in the whole Year, and the calculation formula is as follows:
HHR=2×(No-HH/No-Year) ×100%
wherein HHR represents the vegetation-pigment high overlapping degree, No-HH represents the number of observed data in the vegetation-pigment high-coupling interval, and No-Yeast represents the number of observed data in the whole Year.
5. The method for recognizing tobacco and rice planting patterns based on optical and radar time series data as claimed in claim 1, wherein in step S04, the cultivation and seeding habits and the crop season of tobacco and rice planting patterns are divided into the front and back crop growth periods; sequentially determining the time of the first half year and the time of the second half year as the growth periods of the previous crops and the next crops; the specific strategy is that the 1 st to 182 th days are divided into the growth period of the previous crops; and the 183-.
6. The method for recognizing tobacco rice planting patterns based on optical and radar time sequence data as claimed in claim 1, wherein in step S05, the VV polarization signal annual time sequence data sets are sorted on a pixel-by-pixel basis, and the minimum VV values are recorded respectivelyminFirst quantile VVq1VV of the third quantile q3And maximum value VVmax(ii) a Within the VV polarization signal annual time series data set, calculating VV greater than or equal to a third quantile q3The mean of all data, recorded as VVMeanTopThe VV high value interval mean value is represented; then, within the time-series data set of the VV polarization signal year, a VV less than or equal to the first quantile is calculatedq1Is recorded as VVMeandownThe average value of the VV low value interval is shown; defining the difference between the high-value interval mean value and the low-value interval mean value of the VV polarization signal as a previous and next VV amplitude variation index VVC; the VV amplitude variation index VVC of the previous and next stubbles has the calculation formula as follows:
VVC=VVMeanTop-VVMeandown
wherein VVC represents the variable amplitude index of VV of the succeeding crop, VVMeanTopRepresents the mean value, VVM mean, of all data in the time sequence data set greater than or equal to the third quantile within the VV year of the pixeldownRepresenting the mean of all data in the time series data set less than or equal to the first quantile over the VV year.
7. The method for recognizing tobacco planting patterns based on optical and radar time series data as claimed in claim 1, wherein in step S06, the minimum VH of the annual time series data set of VH polarization signal is searchedminRecording the time as Tmin; searching a VH polarization signal time sequence curve in year from Tmin, counting the continuous increase of VH in 60 days, and accumulating and recording the continuous increase as VHAP(ii) a In the above search process, if the previous one is encounteredTian VH polarization Signal value VHt-1Less than the current day's VH polarization signal value VHtIf so, stopping searching; designing a VH valley bottom curvature index VHR, wherein the calculation formula is as follows:
VHR=VHAP*( VHAP /(VHmax-VHmin))
wherein VHR represents a VH valley bottom curvature index, VHminRepresenting the minimum of the annual time series data set of the VH polarization signal, VHAPIndicates the continuous increase of VH within 60 days before the Tmin.
8. The tobacco and rice planting pattern recognition method based on the optical and radar time series data as claimed in claim 1, wherein in step S07, a tobacco and rice planting pattern recognition technical process is established according to three indexes of previous and subsequent VV amplitude variation VVC, VH valley bottom curvature VHR and vegetation-pigment high-overlapping degree HHR; the specific judgment rule is as follows:
if VVC is satisfied at the same time>θ 1、VHR>θ 2、HHR>θ 3If not, the pixel is in a tobacco and rice planting mode, otherwise, the pixel is in other crop planting modes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637590.5A CN114299393A (en) | 2021-12-30 | 2021-12-30 | Tobacco and rice planting mode identification method based on optical and radar time sequence data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637590.5A CN114299393A (en) | 2021-12-30 | 2021-12-30 | Tobacco and rice planting mode identification method based on optical and radar time sequence data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299393A true CN114299393A (en) | 2022-04-08 |
Family
ID=80971550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111637590.5A Pending CN114299393A (en) | 2021-12-30 | 2021-12-30 | Tobacco and rice planting mode identification method based on optical and radar time sequence data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299393A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782825A (en) * | 2022-06-17 | 2022-07-22 | 中国农业科学院农业资源与农业区划研究所 | Crop identification method and device based on incomplete remote sensing data and electronic equipment |
| CN117745148A (en) * | 2024-02-10 | 2024-03-22 | 安徽省农业科学院烟草研究所 | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017501671A (en) * | 2013-12-04 | 2017-01-12 | ローベルト ボッシュ ゲゼルシャフト ミット ベシュレンクテル ハフツング | Method and apparatus for driving a vehicle |
| CN106772429A (en) * | 2016-12-24 | 2017-05-31 | 福州大学 | Increase and decrease the corn autodraft method of Ratio index based on peak of growing season NMDI |
| CN111191963A (en) * | 2020-01-21 | 2020-05-22 | 福州大学 | Peanut space distribution mapping method based on pigment change characteristics in growing period |
-
2021
- 2021-12-30 CN CN202111637590.5A patent/CN114299393A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017501671A (en) * | 2013-12-04 | 2017-01-12 | ローベルト ボッシュ ゲゼルシャフト ミット ベシュレンクテル ハフツング | Method and apparatus for driving a vehicle |
| CN106772429A (en) * | 2016-12-24 | 2017-05-31 | 福州大学 | Increase and decrease the corn autodraft method of Ratio index based on peak of growing season NMDI |
| CN111191963A (en) * | 2020-01-21 | 2020-05-22 | 福州大学 | Peanut space distribution mapping method based on pigment change characteristics in growing period |
Non-Patent Citations (2)
| Title |
|---|
| 刘冰洁: ""夜间灯光遥感对城市发展类动能与相似性评估"", 《遥感学报》, 31 May 2021 (2021-05-31) * |
| 邱炳文: ""Scale-location Specific Analysis of Temporal Vegetation Coverage in China"", 《PROCEEDINGS 2015 SECOND IEEE INTERNATIONAL CONFERENCE ON SPATIAL DATA MINING AND GEOGRAPHICAL KNOWLEDGE SERVICES (ICSDM 2015)》, 30 September 2016 (2016-09-30) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782825A (en) * | 2022-06-17 | 2022-07-22 | 中国农业科学院农业资源与农业区划研究所 | Crop identification method and device based on incomplete remote sensing data and electronic equipment |
| CN114782825B (en) * | 2022-06-17 | 2022-09-16 | 中国农业科学院农业资源与农业区划研究所 | Crop identification method and device based on incomplete remote sensing data and electronic equipment |
| CN117745148A (en) * | 2024-02-10 | 2024-03-22 | 安徽省农业科学院烟草研究所 | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system |
| CN117745148B (en) * | 2024-02-10 | 2024-05-10 | 安徽省农业科学院烟草研究所 | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111104858B (en) | Large-scale crop phenology extraction method based on morphological model method | |
| CN112197819A (en) | Plant growth accurate control method based on production base | |
| CN114299393A (en) | Tobacco and rice planting mode identification method based on optical and radar time sequence data | |
| CN109543552B (en) | Rice growth area mapping method and system based on multi-feature extraction in growth period | |
| Fernández et al. | Precision irrigation in olive (Olea europaea L.) tree orchards | |
| CN106529451A (en) | Winter wheat-summer corn plantation mode remote sensing recognition method | |
| CN109740570B (en) | Terrace remote sensing identification method based on terrain index and climate difference | |
| CN110909679A (en) | Remote sensing identification method and system for fallow crop rotation information of winter wheat historical planting area | |
| Marino et al. | Validation of an online system for the continuous monitoring of tree water status for sustainable irrigation managements in olive (Olea europaea L.) | |
| AU2021105575A4 (en) | Automatic Tea Garden Identification Method Based on Cloud Platform Fusion of Multi-Source Satellite Images and Tea Phenological Period | |
| CN113221806A (en) | Cloud platform fusion multi-source satellite image and tea tree phenological period based automatic tea garden identification method | |
| CN111191963A (en) | Peanut space distribution mapping method based on pigment change characteristics in growing period | |
| CN111612777B (en) | Soybean mapping method based on leaf aging and water loss index | |
| CN111275567B (en) | SENP cotton yield estimation method based on unmanned aerial vehicle image and estimation model construction method | |
| CN114708490A (en) | Rice planting extraction and multiple cropping index monitoring method, system, terminal and storage medium | |
| CN110516943B (en) | Surface temperature-based dynamic monitoring and remote sensing method for irrigation area in spring irrigation period | |
| Safi et al. | Translating open-source remote sensing data to crop water productivity improvement actions | |
| CN114549967A (en) | Extraction method and device for garlic planting area | |
| CN107340268B (en) | A kind of dry crop recognition methods based on remote sensing time series data | |
| Zhang et al. | Detecting major phenological stages of rice using MODIS-EVI data and Symlet11 wavelet in Northeast China | |
| CN107609695B (en) | Crop yield remote sensing estimation method based on adjustable vegetation index | |
| CN115063690A (en) | Vegetation classification method based on NDVI (normalized difference vegetation index) time sequence characteristics | |
| CN114663780A (en) | Method and system for identifying river-crossing irrigation area planting structure based on GEE and machine learning | |
| Modina et al. | Variable rate irrigation in a vineyard and an orchard | |
| CN113570251B (en) | Potato drawing method based on nitrogen output accumulation index in early and later growth stages |
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 |