CN108959661A - 3S technology-based soil nutrient grade classification map generation method and precision evaluation method thereof - Google Patents
3S technology-based soil nutrient grade classification map generation method and precision evaluation method thereof Download PDFInfo
- Publication number
- CN108959661A CN108959661A CN201810946788.3A CN201810946788A CN108959661A CN 108959661 A CN108959661 A CN 108959661A CN 201810946788 A CN201810946788 A CN 201810946788A CN 108959661 A CN108959661 A CN 108959661A
- Authority
- CN
- China
- Prior art keywords
- soil nutrient
- class
- ground
- soil
- formula
- 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.)
- Granted
Links
- 239000002689 soil Substances 0.000 title claims abstract description 126
- 235000015097 nutrients Nutrition 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000011156 evaluation Methods 0.000 title claims abstract description 18
- 238000005516 engineering process Methods 0.000 title claims abstract description 17
- 238000009826 distribution Methods 0.000 claims abstract description 21
- 238000012732 spatial analysis Methods 0.000 claims abstract description 12
- 238000000926 separation method Methods 0.000 claims description 35
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 14
- 238000011160 research Methods 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 12
- 239000002131 composite material Substances 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 229910052757 nitrogen Inorganic materials 0.000 claims description 7
- 239000010749 BS 2869 Class C1 Substances 0.000 claims description 6
- 239000010750 BS 2869 Class C2 Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 claims description 6
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 5
- 229910052698 phosphorus Inorganic materials 0.000 claims description 5
- 239000011574 phosphorus Substances 0.000 claims description 5
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 4
- 239000011591 potassium Substances 0.000 claims description 4
- 229910052700 potassium Inorganic materials 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 238000009313 farming Methods 0.000 claims description 3
- 238000003306 harvesting Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims 1
- 238000005070 sampling Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 238000013507 mapping Methods 0.000 abstract 1
- 239000006185 dispersion Substances 0.000 description 7
- 238000012876 topography Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000003337 fertilizer Substances 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 241000132092 Aster Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005527 soil sampling Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for generating a grade classification map of soil nutrients based on a 3S technology and a precision evaluation method thereof, which overcome the defect that the grade classification of soil nutrients in a large spatial range is difficult to realize compared with the prior art. The invention comprises the following steps: generating a soil nutrient data space grid graph; setting a classification map of soil nutrient grades; extracting cultivated land plots; and generating a soil nutrient grade classification map of a plot scale. Based on the 3S technology, on the basis of extracting cultivated land plots by using field sampling points and RS acquired by a GPS, the spatial distribution characteristics of soil nutrients in the plot scale are analyzed by comprehensively using GIS spatial analysis and land statistics functions, and soil nutrient grade division, spatial mapping and precision evaluation in a large spatial range and on the plot scale are realized.
Description
Technical field
The present invention relates to remotely-sensed data analysis technical field, a kind of specifically soil nutrient grade based on 3S technology
Classification drawing generating method and its Accuracy Assessment.
Background technique
Soil quality is then the important distinguishing rule for determining farmland quality.The soil quality in arable land is for rapid economic development
Area there is important economic value, and it is protected from environmental very big, shows the characteristic of mutation.It grinds in current arable land
Study carefully and is developed from only focusing on quantity to the direction that quantity, quality and ecological benefits are laid equal stress on.Under the premise of guaranteeing quantity of cultivated land, such as
What promotes farmland quality and especially evaluates its environmental quality, it has also become the hot spot direction for research of ploughing.Dividing for soil nutrient is equal fixed
Grade is practiced for grasping region resource situation and Instructing manufacture, and especially soil testing and fertilizer recommendation has great importance.
In the prior art, many technical thoughts are proposed for many scholars of soil nutrient situation.Such as: Kong Xiangbin passes through
GPS positioning takes soil sample, by GIS Spatial Data Analysis and Kriging Research of interpolation method soil fertility level variation and its
Spatial distribution；Su Lixin etc. analyzes arable soil nutrient；Road apple etc. propose the distribution of farmland tillaging layer soil nutrient in 2005 with
Variation characteristic.
But these researchs are all based on greatly that sample point data is for statistical analysis and region difference is at figure, without fine
To plot scale, it is difficult to be formed and effectively be concluded on a large scale.Therefore, a kind of grade separation figure of soil nutrient how is formed
Have become technical problem urgently to be solved.
Summary of the invention
The purpose of the present invention is to solve be difficult to realize large space range soil nutrient grade classification in the prior art
Defect provides a kind of above-mentioned to solve based on the soil nutrient grade separation drawing generating method of 3S technology and its Accuracy Assessment
Problem.
To achieve the goals above, technical scheme is as follows:
A kind of soil nutrient grade separation drawing generating method based on 3S technology, comprising the following steps:
Soil nutrient data space grid map generalization chooses radial basis function RBF space interpolation method and carries out space parallax
Value generates the grid map of every kind of nutrient；
The setting of soil nutrient grade separation figure is calculated according to the space interpolation figure and weight coefficient of every kind of nutrient
Soil nutrient composite index SNI figure pixel-based is obtained, and classifying rules is formulated according to the codomain range of SNI, is obtained by pole
High, high, medium and low and extremely low five classes soil nutrient grade separation figure；
Plough plot extract, based on research area chief crop growth key developmental stages multi-temporal remote sensing image, using point
The gradually exclusive method that layer classification is extracted, extracts arable land plot and its spatial distribution, generates the Shapefile vector text in arable land plot
Part；
The soil nutrient grade separation figure for generating plot scale, using the arable land plot of Shapefile format as exposure mask file,
Exposure mask is carried out to the soil nutrient map of Complex evaluation generated based on SNI index, forms the soil nutrient grade separation of plot scale
Figure.
The soil nutrient data space grid map generalization the following steps are included:
When acquiring soil sample in arable land, sat using the longitude and latitude that the high-precision handhold GPS of sub-meter grade obtains sampled point
Mark imported into ArcMap spatial analysis platform, generates the point vector file of Shapefile format；
It is poor using radial basis function RBF based on the interpolation method classification tree provided in Geostatistical Analyst
Value method obtains the soil nutrient value of non-sampled point；
Using sample point data, training by RBF network to sample will be between soil nutrient value and plane coordinates x and y
Nonlinear function hide among network after convergence, using the geographical coordinate of unknown point as network inputs, to network
Simulation and prediction is carried out, obtains the soil nutrient value of the unknown point, function expression is as follows:
Z=f (x, y),
Wherein, (x, y) is the geographical coordinate of sampled point or future position, and RBF network is then with x, and y is as network inputs, with right
Answer soil nutrient value as the output of network, i.e. the input layer number of network is 2, and output layer number of nodes is 1；
In ArcMap spatial analysis platform, space interpolation is carried out to every kind of soil nutrient using RBF differential technique, is corresponded to
Space grating trrellis diagram.
The arable land plot extract the following steps are included:
Feature is gone through according to the Planting Patterns of research area chief crop, plantation farming, chooses before planting, grow most productive period and harvest
Three scape multi-temporal remote sensing images afterwards；
Data prediction, including radiation calibration, atmospheric correction and geometric accurate correction are carried out respectively to every scape image；
In the classification software platform of eCognition object-oriented, to pretreated image carry out SEaTH algorithm with
The hierarchical classification that closest supervised classification combines extracts, and by excluding other ground classes, obtains farmland types；
For the distance between two atural object close to 2, directly classify using SEaTH algorithm, generates arable land plot
Shapefile file；
For the distance between two atural object greater than 2, macrotaxonomy is divided into customized normalized differential vegetation index；
Subdivision under macrotaxonomy ground class, using closest supervised classification method, class reanalyses available characteristic of division space over the ground, it
The classification for completing arable land is merged together to the macrotaxonomy and ground class classified afterwards, generates the Shapefile file in arable land plot.
The soil nutrient grade separation figure of the described generation plot scale the following steps are included:
Select soil organism SOM, full nitrogen TN or alkali-hydrolyzable nitrogen AN, rapid available phosphorus AP and available potassium AK totally 4 indexs；
Soil nutrient is obtained respectively to participate in evaluation and electing the weight coefficient of index；
Comprehensive evaluation index is sought, using the composite index constructed based on addition model, seeks the nutrient etc. in each plot
Grade, formula are as follows:
SNI=∑ Fi×Wi(i=1,2,3 ..., n),
In formula: SNI represents the soil nutrient composite index in plot, FiIndicate the score value of i-th of index, WiIt indicates i-th
The weight coefficient of index；
In ArcMap spatial analysis platform, the pixel value of each nutrient and soil nutrient are respectively participated in evaluation and electing the weight system of index
Number is brought into SNI formula, obtains soil nutrient overall merit classification chart, is drawn according to respectively the participate in evaluation and electing codomain grade of index of soil nutrient
Scale division obtains high, high, medium and low and extremely low five classes soil nutrient grade separation figure；
Using the arable land plot Shapefile file of extraction as exposure mask, the soil nutrient ranking score of plot scale is obtained
Class figure.
The SEaTH algorithm classified the following steps are included:
Feature is preferred,
The correlation degree between two ground classes in certain feature is judged using separating degree, separation degree is by JM distance
Come what is calculated, with the separability between this to evaluate class, the formula of JM distance is as follows:
J=2 (1-e-B),
In formula, J indicates JM distance, and B indicates Pasteur's distance, under calculation formula shown in:
Wherein, m1And m2Indicate mean value of the typical sample of output two classifications selection in certain feature, σ1And σ2Then indicate
Variance of two classification samples in certain feature.The value range of JM distance is [0,2], and distance closer to 2, also get over by separability
It is good；
Characteristic threshold value is determining,
Two ground classes are calculated in the optimal threshold of certain sample characteristics, according to gaussian probability distribution formula:
P (x)=p (x | C1)p(C1)p(x|C2)p(C2),
In formula, and p (x | C1) indicate ground class C1It is m that the typical sample characteristic value chosen, which obeys mean value,1, variance σ1 2Just
State distribution, and p (x | C2) indicate ground class C2It is m that the typical sample characteristic value chosen, which obeys mean value,2, variance σ2 2Normal distribution；
The formula of optimal threshold T is as follows:
In formula,n1And n2For ground class C1And C2Selected number of samples；
Object undetermined is determined according to selected typical feature sample and the closest feature space distance of calculating building
Which kind of belongs to；
Select typical ground object sample；
Feature space required for building is classified；
By calculating the eigencenter of various regions class, feature and selected typical sample of the non-classified ground class for classification are calculated
The distance between this statistical nature, it is closer with a distance from the sample from which ground class, just which ground class is non-classified ground class is classified as,
Its calculation formula is as follows:
In formula, d indicates sample ground the distance between class and ground to be sorted class o,Indicate the spy of typical sample local category feature f
Value indicative,Indicate the characteristic value of ground to be sorted category feature f, σfIndicate the standard deviation of feature f.
Further include the Accuracy Assessment of soil nutrient grade classification comprising following steps:
The subregion soil nutrient level data that research on utilization area provides, obtains the corresponding geographical coordinate in ground, and building is obscured
Matrix Calculating obtains overall classification accuracy OA, and formula is as follows:
In formula, NaccurateIt indicates the pixel number correctly classified, is the sum of confusion matrix diagonal line, NtotalFor overall pixel
Number；
Kappa coefficient is constructed, formula is as follows:
In formula, N represent earth's surface really classify in pixel sum；xiiRepresent the value in confusion matrix on the i-th class diagonal line；
K indicates general classification number；xi∑Indicate the i-th class column it is corresponding and；x∑iIndicate the i-th class be expert at it is corresponding and.
Beneficial effect
A kind of soil nutrient grade separation drawing generating method and its Accuracy Assessment based on 3S technology of the invention, with
The prior art compares 3S (GIS GIS-Geographic Information System, the RS remote sensing, GPS geo-location system) technology of being based on, what is obtained with GPS
On the basis of field sampling point and RS extract arable land plot, integrated use GIS spatial analysis and geo-statistic function parse plot ruler
The soil nutrient spatial distribution characteristic of degree is realized within the scope of large space, the soil nutrient grade classification on field scale, space system
Figure and precision evaluation.
The present invention realizes that traditional ground is random by carrying out continuous spatialization expression to discrete soil nutrient index
" point " monitor to " face " analyze spatial spread, can quick obtaining soil nutrient grade separation and spatial distribution differences；Overcome
Based on ground ocean weather station observation and the one-sidedness of soil nutrient grade is divided, has greatly expanded the space monitoring model of soil nutrient
It encloses, reduces the workload and cost of traditional grab sampling and lab analysis chemical examination.
Detailed description of the invention
Fig. 1 is method precedence diagram of the invention；
Fig. 2 is that arable land plot carries out hierarchical classification extractive technique route schematic diagram in the present invention；
Fig. 3 a is the false colour composite image figure using 7,4,2 wave band of Landsat TM；
Fig. 3 b is Beijing arable land plot map space distribution map generated using the method for the invention；
Fig. 4 is Beijing's field scale Soil Nutrient Classification figure generated using the method for the invention.
Specific embodiment
The effect of to make to structure feature of the invention and being reached, has a better understanding and awareness, to preferable
Examples and drawings cooperation detailed description, is described as follows:
As shown in Figure 1, a kind of soil nutrient grade separation drawing generating method based on 3S technology of the present invention, including
Following steps:
The first step, soil nutrient data space grid map generalization.Choose radial basis function RBF (Radial Basis
Function) space interpolation method carries out space interpolation, generates the grid map of every kind of nutrient.The specific steps of which are as follows:
(1) when acquiring soil sample in arable land, the longitude and latitude of sampled point is obtained using the high-precision handhold GPS of sub-meter grade
Coordinate imported into ArcMap spatial analysis platform, generates the point vector file of Shapefile format.
(2) based on the interpolation method classification tree provided in Geostatistical Analyst, radial basis function RBF is used
Difference approach obtains the soil nutrient value of non-sampled point.
Here, being the grade of measurement or model, condition based on spatial autocorrelation using radial basis function RBF difference approach
Not/model complexity, interpolation type, the smoothness of output, processing speed comprehensively consider.Radial basis function (RBF) is inserted
Value method is a series of combination of precise interpolation methods；That is the sampled value that must be measured by each of interpolation surface.With geographical coordinate
RBF interpolation method as network inputs, which is only established between space and geographical coordinate and soil nutrient value, to be contacted.
Using sample point data, training by RBF network to sample will be between soil nutrient value and plane coordinates x and y
Nonlinear function hide among network after convergence, using the geographical coordinate of unknown point as network inputs, to network
Simulation and prediction is carried out, obtains the soil nutrient value of the unknown point, function expression is as follows:
Z=f (x, y),
Wherein, (x, y) is the geographical coordinate of sampled point or future position, and RBF network is then with x, and y is as network inputs, with right
Answer soil nutrient value as the output of network, i.e. the input layer number of network is 2, and output layer number of nodes is 1.
(3) in ArcMap spatial analysis platform, space interpolation is carried out to every kind of soil nutrient using RBF differential technique, is obtained
Corresponding space grating trrellis diagram.
Second step, the setting of soil nutrient grade separation figure.
It is calculated according to the space interpolation figure and weight coefficient of every kind of nutrient based on picture by art methods
Soil nutrient composite index SNI (Soil Nutrient Index) figure of element, and classification gauge is formulated according to the codomain range of SNI
Then, it obtains by high, high, medium and low and extremely low five classes soil nutrient grade separation figure.
Third step, arable land plot are extracted.
Based on research area chief crop growth key developmental stages multi-temporal remote sensing image, using hierarchical classification extract by
Exclusive method is walked, arable land plot and its spatial distribution are extracted, generates the Shapefile vector file in arable land plot.Its specific steps
It is as follows:
(1) feature is gone through according to the Planting Patterns of research area chief crop, plantation farming, before choosing plantation, the growth most productive period and
Three scape multi-temporal remote sensing images after harvest.
(2) data prediction, including radiation calibration, atmospheric correction and geometric accurate correction are carried out respectively to every scape image.
(3) in the classification software platform of eCognition object-oriented, SEaTH algorithm is carried out to pretreated image
The hierarchical classification combined with closest supervised classification extracts, and by excluding other ground classes, obtains farmland types.
As shown in Fig. 2, directly classify close to 2 using SEaTH algorithm for the distance between two atural object, it is raw
At the Shapefile file in arable land plot；For the distance between two atural object greater than 2, with customized normalization vegetation
Index is divided into macrotaxonomy；Subdivision under macrotaxonomy ground class, using closest supervised classification method, reanalyse can for class over the ground
Characteristic of division space is merged together the classification for completing arable land to the macrotaxonomy and ground class classified later, generates arable land
The Shapefile file in plot.
Here, by taking wetland and the other division of the two major class of non-wetland as an example.It is not king-sized for distance, such as plants
Quilt and non-vegetation the two classifications, index can be normalized with customized vegetation come be divided into non-vegetation (artificial surface, its
He, nonirrigated farmland) and vegetation (meadow, forest land, paddy field)；Subdivision under non-vegetation and vegetation ground class, can use closest supervision point
The method of class reanalyses available characteristic of division space to them, is merged together later to the nonirrigated farmland and paddy field classified
Complete the classification in arable land.
Wherein, SEaTH algorithm classified the following steps are included:
A1) feature is preferred.
The correlation degree between two ground classes in certain feature is judged using separating degree, separation degree is by JM
(Jeffries-Matusita) distance calculates, and evaluates the separability between ground class with this.The following institute of the formula of JM distance
Show:
J=2 (1-e-B),
In formula, J indicates JM distance, and B indicates Pasteur's distance, under calculation formula shown in:
Wherein, m1And m2Indicate mean value of the typical sample of output two classifications selection in certain feature, σ1And σ2Then indicate
Variance of two classification samples in certain feature.The value range of JM distance is [0,2], and distance closer to 2, also get over by separability
It is good.
A2) characteristic threshold value determines.
Two ground classes are calculated in the optimal threshold of certain sample characteristics, according to gaussian probability distribution formula:
P (x)=p (x | C1)p(C1)p(x|C2)p(C2),
In formula, and p (x | C1) indicate ground class C1It is m that the typical sample characteristic value chosen, which obeys mean value,1, variance σ1 2Just
State distribution, and p (x | C2) indicate ground class C2It is m that the typical sample characteristic value chosen, which obeys mean value,2, variance σ2 2Normal distribution；
The formula of optimal threshold T is as follows:
In formula,n1And n2For ground class C1And C2Selected number of samples.
A3) undetermined right to determine according to the closest feature space distance of selected typical feature sample and calculating building
As which kind of belongs to.
A31 typical ground object sample) is selected；
A32 feature space required for) building is classified；
A33) by calculating the eigencenter of various regions class, feature and selected allusion quotation of the non-classified ground class for classification are calculated
The distance between this statistical nature of pattern, from which ground class sample with a distance from it is closer, which non-classified ground class is just classified as
Ground class, calculation formula are as follows:
In formula, d indicates sample ground the distance between class and ground to be sorted class o,Indicate the spy of typical sample local category feature f
Value indicative,Indicate the characteristic value of ground to be sorted category feature f, σfIndicate the standard deviation of feature f.
4th step generates the soil nutrient grade separation figure of plot scale.
Using the arable land plot of Shapefile format as exposure mask file, the soil nutrient synthesis generated based on SNI index is commented
Valence figure carries out exposure mask, forms the soil nutrient grade separation figure of plot scale.The specific steps of which are as follows:
(1) soil organism SOM, full nitrogen TN or alkali-hydrolyzable nitrogen AN, rapid available phosphorus AP and available potassium AK totally 4 indexs are selected.
(2) soil nutrient is obtained respectively to participate in evaluation and electing the weight coefficient of index.Here, as shown in table 1, table 1 is by taking Beijing as an example
Soil In Beijing nutrient grade partitioning standards table.
1 Soil In Beijing nutrient grade partitioning standards table of table
* data source: Soil In Beijing resource management information net, http: // 202.112.163.254:8008/new%
20soil/index.html.
(3) for the classification situation of a certain regional soil nutrient of Comprehensive Assessment, comprehensive evaluation index is sought.
Using the composite index constructed based on addition model, the nutrient grade in each plot is sought, formula is as follows:
SNI=Σ Fi×Wi(i=1,2,3 ..., n),
In formula: SNI represents the soil nutrient composite index in plot, FiIndicate the score value of i-th of index, WiIt indicates i-th
The weight coefficient of index.
(4) in ArcMap spatial analysis platform, the pixel value of each nutrient and soil nutrient are respectively participated in evaluation and electing the power of index
Weight coefficient is brought into SNI formula, obtains soil nutrient overall merit classification chart, is respectively participated in evaluation and electing the codomain etc. of index according to soil nutrient
Grade divides scale, obtains high, high, medium and low and extremely low five classes soil nutrient grade separation figure.
(5) using the arable land plot Shapefile file extracted as exposure mask, the soil nutrient grade of plot scale is obtained
Classification chart.
Here, being directed to soil nutrient grade separation figure, a kind of Accuracy Assessment is also provided, i.e. soil nutrient grade is drawn
The Accuracy Assessment divided comprising following steps:
(1) the subregion soil nutrient level data that research on utilization area provides, obtains the corresponding geographical coordinate in ground, and building is mixed
The Matrix Calculating that confuses obtains overall classification accuracy OA, and formula is as follows:
In formula, NaccurateIt indicates the pixel number correctly classified, is the sum of confusion matrix diagonal line, NtotalFor overall pixel
Number.
(2) Kappa coefficient is constructed, formula is as follows:
In formula, N represent earth's surface really classify in pixel sum；xiiRepresent the value in confusion matrix on the i-th class diagonal line；
K indicates general classification number；xi∑Indicate the i-th class column it is corresponding and；x∑iIndicate the i-th class be expert at it is corresponding and.
By taking Beijing as an example, Beijing is located in the north of North China llanura, is located at 39 ° of 38'~40 ° 51'N,
Between 115 ° of 25'~117 ° 20'E.Landforms are made of Mountain Areas of Northwest and two big unit of southeast Plain, total topography table
Now high for northwest, the southeast is low, and is southeastward tilted by northwest.Plain height above sea level is usually no more than 100m, is predominantly located in 20~60m
Between, mountainous region height above sea level is generally between 1000~1500m.Beijing belongs to warm temperate zone grassland climate area, mean annual precipitation
430.9mm, average temperature of the whole year are 13.1 DEG C.Wherein, January is most cold, and temperature on average is -3.9 DEG C；July is most hot, temperature on average
For 26.5 DEG C (Soil In Beijing resource management information nets).Whole city land area 16,410km2.Wherein, Plain area 6338km2,
38.6% is accounted for, mountain area area 10,072km2, account for 61.4% (Bureau of Land and Resources of Beijing).According to statistical yearbook in 2010, north
Capital borough is divided into 14th area, 2 county (year end 2010).Wherein, Mentougou District, Huairou District, Pinggu District, Miyun County and Yanqing County
It is decided to be ecology self-restraint development zone and cultivated area is distributed most districts.The agricultural ground area of the whole city 2008 is 10,
959.81km2, ploughing is 2,316.88
km2, wherein Yanqing County, Huairou District and Miyun County are first three most district of arable land, account for the gross area respectively
15.4%, 14.3% and 14.1%.Beijing staple crops are wheat, corn and vegetables, the sown area of three in 2009
Respectively 226,000ha, 151,000ha and 68,000ha.The remotely-sensed data extracted for Beijing arable land plot is Landsat
TM5 covers entire research area and needs two scape images (orbit number is p123/r32 and p123/r33).Orbit number in 2009 is obtained altogether
For the three scape images of p123/r32: April 15, July 20 and September 22nd.Beijing area very little as shared by p123/r33 scape,
Only have collected the scape on the 22nd of September in 2009.Landsat TM image spatial resolution is 30m, and coverage area 185km is revisited
Period is 16d, comprising 6 multi light spectrum hands (0.45-2.35 μm) and Thermal infrared bands (spatial resolution 120m,
10.40-12.50μm)。
Before carrying out arable land plot and extracting, need to carry out every scape image respectively data prediction: radiation calibration, atmosphere school
Just and geometric accurate correction.Geometric correction automatically corrects modules A utosync using ERDAS's 9.1, selects the phase same month with reference to image
Part corrected Landsat ETM+, it is desirable that RMSE is controlled in 0.5 pixel.Then, in the digital photogrammetry of ERDAS
And remote sensing processing software
Under LPS (Leica Photogrammetry Suite) module, while importing the Landsat TM after geometric correction
Ortho-rectification is carried out with the ASTER GDEM altitude data of 30m resolution ratio, the mountainous region fluctuating bring for eliminating northwest of Beijing is missed
Difference.After geometric accurate correction, image is imported into ENVI software
FLAASH(Fast Light-of-sight Atmospheric Analysis of Spectral
Hypercubes) atmospheric correction module carries out atmospheric correction.Soil sampling point and Soil In Beijing fertilizer work station based on collection
Four kinds of indexs are carried out space interpolations by the soil nutrient grade determination standard of formulation, and output resolution ratio is set as 30m, with
The resolution ratio of Landsat TM remote sensing image matches.Using the spatial analysis module (Spatial Analyst) of ArcMap,
The arable soil nutrient spatial distribution map in research area is calculated in raster symbol-base device.As shown in figure 4, finally, utilizing extraction
Arable land plot carries out exposure mask, obtains the Soil In Beijing nutrient grade spatial distribution map based on plot scale.
As shown in Figure 3a and Figure 3b shows, Fig. 3 a is the false colour composite image of 7,4,2 wave band of Beijing Landsat TM, figure
3b is its plot figure of ploughing.The arable land of Beijing is mainly distributed on southeast region of no relief it can be seen from Fig. 3 a and Fig. 3 b.Its
In, the arable land distribution of Shunyi District, Tongzhou District and Daxing District is the most intensive, almost spreads over entire administrative area；Fangshan District, Pinggu District,
Due to there is mountain topography in Changping District, Miyun County and Yanqing County, so that arable land focuses primarily upon topography flat country within the border；It compares
District based on other mountain area landforms, the arable land of Yanqing County is more, is mainly distributed on southwest corner；Chaoyang District, Haidian District, Shijingshan
Area, Fengtai District and urban district are then almost without arable land distribution.
For soil organism index: the content highest of Fangshan District, average value 23.34g/kg；The content of Pinggu District is most
Low, average value is only 1.78g/kg；Meanwhile the standard deviation of the Fangshan District soil organism is also maximum (23.69), shows the index
Spatial spreading degree is bigger compared to other districts；The smallest soil organism for Pinggu District of dispersion, standard deviation is only 0.77.
For full nitrogen index: the content highest of Huairou District, average value 1.04g/kg；The content of Pinggu District is minimum, and average value is only
For 0.11g/kg；Huairou District, Miyun County, Changping District, Shunyi District, the dispersion degree of Tongzhou District and Daxing District are close, and standard deviation exists
Near 0.3, and the dispersion of Pinggu District is minimum, and standard deviation is only 0.03.In rapid available phosphorus index: Huairou District content is maximum, puts down
Mean value is 50.08g/kg；Mentougou District content is minimum, and average value is only 17.23g/kg；The dispersion degree of Tongzhou District is most violent,
Standard deviation reaches 50.08；The rapid available phosphorus index dispersion of Mentougou District is minimum, standard deviation 27.13.In available potassium index:
The content highest of Mentougou District, average value reach 204.00g/kg；The content of Daxing District is minimum, average value 110.03g/kg；
The Fangshan District index dispersion is maximum, and standard deviation reaches 167.60；The dispersion of Huairou District is minimum, standard deviation 63.60.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and what is described in the above embodiment and the description is only the present invention
Principle, various changes and improvements may be made to the invention without departing from the spirit and scope of the present invention, these variation and
Improvement is both fallen in the range of claimed invention.The present invention claims protection scope by appended claims and its
Equivalent defines.
Claims (6)
1. a kind of soil nutrient grade separation drawing generating method based on 3S technology, which comprises the following steps:
11) soil nutrient data space grid map generalization chooses radial basis function RBF space interpolation method and carries out space parallax
Value generates the grid map of every kind of nutrient；
12) setting of soil nutrient grade separation figure is calculated according to the space interpolation figure and weight coefficient of every kind of nutrient
To soil nutrient composite index SNI pixel-based scheme, and according to the codomain range of SNI formulate classifying rules, obtain by it is high,
High, medium and low and extremely low five classes soil nutrient grade separation figure；
13) arable land plot is extracted, based on the multi-temporal remote sensing image of research area chief crop growth key developmental stages, using layering
The gradually exclusive method that classification is extracted extracts arable land plot and its spatial distribution, generates the Shapefile vector text in plot of ploughing
Part；
14) the soil nutrient grade separation figure for generating plot scale, using the arable land plot of Shapefile format as exposure mask file,
Exposure mask is carried out to the soil nutrient map of Complex evaluation generated based on SNI index, forms the soil nutrient grade separation of plot scale
Figure.
2. a kind of soil nutrient grade separation drawing generating method based on 3S technology according to claim 1, feature exist
In, the soil nutrient data space grid map generalization the following steps are included:
21) it when acquiring soil sample in arable land, is sat using the longitude and latitude that the high-precision handhold GPS of sub-meter grade obtains sampled point
Mark imported into ArcMap spatial analysis platform, generates the point vector file of Shapefile format；
22) based on the interpolation method classification tree provided in Geostatistical Analyst, radial basis function RBF difference is used
Method obtains the soil nutrient value of non-sampled point；
Using sample point data, training by RBF network to sample will be non-between soil nutrient value and plane coordinates x and y
Linear functional relation is hidden among network after convergence, using the geographical coordinate of unknown point as network inputs, carries out to network
Simulation and prediction obtains the soil nutrient value of the unknown point, and function expression is as follows:
Z=f (x, y),
Wherein, (x, y) is the geographical coordinate of sampled point or future position, and RBF network is then with x, and y is as network inputs, with corresponding soil
Output of the earth nutrient value as network, i.e. the input layer number of network are 2, and output layer number of nodes is 1；
23) in ArcMap spatial analysis platform, space interpolation is carried out to every kind of soil nutrient using RBF differential technique, is corresponded to
Space grating trrellis diagram.
3. a kind of soil nutrient grade separation drawing generating method based on 3S technology according to claim 1, feature exist
Extract in, the arable land plot the following steps are included:
31) feature is gone through according to the Planting Patterns of research area chief crop, plantation farming, chooses before planting, grows most productive period and harvest
Three scape multi-temporal remote sensing images afterwards；
32) data prediction, including radiation calibration, atmospheric correction and geometric accurate correction are carried out respectively to every scape image；
33) in the classification software platform of eCognition object-oriented, to pretreated image progress SEaTH algorithm and most
The hierarchical classification that neighbouring supervised classification combines extracts, and by excluding other ground classes, obtains farmland types；
For the distance between two atural object close to 2, directly classify using SEaTH algorithm, generates arable land plot
Shapefile file；
For the distance between two atural object greater than 2, macrotaxonomy is divided into customized normalized differential vegetation index；Big point
Subdivision under class ground class, using closest supervised classification method, class reanalyses available characteristic of division space over the ground, right later
The macrotaxonomy and ground class classified are merged together the classification for completing arable land, generate the Shapefile file in arable land plot.
4. a kind of soil nutrient grade separation drawing generating method based on 3S technology according to claim 1, feature exist
In, the described generation plot scale soil nutrient grade separation figure the following steps are included:
41) soil organism SOM, full nitrogen TN or alkali-hydrolyzable nitrogen AN, rapid available phosphorus AP and available potassium AK totally 4 indexs are selected；
42) soil nutrient is obtained respectively to participate in evaluation and electing the weight coefficient of index；
43) comprehensive evaluation index is sought, using the composite index constructed based on addition model, seeks the nutrient etc. in each plot
Grade, formula are as follows:
SNI=∑ Fi×Wi(i=1,2,3 ..., n),
In formula: SNI represents the soil nutrient composite index in plot, FiIndicate the score value of i-th of index, WiIndicate i-th of index
Weight coefficient；
44) in ArcMap spatial analysis platform, the pixel value of each nutrient and soil nutrient are respectively participated in evaluation and electing the weight system of index
Number is brought into SNI formula, obtains soil nutrient overall merit classification chart, is drawn according to respectively the participate in evaluation and electing codomain grade of index of soil nutrient
Scale division obtains high, high, medium and low and extremely low five classes soil nutrient grade separation figure；
45) using the arable land plot Shapefile file extracted as exposure mask, the soil nutrient grade separation of plot scale is obtained
Figure.
5. a kind of soil nutrient grade separation drawing generating method based on 3S technology according to claim 3, feature exist
Classified in, the SEaTH algorithm the following steps are included:
51) feature is preferred,
The correlation degree between two ground classes in certain feature is judged using separating degree, separation degree is counted by JM distance
It calculates, with the separability between this to evaluate class, the formula of JM distance is as follows:
J=2 (1-e-B),
In formula, J indicates JM distance, and B indicates Pasteur's distance, under calculation formula shown in:
Wherein, m1And m2Indicate mean value of the typical sample of output two classifications selection in certain feature, σ1And σ2Then indicate at two
Variance of the classification sample in certain feature.The value range of JM distance is [0,2], and for distance closer to 2, separability is also better；
52) characteristic threshold value determines,
Two ground classes are calculated in the optimal threshold of certain sample characteristics, according to gaussian probability distribution formula:
P (x)=p (x | C1)p(C1)p(x|C2)p(C2),
In formula, and p (x | C1) indicate ground class C1It is m that the typical sample characteristic value chosen, which obeys mean value,1, variance σ1 2Normal state point
Cloth, and p (x | C2) indicate ground class C2It is m that the typical sample characteristic value chosen, which obeys mean value,2, variance σ2 2Normal distribution；
The formula of optimal threshold T is as follows:
In formula,n1And n2For ground class C1And C2Selected number of samples；
53) object category undetermined is determined according to selected typical feature sample and the closest feature space distance of calculating building
In which kind of；
531) typical ground object sample is selected；
532) feature space required for building is classified；
533) by calculating the eigencenter of various regions class, feature and selected typical sample of the non-classified ground class for classification are calculated
The distance between this statistical nature, it is closer with a distance from the sample from which ground class, just which ground class is non-classified ground class is classified as,
Its calculation formula is as follows:
In formula, d indicates sample ground the distance between class and ground to be sorted class o,Indicate the feature of typical sample local category feature f
Value,Indicate the characteristic value of ground to be sorted category feature f, σfIndicate the standard deviation of feature f.
6. a kind of soil nutrient grade separation drawing generating method based on 3S technology according to claim 1, feature exist
In further including the Accuracy Assessment of soil nutrient grade classification comprising following steps:
61) the subregion soil nutrient level data that research on utilization area provides, obtains the corresponding geographical coordinate in ground, and square is obscured in building
Battle array acquires overall classification accuracy OA, and formula is as follows:
In formula, NaccurateIt indicates the pixel number correctly classified, is the sum of confusion matrix diagonal line, NtotalFor overall pixel number；
62) Kappa coefficient is constructed, formula is as follows:
In formula, N represent earth's surface really classify in pixel sum；xiiRepresent the value in confusion matrix on the i-th class diagonal line；K table
Show general classification number；xi∑Indicate the i-th class column it is corresponding and；x∑iIndicate the i-th class be expert at it is corresponding and.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946788.3A CN108959661B (en) | 2018-08-20 | 2018-08-20 | 3S technology-based soil nutrient grade classification map generation method and precision evaluation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946788.3A CN108959661B (en) | 2018-08-20 | 2018-08-20 | 3S technology-based soil nutrient grade classification map generation method and precision evaluation method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108959661A true CN108959661A (en) | 2018-12-07 |
| CN108959661B CN108959661B (en) | 2021-08-06 |
Family
ID=64470720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810946788.3A Active CN108959661B (en) | 2018-08-20 | 2018-08-20 | 3S technology-based soil nutrient grade classification map generation method and precision evaluation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108959661B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244018A (en) * | 2019-03-28 | 2019-09-17 | 国智恒北斗好年景农业科技有限公司 | A kind of soil moisture content remote real-time monitoring method based on 3S technology |
| CN110596008A (en) * | 2019-09-06 | 2019-12-20 | 中国科学院遥感与数字地球研究所 | Plot-based soil nutrient digital mapping method for agricultural region of Chinese Hongsheng plain |
| CN110658011A (en) * | 2019-11-05 | 2020-01-07 | 新疆农业科学院土壤肥料与农业节水研究所(新疆维吾尔自治区新型肥料研究中心) | County scale orchard soil quality sampling method |
| CN111289512A (en) * | 2020-02-28 | 2020-06-16 | 中国水稻研究所 | Rice grain alkali elimination value high-throughput determination method based on deep convolutional neural network |
| CN115344813A (en) * | 2022-08-25 | 2022-11-15 | 珠江水利委员会珠江水利科学研究院 | Mountain height inversion method based on shadow |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7047135B2 (en) * | 2003-01-31 | 2006-05-16 | Deere & Company | Method and system of evaluating performance of a crop |
| CN103930919A (en) * | 2011-10-24 | 2014-07-16 | 天宝导航有限公司 | Agricultural and soil management |
| CN104459087A (en) * | 2014-12-05 | 2015-03-25 | 广西壮族自治区林业科学研究院 | Forest soil nutrient classification method |
| CN106888781A (en) * | 2017-01-19 | 2017-06-27 | 交通运输部科学研究院 | The table soil and the method for turf coordinating protection being combined with field investigation based on remote sensing subregion |
| US9904747B2 (en) * | 2015-03-19 | 2018-02-27 | Trimble Inc. | Agricultural terrain forming based on soil modeling |
-
2018
- 2018-08-20 CN CN201810946788.3A patent/CN108959661B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7047135B2 (en) * | 2003-01-31 | 2006-05-16 | Deere & Company | Method and system of evaluating performance of a crop |
| CN103930919A (en) * | 2011-10-24 | 2014-07-16 | 天宝导航有限公司 | Agricultural and soil management |
| CN104459087A (en) * | 2014-12-05 | 2015-03-25 | 广西壮族自治区林业科学研究院 | Forest soil nutrient classification method |
| US9904747B2 (en) * | 2015-03-19 | 2018-02-27 | Trimble Inc. | Agricultural terrain forming based on soil modeling |
| CN106888781A (en) * | 2017-01-19 | 2017-06-27 | 交通运输部科学研究院 | The table soil and the method for turf coordinating protection being combined with field investigation based on remote sensing subregion |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244018A (en) * | 2019-03-28 | 2019-09-17 | 国智恒北斗好年景农业科技有限公司 | A kind of soil moisture content remote real-time monitoring method based on 3S technology |
| CN110596008A (en) * | 2019-09-06 | 2019-12-20 | 中国科学院遥感与数字地球研究所 | Plot-based soil nutrient digital mapping method for agricultural region of Chinese Hongsheng plain |
| CN110596008B (en) * | 2019-09-06 | 2020-10-23 | 中国科学院空天信息创新研究院 | Plot-based soil nutrient digital mapping method for agricultural region of Chinese Hongsheng plain |
| CN110658011A (en) * | 2019-11-05 | 2020-01-07 | 新疆农业科学院土壤肥料与农业节水研究所(新疆维吾尔自治区新型肥料研究中心) | County scale orchard soil quality sampling method |
| CN111289512A (en) * | 2020-02-28 | 2020-06-16 | 中国水稻研究所 | Rice grain alkali elimination value high-throughput determination method based on deep convolutional neural network |
| CN115344813A (en) * | 2022-08-25 | 2022-11-15 | 珠江水利委员会珠江水利科学研究院 | Mountain height inversion method based on shadow |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108959661B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108959661A (en) | 3S technology-based soil nutrient grade classification map generation method and precision evaluation method thereof | |
| Rujoiu-Mare et al. | Mapping land cover using remote sensing data and GIS techniques: A case study of Prahova Subcarpathians | |
| CN105740759B (en) | Semilate rice information decision tree classification approach based on feature extraction in multi-temporal data | |
| Zhang et al. | Estimation of forest leaf area index using height and canopy cover information extracted from unmanned aerial vehicle stereo imagery | |
| Li et al. | Critical analysis of methods to estimate the fraction of absorbed or intercepted photosynthetically active radiation from ground measurements: Application to rice crops | |
| Li et al. | Estimation of aboveground vegetation biomass based on Landsat-8 OLI satellite images in the Guanzhong Basin, China | |
| CN114005048A (en) | Multi-temporal data-based land cover change and thermal environment influence research method | |
| Wang et al. | Fractional vegetation cover estimation method through dynamic Bayesian network combining radiative transfer model and crop growth model | |
| Choudhary et al. | Random Forest for rice yield mapping and prediction using Sentinel-2 data with Google Earth Engine | |
| Fitzgerald et al. | Directed sampling using remote sensing with a response surface sampling design for site-specific agriculture | |
| Cai et al. | Consistency Assessments of the land cover products on the Tibetan Plateau | |
| Wang et al. | A comparative analysis of grid-based and object-based modeling approaches for poplar forest growing stock volume estimation in plain regions using airborne LIDAR data | |
| Rimal et al. | Crop cycles and crop land classification in Nepal using MODIS NDVI | |
| Shang et al. | Using multi-source remote sensing data to classify larch plantations in Northeast China and support the development of multi-purpose silviculture | |
| Cuo et al. | Topographic normalization for improving vegetation classification in a mountainous watershed in Northern Thailand | |
| Jin et al. | Generating high spatial resolution GLASS FAPAR product from Landsat images | |
| Zhang et al. | Mapping irrigated and rainfed wheat areas using high spatial–temporal resolution data generated by Moderate Resolution Imaging Spectroradiometer and Landsat | |
| Yimer et al. | Seasonal effect on the accuracy of Land use/Land cover classification in the Bilate Sub-basin, Abaya-Chamo Basin, Rift valley Lakes Basin of Ethiopia. | |
| Jande et al. | Assessment of land use and land cover changes and urban expansion using remote sensing and GIS in Gboko, Benue State, Nigeria | |
| CN115830464A (en) | Plateau mountain agricultural greenhouse automatic extraction method based on multi-source data | |
| Sang et al. | Farmland distribution dataset of the Yarlung Zangbo–Lhasa–Nyangqu River region of the Tibetan Plateau | |
| Ramachandra | Comparative assessment of techniques for bioresource monitoring using GIS and remote sensing | |
| Jahan | Vegetation indices, FAPAR and spatial seasonality analysis of crops in southern Sweden | |
| Zhang et al. | Mapping dominant vegetation communities at Meili Snow Mountain, Yunnan Province, China using satellite imagery and plant community data | |
| Ali et al. | Comparative performance analysis of a hyper-temporal NDVI analysis approach and a landscape-ecological mapping approach |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |