CN110363442A - Obtain the method and device of the indexes such as province domain arable land nature - Google Patents
Obtain the method and device of the indexes such as province domain arable land nature Download PDFInfo
- Publication number
- CN110363442A CN110363442A CN201910654550.8A CN201910654550A CN110363442A CN 110363442 A CN110363442 A CN 110363442A CN 201910654550 A CN201910654550 A CN 201910654550A CN 110363442 A CN110363442 A CN 110363442A
- Authority
- CN
- China
- Prior art keywords
- small towns
- indexes
- arable land
- nature
- alternative
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000005303 weighing Methods 0.000 claims abstract description 27
- 238000012216 screening Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 7
- 238000001556 precipitation Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 5
- 230000001052 transient effect Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 description 5
- 241000208340 Araliaceae Species 0.000 description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 235000008434 ginseng Nutrition 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 235000015097 nutrients Nutrition 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of method and device of the indexes such as acquisition province domain arable land nature, belongs to Evaluation for cultivated-land technical field.Include: the related coefficient between the reference value according to indexes such as the arable land natures in related coefficient and each alternative index between each alternative index and the province domain small towns Nei Ge, each alternative index is screened, using the alternative index filtered out as the indexs such as dividing；Refer to that the reference value of the indexes such as target value and the arable land nature in each small towns returns to each point etc. of each small towns, determines the indexs such as each point to the weighing factor of the indexes such as the arable land nature in each small towns；Refer to the corresponding weighing factor of the indexs such as each point of target value and each small towns according to each point etc. of each small towns, determines the indexes such as the arable land nature in each small towns in province domain.Due to that can evaluate from more macroscopical angle farmland quality, and in view of point etc. indexs Space atmosphere, so as to it is more objective, accurately farmland quality is evaluated.
Description
Technical field
The present invention relates to Evaluation for cultivated-land technical field more particularly to a kind of sides for obtaining the indexes such as province domain arable land nature
Method and device.
Background technique
Cultivated land protection at present faces new situation and requirement, needs to go deep into promote Ecological Civilization Construction, carry out from cultivated
These three aspects of ground quantity, quality and ecology are protected, and this requires the essence of further further exploration farmland quality.With
People gradually increase the attention rate of farmland quality, so that carrying out evaluation to province domain farmland quality from the angle of macroscopic view has very
Important meaning.
In the related art, the most common method for obtaining the indexes such as province, arable land, domain nature is to pass through sample within the scope of county domain
Point investigation, obtains each index value, and the score value and weight of each index are determined by the method for expert estimation, to be calculated every
The indexes such as the nature of a arable land figure spot.But the indexes such as this obtained nature of method are subjective, and are single with county
The calculating that position carries out the indexes such as arable land nature is unfavorable for evaluating farmland quality from the angle of macroscopic view.
Summary of the invention
To solve the above-mentioned problems, the embodiment of the present invention provide one kind overcome the above problem or at least partly area solve
The method and device for obtaining the indexes such as province domain arable land nature of the above problem.
According to a first aspect of the embodiments of the present invention, a kind of method of the indexes such as acquisition province domain arable land nature, packet are provided
It includes:
Each alternative finger target value in each small towns is obtained, and each alternative finger target value in each small towns is normalized；
According to the indexes such as nature of ploughing of related coefficient and each alternative index and each small towns between each alternative index
Related coefficient between reference value screens each alternative index, using the alternative index filtered out as point etc. indexs；
Refer to that the reference value of the indexes such as target value and the arable land nature in each small towns returns to each point etc. of each small towns, determines
Weighing factor of the indexs such as each point to indexes such as the arable land natures in each small towns；
Refer to the corresponding weighing factor of the indexs such as each point of target value and each small towns according to each point etc. of each small towns,
Determine the indexes such as the arable land nature in each small towns.
According to a second aspect of the embodiments of the present invention, a kind of device of the indexes such as acquisition province domain arable land nature, packet are provided
It includes:
First obtains module, obtains each alternative finger target value in each small towns；
Normalized module is normalized for each alternative finger target value to each small towns；
Screening module, for according between each alternative index related coefficient and each alternative index and each small towns plough
Related coefficient between the reference values of indexes such as ground nature, screens each alternative index, and the alternative index filtered out is made
For point etc. indexs；
Regression block, the indexes such as arable land nature for referring to target value and each department small towns to each point etc. of each department small towns
Reference value returned, determine the indexs such as each point to the weighing factor of the arable land indexes such as nature in each department small towns；
First determining module, for being referred to according to each point etc. of each small towns each point etc. for referring to target value and each small towns
Corresponding weighing factor is marked, determines the indexes such as the arable land nature in each small towns.
According to a third aspect of the embodiments of the present invention, a kind of electronic equipment is provided, comprising:
At least one processor；And
At least one processor being connect with processor communication, in which:
Memory is stored with the program instruction that can be executed by processor, and the instruction of processor caller is able to carry out first party
The indexes such as province domain arable land nature are obtained in the various possible implementations in face provided by any possible implementation
Method.
According to the fourth aspect of the invention, a kind of non-transient computer readable storage medium, non-transient computer are provided
Readable storage medium storing program for executing stores computer instruction, and computer instruction makes the various possible implementations of computer execution first aspect
In obtain domain of provinceing provided by any possible implementation and plough the methods of the indexes such as nature.
The domain of provinceing provided in an embodiment of the present invention that obtains is ploughed the method and devices of the indexes such as nature, due to can be from more macroscopical
Angle farmland quality is evaluated, and in view of point etc. indexs Space atmosphere, so as to more objective, accurate
Farmland quality is evaluated.The related coefficient and alternatively finger between each alternative index are probed into using the method for correlation analysis
The related coefficient between the indexes such as nature of arable land is marked, it being capable of more accurately screening and assessment index.With Geographical Weighted Regression
Method calculate weighing factor, can solve not consider resultant error caused by special heterogeneity to a certain extent, overcome sky
Between interference of the heterogeneity to models fitting so that calculated result is more objective and tallies with the actual situation.
It should be noted that arable land is used as a kind of typical geospatial entity, landform, soil nutrient, economic input
It is horizontal that all there is regional scale and regional differentiation, thus on different space scales, form, property and the regularity of distribution
Also it will appear different geographical space expression effects.In embodiments of the present invention, farmland quality can be screened from excellent layout
Influence factor, and farmland quality is evaluated based on excellent layout, relative to the Evaluation for cultivated-land of County Scale, more favorably
In the distribution situation for understanding farmland quality from macro-scale.
It should be understood that above general description and following detailed description be it is exemplary and explanatory, can not
Limit the embodiment of the present invention.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of method flow schematic diagram for obtaining the indexes such as province domain arable land nature provided in an embodiment of the present invention；
Fig. 2 is a kind of structural schematic diagram for obtaining the devices of indexes such as province domain arable land nature provided in an embodiment of the present invention；
Fig. 3 is the block diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
For the problems in the relevant technologies, the embodiment of the invention provides a kind of sides of the indexes such as acquisition province domain arable land nature
Method.Wherein, the indexes such as nature of ploughing can be used for evaluating farmland quality.This method can be used for obtaining the arable land nature in province domain etc.
Index.It should be noted that the method and device provided in an embodiment of the present invention for obtaining the indexes such as province domain arable land nature can be it
He saves or even the evaluation of the Natural quality of cultivated land in the whole nation provides Technical Reference.Referring to Fig. 1, this method comprises:
101, each alternative finger target value in each small towns is obtained, and place is normalized to each alternative finger target value in each small towns
Reason；
102, referred to according to the arable land nature of related coefficient and each alternative index and each small towns etc. between each alternative index
Related coefficient between several reference values screens each alternative index, using the alternative index filtered out as point etc. indexs；
103, the reference value of the finger indexes such as target value and the arable land nature in each small towns such as each point in each small towns is returned,
Determine the indexs such as each point to the weighing factor of the indexes such as the arable land nature in each small towns；
104, refer to the corresponding influence of the indexs such as each point in target value and each small towns according to each point etc. of each small towns
Weight determines the indexes such as the arable land nature in each small towns.
Wherein, the alternative index in 101 refers to will affect the natural index of farmland quality.Two can be screened out in 102
The biggish alternative index of pairwise correlation coefficient, and retain the related coefficient between the reference values of indexes such as the arable land nature in each small towns
Biggish alternative index.By 102 after the indexs such as filtering out point, the indexs such as each point can be determined to each small towns by 103
The weighing factor of the indexes such as arable land nature, it should be noted that shadow of the indexs such as same point to indexes such as different small towns arable land natures
Ringing weight may be different.In 104, it can refer to each point of target value and each small towns to each point etc. of each small towns
Etc. the corresponding weighing factor of indexs be weighted summation, to obtain the indexes such as the arable land nature in each small towns.
Method provided in an embodiment of the present invention, due to that can evaluate from more macroscopical angle farmland quality, and
In view of point etc. indexs Space atmosphere, so as to it is more objective, accurately farmland quality is evaluated.Utilize correlation
The method of analysis is probed into related between the related coefficient between each alternative index and alternative index and the indexes such as nature of ploughing
Coefficient, being capable of more accurately screening and assessment index.Weighing factor is calculated with the method for Geographical Weighted Regression, it can be certain
It solves not considering resultant error caused by special heterogeneity in degree, overcomes interference of the special heterogeneity to models fitting, so that
Calculated result is more objective and tallies with the actual situation.
It should be noted that arable land is used as a kind of typical geospatial entity, landform, soil nutrient, economic input
It is horizontal that all there is regional scale and regional differentiation, thus on different space scales, form, property and the regularity of distribution
Also it will appear different geographical space expression effects.In embodiments of the present invention, farmland quality can be screened from excellent layout
Influence factor, and farmland quality is evaluated based on excellent layout, relative to the Evaluation for cultivated-land of County Scale, more favorably
In the distribution situation for understanding farmland quality from macro-scale.
Content based on the above embodiment, as a kind of alternative embodiment, the embodiment of the present invention is not to each small towns of acquisition
Each alternative mode for referring to target value specifically limits, including but not limited to: for any small towns, according to the elevation mould in any small towns
Type data extract the mean sea level and mean inclination in any small towns；Interpolation is carried out by the meteorological site data to any small towns,
The mean sea level in any small towns, mean inclination, average year drop in the average annual precipitation and average temperature of the whole year for obtaining any small towns
Each alternative finger target value of water and average temperature of the whole year respectively as any small towns.
Specifically, extract analysis using elevation model data of the GIS software to all small towns in province domain, using point
Area's statistical tool obtains the mean sea level in all small towns in province domain, and extracts the gradient using 3D analysis, to calculate each township
The mean inclination in town.Using meteorological site data, the mean annual precipitation and year-round average temperature in all small towns in province domain are calculated.
Wherein, mean sea level, mean inclination, average annual precipitation and average temperature of the whole year can have respectively as an alternative index
The value that body is calculated is respective specific value.
Content based on the above embodiment, as a kind of alternative embodiment, about each alternative finger target value to each small towns
The mode being normalized, the present invention is not especially limit this, for the alternative index of the i-th class in any small towns
Value, normalized can be made by following formula:
Wherein, KiIndicate that i-th class in any small towns alternatively refers to the corresponding normalization of target value as a result, xiIndicate any small towns
The i-th class alternatively refer to target value, xminIndicate that i-th class in each small towns alternatively refers to the minimum value in target value, xmaxIndicate each small towns
The i-th class alternatively refer to the maximum value in target value.
It should be noted that every class in the small towns alternatively refers to that target value can be according to above-mentioned formula for any small towns
Make normalized, and every class in other small towns alternatively refers to that target value can also make normalized according to above-mentioned formula.In addition,
Why the embodiment of the present invention will do normalized, primarily to eliminating the dimension of alternative index by normalization.Wherein,
Alternative its value range of finger target value after normalization is [0,1].
Content based on the above embodiment, as a kind of alternative embodiment, according to the phase relation between each alternative index
Related coefficient between the reference values of indexes such as the arable land nature in several and each alternative index and each small towns, to each alternative index
Screened, using the alternative index filtered out as point etc. before indexs, further includes: for any small towns, according to current arable land
Quality annual update data, obtain the indexes such as the arable land nature of each arable land figure spot in any small towns；It is ploughed according to each in any small towns
The area accounting of the indexes such as the arable land nature of ground figure spot and each arable land figure spot determines the ginseng of the indexes such as the arable land nature in any small towns
Examine value.
By taking any small towns as an example, the indexes such as arable land nature of each arable land figure spot can be got in advance in the small towns.For
Any arable land figure spot in the small towns, the area accounting of the arable land figure spot are that the area of the arable land figure spot and total in the small towns plough
Ratio between ground area.By the area accounting of the arable land indexes such as nature of each arable land figure spot in the small towns and each arable land figure spot into
The reference value of the indexes such as the arable land nature in the small towns can be obtained in row weighted sum.
Content based on the above embodiment, as a kind of alternative embodiment, according to the phase relation between each alternative index
Related coefficient between the reference values of indexes such as the arable land nature in several and each alternative index and each small towns, to each alternative index
Screened, using the alternative index filtered out as point etc. before indexs, further includes: for any alternative index of two classes, will appoint
The alternative index of two classes of anticipating is obtained as the alternative index of the i-th class and the alternative index of jth class by the alternative index of the i-th class in each small towns
Primary vector composed by being worth obtains and alternatively refers to secondary vector composed by target value as the jth class in each small towns；Calculate first to
Related coefficient between amount and secondary vector, and as the related coefficient between the alternative index of the i-th class and the alternative index of jth class.
Wherein, the related coefficient between the alternative index of the i-th class and the alternative index of jth class is calculated, can refer to following formula:
In above-mentioned formula, ρxyIndicate the related coefficient between the alternative index of the i-th class and the alternative index of jth class.X indicates the
One vector, y indicate secondary vector.μxIndicate that i-th class in each small towns alternatively refers to the corresponding mean value of target value, μyIndicate each small towns
Jth class alternatively refers to the corresponding mean value of target value, SxIndicate that i-th class in each small towns alternatively refers to the corresponding standard deviation of target value, SyIt indicates
The jth class in each small towns alternatively refers to the corresponding standard deviation of target value.Wherein, the value range of related coefficient is [- 1,1], absolutely
Value then illustrates that two correlation of variables are bigger closer to 1；Its absolute value then illustrates that the correlation of two variables is got over closer to 0
It is small.And during actual implementation, the embodiment of the present invention can screen out one alternatively from correlation biggish two alternative indexs
Index.
Content based on the above embodiment, as a kind of alternative embodiment, according to the phase relation between each alternative index
Related coefficient between the reference values of indexes such as the arable land nature in several and each alternative index and each small towns, to each alternative index
Screened, using the alternative index filtered out as point etc. before indexs, further includes: index alternative for any sort, obtain by
Any sort in each small towns alternatively refers to third vector composed by target value, obtains by the reference of the indexes such as the arable land nature in each small towns
4th vector composed by being worth；The related coefficient between third vector and the 4th vector is calculated, and as the alternative index of any sort
Related coefficient between the reference value of the indexes such as nature of ploughing in each small towns.
Wherein, index alternative for any sort calculates the ginseng of the indexes such as the arable land nature of such alternative index and each department
The related coefficient between value is examined, equally can refer to the formula for calculating related coefficient in above-described embodiment, details are not described herein again.It is practical
In implementation process, the embodiment of the present invention can retain related between the reference value of the indexes such as the arable land nature in each small towns as far as possible
The biggish alternative index of coefficient.
Content based on the above embodiment, as a kind of alternative embodiment, the embodiment of the present invention is not to according to each alternative finger
Phase relation between the reference value of indexes such as related coefficient and each alternative index between mark and the arable land nature in each small towns
Number, screens each alternative index, using the alternative index filtered out as the modes of indexs such as dividing specifically to limit, including but
It is not limited to: according to the related coefficient between each alternative index, each alternative index being screened to obtain first set；According to each standby
The related coefficient between the reference values of indexes such as the arable land nature in index and each small towns is selected, each alternative index is screened to obtain
Second set；According to first set and second set, the indexs such as determining point.
Specifically, with there are the alternative indexs of 5 classes, and respectively for a, b, c, d and e.It is providing through the foregoing embodiment
Mode can first determine after the related coefficient of the alternative index of 5 class between any two is calculated and fall into the corresponding threshold of strong correlation
The related coefficient being worth in section, and further determine that the corresponding alternative index of these related coefficients.It then, can be alternative to these
Index is screened.When screening to these alternative indexs, those alternative indexs for being not easy to acquire numerical value can be screened out,
Retain and relatively easily collect the alternative index of numerical value, using as first set.
In addition, referring to calculating separately to obtain arable land nature in each alternative index and each small towns etc. in this alternative index of 5 class
After related coefficient between several reference values, which can be sorted from large to small, before reservation sequence is forward
The corresponding alternative index (n is the positive integer greater than 0 and no more than 5) of n related coefficient, and as second set.Obtaining
It, can be with reference to first set and second set, to be further determined that from the alternative index of 5 classes after one set and second set
Point etc. indexs.
It should be noted that above two related coefficient may be incorporated for screening alternative index, actual implementation mistake
It can be combined according to demand in journey, the present invention is not especially limit this.For example, if phase relation between a and b
Number corresponds to strong correlation, to need to screen out a kind of alternative index from a and b.During actual implementation, be calculated a with
The ginseng of the indexes such as the arable land nature of related coefficient and b and small towns between the reference values of indexes such as the arable land nature in each small towns
After examining the related coefficient between value, the size of the two related coefficients can be compared.If the corresponding related coefficient of b is big, from a with
The alternative index of a class is screened out in b, retains the alternative index of b class.Conversely, then screening out the alternative index of b class from a and b, it is alternative to retain a class
Index.
Content based on the above embodiment refers to target value about each point etc. to each small towns as a kind of alternative embodiment
It is returned with the reference value of the indexes such as the arable land nature in each small towns, determines the indexs such as each point to the arable land nature etc. in each small towns
The mode of the weighing factor of index, the present invention is not especially limit this, including but not limited to: for any small towns,
The optimum bandwidth in any small towns is determined based on cross-validation method；It determines in any small towns and optimum bandwidth between other each small towns
Distance weighting；According to the distance between other each small towns in any small towns and optimum bandwidth weight, any small towns pair is determined
The corresponding estimation parameter of the indexs such as each point in the Geographical Weighted Regression Model answered；Refer to target value according to each point etc. of any small towns
With the reference value of the indexes such as nature of ploughing in any small towns, the corresponding Geographical Weighted Regression Model in any small towns is solved,
Determine the indexs such as each point to the weighing factor of the indexes such as the arable land nature in any small towns.
Wherein, for any small towns, in the optimum bandwidth for determining the small towns, the method that cross validation can be used, specifically
It can refer to following formula:
It should be noted that according to above-mentioned formula, regression parameter does not include regression point itself when estimating, i.e., only according to recurrence
Data point around point carries out recurrence calculating.Different bandwidth b CV values corresponding with it is depicted as Trendline, it can be very straight
Find optimum bandwidth corresponding to minimum value with seeing.
After determining the optimum bandwidth in the small towns, it can determine again in the small towns and optimum bandwidth between other each small towns
Distance weighting.Specifically, Gaussian function method can be used and determine distance weighting wij, the basic thought of this method is exactly to pass through selection
One continuous monotonic decreasing function indicates wijWith dij(the distance between i-th of small towns and j-th of small towns, j-th of small towns are
In the optimum bandwidth in i-th of small towns) between relationship, detailed process can refer to following formula:
wij=exp (- (dij/b)2)；
In above-mentioned formula, b is the non-negative attenuation parameter for describing functional relation between weight and distance, referred to as bandwidth.Band
Wide bigger, weight increases the slower of decaying with distance.Bandwidth is smaller, and weight increases the faster of decaying with distance.
At a distance from determining the small towns between each small towns after weight, can further the corresponding geography in the small towns it weight back
Return the corresponding estimation parameter of the indexs such as each point in model.Wherein, which weights back
Model is returned to can refer to following formula:
In order to express easily, above-mentioned formula can be abbreviated as following formula:
In above-mentioned formula, (μi,νi) indicate i-th of small towns position, βikIndicate the corresponding geographical weighting in i-th of small towns
The corresponding estimation parameter of the indexs such as k-th point, x in regression modelikIndicate the indexs such as k-th point to the arable land in i-th of small towns from
So wait the weighing factor of indexes.In addition, δi∽(0,σ2), Cov (δi,δj)=0 (i ≠ j).
In the regression parameter of estimating sampling point, the importance of the observation at different observation points is different, range points
Closer observation importance is bigger, and remoter observation importance is smaller.Correspondingly, it can establish and βi0And βikRelevant mesh
Scalar functions, specific as follows:
By above-mentioned objective function, β can be calculatedi0,βi1,...,βip。
Content based on the above embodiment, the embodiment of the invention provides a kind of dresses of the indexes such as acquisition province domain arable land nature
It sets, the device of the indexes such as acquisition province domain arable land nature is used to execute the acquisition province domain arable land provided in above method embodiment certainly
So wait the method for indexes.Referring to fig. 2, which includes:
First obtains module 201, obtains each alternative finger target value in each small towns；
Normalized module 202 is normalized for each alternative finger target value to each small towns；
Screening module 203, for according between each alternative index related coefficient and each alternative index and each small towns
Related coefficient between the reference values of indexes such as nature of ploughing, screens each alternative index, the alternative index that will be filtered out
As point etc. indexs；
Regression block 204, the ginseng of the indexes such as arable land nature for referring to target value and each small towns to each point etc. of each small towns
It examines value to be returned, determines the indexs such as each point to the weighing factor of the indexes such as the arable land nature in each small towns；
First determining module 205, for referring to each point of target value and each small towns according to each point etc. of each small towns
Etc. the corresponding weighing factor of indexs, determine the indexes such as the arable land nature in each small towns.
As a kind of alternative embodiment, module 201 is obtained, is used for for any small towns, according to the elevation mould in any small towns
Type data extract the mean sea level and mean inclination in any small towns；
Interpolation is carried out by the meteorological site data to any small towns, obtains the average annual precipitation and Nian Ping in any small towns
Equal temperature, using the mean sea level in any small towns, mean inclination, average annual precipitation and average temperature of the whole year as any small towns
Each alternative finger target value.
As a kind of alternative embodiment, normalized module 202, for being normalized by following formula:
Wherein, KiIndicate that i-th class in any small towns alternatively refers to the corresponding normalization of target value as a result, xiIndicate any small towns
The i-th class alternatively refer to target value, xminIndicate that i-th class in each small towns alternatively refers to the minimum value in target value, xmaxIndicate each small towns
The i-th class alternatively refer to the maximum value in target value.
As a kind of alternative embodiment, the device further include:
Second obtains module, for obtaining any township according to current farmland quality annual update data for any small towns
The indexes such as arable land nature of each arable land figure spot in town；
Second determining module, for indexes and each arable land figure spots such as arable land natures according to each arable land figure spot in any small towns
Area accounting, determine the reference value of the arable land indexes such as nature in any small towns.
As a kind of alternative embodiment, the device further include:
Third obtains module, is used for for any alternative index of two classes, and any alternative index of two classes is alternative as the i-th class
Index and the alternative index of jth class obtain and alternatively refer to primary vector composed by target value as i-th class in each small towns, obtain by each
The jth class in small towns alternatively refers to secondary vector composed by target value；
First computing module, for calculating the related coefficient between primary vector and secondary vector, and it is alternative as the i-th class
Related coefficient between index and the alternative index of jth class.
As a kind of alternative embodiment, the device further include:
4th obtains module, is used for index alternative for any sort, obtains and alternatively refers to target value by any sort in each small towns
Composed third vector obtains the 4th vector as composed by the reference value of the indexes such as the arable land nature in each small towns；
Second computing module, for calculating the related coefficient between third vector and the 4th vector, and it is standby as any sort
Select the related coefficient between the reference values of indexes such as the arable land nature in index and each small towns.
As a kind of alternative embodiment, screening module 203, for according to the related coefficient between each alternative index, to each
Alternative index is screened to obtain first set；The reference value of the indexes such as the arable land nature according to each alternative index and each small towns it
Between related coefficient, each alternative index is screened to obtain second set；According to first set and second set, determining point etc.
Index.
Regression block, each index weight back the exponential effects weighteds such as each small towns arable land nature using geography
The method returned determines each index to exponential effects weights such as each small towns arable land natures.Select the indexes such as nature as because becoming
Amount, each index after normalization is as explanatory variable；Selection Adaptive Gaussian kernel is simultaneously determined by cross-validation method
Optimum bandwidth.
As a kind of alternative embodiment, regression block 204, for being determined and being appointed based on cross-validation method for any small towns
The optimum bandwidth in one small towns；Determine the distance between other each small towns weight in any small towns and optimum bandwidth；According to any
The distance between other each small towns weight, determines the corresponding Geographical Weighted Regression Model in any small towns in small towns and optimum bandwidth
In the corresponding estimation parameter of the indexs such as each point；Refer to the arable land nature of target value Yu any small towns according to each point etc. of any small towns
The reference value of equal indexes, solves the corresponding Geographical Weighted Regression Model in any small towns, determines the indexs such as each point to appointing
The weighing factor of the indexes such as the arable land nature in one small towns.
Device provided in an embodiment of the present invention, due to that can evaluate from more macroscopical angle farmland quality, and
In view of point etc. indexs Space atmosphere, so as to it is more objective, accurately farmland quality is evaluated.Utilize correlation
The method of analysis is probed into related between the related coefficient between each alternative index and alternative index and the indexes such as nature of ploughing
Coefficient, being capable of more accurately screening and assessment index.Weighing factor is calculated with the method for Geographical Weighted Regression, it can be certain
It solves not considering resultant error caused by special heterogeneity in degree, overcomes interference of the special heterogeneity to models fitting, so that
Calculated result is more objective and tallies with the actual situation.
It should be noted that arable land is used as a kind of typical geospatial entity, landform, soil nutrient, economic input
It is horizontal that all there is regional scale and regional differentiation, thus on different space scales, form, property and the regularity of distribution
Also it will appear different geographical space expression effects.In embodiments of the present invention, farmland quality can be screened from excellent layout
Influence factor, and farmland quality is evaluated based on excellent layout, relative to the Evaluation for cultivated-land of County Scale, more favorably
In the distribution situation for understanding farmland quality from macro-scale.
Fig. 3 illustrates the entity structure schematic diagram of a kind of electronic equipment, as shown in figure 3, the electronic equipment may include: place
Manage device (processor) 310, communication interface (Communications Interface) 320,330 He of memory (memory)
Communication bus 340, wherein processor 310, communication interface 320, memory 330 complete mutual lead to by communication bus 340
Letter.Processor 310 can call the logical order in memory 330, to execute following method: obtain each alternative finger in each small towns
Target value, and each alternative finger target value in each small towns is normalized；According to the related coefficient between each alternative index,
And the related coefficient between each alternative index and the reference values of indexes such as nature of ploughing in each small towns, each alternative index is carried out
Screening, using the alternative index filtered out as divide etc. indexs；The arable land for referring to target value and each small towns to each point etc. of each small towns from
So the reference value of indexes is waited to be returned, determines the indexs such as each point to the weighing factor of the indexes such as the arable land nature in each small towns；
The corresponding weighing factor of the indexs such as each point for referring to target value and each small towns according to each point etc. of each small towns, determines each
The indexes such as the arable land nature in small towns.
In addition, the logical order in above-mentioned memory 330 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
Substantially the part of the part that contributes to existing technology or the technical solution can be in other words for the technical solution of invention
The form of software product embodies, which is stored in a storage medium, including some instructions to
So that a computer equipment (can be personal computer, electronic equipment or the network equipment etc.) executes each reality of the present invention
Apply all or part of the steps of a method.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random AccessMemory), magnetic or disk etc. it is various
It can store the medium of program code.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, is stored thereon with computer program,
The computer program is implemented to carry out the various embodiments described above offer method when being executed by processor, for example, obtain each township
Each alternative finger target value in town, and each alternative finger target value in each small towns is normalized；According to each alternative index it
Between related coefficient and each alternative index and each small towns the reference value of indexes such as arable land nature between related coefficient, it is right
Each alternative index is screened, using the alternative index filtered out as point etc. indexs；To each point etc. of each small towns refer to target value with
The reference value of the indexes such as the arable land nature in each small towns is returned, and determines that the indexs such as each point refer to the arable land nature in each small towns etc.
Several weighing factors；Refer to the corresponding influence of the indexs such as each point of target value and each small towns according to each point etc. of each small towns
Weight determines the indexes such as the arable land nature in each small towns.
The apparatus embodiments described above are merely exemplary, wherein unit can be as illustrated by the separation member
Or may not be and be physically separated, component shown as a unit may or may not be physical unit, i.e.,
It can be located in one place, or may be distributed over multiple network units.It can select according to the actual needs therein
Some or all of the modules achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creative labor
In the case where dynamic, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (11)
1. a kind of method for obtaining the indexes such as province domain arable land nature characterized by comprising
Each alternative finger target value of each department is obtained, and each alternative finger target value in each small towns is normalized；
According to the reference of the indexes such as nature of ploughing of related coefficient and each alternative index and each small towns between each alternative index
Related coefficient between value screens each alternative index, using the alternative index filtered out as point etc. indexs；
Refer to that the reference value of the indexes such as target value and the arable land nature in each small towns returns to each point etc. of each small towns, determines each
Point etc. indexs to the weighing factors of the arable land indexes such as nature in each small towns；
Refer to the corresponding weighing factor of the indexs such as each point of target value and each small towns according to each point etc. of each small towns, determines
The indexes such as the arable land nature in each small towns.
2. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described to obtain each township
Each alternative finger target value in town, comprising:
The average sea in any small towns is extracted according to the Law of DEM Data in any small towns for any small towns
It pulls out and mean inclination；
Carry out interpolation by meteorological site data to any small towns, obtain any small towns average annual precipitation and
Average temperature of the whole year, using the mean sea level of any area, mean inclination, average annual precipitation and average temperature of the whole year as
Each alternative finger target value in any small towns.
3. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described to each small towns
Each alternative finger target value be normalized, comprising:
Wherein, KiIndicate that i-th class in a certain small towns alternatively refers to the corresponding normalization of target value as a result, xiIndicate the i-th of a certain small towns
Class alternatively refers to target value, xminIndicate that i-th class in each small towns alternatively refers to the minimum value in target value, xmaxIndicate the i-th of each small towns
Class alternatively refers to the maximum value in target value.
4. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described according to each standby
It selects related between related coefficient and each alternative index between index and the reference value of the indexes such as nature of ploughing in each small towns
Coefficient screens each alternative index, using the alternative index filtered out as point etc. before indexs, further includes:
For any small towns, according to current farmland quality annual update data, each arable land figure spot in any small towns is obtained
The indexes such as arable land nature；
The area accounting of the indexes such as the arable land nature according to each arable land figure spot in any small towns and each arable land figure spot, determines institute
State the reference value of the indexes such as the arable land nature in any small towns.
5. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described according to each standby
It selects related between related coefficient and each alternative index between index and the reference value of the indexes such as nature of ploughing in each small towns
Coefficient screens each alternative index, using the alternative index filtered out as point etc. before indexs, further includes:
For any alternative index of two classes, alternatively refer to using any alternative index of two classes as the alternative index of the i-th class and jth class
Mark, obtains and alternatively refers to primary vector composed by target value as i-th class in each small towns, and acquisition is alternatively referred to by the jth class in each small towns
Secondary vector composed by target value；
The related coefficient between the primary vector and the secondary vector is calculated, and standby as the alternative index of the i-th class and jth class
Select the related coefficient between index.
6. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described according to each standby
It selects related between related coefficient and each alternative index between index and the reference value of the indexes such as nature of ploughing in each small towns
Coefficient screens each alternative index, using the alternative index filtered out as point etc. before indexs, further includes:
Index alternative for any sort obtains and alternatively refers to third vector composed by target value as any sort in each small towns,
Obtain the 4th vector as composed by the reference value of the indexes such as the arable land nature in each small towns；
The related coefficient between the third vector and the 4th vector is calculated, and as the alternative index of any sort and respectively
Related coefficient between the reference values of indexes such as the arable land nature in small towns.
7. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described according to each standby
It selects related between related coefficient and each alternative index between index and the reference value of the indexes such as nature of ploughing in each small towns
Coefficient screens each alternative index, using the alternative index filtered out as point etc. indexs, comprising:
According to the related coefficient between each alternative index, each alternative index is screened to obtain first set；
According to the related coefficient between the reference value of the indexes such as the arable land nature in each alternative index and each small towns, to each alternative index
It is screened to obtain second set；
According to the first set and the second set, the indexs such as determining point.
8. the method according to claim 1 for obtaining the indexes such as province domain arable land nature, which is characterized in that described to each small towns
Each point etc. refer to that the reference value of the indexes such as target value and the arable land nature in each small towns is returned, determine the indexs such as each point to each
The weighing factor of the indexes such as the arable land nature in small towns, comprising:
For any small towns, the optimum bandwidth in any small towns is determined based on cross-validation method；
Determine the distance between other each small towns weight in any small towns and the optimum bandwidth；
According to the distance between other each small towns in any small towns and optimum bandwidth weight, any township is determined
The corresponding estimation parameter of the indexs such as each point in the corresponding Geographical Weighted Regression Model in town；
The reference value of the indexes such as the arable land nature for referring to target value and any small towns according to each point etc. of any small towns is right
The corresponding Geographical Weighted Regression Model in any small towns is solved, and determines that the indexs such as each point plough any small towns
The weighing factor of the indexes such as ground nature.
9. a kind of device for obtaining the indexes such as province domain arable land nature characterized by comprising
First obtains module, obtains each alternative finger target value in each small towns；
Normalized module is normalized for each alternative finger target value to each small towns；
Screening module, for according to the arable land of related coefficient and each alternative index and each small towns between each alternative index from
So related coefficient between the reference value of equal indexes, screens each alternative index, using the alternative index filtered out as dividing
Etc. indexs；
The reference value of regression block, the indexes such as arable land nature for referring to target value and each small towns to each point etc. of each small towns carries out
It returns, determines the indexs such as each point to the weighing factor of the indexes such as the arable land nature in each small towns；
First determining module, for referring to the indexs pair such as each point in target value and each small towns according to each point etc. of each small towns
The weighing factor answered determines the indexes such as the arable land nature in each small towns.
10. a kind of electronic equipment characterized by comprising
At least one processor；And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough execute method as described in any of the claims 1 to 8.
11. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute method as described in any of the claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910654550.8A CN110363442B (en) | 2019-07-19 | 2019-07-19 | Method and device for acquiring natural equal index of provincial farmland |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910654550.8A CN110363442B (en) | 2019-07-19 | 2019-07-19 | Method and device for acquiring natural equal index of provincial farmland |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110363442A true CN110363442A (en) | 2019-10-22 |
| CN110363442B CN110363442B (en) | 2021-09-10 |
Family
ID=68220365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910654550.8A Expired - Fee Related CN110363442B (en) | 2019-07-19 | 2019-07-19 | Method and device for acquiring natural equal index of provincial farmland |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363442B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140146437A (en) * | 2013-06-17 | 2014-12-26 | 고려대학교 산학협력단 | Apparatus and method for forecasting business performance based on patent information |
| CN104794535A (en) * | 2015-04-16 | 2015-07-22 | 清华大学 | Leading industry based electricity demand prediction and early warning method |
| CN107239339A (en) * | 2016-03-29 | 2017-10-10 | 阿里巴巴集团控股有限公司 | System function optimization parameter determination method, system function optimization method and device |
| CN108241779A (en) * | 2017-12-29 | 2018-07-03 | 武汉大学 | Ground PM2.5 Density feature vectors space filter value modeling method based on remotely-sensed data |
-
2019
- 2019-07-19 CN CN201910654550.8A patent/CN110363442B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140146437A (en) * | 2013-06-17 | 2014-12-26 | 고려대학교 산학협력단 | Apparatus and method for forecasting business performance based on patent information |
| CN104794535A (en) * | 2015-04-16 | 2015-07-22 | 清华大学 | Leading industry based electricity demand prediction and early warning method |
| CN107239339A (en) * | 2016-03-29 | 2017-10-10 | 阿里巴巴集团控股有限公司 | System function optimization parameter determination method, system function optimization method and device |
| CN108241779A (en) * | 2017-12-29 | 2018-07-03 | 武汉大学 | Ground PM2.5 Density feature vectors space filter value modeling method based on remotely-sensed data |
Non-Patent Citations (3)
| Title |
|---|
| 杨永侠 等: ""京津冀地区耕地质量空间分布分形机制研究"", 《农业机械学报》 * |
| 杨永侠 等: ""基于空间自相关的耕地等别指数检验方法研究"", 《农业机械学报》 * |
| 郧文聚: ""农用地分等及其应用研究"", 《中国博士学位论文全文数据库 社会科学Ⅰ辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110363442B (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Berger et al. | Creating agents and landscapes for multiagent systems from random samples | |
| Attardi et al. | Non-compensatory composite indicators for the evaluation of urban planning policy: The Land-Use Policy Efficiency Index (LUPEI) | |
| González Tánago et al. | Learning from experience: a systematic review of assessments of vulnerability to drought | |
| Beaulieu et al. | Modeling stabilizing selection: expanding the Ornstein–Uhlenbeck model of adaptive evolution | |
| McMillan et al. | Rainfall‐runoff model calibration using informal likelihood measures within a Markov chain Monte Carlo sampling scheme | |
| Awotwi et al. | Climate change impact on streamflow in a tropical basin of Ghana, West Africa | |
| Mediero et al. | Probabilistic calibration of a distributed hydrological model for flood forecasting | |
| Moe et al. | Integrated assessment of ecological status and misclassification of lakes: the role of uncertainty and index combination rules | |
| Wu et al. | Characterization and evaluation of elevation data uncertainty in water resources modeling with GIS | |
| CN110598513A (en) | Urban development boundary prediction method based on SLUTH model | |
| Bock et al. | Quantifying uncertainty in simulated streamflow and runoff from a continental-scale monthly water balance model | |
| CN109615166A (en) | A kind of steppe vegetation degeneration remote-sensing monitoring method and device | |
| Chen et al. | Simulating the optimal land-use pattern in the farming-pastoral transitional zone of Northern China | |
| Yu et al. | Assessment of land degradation in the North China Plain driven by food security goals | |
| Fernandes et al. | A novel downscaling approach to predict plant invasions and improve local conservation actions | |
| Mustafa et al. | Measuring the effect of stochastic perturbation component in cellular automata urban growth model | |
| Su et al. | Priority areas for mixed-species mangrove restoration: the suitable species in the right sites | |
| Makido et al. | Weighting function alternatives for a subpixel allocation model | |
| Munoz et al. | Watersheds are not static: Implications of climate variability and hydrologic dynamics in modeling | |
| Luo et al. | Responses of remnant wetlands in the Sanjiang Plain to farming-landscape patterns | |
| Arif et al. | Analysis of artificial neural network in erosion modeling: a case study of Serang watershed | |
| Bivand et al. | Further explorations of interactions between agricultural policy and regional growth in Western Europe-approaches to nonstationarity in spatial econometrics | |
| CN110363442A (en) | Obtain the method and device of the indexes such as province domain arable land nature | |
| Garcia et al. | Filling in missing rainfall data in the Andes region of Venezuela, based on a cluster | |
| Peeters et al. | Conceptual evaluation of continental land-surface model behaviour |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210910 |