CN110363442B - Method and device for acquiring natural equal index of provincial farmland - Google Patents
Method and device for acquiring natural equal index of provincial farmland Download PDFInfo
- Publication number
- CN110363442B CN110363442B CN201910654550.8A CN201910654550A CN110363442B CN 110363442 B CN110363442 B CN 110363442B CN 201910654550 A CN201910654550 A CN 201910654550A CN 110363442 B CN110363442 B CN 110363442B
- Authority
- CN
- China
- Prior art keywords
- index
- town
- village
- indexes
- farmland
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012216 screening Methods 0.000 claims abstract description 27
- 238000010606 normalization Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 15
- 238000001556 precipitation Methods 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 5
- 238000013441 quality evaluation Methods 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000002349 favourable effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 235000015097 nutrients Nutrition 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000012876 topography Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method and a device for acquiring indexes of nature and the like of provincial farmland, belonging to the technical field of farmland quality evaluation. The method comprises the following steps: screening each alternative index according to the correlation coefficient among the alternative indexes and the correlation coefficient between each alternative index and the reference value of the index of nature and the like of the cultivated land of each village and town in the province, and taking the screened alternative index as a grading index; regressing the value of each index of the villages and towns and the reference value of the index of the nature of the cultivated land of each village and towns, and determining the influence weight of each index of the grade on the index of the nature of the cultivated land of each village and towns; and determining the indexes of the nature of the cultivated land of each village and town in the province according to the value of each index of each village and town and the influence weight corresponding to each index of each village and town. The farmland quality can be evaluated from a macroscopic angle, and the spatial non-stationarity of the grading indexes is considered, so that the farmland quality can be evaluated more objectively and accurately.
Description
Technical Field
The invention relates to the technical field of farmland quality evaluation, in particular to a method and a device for acquiring indexes of provincial farmland nature and the like.
Background
At present, the protection work of the cultivated land faces new situation and requirements, ecological civilization construction needs to be deeply promoted, and protection is carried out from three aspects of the cultivated land quantity, the cultivated land quality and the ecology, so that the essence of the cultivated land quality needs to be further deeply known. With the increasing attention of people to the farmland quality, the method has important significance in evaluating the farmland quality in province from the macroscopic perspective.
In the related art, the most commonly used method for obtaining the index of nature and the like of the provincial farmland is to obtain each index value through sample point investigation in a county area range, determine the score and the weight of each index through an expert scoring method, and calculate and obtain the index of nature and the like of each farmland map spot. However, the index of nature and the like obtained by this method is highly subjective, and the calculation of the index of nature and the like of cultivated land on a prefecture basis is not favorable for the evaluation of the quality of cultivated land from a macroscopic point of view.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a method and an apparatus for obtaining a natural index of a provincial region farmland, which overcome the above problems or at least partially solve the above problems.
According to a first aspect of the embodiments of the present invention, there is provided a method for obtaining a natural index of a provincial farmland, including:
acquiring values of all alternative indexes of all towns, and carrying out normalization processing on the values of all alternative indexes of all towns;
screening the alternative indexes according to the correlation coefficient among the alternative indexes and the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each town, and taking the screened alternative indexes as ranking indexes;
regressing the value of each index of the villages and towns and the reference value of the index of the nature of the cultivated land of each village and towns, and determining the influence weight of each index of the grade on the index of the nature of the cultivated land of each village and towns;
and determining the indexes of nature of cultivated land of each village and town according to the value of each index of the village and town and the influence weight corresponding to each index of the village and town.
According to a second aspect of the embodiments of the present invention, there is provided an apparatus for obtaining a natural index of a provincial farmland, including:
the first acquisition module is used for acquiring the value of each alternative index of each village and town;
the normalization processing module is used for performing normalization processing on the values of the alternative indexes of the towns;
the screening module is used for screening the alternative indexes according to the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each village and town, and taking the screened alternative indexes as the grading indexes;
the regression module is used for performing regression on the value of each index such as the division of each village and town in each region and the reference value of the index such as the nature of the cultivated land in each village and town, and determining the influence weight of each index such as the division on the index such as the nature of the cultivated land in each village and town;
the first determining module is used for determining indexes of nature of cultivated land of each village and town according to the value of each index of each village and town and the influence weight corresponding to each index of each village and town.
According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for acquiring the index of the provincial region farmland nature and the like provided by any one of the various possible implementation manners of the first aspect.
According to a fourth aspect of the present invention, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for obtaining indices of nature of provincial regions of farmland as provided in any one of the various possible implementations of the first aspect.
According to the method and the device for acquiring the indexes of the provincial farmland nature and the like, which are provided by the embodiment of the invention, the farmland quality can be evaluated from a more macroscopic angle, and the spatial non-stationarity of the grading indexes is considered, so that the farmland quality can be evaluated more objectively and accurately. The correlation coefficient among all the candidate indexes and the correlation coefficient between the candidate indexes and the indexes such as the nature of cultivated land are explored by using a correlation analysis method, so that the evaluation indexes can be screened more accurately. The influence weight is calculated by using a geographical weighted regression method, so that the problem of result error caused by not considering spatial heterogeneity can be solved to a certain extent, the interference of the spatial heterogeneity on model fitting is overcome, and the calculation result is more objective and accords with the actual situation.
It should be noted that, as a typical geospatial entity, the topography, soil nutrients, and economic input levels of the cultivated land have regional scalability and regional diversity, and thus, on different spatial scales, the morphology, properties, and distribution rules of the cultivated land can also have different geospatial expression effects. In the embodiment of the invention, the influence factors of the farmland quality can be screened from the provincial scale, the farmland quality is evaluated based on the provincial scale, and the method is more favorable for knowing the distribution condition of the farmland quality from the macroscopic scale compared with the farmland quality evaluation of the county scale.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of embodiments of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for obtaining indexes such as nature of provincial farmland according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus for obtaining natural index of provincial cultivated land according to an embodiment of the present invention;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Aiming at the problems in the related art, the embodiment of the invention provides a method for acquiring indexes of provincial farmland nature and the like. Wherein, indexes of farmland nature and the like can be used for evaluating the farmland quality. The method can be used for obtaining indexes of farmland nature and the like of provincial areas. The method and the device for acquiring indexes such as the provincial farmland nature and the like provided by the embodiment of the invention can provide technical references for evaluating the nature quality of other provincial or national farmlands. Referring to fig. 1, the method includes:
101. acquiring values of all alternative indexes of all towns, and carrying out normalization processing on the values of all alternative indexes of all towns;
102. screening the alternative indexes according to the correlation coefficient among the alternative indexes and the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each town, and taking the screened alternative indexes as ranking indexes;
103. regressing the value of each index of the villages and towns and the reference value of the index of the nature of the cultivated land of each village and towns, and determining the influence weight of each index of the grade on the index of the nature of the cultivated land of each village and towns;
104. and determining the indexes of nature of cultivated land of each village and town according to the value of each index of the village and town and the influence weight corresponding to each index of the village and town.
The candidate index in 101 refers to a natural index that may affect the quality of cultivated land. 102, candidate indexes with larger correlation coefficients can be screened out, and the candidate indexes with larger correlation coefficients between the candidate indexes and reference values of indexes such as farmland nature of various villages and towns can be reserved. After the grading indexes are screened out by the 102, the influence weight of each grading index on each index of nature and the like of the rural cultivated land can be determined by the 103, and it should be noted that the influence weight of the same grading index on the index of nature and the like of the rural cultivated land can be different. In 104, the value of each index of each town and the influence weight corresponding to each index of each town may be weighted and summed, so as to obtain the index of natural farmland in each town.
The method provided by the embodiment of the invention can evaluate the farmland quality from a macroscopic angle and considers the spatial non-stationarity of the grading indexes, so that the farmland quality can be evaluated more objectively and accurately. The correlation coefficient among all the candidate indexes and the correlation coefficient between the candidate indexes and the indexes such as the nature of cultivated land are explored by using a correlation analysis method, so that the evaluation indexes can be screened more accurately. The influence weight is calculated by using a geographical weighted regression method, so that the problem of result error caused by not considering spatial heterogeneity can be solved to a certain extent, the interference of the spatial heterogeneity on model fitting is overcome, and the calculation result is more objective and accords with the actual situation.
It should be noted that, as a typical geospatial entity, the topography, soil nutrients, and economic input levels of the cultivated land have regional scalability and regional diversity, and thus, on different spatial scales, the morphology, properties, and distribution rules of the cultivated land can also have different geospatial expression effects. In the embodiment of the invention, the influence factors of the farmland quality can be screened from the provincial scale, the farmland quality is evaluated based on the provincial scale, and the method is more favorable for knowing the distribution condition of the farmland quality from the macroscopic scale compared with the farmland quality evaluation of the county scale.
Based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner of obtaining the value of each candidate index of each town, which includes but is not limited to: for any village and town, extracting the average altitude and the average gradient of any village and town according to the elevation model data of any village and town; the average annual precipitation and the annual average air temperature of any village and town are obtained by interpolating the meteorological site data of any village and town, and the average altitude, the average gradient, the average annual precipitation and the annual average air temperature of any village and town are respectively used as the values of all candidate indexes of any village and town.
Specifically, the GIS software can be used for extracting and analyzing elevation model data of all villages and towns in the province, the subarea statistical tool is used for obtaining the average altitude of all villages and towns in the province, and the 3D analysis is used for extracting the gradient, so that the average gradient of each village and town is calculated. And calculating the annual average precipitation and annual average temperature of all villages and towns in the province by using the meteorological site data. The average altitude, the average gradient, the average annual precipitation and the annual average air temperature can be respectively used as an alternative index, and the specifically calculated value is a specific numerical value of each.
Based on the content of the foregoing embodiment, as an optional embodiment, regarding a way of performing normalization processing on the values of the candidate indicators of each village and town, the embodiment of the present invention is not specifically limited to this, and for the value of the i-th type candidate indicator of any village and town, normalization processing may be performed by the following formula:
wherein, KiNormalization result, x, corresponding to the value of the i-th class candidate index representing any village and towniValue, x, of the i-th class candidate index representing any village and townminMinimum value, x, among values of i-th class candidate indexes representing respective townsmaxThe maximum value among the values of the i-th class candidate index representing each town.
It should be noted that, for any village and town, the value of each type of candidate index of the village and town may be normalized according to the above formula, and the values of each type of candidate index of other villages and towns may also be normalized according to the above formula. In addition, the embodiment of the invention is mainly used for eliminating the dimension of the alternative index through normalization. Wherein, the value range of the normalized alternative index is [0, 1 ].
Based on the content of the foregoing embodiment, as an optional embodiment, before screening each candidate index according to a correlation coefficient between each candidate index and a reference value of a natural index of farmland in each town, and taking the screened candidate index as a ranking index, the method further includes: for any village and town, annual updating data according to the current cultivated land quality, and acquiring cultivated land natural indexes of the pattern spots of each cultivated land in any village and town; and determining a reference value of the farmland natural equal index of any village and town according to the farmland natural equal index of each farmland pattern spot and the area ratio of each farmland pattern spot in any village and town.
Taking any village and town as an example, the indexes of the nature of the cultivated land of the pattern spots of each cultivated land in the village and town can be obtained in advance. For any cultivated land pattern spot in the village and town, the area proportion of the cultivated land pattern spot is the ratio between the area of the cultivated land pattern spot and the total cultivated land area in the village and town. And weighting and summing the indexes of the nature of the cultivated land of the pattern spots of each cultivated land in the village and the town and the area ratio of the pattern spots of each cultivated land to obtain the reference value of the indexes of the nature of the cultivated land of the village and the town.
Based on the content of the foregoing embodiment, as an optional embodiment, before screening each candidate index according to a correlation coefficient between each candidate index and a reference value of a natural index of farmland in each town, and taking the screened candidate index as a ranking index, the method further includes: for any two types of alternative indexes, taking any two types of alternative indexes as an ith type of alternative index and a jth type of alternative index, acquiring a first vector consisting of the values of the ith type of alternative indexes of each village and each town, and acquiring a second vector consisting of the values of the jth type of alternative indexes of each village and each town; and calculating a correlation coefficient between the first vector and the second vector, and taking the correlation coefficient as a correlation coefficient between the i-th type candidate index and the j-th type candidate index.
Wherein, calculating the correlation coefficient between the i-th class candidate index and the j-th class candidate index may refer to the following formula:
in the above formula, ρxyRepresenting i-th class candidate index and j-th class candidate indexThe correlation coefficient between them. x denotes a first vector and y denotes a second vector. Mu.sxMean value, mu, corresponding to value of i-th type candidate index representing each townyMean value, S, corresponding to the value of the jth candidate index representing each village and townxStandard deviation, S, corresponding to the value of the i-th candidate index for each townyAnd the standard deviation of the value of the jth candidate index of each town is shown. Wherein, the value range of the correlation coefficient is [ -1, 1]The closer the absolute value is to 1, the greater the correlation between the two variables is; the closer the absolute value is to 0, the smaller the correlation between the two variables. In the practical implementation process, one alternative index can be screened from two alternative indexes with relatively high correlation.
Based on the content of the foregoing embodiment, as an optional embodiment, before screening each candidate index according to a correlation coefficient between each candidate index and a reference value of a natural index of farmland in each town, and taking the screened candidate index as a ranking index, the method further includes: for any type of alternative indexes, acquiring a third vector consisting of values of any type of alternative indexes of all villages and towns, and acquiring a fourth vector consisting of reference values of farmland natural equal indexes of all villages and towns; and calculating a correlation coefficient between the third vector and the fourth vector, and taking the correlation coefficient as a correlation coefficient between any type of candidate indexes and a reference value of farmland natural index of each town.
For any kind of alternative indexes, the correlation coefficient between the kind of alternative indexes and the reference value of the index such as the natural farmland index of each region is calculated, and the formula for calculating the correlation coefficient in the above embodiment can be referred as well, and is not described herein again. In the practical implementation process, the embodiment of the invention can reserve the alternative indexes with larger correlation coefficients between the reference values of the indexes such as the farmland nature of various towns and towns as much as possible.
Based on the content of the foregoing embodiment, as an optional embodiment, the embodiment of the present invention does not specifically limit the manner in which each candidate index is screened according to the correlation coefficient between each candidate index and the reference value of the index such as natural farmland of each town, and the screened candidate index is used as the ranking index, and the manner includes, but is not limited to: screening all the alternative indexes to obtain a first set according to the correlation coefficient among all the alternative indexes; screening each alternative index to obtain a second set according to a correlation coefficient between each alternative index and a reference value of the farmland natural index of each town; and determining a ranking index according to the first set and the second set.
Specifically, it is exemplified that there are 5 types of candidate indexes, and a, b, c, d, and e, respectively. In the manner provided by the above embodiment, after the correlation coefficient between every two of the 5 types of candidate indexes is obtained through calculation, the correlation coefficient falling within the threshold interval corresponding to the strong correlation may be determined first, and the candidate indexes corresponding to the correlation coefficients may be further determined. These candidate indices may then be screened. When the candidate indexes are screened, the candidate indexes which are not easy to acquire numerical values can be screened, and the candidate indexes which are relatively easy to acquire numerical values are reserved to be used as a first set.
In addition, after the correlation coefficients between each candidate index in the 5 types of candidate indexes and the reference value of the index of nature of farmland in each town are respectively calculated, the 5 correlation coefficients can be sorted from large to small, and the candidate indexes (n is a positive integer greater than 0 and not greater than 5) corresponding to the top n correlation numbers in the front sorting are reserved and used as a second set. After the first set and the second set are obtained, the first set and the second set can be referred to simultaneously to further determine the index of the rank from the 5 types of candidate indexes.
It should be noted that both the above two correlation coefficients may be used to screen candidate indexes, and may be combined according to needs in an actual implementation process, which is not specifically limited in this embodiment of the present invention. For example, if the correlation coefficient between a and b is strong, a kind of candidate indexes needs to be screened out from a and b. In the actual implementation process, after the correlation coefficient between the reference value of the index such as the nature of the cultivated land of each village and town and the correlation coefficient between the reference value of the index such as the nature of the cultivated land of each village and town are obtained through calculation, the two correlation coefficients can be compared. If the correlation coefficient corresponding to b is large, screening the a-type alternative indexes from a and b, and reserving the b-type alternative indexes. Otherwise, screening the b-type alternative indexes from the a and the b, and reserving the a-type alternative indexes.
Based on the content of the foregoing embodiment, as an alternative embodiment, regarding a manner of performing regression on the value of each index such as the index of the farmland nature and the like of each village and town, and determining the influence weight of each index on the index of the farmland nature and the like of each village and town, the embodiment of the present invention is not particularly limited to this, and includes but is not limited to: for any village and town, determining the optimal bandwidth of any village and town based on a cross-validation method; determining the distance weight between any village and each other village in the optimal bandwidth; determining an estimation parameter corresponding to each grading index in a geographic weighting regression model corresponding to any village and town according to the distance weight between the any village and town in the optimal bandwidth; and solving the geographic weighted regression model corresponding to any village and town according to the value of each index such as the grade of any village and the reference value of the index such as the nature of the cultivated land of any village and town, and determining the influence weight of each grade of index on the index such as the nature of the cultivated land of any village and town.
For any village and town, when determining the optimal bandwidth of the village and town, a cross-validation method may be used, which may specifically refer to the following formula:
it should be noted that, according to the above formula, the regression parameters are estimated without including the regression point itself, that is, only the regression calculation is performed according to the data points around the regression point. And drawing different bandwidths b and CV values corresponding to the bandwidths b into a trend line, so that the optimal bandwidth corresponding to the minimum value can be found very intuitively.
After determining the best bandwidth for the village, distance weights between the village and each of the other villages within the best bandwidth may be determined. In particular, the distance weight w may be determined using a Gaussian function methodijThe basic idea of the method is to select a continuous sheetAdjusting decreasing function to represent wijAnd dij(the distance between the ith village and the jth village, the jth village is within the optimal bandwidth of the ith village), the specific process can refer to the following formula:
wij＝exp(-(dij/b)2)；
in the above formula, b is a non-negative attenuation parameter describing the functional relationship between weight and distance, called bandwidth. The larger the bandwidth, the slower the weight decays with increasing distance. The smaller the bandwidth, the faster the weight decays with increasing distance.
After the distance weight between the village and each village is determined, the estimation parameters corresponding to each ranking index in the geographic weighted regression model corresponding to the village can be further estimated. The geographic weighted regression model corresponding to the village and town (i.e. the ith village and town) may refer to the following formula:
for convenience of expression, the above formula can be abbreviated as the following formula:
in the above formula, (μ)i,νi) Indicates the location of the ith town, betaikRepresents the estimation parameter, x, corresponding to the k-th ranking index in the geographic weighted regression model corresponding to the ith village and townikAnd the influence weight of the k-th ranking index on the farmland natural equal index of the ith town is shown. In addition, deltai∽(0,σ2)，Cov(δi,δj)＝0(i≠j)。
When estimating the regression parameters of the sampling points, the importance of the observed values at different observation points is different, and the closer the observation point is, the more important the observed value is, the farther the observation value is, the less important the observed value is. Accordingly, β can be establishedi0And betaikThe related objective function is as follows:
by the above objective function, beta can be calculatedi0,βi1,...,βip。
Based on the content of the above embodiments, the embodiment of the present invention provides an apparatus for acquiring a natural equal index of a provincial farmland, which is used for executing the method for acquiring a natural equal index of a provincial farmland provided in the above method embodiments. Referring to fig. 2, the apparatus includes:
a first obtaining module 201, configured to obtain values of alternative indexes of each town;
a normalization processing module 202, configured to perform normalization processing on the values of the candidate indexes of each town;
the screening module 203 is used for screening the alternative indexes according to the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each village and town, and taking the screened alternative indexes as the grading indexes;
the regression module 204 is used for performing regression on the value of each index of each town and the reference value of the index of nature of the cultivated land of each town, and determining the influence weight of each index of each grade on the index of nature of the cultivated land of each town;
the first determining module 205 is configured to determine indexes of natural cultivated land of each village and town according to a value of each index of each village and town and an influence weight corresponding to each index of each village and town.
As an optional embodiment, the obtaining module 201 is configured to, for any village and town, extract an average altitude and an average gradient of any village and town according to elevation model data of any village and town;
the average annual precipitation and the annual average air temperature of any village and town are obtained by interpolating the meteorological site data of any village and town, and the average altitude, the average gradient, the average annual precipitation and the annual average air temperature of any village and town are respectively used as the values of all candidate indexes of any village and town.
As an alternative embodiment, the normalization processing module 202 is configured to perform normalization processing according to the following formula:
wherein, KiNormalization result, x, corresponding to the value of the i-th class candidate index representing any village and towniValue, x, of the i-th class candidate index representing any village and townminMinimum value, x, among values of i-th class candidate indexes representing respective townsmaxThe maximum value among the values of the i-th class candidate index representing each town.
As an alternative embodiment, the apparatus further comprises:
the second acquisition module is used for acquiring indexes of farmland nature and the like of each farmland pattern spot in any village and town according to current annual updating data of farmland quality;
and the second determination module is used for determining a reference value of the farmland natural equal index of any village and any town according to the farmland natural equal index of each farmland pattern spot in any village and town and the area ratio of each farmland pattern spot.
As an alternative embodiment, the apparatus further comprises:
a third obtaining module, configured to, for any two types of candidate indexes, use any two types of candidate indexes as an i-th type candidate index and a j-th type candidate index, obtain a first vector formed by values of the i-th type candidate indexes of each town, and obtain a second vector formed by values of the j-th type candidate indexes of each town;
and the first calculating module is used for calculating a correlation coefficient between the first vector and the second vector and is used as a correlation coefficient between the i-th type candidate index and the j-th type candidate index.
As an alternative embodiment, the apparatus further comprises:
the fourth acquisition module is used for acquiring a third vector consisting of values of any type of alternative indexes of all villages and towns and acquiring a fourth vector consisting of reference values of indexes such as farmland natural indexes of all villages and towns for any type of alternative indexes;
and the second calculation module is used for calculating a correlation coefficient between the third vector and the fourth vector and is used as a correlation coefficient between any type of candidate indexes and a reference value of farmland natural index and the like of each village and town.
As an optional embodiment, the screening module 203 is configured to screen the candidate indexes to obtain a first set according to correlation coefficients between the candidate indexes; screening each alternative index to obtain a second set according to a correlation coefficient between each alternative index and a reference value of the farmland natural index of each town; and determining a ranking index according to the first set and the second set.
And the regression module is used for determining the influence weight of each index on the natural equal index of each rural land by adopting a geographical weighted regression method, wherein the influence weight of each index on the natural equal index of each rural land is different. Selecting natural equal indexes as dependent variables, and taking each normalized index as an explanatory variable; an adaptive gaussian kernel is selected and the optimal bandwidth is determined by cross-validation.
As an alternative embodiment, the regression module 204 is configured to determine, for any village and town, the optimal bandwidth for any village and town based on the cross-validation method; determining the distance weight between any village and each other village in the optimal bandwidth; determining an estimation parameter corresponding to each grading index in a geographic weighting regression model corresponding to any village and town according to the distance weight between the any village and town in the optimal bandwidth; and solving the geographic weighted regression model corresponding to any village and town according to the value of each index such as the grade of any village and the reference value of the index such as the nature of the cultivated land of any village and town, and determining the influence weight of each grade of index on the index such as the nature of the cultivated land of any village and town.
The device provided by the embodiment of the invention can evaluate the farmland quality from a macroscopic angle and consider the spatial non-stationarity of the grading indexes, so that the farmland quality can be evaluated more objectively and accurately. The correlation coefficient among all the candidate indexes and the correlation coefficient between the candidate indexes and the indexes such as the nature of cultivated land are explored by using a correlation analysis method, so that the evaluation indexes can be screened more accurately. The influence weight is calculated by using a geographical weighted regression method, so that the problem of result error caused by not considering spatial heterogeneity can be solved to a certain extent, the interference of the spatial heterogeneity on model fitting is overcome, and the calculation result is more objective and accords with the actual situation.
It should be noted that, as a typical geospatial entity, the topography, soil nutrients, and economic input levels of the cultivated land have regional scalability and regional diversity, and thus, on different spatial scales, the morphology, properties, and distribution rules of the cultivated land can also have different geospatial expression effects. In the embodiment of the invention, the influence factors of the farmland quality can be screened from the provincial scale, the farmland quality is evaluated based on the provincial scale, and the method is more favorable for knowing the distribution condition of the farmland quality from the macroscopic scale compared with the farmland quality evaluation of the county scale.
Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call logic instructions in the memory 330 to perform the following method: acquiring values of all alternative indexes of all towns, and carrying out normalization processing on the values of all alternative indexes of all towns; screening the alternative indexes according to the correlation coefficient among the alternative indexes and the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each town, and taking the screened alternative indexes as ranking indexes; regressing the value of each index of the villages and towns and the reference value of the index of the nature of the cultivated land of each village and towns, and determining the influence weight of each index of the grade on the index of the nature of the cultivated land of each village and towns; and determining the indexes of nature of cultivated land of each village and town according to the value of each index of the village and town and the influence weight corresponding to each index of the village and town.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method provided in the foregoing embodiments when executed by a processor, and the method includes: acquiring values of all alternative indexes of all towns, and carrying out normalization processing on the values of all alternative indexes of all towns; screening the alternative indexes according to the correlation coefficient among the alternative indexes and the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each town, and taking the screened alternative indexes as ranking indexes; regressing the value of each index of the villages and towns and the reference value of the index of the nature of the cultivated land of each village and towns, and determining the influence weight of each index of the grade on the index of the nature of the cultivated land of each village and towns; and determining the indexes of nature of cultivated land of each village and town according to the value of each index of the village and town and the influence weight corresponding to each index of the village and town.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for obtaining the natural equal index of provincial cultivated land is characterized by comprising the following steps:
acquiring values of all alternative indexes of all towns, and carrying out normalization processing on the values of all alternative indexes of all towns;
screening the alternative indexes according to the correlation coefficient among the alternative indexes and the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each town, and taking the screened alternative indexes as ranking indexes;
regressing the value of each index of the villages and towns and the reference value of the index of the nature of the cultivated land of each village and towns, and determining the influence weight of each index of the grade on the index of the nature of the cultivated land of each village and towns;
determining indexes of nature of cultivated land of each village and town according to the value of each index of the village and the influence weight corresponding to each index of the village and town;
wherein, the alternative indexes are natural indexes which may affect the cultivated land quality;
the method for screening the alternative indexes according to the correlation coefficient between the alternative indexes and the reference value of the index of nature of the cultivated land of each village and town further comprises the following steps before the screened alternative indexes are used as the grading indexes:
for any village and town, acquiring indexes of farmland nature and the like of each farmland pattern spot in the village and town according to current annual updating data of farmland quality;
and determining a reference value of the farmland natural equal index of any village and town according to the farmland natural equal index of each farmland pattern spot and the area ratio of each farmland pattern spot in any village and town.
2. The method for obtaining natural index of provincial farmland according to claim 1, wherein the obtaining of the value of each candidate index of each village and town comprises:
for any village and town, extracting the average altitude and the average gradient of the any village and town according to the digital elevation model data of the any village and town;
and obtaining the average annual precipitation and the average annual air temperature of any village and town by interpolating the meteorological site data of any village and town, and respectively taking the average altitude, the average gradient, the average annual precipitation and the average annual air temperature of any region as the values of all candidate indexes of any village and town.
3. The method for obtaining the index of nature of the provincial farmland according to claim 1, wherein the normalization of the values of the candidate indexes of the towns comprises:
wherein, KiNormalization result, x, corresponding to the value of the i-th class candidate index representing a certain towniValue, x, of class i candidate indicator representing a certain townminMinimum value, x, among values of i-th class candidate indexes representing respective townsmaxThe maximum value among the values of the i-th class candidate index representing each town.
4. The method according to claim 1, wherein the step of screening the candidate indexes according to the correlation coefficient between the candidate indexes and the reference value of the natural index of the farmland in each town, and before the step of using the screened candidate indexes as the ranking indexes, further comprises:
for any two types of alternative indexes, taking the two types of alternative indexes as an ith type of alternative index and a jth type of alternative index, acquiring a first vector consisting of the values of the ith type of alternative indexes of each village and each town, and acquiring a second vector consisting of the values of the jth type of alternative indexes of each village and each town;
and calculating a correlation coefficient between the first vector and the second vector, and taking the correlation coefficient as a correlation coefficient between the i-th type candidate index and the j-th type candidate index.
5. The method according to claim 1, wherein the step of screening the candidate indexes according to the correlation coefficient between the candidate indexes and the reference value of the natural index of the farmland in each town, and before the step of using the screened candidate indexes as the ranking indexes, further comprises:
for any type of candidate indexes, acquiring a third vector consisting of values of the any type of candidate indexes of each village and town, and acquiring a fourth vector consisting of reference values of farmland natural equal indexes of each village and town;
and calculating a correlation coefficient between the third vector and the fourth vector, and taking the correlation coefficient as a correlation coefficient between any type of candidate indexes and a reference value of farmland natural equal index of each town.
6. The method for obtaining natural index of farmland in province according to claim 1, wherein the step of screening each candidate index according to the correlation coefficient between each candidate index and the reference value of the natural index of farmland in each village and town, and taking the screened candidate index as the ranking index comprises the steps of:
screening all the alternative indexes to obtain a first set according to the correlation coefficient among all the alternative indexes;
screening each alternative index to obtain a second set according to a correlation coefficient between each alternative index and a reference value of the farmland natural index of each town;
and determining a ranking index according to the first set and the second set.
7. The method for obtaining natural equal-index farmland in province according to claim 1, wherein the regression of the value of each index of each town and the reference value of the natural equal-index farmland in each town is performed to determine the influence weight of each index on the natural equal-index farmland in each town, and the method comprises the following steps:
for any village and town, determining the optimal bandwidth of the village and town based on a cross-validation method;
determining a distance weight between said any one village and each other village within said optimal bandwidth;
determining an estimation parameter corresponding to each grading index in a geographic weighted regression model corresponding to any village and town according to the distance weight between the any village and each other village and town in the optimal bandwidth;
and solving a geographic weighted regression model corresponding to any village and town according to the value of each index such as the grade of the any village and the reference value of the index such as the nature of the cultivated land of the any village and town, and determining the influence weight of each index such as the grade on the index such as the nature of the cultivated land of the any village and town.
8. An apparatus for obtaining natural index of provincial farmland, comprising:
the first acquisition module is used for acquiring the value of each alternative index of each village and town;
the normalization processing module is used for performing normalization processing on the values of the alternative indexes of the towns;
the screening module is used for screening the alternative indexes according to the correlation coefficient between the alternative indexes and the reference value of the farmland natural index of each village and town, and taking the screened alternative indexes as the grading indexes;
the regression module is used for performing regression on the value of each index of each town and the reference value of the index of the nature of the cultivated land of each town, and determining the influence weight of each index on the index of the nature of the cultivated land of each town;
the first determining module is used for determining indexes of nature of cultivated land of each village and town according to the value of each index of each village and town and the influence weight corresponding to each index of each village and town;
wherein, the alternative indexes are natural indexes which may affect the cultivated land quality;
the second acquisition module is used for acquiring indexes of farmland nature and the like of each farmland pattern spot in any village and town according to current annual updating data of farmland quality;
and the second determination module is used for determining a reference value of the farmland natural equal index of any village and any town according to the farmland natural equal index of each farmland pattern spot in any village and town and the area ratio of each farmland pattern spot.
9. An electronic device, comprising:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 7.
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 CN110363442A (en) | 2019-10-22 |
| CN110363442B true CN110363442B (en) | 2021-09-10 |
Family
ID=68220365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910654550.8A Active 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 active Active
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 |
|---|
| "京津冀地区耕地质量空间分布分形机制研究";杨永侠 等;《农业机械学报》;20170228;全文 * |
| "农用地分等及其应用研究";郧文聚;《中国博士学位论文全文数据库 社会科学Ⅰ辑》;20050915;全文 * |
| "基于空间自相关的耕地等别指数检验方法研究";杨永侠 等;《农业机械学报》;20160531;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110363442A (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ghosh et al. | Outliers: An evaluation of methodologies | |
| US20170300546A1 (en) | Method and Apparatus for Data Processing in Data Modeling | |
| Cravo et al. | Economic growth in Brazil: a spatial filtering approach | |
| CN103886168A (en) | Multi-channel analysis method and device based on analytic hierarchy process | |
| CN107729519A (en) | Appraisal procedure and device, terminal based on multi-source multidimensional data | |
| Glatthorn et al. | Classifying development stages of primeval European beech forests: is clustering a useful tool? | |
| CN109298139B (en) | Tobacco leaf quality evaluation method and device | |
| CN107360577A (en) | A kind of frequency spectrum sensing method and device based on machine learning | |
| CN107679756B (en) | Soil suitability evaluation method and device | |
| Del Ponte et al. | How much do standard area diagrams improve accuracy of visual estimates of the percentage area diseased? A systematic review and meta-analysis | |
| Núñez et al. | Resolving regional frequency analysis of precipitation at large and complex scales using a bottom-up approach: The Latin America and the Caribbean Drought Atlas | |
| CN110797046B (en) | Method and device for establishing prediction model of voice quality MOS value | |
| CN110363442B (en) | Method and device for acquiring natural equal index of provincial farmland | |
| CN108509340B (en) | Method for determining and quantitatively evaluating quality factors of ship command control system software | |
| Mehtätalo et al. | Combining a predicted diameter distribution with an estimate based on a small sample of diameters | |
| CN110852322B (en) | Method and device for determining region of interest | |
| CN110706004B (en) | Farmland heavy metal pollutant tracing method based on hierarchical clustering | |
| CN116739742A (en) | Monitoring method, device, equipment and storage medium of credit wind control model | |
| CN115062859B (en) | Method and device for predicting density of gerbil unguiculatus | |
| CN113435713B (en) | Risk map compiling method and system based on GIS technology and two-model fusion | |
| Dickinson et al. | Evaluation of the FVS-CR diameter growth model in structurally-heterogeneous ponderosa pine (Pinus ponderosa Douglas ex C. Lawson) stands in the Southern Rockies, and potential modifications | |
| CN114998732A (en) | Plant disease severity assessment method and device | |
| CN115778317A (en) | Skin evaluation method, skin evaluation device, and storage medium | |
| CN113506186B (en) | Method and device for screening disturbed track of power system, electronic equipment and storage medium | |
| CN116307086A (en) | Method and device for predicting organic carbon in soil |
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 |