CN111062446B - Land type classification method based on multi-source homeland resource data - Google Patents
Land type classification method based on multi-source homeland resource data Download PDFInfo
- Publication number
- CN111062446B CN111062446B CN201911355597.0A CN201911355597A CN111062446B CN 111062446 B CN111062446 B CN 111062446B CN 201911355597 A CN201911355597 A CN 201911355597A CN 111062446 B CN111062446 B CN 111062446B
- Authority
- CN
- China
- Prior art keywords
- land
- types
- poi
- density
- data
- 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 20
- 239000002689 soil Substances 0.000 claims abstract description 57
- 238000010276 construction Methods 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000003064 k means clustering Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 235000019738 Limestone Nutrition 0.000 claims description 3
- 239000006028 limestone Substances 0.000 claims description 3
- 230000008901 benefit Effects 0.000 claims description 2
- 238000011160 research Methods 0.000 abstract description 9
- 238000011835 investigation Methods 0.000 abstract description 6
- 238000012795 verification Methods 0.000 abstract description 5
- 238000007726 management method Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- 229910052698 phosphorus Inorganic materials 0.000 description 2
- 239000011574 phosphorus Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 238000011166 aliquoting Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a land type classification method based on multi-source national land resource data, which is characterized in that a mesoscale land type classification system is constructed by means of multi-source data such as secondary national soil census, land utilization status investigation, geographical national condition census, internet data and the like, and attribute indexes reflecting comprehensive characteristics of land resources such as landform types, soil types, land utilization intensity and the like are fused, and a classification result verification method system integrating typical verification, layered verification and the like is provided. The invention aims to improve the efficiency and practicability of land type research, realize the accurate classification of land resource comprehensive information, and serve important strategic application requirements such as national land resource investigation, geographical national condition census and the like.
Description
Technical Field
The invention relates to a land type classification method based on multisource homeland resource data, and belongs to the technical field of natural geography.
Background
The land is a comprehensive system which is constantly interacted with the surrounding natural and humane environment for substance and energy. Under the influence of the influence, various elements in the land system are differentiated and replaced, and the differences of the appearance and the functions of the land are further displayed. The land type research is an effective means for exploring the comprehensive geographic characteristics of the region, can reveal the basic characteristics of formation, characteristics, dissimilarity, succession and the like of a land complex, can intuitively reflect the comprehensive attribute information of land resources, and has great practical value for enriching the investigation content of the national resources, realizing the control of the global full-type national space use and the like. The construction of the land type classification system is the basis of land type research and is also the premise of land type visual expression and land type application research.
Traditional land type classification researches are mostly based on field investigation, and focus on type division of natural geographic elements (such as terrain, climate, vegetation and the like), but huge workload limits timeliness of results, so that classification results cannot be timely applied. In addition, the influence of human activity intensity on land type diversity is weakened by the research, so that classification results are difficult to apply to the problem of urban scale homeland space planning, and the traditional land type research focusing on natural geographic element diversity is slightly insufficient in comprehensiveness along with the deepening of the influence degree of human activity on land attribute diversity.
Disclosure of Invention
The invention aims to solve the technical problems that: the land type classification method based on the multi-source homeland resource data can intuitively reflect comprehensive properties of land resources, and further improves the efficiency and practicability of land type research.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: a land type classification method based on multi-source homeland resource data comprises the following steps:
dividing a region to be classified into basic landform types, wherein the basic landform types comprise plain, bench, hilly, small undulating mountain, medium undulating mountain, large undulating mountain and extremely large undulating mountain, and dividing the region to be classified into a plurality of different region units according to the basic landform types;
dividing soil types of the region to be classified according to the second national soil census data, wherein the soil types comprise paddy soil, middle loam, crazing soil, new deposited soil, red soil, limestone soil, coarse aggregate soil, huang Hetu, swamp soil and yellow brown soil; dividing each regional unit into a plurality of regional subunits according to the soil type;
dividing land utilization types in the area to be classified according to land utilization current situation classification data, wherein the land utilization types comprise agricultural lands, construction lands, forest lands, natural reserved lands and water areas; dividing each regional subunit into a plurality of regional blocks according to the land utilization type;
step four, further subdividing the agricultural land, the construction land and the forest land through land utilization intensity, and not subdividing the natural reserved land and the water area, wherein:
1) For the regional blocks belonging to the agricultural land, grading the quality and the like of the regional blocks belonging to the agricultural land according to the grading data of the quality grading of the cultivated land obtained according to GBT 28407-2012 agricultural land quality grading rules by calculating the ratio of the crop yield of sampling points in the regional blocks to the highest yield of the specified standard crops;
2) For the area blocks belonging to the forest land, calculating and expressing the forest utilization intensity according to the coverage of the forest land, and grading the area blocks belonging to the forest land according to the forest utilization intensity;
3) For the regional blocks belonging to the construction land, firstly dividing each regional block belonging to the construction land into different blocks according to road network data of the region to be classified, and carrying out the following processing on each block:
s1, acquiring POI point data contained in a regional block belonging to a construction land from a map, wherein the POI point data is an abstract record of a geographic entity and contains longitude and latitude, names and categories of the geographic entity;
s2, dividing POI data in a neighborhood into four types of POI data sets of business, residential, industrial and public management and public service according to the name and the category of the POI data;
s3, according to the spatial position relation between the block and the POI point data set, if the block contains the POI point data of the public management and public service land, the block is the public management and public service land; if the block does not contain public administration and public service POI point data, the following steps are executed:
s31, clustering analysis is carried out on POI point data sets of different types through Ripley' s_K functions in ArcGIS software, and the most significant spatial clustering degree distance corresponding to the POI point data sets of the types is found out and used as the clustering distance corresponding to the POI point data sets of the types; the clustering distances corresponding to the commercial POI data set, the residential POI data set and the industrial POI data set are respectively marked as commercial clustering distances, residential clustering distances and industrial clustering distances;
s32, firstly, constructing an external rectangle of the neighborhood, then dividing the rectangle into grid data sets, respectively taking a commercial POI data set, a residential POI data set and an industrial POI data set as input elements, carrying out nuclear density analysis by taking half of the clustering distance of corresponding type POI data as a radius through a nuclear density analysis function in ArcGIS software, taking any grid as a center, taking half of the clustering distance corresponding to a certain POI data set as a search radius, calculating the nuclear density of the POI in the range as the value of the grid, and traversing all the grid data sets to obtain nuclear density analysis result grids covering all construction land area blocks and different types of POI points, namely respectively obtaining commercial nuclear density grids, industrial nuclear density grids and residential nuclear density grids of the neighborhood;
s33, respectively taking a nuclear density grid as input data through a K-means clustering function in MATLAB software, and dividing the input data into 3 types, namely, clustering results of commercial nuclear density grids respectively correspond to high-density, medium-density and low-density commercial area types; the clustering results of the industrial nuclear density grids respectively correspond to the types of the high-density, medium-density and low-density industrial areas; the clustering results of the living core density grids also correspond to the types of the high-density living areas, the medium-density living areas and the low-density living areas respectively.
The beneficial effects brought by the invention are as follows: the invention overcomes the defects of poor land type classification efficiency, weak practicability and incapability of effective verification in the prior art, synthesizes large data of national resources such as remote sensing information, internet information (map) and field investigation information, greatly improves the timeliness of land type classification, and realizes accurate classification of mesoscale (1:100,000) land types. The innovation point of the invention is not redefined of land type classification rules, but on the premise of executing the existing land type classification rules (namely, the land type classification rules adopted by the invention are all the existing rules), the timeliness and the accuracy of land type classification are improved, namely, the land type is accurately classified by fully utilizing the national standard and multi-source national resource big data and by a man-machine interaction operation method, the result is stable and reliable, and the efficiency is greatly improved.
Drawings
FIG. 1 is a schematic diagram of the basic landform type in Changzhou city.
Fig. 2 is a schematic diagram of a land use pattern in Changzhou market.
Fig. 3 is a schematic diagram of the quality of a farm land in Changzhou city, among others.
Fig. 4 is a schematic representation of a evergreen land coverage.
Fig. 5 is a schematic diagram of a city of evergreen.
Fig. 6 is a schematic diagram of verification of land classification results for a region of Changzhou city.
Detailed Description
Examples
In this embodiment, changzhou city is taken as an example, i.e. Changzhou city is taken as a region to be classified, and the present invention is further described with reference to the accompanying drawings.
The homeland resource data adopted in the embodiment comprises 'China 1:100 land type map drawing Specification', second national soil census data, land utilization status classification data based on national standard (GB/T21010-2007), and cultivated quality grading data based on national classification standard (GBT 28407-2012). The data are all public data and can be obtained through an effective way.
According to the classification system and principle of China 1:100 ten thousand land type drawing regulations, the land type classification system comprises a climate type, a landform type, a soil type and a vegetation type. The climate type shows greater homogeneity on the scale of 1:10 ten thousand, so the embodiment weakens the expression and eliminates the expression.
In addition, the embodiment incorporates the land use type and land use intensity expressing human activities into a classification system, namely, the land use type, the soil type, the land use type and the land use intensity are fused to construct a land type classification system.
The land type classification method based on the multisource homeland resource data of the embodiment comprises the following steps:
dividing a region to be classified into basic landform types, wherein the basic landform types comprise plain, bench, hilly, small undulating mountain, medium undulating mountain, large undulating mountain and extremely large undulating mountain, and dividing the region to be classified into a plurality of different region units according to the basic landform types.
In the prior art, a relatively complete basic landform type dividing system is formed by a landform type dividing technology based on terrain factor analysis, and a China land 1:100 ten thousand digital landform classification system is widely applied by virtue of factors such as elevation, surface relief and the like, and the example is based on the classification system, so that the Changzhou city is divided into a plurality of area units according to the basic landform types.
Generally speaking, the regions with abrupt changes in gradient are mostly boundaries of different landform types, so that in this example, based on research methods such as DEM data and multi-scale segmentation, elevation, gradient, surface relief, gradient change rate and the like are selected as landform factors, and the landform types are divided by combining a multi-scale segmentation algorithm, wherein the gradient change rate is the basis for dividing landform boundaries.
In this example, the steps of dividing the region to be classified into basic landform types are as follows:
(1) calculating elevation, surface relief and gradient change rate based on the DEM and the mean value change point method;
(2) carrying out multi-scale segmentation on the gradient change rate;
(3) and (3) calculating the maximum value of the elevation and the surface relief in the gradient change rate segmentation plaque, and dividing the basic landform type according to a China land 1:100 ten thousand digital landform classification system.
The physiognomic factors and their meanings are shown in table 1 below:
TABLE 1
The China land 1:100 ten thousand digital landform classification system is shown in the following Table 2:
TABLE 2
The above is in the prior art, and reference is made to the relevant data.
Applicant classifies the types of the everse landforms into three main categories, namely plain, bench and hills, based on the 1:100 ten thousand digital landform classification system of the Chinese land, and comparing the elevation and surface relief values of the everse with the 1:100 ten thousand digital landform classification system of the Chinese land (table 2), as shown in figure 1.
Dividing soil types of the region to be classified according to the second national soil census data, wherein the soil types comprise paddy soil, middle loam, crazing soil, new deposited soil, red soil, limestone soil, coarse aggregate soil, huang Hetu, swamp soil and yellow brown soil; each zone unit is divided into a plurality of zone subunits based on soil type.
The second national soil screening data provides national soil type samples and their attributes (including pH, organic matter, total nitrogen, total phosphorus, available phosphorus, and fast-acting potassium, etc.), which determine the soil type of the samples. For one of the regional units, the regional units are rasterized, one sample point is only positioned in one grid, the soil type of the sample point is the soil type of the corresponding grid, the soil attribute value of each grid in the regional units is calculated by adopting common Kriging interpolation, and then the spatial clustering between the attribute value of each grid and the sample point is calculated, so that the regional units are divided into a plurality of regional subunits according to the soil type.
The soil type division of the region to be classified is the prior art, the principle of the soil type division is briefly described by taking a certain grid i as an example, and the specific calculation process can refer to related documents. Firstly, calculating the attribute value distance between the grid i and each sample point, and then taking the soil type of the sample point with the closest attribute value distance as the soil type of the grid i, namely defining:
wherein Distance represents the Distance between the grid i and the attribute value of the sample point s, n represents the number of soil attributes used for calculation, j represents a certain soil attribute, and d ij -d sj The distance between the grid i corresponding to the soil property j and the sample point s is represented.
Dividing land utilization types in the area to be classified according to land utilization current situation classification data, wherein the land utilization types comprise agricultural lands, construction lands, forest lands, natural reserved lands and water areas; each regional subunit is divided into a plurality of regional blocks based on the land use type.
The division system of land utilization types follows GB/T21010-2007, and the division of land utilization types into areas to be classified is also the prior art, and is not repeated. The divided evergreen land use pattern diagram is shown in fig. 2.
Step four, further subdividing the agricultural land, the construction land and the forest land through land utilization intensity, and not subdividing the natural reserved land and the water area, wherein:
1) For the regional blocks belonging to the agricultural land, grading the quality and the like of the regional blocks belonging to the agricultural land by calculating the ratio of the crop yield of sampling points in the regional blocks to the highest yield of the specified standard crops and obtaining grading data of the quality grading according to the GBT 28407-2012 agricultural land quality grading rules. This is the prior art, reference may be made to the related literature, the detailed calculation process is not repeated, and the quality of the farm land in Changzhou is shown in fig. 3.
2) For the area blocks belonging to the woodland, calculating and expressing the woodland utilization intensity according to the woodland coverage, and grading the area blocks belonging to the woodland according to the woodland utilization intensity. Typically, based on statistics, forest land coverage may be divided into three levels in an aliquoting manner: the coverage of the forest land in Changzhou city is shown in FIG. 4, wherein the coverage of the forest land is 33% or less, the coverage of the forest land is 33% < 66% or less, and the coverage of the forest land is 66% or more.
3) For the regional blocks belonging to the construction land, firstly dividing each regional block belonging to the construction land into different blocks according to road network data of the region to be classified, and carrying out the following processing on each block:
s1, acquiring POI point data contained in an area block belonging to a construction land from a map, wherein the POI point data is an abstract record of a geographic entity and contains longitude and latitude, names and categories of the geographic entity. POI point data may be directly grabbed from a hundred degree map or a german map.
S2, dividing the POI data in the neighborhood into four types of POI data sets of business, residential, industrial and public management and public service according to the name and the category of the POI data. According to the captured data statistics, the commercial POI points in Changzhou city are 16460, the residential POI points are 2582, the industrial POI points are 23066, and the public management and public service POI points are 81.
S3, according to the spatial position relation between the block and the POI point data set, if the block contains the POI point data of the public management and public service land, the block is the public management and public service land; if the block does not contain public administration and public service POI point data, the following steps are executed:
s31, clustering analysis is carried out on POI point data sets of different types through Ripley' s_K functions in ArcGIS software, and the most significant spatial clustering degree distance corresponding to the POI point data sets of the types is found out and used as the clustering distance corresponding to the POI point data sets of the types; and the commercial POI data set, the residential POI data set and the clustering distances corresponding to the industrial POI data set are respectively marked as commercial clustering distances, residential clustering distances and industrial clustering distances. This distance characterizes at what distance threshold the POI points of the same type exhibit an aggregate distribution, whereas beyond this distance the POI points exhibit a discrete distribution trend.
The clustering analysis by Ripley 's_K function division is prior art, and the principle thereof can be referred to in the publication Enabling point pattern analysis on spatial big data using cloud computing: optimizing and accelerating Ripley's function (author: zhang et al International Journal of Geographical Information Science (11): 2230-2252,November 2016).
S32, firstly constructing an external rectangle of the neighborhood, then dividing the rectangle into grid data sets, respectively taking a commercial POI data set, a residential POI data set and an industrial POI data set as input elements, carrying out nuclear density analysis by taking half of the clustering distance of corresponding type POI data as a radius through a nuclear density analysis function in ArcGIS software, taking any grid as a center, taking half of the clustering distance corresponding to a certain POI data set as a search radius, calculating the nuclear density of the POI in the range as the value of the grid, and traversing all the grid data sets to obtain nuclear density analysis result grids covering all construction land area blocks and different types of POI points, namely respectively obtaining commercial nuclear density grids, industrial nuclear density grids and residential nuclear density grids of the neighborhood.
Nuclear density analysis is also known in the art, and its calculation principle can be referred to in AReliable Data-Based Bandwidth Selection Method for Kernel Density-Estimation (Sheather and Jones, journal of the Royal Statistical society. Series B: method logical 53:683-690, january 1991).
S33, respectively taking a nuclear density grid as input data through a K-means clustering function in MATLAB software, and dividing the input data into 3 types, namely, clustering results of commercial nuclear density grids respectively correspond to high-density, medium-density and low-density commercial area types; the clustering results of the industrial nuclear density grids respectively correspond to the types of the high-density, medium-density and low-density industrial areas; the clustering results of the living core density grids also correspond to the types of the high-density living areas, the medium-density living areas and the low-density living areas respectively. The continuously changing density grids are divided into grade grids by adopting a K-means clustering function, namely, the final result is high-density, medium-density and low-density areas of residential areas/industrial areas/commercial areas.
The K-means clustering function is the prior art, and its calculation principle can be referred to in Algorithm AS 136:A K-Means Clustering Algorithm (J.Hartigan, and M.Wong. Applied Statistics 28 (1): 100-108, 1979).
S34, dividing the blocks according to the commercial block types, the industrial block types, the residential block types and the spatial positions of the blocks, which are obtained by K-means clustering: 1) If the business district type, the industrial district type and the living district type in the district are all medium density districts or high density districts, the district is a mixed functional district; 2) If one type is higher than the other types in the neighborhood, the neighborhood is included in the functional region with the highest clustering result; 3) If the types of business areas, industrial areas and living areas in the neighborhood are all low-density, counting the number of POI points of different types in the neighborhood, and incorporating the POI points into corresponding functional areas in a mode of taking advantage of the number of the POI points; 4) If none of the blocks meets the rule, the blocks are summarized as village and town construction land. And after the classification is finished, stacking the result graphs in the steps to obtain land type classification results.
The applicant verifies the land type classification result of the embodiment, and constructs a standard land type sample point by integrating internet data and field investigation data. For a certain region in Changzhou, determining grain yield of a farmland in the certain region by field measurement and field observation methods, determining farmland quality by comparison with agricultural quality classification rules (GBT 28407-2012), and supplementing landform, soil and land use type information of each point in the region according to the current classification standard, thereby verifying the accuracy of land type sampling points. The applicant obtains 11 agricultural land type sampling points and 63 land type sampling points for construction in total, and through comparative analysis, as shown in fig. 6, the accuracy of the classification result of the embodiment exceeds 80%, so that the actual needs of the present land resource in many aspects such as planning, prediction, reasonable utilization and the like can be met.
It should be emphasized that in this embodiment, classification rules of land feature type, soil type, land use type, and land use intensity are all in the prior art, for example: the commercial area, the residential area and the industrial area are divided into three types of high density, medium density and low density, the street area is divided into a mixed functional area, a village construction land, a commercial area, the residential area and the industrial area, and the forest land is divided into a low coverage forest land, a medium coverage forest land, a high coverage forest land and the like, which are all existing classification rules. The applicant carries out step-by-step processing on the multisource homeland resource data, and accurately divides the land types, so that the result is stable and reliable, and the efficiency is greatly improved.
The present invention is not limited to the specific technical solutions described in the above embodiments, and other embodiments may be provided in addition to the above embodiments. Any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art, which are within the spirit and principles of the present invention, are intended to be included within the scope of the present invention.
Claims (4)
1. A land type classification method based on multi-source homeland resource data comprises the following steps:
dividing a region to be classified into basic landform types, wherein the basic landform types comprise plain, bench, hilly, small undulating mountain, medium undulating mountain, large undulating mountain and extremely large undulating mountain, and dividing the region to be classified into a plurality of different region units according to the basic landform types;
dividing soil types of the region to be classified according to the second national soil census data, wherein the soil types comprise paddy soil, middle loam, crazing soil, new deposited soil, red soil, limestone soil, coarse aggregate soil, huang Hetu, swamp soil and yellow brown soil; dividing each regional unit into a plurality of regional subunits according to the soil type;
dividing land utilization types in the area to be classified according to land utilization current situation classification data, wherein the land utilization types comprise agricultural lands, construction lands, forest lands, natural reserved lands and water areas; dividing each regional subunit into a plurality of regional blocks according to the land utilization type;
step four, further subdividing the agricultural land, the construction land and the forest land through land utilization intensity, and not subdividing the natural reserved land and the water area, wherein:
1) For the regional blocks belonging to the agricultural land, grading the quality and the like of the regional blocks belonging to the agricultural land according to the grading data of the quality grading of the cultivated land obtained according to GBT 28407-2012 agricultural land quality grading rules by calculating the ratio of the crop yield of sampling points in the regional blocks to the highest yield of the specified standard crops;
2) For the area blocks belonging to the forest land, calculating and expressing the forest utilization intensity according to the coverage of the forest land, and grading the area blocks belonging to the forest land according to the forest utilization intensity;
3) For the regional blocks belonging to the construction land, firstly dividing each regional block belonging to the construction land into different blocks according to road network data of the region to be classified, and carrying out the following processing on each block:
s1, acquiring POI point data contained in a regional block belonging to a construction land from a map, wherein the POI point data is an abstract record of a geographic entity and contains longitude and latitude, names and categories of the geographic entity;
s2, dividing POI data in a neighborhood into four types of POI data sets of business, residential, industrial and public management and public service according to the name and the category of the POI data;
s3, according to the spatial position relation between the block and the POI point data set, if the block contains the POI point data of the public management and public service land, the block is the public management and public service land; if the block does not contain public administration and public service POI point data, the following steps are executed:
s31, clustering analysis is carried out on POI point data sets of different types through Ripley' s_K functions in ArcGIS software, and the most significant spatial clustering degree distance corresponding to the POI point data sets of the types is found out and used as the clustering distance corresponding to the POI point data sets of the types; the clustering distances corresponding to the commercial POI data set, the residential POI data set and the industrial POI data set are respectively marked as commercial clustering distances, residential clustering distances and industrial clustering distances;
s32, firstly, constructing an external rectangle of the neighborhood, then dividing the rectangle into grid data sets, respectively taking a commercial POI data set, a residential POI data set and an industrial POI data set as input elements, carrying out nuclear density analysis by taking half of the clustering distance of corresponding type POI data as a radius through a nuclear density analysis function in ArcGIS software, taking any grid as a center, taking half of the clustering distance corresponding to a certain POI data set as a search radius, calculating the nuclear density of the POI in the range as the value of the grid, and traversing all the grid data sets to obtain nuclear density analysis result grids covering all construction land area blocks and different types of POI points, namely respectively obtaining commercial nuclear density grids, industrial nuclear density grids and residential nuclear density grids of the neighborhood;
s33, respectively taking a nuclear density grid as input data through a K-means clustering function in MATLAB software, and dividing the input data into 3 types, namely, clustering results of commercial nuclear density grids respectively correspond to high-density, medium-density and low-density commercial area types; the clustering results of the industrial nuclear density grids respectively correspond to the types of the high-density, medium-density and low-density industrial areas; the clustering results of the living core density grids also correspond to the types of the high-density living areas, the medium-density living areas and the low-density living areas respectively.
2. The land type classification method based on multi-source homeland resource data as set forth in claim 1, wherein: in the fourth step, when the block belonging to the construction site is processed, the method further includes:
s34, dividing the blocks according to the commercial block types, the industrial block types, the residential block types and the spatial positions of the blocks, which are obtained by K-means clustering: 1) If the business district type, the industrial district type and the living district type in the district are all medium density districts or high density districts, the district is a mixed functional district; 2) If one type is higher than the other types in the neighborhood, the neighborhood is included in the functional region with the highest clustering result; 3) If the types of business areas, industrial areas and living areas in the neighborhood are all low-density, counting the number of POI points of different types in the neighborhood, and incorporating the POI points into corresponding functional areas in a mode of taking advantage of the number of the POI points; 4) If none of the blocks meets the rule, the blocks are summarized as village and town construction land.
3. The land type classification method based on multi-source homeland resource data as set forth in claim 1, wherein: in the fourth step, when the regional blocks belonging to the forest land are processed, the forest land coverage is divided into three stages in an equal division manner: the land with the low coverage rate is less than or equal to 33 percent, the land with the medium coverage rate is less than or equal to 66 percent, and the land with the high coverage rate is more than or equal to 66 percent.
4. The land type classification method based on multi-source homeland resource data as set forth in claim 1, wherein: in the fourth step, POI point data can be directly captured from a hundred-degree map or a high-altitude map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911355597.0A CN111062446B (en) | 2019-12-25 | 2019-12-25 | Land type classification method based on multi-source homeland resource data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911355597.0A CN111062446B (en) | 2019-12-25 | 2019-12-25 | Land type classification method based on multi-source homeland resource data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062446A CN111062446A (en) | 2020-04-24 |
| CN111062446B true CN111062446B (en) | 2023-05-09 |
Family
ID=70303404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911355597.0A Active CN111062446B (en) | 2019-12-25 | 2019-12-25 | Land type classification method based on multi-source homeland resource data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062446B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476325B (en) * | 2020-06-29 | 2020-09-29 | 河南大学 | Urban construction land classification identification method and system based on big data |
| CN112052848B (en) * | 2020-08-24 | 2022-09-20 | 腾讯科技（深圳）有限公司 | Method and device for acquiring sample data in street labeling |
| CN112365391A (en) * | 2020-11-12 | 2021-02-12 | 河北工程大学 | Land diversity measurement method based on 'homeland survey' data |
| CN114663764B (en) * | 2022-04-01 | 2023-04-07 | 中国科学院地理科学与资源研究所 | Method, device, medium and terminal equipment for zoning soil environment quality of cultivated land |
| CN114971234B (en) * | 2022-05-11 | 2023-04-07 | 北京中色测绘院有限公司 | Soil general survey technical method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3312742A1 (en) * | 2016-10-21 | 2018-04-25 | HERE Global B.V. | Method and apparatus for hierarchical clustering of geographical data |
| CN110175216A (en) * | 2019-05-15 | 2019-08-27 | 腾讯科技（深圳）有限公司 | Coordinate error correction method, device and computer equipment |
-
2019
- 2019-12-25 CN CN201911355597.0A patent/CN111062446B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3312742A1 (en) * | 2016-10-21 | 2018-04-25 | HERE Global B.V. | Method and apparatus for hierarchical clustering of geographical data |
| CN110175216A (en) * | 2019-05-15 | 2019-08-27 | 腾讯科技（深圳）有限公司 | Coordinate error correction method, device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062446A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111062446B (en) | Land type classification method based on multi-source homeland resource data | |
| Yang et al. | Spatiotemporal evolution of urban agglomerations in four major bay areas of US, China and Japan from 1987 to 2017: Evidence from remote sensing images | |
| Liu et al. | Global urban expansion offsets climate-driven increases in terrestrial net primary productivity | |
| Yeprintsev et al. | Technologies for creating geographic information resources for monitoring the socio-ecological conditions of cities | |
| Biondi et al. | Phytosociological synrelevés and plant landscape mapping: From theory to practice | |
| CN110413666A (en) | A kind of multi-source heterogeneous data integration method of farmland quality | |
| CN106709989B (en) | Geographic ontology modeling and semantic reasoning method based on object-oriented image features | |
| Zhao et al. | Woody vegetation composition and structure in peri-urban Chongming Island, China | |
| Tian et al. | Suburban identification based on multi-source data and landscape analysis of its construction land: A case study of Jiangsu Province, China | |
| CN112365391A (en) | Land diversity measurement method based on 'homeland survey' data | |
| CN116310853A (en) | Multi-source data-based extraction method for edge regions of medium and small cities | |
| Luo et al. | Understanding the relationship between 2D/3D variables and land surface temperature in plain and mountainous cities: Relative importance and interaction effects | |
| Jiang et al. | The impact of gradient expansion of urban–rural construction land on landscape fragmentation in typical mountain cities, China | |
| WO2018196214A1 (en) | Statistics system and statistics method for geographical influence on vernacular architectural form | |
| Zhang | The spatial distribution and evolution of traditional villages based on remote sensing technology | |
| KR102526361B1 (en) | System and method for analyzing effect of ground surface regarding heat wave and cold wave at local level | |
| Lu et al. | Mapping the terraces on the Loess Plateau based on a deep learning-based model at 1.89 m resolution | |
| Bibby et al. | Monitoring land cover and land use for urban and regional planning | |
| Li et al. | Landslide susceptibility-oriented suitability evaluation of construction land in mountainous areas | |
| Jande et al. | Assessment of land use and land cover changes and urban expansion using remote sensing and GIS in Gboko, Benue State, Nigeria | |
| Zhang et al. | An estimation and development model of tourism resource values at the township scale on Hainan Island, China | |
| CN114943377A (en) | Method for identifying evolution of spatial form and pattern of villages and towns | |
| Gao et al. | Spatial planning zoning based on land-type mapping: a case study in Changzhou City, Eastern China | |
| CN109948956A (en) | A kind of preferential growing area area selecting method of urban forests trees and system | |
| Wen et al. | Research on risk assessment of natural disaster based on cloud fuzzy clustering algorithm in Taihang Mountain |
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 |