CN116304991A - Multi-source heterogeneous species distribution data fusion method and device - Google Patents

Multi-source heterogeneous species distribution data fusion method and device Download PDF

Info

Publication number
CN116304991A
CN116304991A CN202310544496.8A CN202310544496A CN116304991A CN 116304991 A CN116304991 A CN 116304991A CN 202310544496 A CN202310544496 A CN 202310544496A CN 116304991 A CN116304991 A CN 116304991A
Authority
CN
China
Prior art keywords
data
species
distribution
fusion
distribution 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.)
Granted
Application number
CN202310544496.8A
Other languages
Chinese (zh)
Other versions
CN116304991B (en
Inventor
李雪艳
苏泳娴
吴建平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Institute of Geography of GDAS
Original Assignee
Guangzhou Institute of Geography of GDAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Institute of Geography of GDAS filed Critical Guangzhou Institute of Geography of GDAS
Priority to CN202310544496.8A priority Critical patent/CN116304991B/en
Publication of CN116304991A publication Critical patent/CN116304991A/en
Application granted granted Critical
Publication of CN116304991B publication Critical patent/CN116304991B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The application discloses a multi-source heterogeneous species distribution data fusion method and device, wherein the method comprises the following steps: acquiring multi-source heterogeneous species distribution data of a target species including species distribution data of at least three data structures; acquiring a data distribution grid of species distribution data of the target species in various data structures from multi-source heterogeneous species distribution data according to ecological environment data, altitude data and climate data suitable for survival of the target species; acquiring the distribution data weight of the species distribution data of various data structures according to the species distribution data of various data structures and the corresponding data source information; and carrying out data fusion on the data distribution grids of the species distribution data of various data structures according to the distribution data weight to obtain a plurality of fusion data distribution grids and the probability of the target species appearing in each fusion data distribution grid. The species distribution data with higher accuracy, smaller error and more comprehensive performance can be obtained.

Description

Multi-source heterogeneous species distribution data fusion method and device
Technical Field
The application relates to the technical field of species distribution data processing, in particular to a multi-source heterogeneous species distribution data fusion method and device.
Background
Species distribution data is the basis of biodiversity protection, but due to the fact that different investigation methods are used by personnel for carrying out investigation, point, line, surface and other multi-source heterogeneous data exist, each type of data has different errors, comprehensive and accurate species distribution data cannot be obtained, and difficulty is brought to formulation of biodiversity protection policies.
Disclosure of Invention
The purpose of the application is to overcome the defects and shortcomings in the prior art, and provide a multi-source heterogeneous species distribution data fusion method and device, which can be used for carrying out data fusion on multi-source heterogeneous species distribution data of species, so as to obtain species distribution data with higher accuracy, smaller error and more comprehensiveness.
A first embodiment of the present application provides a multi-source heterogeneous species distribution data fusion method, including:
acquiring multi-source heterogeneous species distribution data of a target species, wherein the multi-source heterogeneous species distribution data comprises species distribution data of at least three data structures;
acquiring a data distribution grid of species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to ecological environment data, altitude data and climate data suitable for survival of the target species;
Acquiring the distribution data weight of the species distribution data of various data structures according to the species distribution data of the target species in various data structures and the data source information of the species distribution data of various data structures;
and carrying out data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weight of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and the probability that the target species appears in each fusion data distribution grid.
A second embodiment of the present application provides a multi-source heterogeneous species distribution data fusion device, including:
the multi-source heterogeneous species distribution data acquisition module is used for acquiring multi-source heterogeneous species distribution data of a target species, wherein the multi-source heterogeneous species distribution data comprise species distribution data of at least three data structures;
the data distribution grid acquisition module is used for acquiring the data distribution grids of the species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to the ecological environment data, the altitude data and the climate data of the target species suitable for survival;
The distributed data weight acquisition module is used for acquiring the distributed data weights of the species distribution data of various data structures according to the species distribution data of the target species in various data structures and the data source information of the species distribution data of various data structures;
and the data fusion module is used for carrying out data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weight of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and the probability that the target species appears in each fusion data distribution grid.
Compared with the related art, the method and the device acquire the data distribution grids of the species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data of the target species according to the ecological environment data, the altitude data and the climate data suitable for survival of the target species, acquire the distribution data weights of the species distribution data of various data structures according to the data distribution grids of the species distribution data of various data structures and the data source information of the species distribution data of various data structures, and perform data fusion on the data distribution grids according to the distribution data weights to acquire a plurality of fusion data distribution grids and the probability of the target species appearing in each fusion data distribution grid as the distribution data of the target species, so that the technical effects of performing data fusion on the multi-source heterogeneous species distribution data of the species are achieved, and the species distribution data with higher accuracy, smaller errors and more comprehensiveness are obtained.
In order that the present application may be more clearly understood, specific embodiments thereof will be described below with reference to the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a multi-source heterogeneous species distribution data fusion method according to one embodiment of the present application.
Fig. 2 is a schematic diagram of a buffer region of point-like structure species distribution data of a multi-source heterogeneous species distribution data fusion method according to an embodiment of the present application.
Fig. 3 is a data distribution grid extracted from point-like structure species distribution data of a multi-source heterogeneous species distribution data fusion method according to an embodiment of the present application.
FIG. 4 is a schematic diagram of a buffer region of linear structure species distribution data of a multi-source heterogeneous species distribution data fusion method according to one embodiment of the present application.
Fig. 5 is a schematic diagram of a buffer region of planar structure species distribution data of a multi-source heterogeneous species distribution data fusion method according to an embodiment of the present application.
Fig. 6 is a schematic diagram of module connection of a multi-source heterogeneous species distribution data fusion device according to an embodiment of the present application.
100. The multi-source heterogeneous species distribution data fusion device; 101. the multi-source heterogeneous species distribution data acquisition module; 102. a data distribution grid acquisition module; 103. a distributed data weight acquisition module; 104. and a data fusion module.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the embodiments of the present application, are within the scope of the embodiments of the present application.
When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. In the description of this application, it should be understood that the terms "first," "second," "third," and the like are used merely to distinguish between similar objects and are not necessarily used to describe a particular order or sequence, nor should they be construed to indicate or imply relative importance. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art as the case may be. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The word "if"/"if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination".
Furthermore, in the description of the present application, unless otherwise indicated, "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
Referring to fig. 1, a flowchart of a multi-source heterogeneous species distribution data fusion method according to a first embodiment of the present application is shown, and the method includes:
s1: multi-source heterogeneous species distribution data of a target species is obtained, the multi-source heterogeneous species distribution data including species distribution data of at least three data structures.
The multi-source heterogeneous species distribution data comprise dot-shaped structure species distribution data, linear structure species distribution data and planar structure species distribution data, and further comprise a land coverage map, an altitude map and a climate zone distribution map of a region where the species distribution data of the corresponding data structure are located.
S2: and acquiring a data distribution grid of species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to ecological environment data, altitude data and climate data suitable for survival of the target species.
The ecological environment data is an ecological environment type suitable for the target species to survive, for example: the ecological environment types such as grasslands, woodlands, sand lands and the like can find out a land coverage type grid suitable for survival of target species from a land coverage map according to the ecological environment data; altitude data is an altitude range where the target species is suitable for survival, for example, 300 meters to 1000 meters, and an altitude grid where the target species is suitable for survival can be found out from an altitude map according to the altitude data; the climate data is a climate zone range suitable for the survival of the target species, and the climate zone grid suitable for the survival of the target species can be found out from the climate zone distribution diagram according to the climate data; and then acquiring a data distribution grid of species distribution data of the target species in various data structures according to the land cover type grid, the altitude grid and the weather zone grid.
S3: and acquiring the distribution data weight of the species distribution data of the various data structures according to the species distribution data of the target species in the various data structures and the data source information of the species distribution data of the various data structures.
S4: and carrying out data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weight of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and the probability that the target species appears in each fusion data distribution grid.
Compared with the related art, the method and the device acquire the data distribution grids of the species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data of the target species according to the ecological environment data, the altitude data and the climate data suitable for survival of the target species, acquire the distribution data weights of the species distribution data of various data structures according to the data distribution grids of the species distribution data of various data structures and the data source information of the species distribution data of various data structures, and perform data fusion on the data distribution grids according to the distribution data weights to acquire a plurality of fusion data distribution grids and the probability of the target species appearing in each fusion data distribution grid as the distribution data of the target species, so that the technical effect of performing data fusion on the multi-source heterogeneous species distribution data of the species and obtaining the species distribution data with higher accuracy is realized.
In one possible embodiment, the step S2: and acquiring a data distribution grid of species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to ecological environment data, altitude data and climate data suitable for survival of the target species, wherein the data distribution grid comprises the following steps:
s21: and obtaining the buffer areas of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data.
Wherein the range of the buffer of the species distribution data of the various data structures is larger than the range of the species distribution data of the same data structure, and the range of the buffer of the species distribution data of the various data structures includes the range of the species distribution data of the same data structure.
S22: and acquiring a plurality of common grids from the buffer area according to the ecological environment data, the elevation data and the climate data.
The common grid refers to a plurality of grids in the buffer area which simultaneously satisfy ecological environment data, altitude data and climate data, namely, a plurality of grids which simultaneously belong to a land cover type grid, an altitude grid and a climate zone grid.
S23: and acquiring the data distribution grids of the species distribution data of the various data structures from the common grid according to a preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures.
Wherein the number of common grids is greater than the number of data distribution grids of species distribution data of the same data structure.
In this embodiment, a plurality of common grids satisfying ecological environment data, altitude data and climate data are obtained from a buffer area with an expanded range, and then data distribution grids of species distribution data of various data structures are obtained from the common grids according to a preset data distribution grid obtaining method corresponding to the species distribution data of various data structures, so that species distribution data errors are reduced, and the comprehensiveness and accuracy of the data distribution grids are improved.
In a possible embodiment, the multi-source heterogeneous species distribution data comprises punctate structure species distribution data of the target species;
the step S21: the step of obtaining the buffer area of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data comprises the following steps:
s2101: and acquiring a plurality of initial distribution points of the point-shaped structure species distribution data, expanding each initial distribution point according to the diffusion capability of the target species, and obtaining a plurality of buffer areas.
Specifically, with the initial distribution points as the circle centers and the diffusion capability of the target species as the expansion radius, the buffer areas corresponding to the initial distribution points can be obtained.
The S23: according to the preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures, acquiring the data distribution grid of the species distribution data of the various data structures from the common grid, wherein the data distribution grid comprises the following steps:
s2301: and acquiring the first occurrence probability of the species of each common grid according to the shortest distance between each common grid corresponding to the point-like structure species distribution data and the plurality of initial distribution points.
The distance between each common grid corresponding to the dot-shaped structure species distribution data and a plurality of initial distribution points is obtained through the following formula:
Figure SMS_1
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_3
is a shared grid->
Figure SMS_5
And the initial distribution point->
Figure SMS_7
Distance of->
Figure SMS_4
For the initial distribution point->
Figure SMS_6
Coordinates of the center point of>
Figure SMS_8
Is a shared grid->
Figure SMS_9
Coordinates of the center point of>
Figure SMS_2
Is the earth radius.
And selecting the distance with the smallest absolute value from the distances between the shared grids and the plurality of initial distribution points as a first shortest distance, wherein the first occurrence probability of the species of each shared grid is the reciprocal of the first shortest distance.
S2302: and acquiring the data distribution grids from a plurality of common grids corresponding to the species distribution data of the dot-shaped structure according to the first occurrence probability of the species.
The data distribution grids obtained in step S2302 are extracted from the respective common grids based on the first occurrence probability of the species of the respective common grids, and the number of the data distribution grids is smaller than the number of the common grids. The number of data distribution grids may be a preset number.
Referring to fig. 2-3, distances between a common grid corresponding to the dot-like structure species distribution data and a plurality of initial distribution points are shown in fig. 2, black dots are positions of the initial distribution points in fig. 2, a dashed circle is a buffer area range, a light gray grid is a common grid suitable for species in the buffer area, a crossing point of the black cross is a center point of the common grid, and a dark gray grid is a data distribution grid extracted according to the first occurrence probability. As shown in fig. 3, the data distribution grid and the common grid not being extracted may be better distinguished by binarization, for example, a value of 1 may be assigned to the data distribution grid obtained by extraction, and a value of 0 may be assigned to the common grid not being extracted.
In this embodiment, the buffer region of the dot-shaped structure species distribution data may be acquired through step S2101, and the data distribution grid corresponding to the dot-shaped structure species distribution data may be acquired through steps S2301-S2302 according to the common grid in the buffer region of the dot-shaped structure species distribution data.
For punctiform distribution data without longitude and latitude, the place name in the punctiform distribution data can be extracted through a text recognition method, and then the longitude and latitude of the position corresponding to the place name is searched from an electronic map or a preset database to obtain the longitude and latitude information of the punctiform distribution data, but the positioning of the punctiform distribution data without longitude and latitude is easy to generate errors, so that the positioning needs to be corrected according to the ecological environment of the longitude and latitude position and the ecological environment which is properly generated by the corresponding target species. The processing step of the punctiform distribution data without longitude and latitude comprises the following steps:
(1) the description about the found place in the extracted data is generally mixed text information containing numbers, characters and words, so that the mixed text information needs to be divided into a plurality of strings according to separators such as commas, stop signs, spaces and the like.
(2) And screening a plurality of word strings according to a certain rule to remove nonsensical word strings such as symbols, misspellings and the like.
(3) Searching whether the screened strings comprise keywords (including but not limited to: to, -, -) representing routes. If such keywords indicating observation during the course are included, the data is considered to be linear distribution data, and the data is processed according to a processing flow of linear distribution data having no longitude and latitude. If no keywords are included that represent observations in the way, the data is considered to be punctiform structure species distribution data.
(4) Searching the screened word strings through matching with a preset database (a common bird-looking place name database built by the user comprises geographical position information of thousands of floors), an electronic map and the like, and obtaining longitude and latitude coordinates of the geographical positions corresponding to the word strings.
(5) The initial distribution point is generated from the longitude and latitude coordinates, but since the positioning error of the data is generally large at this time, 2 times the diffusion capacity data of the species is adopted as the buffer radius when S2101 is performed.
In one possible embodiment, the multi-source heterogeneous species distribution data comprises wireform species distribution data of the target species;
the step S21: the step of obtaining the buffer area of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data comprises the following steps:
s2111: and acquiring a distribution sample line of the linear structure species distribution data, expanding the distribution sample line according to the diffusion capability of the target species, and obtaining the buffer area.
Specifically, both sides of the distribution pattern are spread with the diffusion capability of the target species to obtain a buffer region of increased width.
The S23: according to the preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures, acquiring the data distribution grid of the species distribution data of the various data structures from the common grid, wherein the data distribution grid comprises the following steps:
S2311: and obtaining the second occurrence probability of the species of each common grid according to the shortest distance between each common grid corresponding to the linear structure species distribution data and the distribution sample line.
And replacing the relevant parameters of the initial distribution points in the distance operation of the common grid corresponding to the point-shaped structure species distribution data and the initial distribution points with the relevant parameters of the sampling line points, so as to obtain the distance operation between the common grid of the linear structure species distribution data and each sampling line point of the distribution sampling line.
And selecting the distance with the smallest absolute value from the distances between the common grids of the species distribution data of the linear structure and each sample line point position of the distribution sample line as a second shortest distance, wherein the second occurrence probability of the species of each common grid is the reciprocal of the second shortest distance.
S2312: and acquiring the data distribution grids from a plurality of common grids corresponding to the linear structure species distribution data according to the second occurrence probability of the species.
The data distribution grids obtained in step S2312 are extracted from the respective common grids based on the second occurrence probability of the species of the respective common grids, and the number of the data distribution grids is smaller than the number of the common grids. The number of data distribution grids may be a preset number.
Referring to fig. 4, distances between the common grid corresponding to the distribution data of the linear structure species and each sample line point of the distribution sample line are shown in fig. 4, wherein a black curved solid line is the distribution sample line, a black curved dashed line is a boundary of the buffer region, a light gray grid is the common grid with suitable species in the buffer region, and a cross point of the black cross is a center point of the common grid.
In this embodiment, the buffer region of the linear structure species distribution data can be obtained through step S2111, and the data distribution grid corresponding to the dot-like structure species distribution data can be obtained through steps S2311-S2312 according to the common grid in the buffer region of the linear structure species distribution data.
For the species distribution data of the linear structure without geographic positioning information, the longitude and latitude of the position where the key place name is located can be obtained from the text description, and a plurality of distribution points are generated according to the longitude and latitude and are connected into a sample line. But because the species cannot fully occupy all geographic areas along the survey line, and the data is not of a fixed survey breadth. This type of data therefore typically has large misclassification errors and misclassification errors, and therefore requires extraction and refinement around the sample line to obtain a buffer of the line structure species distribution data. The processing step for the line structure species distribution data without geolocation information comprises:
(1) Firstly, extracting the description about the found place in the data, wherein the description is generally mixed text information containing numbers, characters and words, so that the mixed text information needs to be divided into a plurality of strings according to separators such as commas, stop signs, spaces and the like.
(2) And screening a plurality of word strings according to a certain rule to remove nonsensical word strings such as symbols, misspellings and the like.
(3) Searching whether the screened strings comprise keywords (to, -) representing the routes. If the keywords representing the observation in the road are not included, the data is considered to be punctiform distribution data, and the punctiform distribution data is processed according to a processing flow without longitude and latitude. If keywords representing observations in transit are included, the data is considered as linear distribution data.
(4) Searching and matching the screened strings by using a preset database (a common sightseeing place name database built by the user comprises geographical position information of thousands of floors), an electronic map and the like, and obtaining longitude and latitude coordinates of the geographical positions corresponding to the strings.
(5) Generating a plurality of distribution points according to the longitude and latitude coordinates, and connecting the distribution points into linear distribution data according to the sequence. However, since the investigation width of the data at this time is generally not determined, 2 times the diffusion capacity data of the species is adopted as the expansion data of the buffer zone when step S2111 is performed.
In one possible embodiment, the multi-source heterogeneous species distribution data comprises planar structure species distribution data of the target species;
the step S21: the step of obtaining the buffer area of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data comprises the following steps:
s2121: and acquiring the distribution range of the species distribution data of the planar structure, and determining the distribution range as the buffer area.
The S23: according to the preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures, acquiring the data distribution grid of the species distribution data of the various data structures from the common grid, wherein the data distribution grid comprises the following steps:
s2321: and acquiring the data distribution grids from the common grids corresponding to the species distribution data of the planar structure.
The data distribution grids obtained in step S2321 are extracted from the corresponding common grids, and the number of the data distribution grids may be a preset number.
Referring to fig. 5, the black curve surrounds the distribution range of the species distribution data of the planar structure, which is also the corresponding buffer, and the light gray grid is a common grid suitable for the species in the buffer.
In this embodiment, the buffer region of the planar structure species distribution data may be acquired in step S2121, and the data distribution grid corresponding to the planar structure species distribution data may be acquired in step S2321 according to the common grid in the buffer region of the planar structure species distribution data.
For the species distribution data of the planar structure without the geographic positioning information, the area range where the key place name is located can be obtained from the description, which includes:
(1) firstly, extracting the description about the found place in the data, wherein the description is generally mixed text information containing numbers, characters and words, so that the mixed text information needs to be divided into a plurality of strings according to separators such as commas, stop signs, spaces and the like.
(2) And screening a plurality of word strings according to a certain rule to remove nonsensical word strings such as symbols, misspellings and the like.
(3) Searching whether the screened strings comprise keywords (to, -) representing the routes. If such keywords indicating observation during the course are included, the data is considered to be linear distribution data, and the data is processed according to a processing flow of dot distribution data having no longitude and latitude. If keywords representing observations in the way are not included, the data is considered to be punctiform distribution data.
(4) Searching the screened strings by using a preset database (a commonly-used sightseeing place name database built by the user comprises geographical position information of thousands of floors), an electronic map and the like, and obtaining a geographical position range corresponding to the strings to obtain species distribution data of the planar structure.
In one possible embodiment, the data source information includes auditor information, time information, and publishing information;
the S3: obtaining the distribution data weight of the species distribution data of various data structures according to the species distribution data of the target species in various data structures and the data source information of the species distribution data of various data structures, wherein the step comprises the following steps:
s31: and obtaining a first score of the species distribution data of the various data structures and a first highest score corresponding to the species number information according to the species number information recorded in the species distribution data of the various data structures.
S32: and obtaining second scores of species distribution data of various data structures and second highest scores corresponding to the auditor information according to the auditor information.
S33: and obtaining third scores of species distribution data of various data structures and third highest scores corresponding to the time information according to the time information.
S34: and obtaining fourth scores of species distribution data of various data structures and fourth highest scores corresponding to the publishing information according to the publishing information.
Wherein, the scores of the species distribution data of steps S31-S34 are shown in the following table:
Figure SMS_10
s35: and acquiring the distribution data weight of species distribution data of various data structures according to the first score, the second score, the third score, the fourth score, the first highest score, the second highest score, the third highest score and the fourth highest score.
The distribution data weight of species distribution data of various data structures is calculated by the following formula:
Figure SMS_11
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_12
is->
Figure SMS_13
The distribution data weight of the species distribution data of the species data structure.
In this embodiment, through the above steps, the distribution data weight of the species distribution data of the various data structures may be obtained according to the species distribution data of the various data structures and the data source information of the species distribution data of the various data structures.
In one possible embodiment, the step S4: according to the distribution data weight of the species distribution data of various data structures, carrying out data fusion on the data distribution grids of the species distribution data of various data structures to obtain a plurality of fusion data distribution grids, and the probability that the target species appears in each fusion data distribution grid, wherein the method comprises the following steps:
S41: and carrying out data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weight of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and fusion values of each fusion data distribution grid.
The fusion value of each fusion data distribution grid is obtained by the following formula:
Figure SMS_14
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_15
is->
Figure SMS_16
Individual fusion data divisionsFusion value of the cloth grid, +.>
Figure SMS_17
Is->
Figure SMS_18
Seed data at->
Figure SMS_19
Probability of species distribution of the individual grids, +.>
Figure SMS_20
Is the maximum number of species.
S42: and obtaining the probability that the target species appears in each fusion data distribution grid according to the highest fusion value and the fusion value of each fusion data distribution grid.
The probability of the target species appearing in each of the fused data distribution grids is obtained by the following formula:
Figure SMS_21
；
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_22
for the target species to appear at +.>
Figure SMS_23
Probability of individual fusion data distribution grid, +.>
Figure SMS_24
Is the highest fusion value.
In one possible embodiment, for a common grid near the fused data distribution grid, interpolation is performed by the kriging method based on the probability of each fused data distribution grid to obtain spatially continuous fused species distribution grid data.
In this embodiment, the probability that the target species appears in each of the fusion data distribution grids may be obtained through the above steps.
In a possible embodiment, after obtaining the fusion species distribution raster data, the method further includes a step of performing accuracy check on the fusion species distribution raster data according to a preset verification sample.
The precision test of the dot-shaped structure species distribution data based on dot-shaped verification data comprises the following steps:
a1, firstly acquiring diffusion capacity data of a species, and generating a buffer area around each species existence point (existence point for short) and/or species non-existence point (non-existence point for short) of verification data by taking the diffusion capacity data of the species as a radius. Setting the values of all grids in a buffer area of the verification data species existence point to be 1, namely the species distribution probability is 100%; the value of all grids in the buffer around the absence point is set to 0 (if there is an absence point), i.e. the probability of a species distribution is 0%. Wherein, a species presence point means that the species is distributed at the geographic location; the species does not exist at a point, i.e., the species is not distributed in the geographic location.
A2, overlapping and calculating the space-continuous fusion species distribution raster data and the dot-shaped verification data buffer area, and judging whether the fusion species distribution raster data exist in the verification data buffer area. If no species corresponding to the fusion species distribution raster data exists in the raster within the verification data range, the accuracy cannot be verified. If the presence grid of the species corresponding to the fusion species distribution grid data falls within the verification data range, the next step is performed.
And A3, extracting a fusion data grid representing fusion species distribution grid data in the range of the verification data buffer area to perform precision calculation.
The embodiment provides two precision calculation methods, one is based on probability: and for verification data with only existence points and no non-existence points, calculating species distribution probability average values of all fusion data grids in the buffer area range of the existence points of the verification data, and taking the species distribution probability average values as the precision of the existence points of the fusion data. For verification data with existing points and verification data without existing points, the precision of the fusion data is calculated according to the precision calculation method of the verification data with only existing points and verification data without existing points, and the precision of the verification data with existing points and verification data without existing points is used as the precision of the fusion data; the species distribution probability mean of all the fusion data grids within the verification data non-existence point buffer area is also calculated, and the difference of 1-mean value is used as the precision of the fusion data non-existence point.
The other is threshold-based: for two types of verification data, namely only existence points, no existence points and both existence points and no existence points, species distribution probabilities of continuous changes (0, 1) of the fusion data grids in the verification data buffer area are divided into two types according to thresholds, namely existence (value of 1) and nonexistence (value of 0). Statistics of the number of grids in the verification data buffer area based on existence/nonexistence of the fusion data and the number of grids based on existence/nonexistence of the verification data, and a confusion matrix is constructed, wherein the confusion matrix is shown in the following table:
Figure SMS_25
Where a is the number of grids in the buffer based on the presence of the species in both the validation data and the fusion data, b is the number of grids that are not present in the validation data but are present in the fusion data, c is the number of grids that are present in the validation data to not present in the fusion data, and d is the number of grids that are not present in both the validation and fusion data. n is the number of all grids, n=a+b+c+d.
From the above data, the accuracy can be calculated based on the confusion matrix according to the following formula:
sensitivity to
Figure SMS_26
：/>
Figure SMS_27
；
Specificity (specificity)
Figure SMS_28
：/>
Figure SMS_29
；
Precision of
Figure SMS_30
：/>
Figure SMS_31
；
Overall prediction success rate
Figure SMS_32
：/>
Figure SMS_33
；
Kappa index:
Figure SMS_34
；
based on the above data, the threshold determination method may employ the following method:
a. fixed threshold method: a grid with the species distribution probability of more than 0.5 in the fusion data is a species existence grid by taking 0.5 as a threshold value, and the value is 1; and a grid with the species distribution probability smaller than 0.5 in the fusion data is a grid with no species, and the value is 0.
b. Custom thresholding: according to the species distribution probability (for example, 0.25) defined by a user as a threshold, a grid with the species distribution probability greater than the self-defined threshold in the fusion data is a species existence grid, and the value is 1; and a grid with the species distribution probability smaller than 0 and smaller than the self-defined threshold value in the fusion data is a grid with no species, and the value is 0.
c. Median method: taking the median value of species distribution probabilities of the fusion data grids in the range of all verification data buffers as a threshold value.
d. Maximizing Kappa method: a threshold value that maximizes Kappa value.
e. Maximizing OPS method: a threshold value for maximizing the OPS value.
f. Sum thresholding to maximize sensitivity and specificity: a threshold at which the sum of sensitivity and specificity is maximized.
The method for verifying the accuracy of the linear structure species distribution data based on the linear verification data comprises the following steps:
b1, firstly acquiring diffusion capacity data of the species, and generating buffer bands with certain widths on two sides of the linear verification data according to the diffusion capacity data of the species.
And B2, superposing and calculating a buffer zone of the fusion species distribution raster data and the linear verification data, judging whether the fusion data species exist in the range of the verification data buffer zone, and if the species corresponding to the fusion species distribution raster data exist in the range of the verification data, failing to verify the precision. If the presence grid of the species corresponding to the fusion species distribution grid data falls within the verification data range, the next step is performed.
And B3, extracting a fusion data grid representing fusion species distribution grid data in the range of the verification data buffer area to perform accuracy calculation, wherein the fusion data grid comprises two accuracy calculation methods based on probability and threshold.
Accuracy testing of the planar structure species distribution data based on the planar verification data, comprising the steps of:
and C1, overlapping and calculating the space-continuous fusion species distribution raster data and the planar verification data buffer area, and judging whether the fusion species distribution raster data exist in the range of the verification data buffer area. If no species corresponding to the fusion species distribution raster data exists in the raster within the verification data range, the accuracy cannot be verified. If the presence grid of the species corresponding to the fusion species distribution grid data falls within the verification data range, the next step is performed.
And C2, extracting a fusion data grid representing fusion species distribution grid data in the range of the verification data buffer area to perform precision calculation, wherein the fusion data grid comprises two precision calculation methods based on probability and threshold.
Referring to fig. 6, a second embodiment of the present application provides a multi-source heterogeneous species distribution data fusion apparatus 100, including:
the multi-source heterogeneous species distribution data acquisition module 101 is configured to acquire multi-source heterogeneous species distribution data of a target species, where the multi-source heterogeneous species distribution data includes species distribution data of at least three data structures.
The data distribution grid acquiring module 102 is configured to acquire, from the multi-source heterogeneous species distribution data, a data distribution grid of species distribution data of the target species in various data structures according to ecological environment data, altitude data and climate data suitable for survival of the target species.
The distribution data weight obtaining module 103 is configured to obtain the distribution data weights of the species distribution data of the various data structures according to the species distribution data of the target species in the various data structures and the data source information of the species distribution data of the various data structures.
The data fusion module 104 is configured to perform data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weights of the species distribution data of the various data structures, so as to obtain a plurality of fusion data distribution grids and probabilities of the target species appearing in each fusion data distribution grid.
The data source information comprises auditor information, time information and publishing information;
the distributed data weight obtaining module 103 includes:
the first score acquisition module is used for acquiring first scores of species distribution data of various data structures and first highest scores corresponding to the species number information according to the species number information recorded by the species distribution data of the various data structures;
The second score acquisition module is used for acquiring second scores of species distribution data of various data structures and second highest scores corresponding to the auditor information according to the auditor information;
the third score acquisition module is used for acquiring third scores of species distribution data of various data structures and third highest scores corresponding to the time information according to the time information;
a fourth score obtaining module, configured to obtain a fourth score of species distribution data of various data structures and a fourth highest score corresponding to the publishing information according to the publishing information;
and the data weight acquisition module is used for acquiring the distribution data weights of the species distribution data of various data structures according to the first score, the second score, the third score, the fourth score, the first highest score, the second highest score, the third highest score and the fourth highest score.
The data fusion module 104 includes:
according to the distribution data weight of the species distribution data of various data structures, carrying out data fusion on the data distribution grids of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and fusion values of each fusion data distribution grid;
And obtaining the probability that the target species appears in each fusion data distribution grid according to the highest fusion value and the fusion value of each fusion data distribution grid.
It should be noted that, when the multi-source heterogeneous species distribution data fusion apparatus 100 according to the second embodiment of the present application performs the multi-source heterogeneous species distribution data fusion method, only the above-mentioned division of each functional module is used as an example, in practical application, the above-mentioned functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to perform all or part of the above-mentioned functions. In addition, the multi-source heterogeneous species distribution data fusion device 100 provided in the second embodiment of the present application belongs to the same concept as the multi-source heterogeneous species distribution data fusion method in the first embodiment of the present application, and detailed implementation processes are shown in the method embodiment and are not repeated here.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method. Where the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (10)

1. A method for multi-source heterogeneous species distribution data fusion, comprising:
acquiring multi-source heterogeneous species distribution data of a target species, wherein the multi-source heterogeneous species distribution data comprises species distribution data of at least three data structures;
acquiring a data distribution grid of species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to ecological environment data, altitude data and climate data suitable for survival of the target species;
acquiring the distribution data weight of the species distribution data of various data structures according to the species distribution data of the target species in various data structures and the data source information of the species distribution data of various data structures;
and carrying out data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weight of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and the probability that the target species appears in each fusion data distribution grid.
2. The multi-source heterogeneous species distribution data fusion method of claim 1, wherein the data source information comprises auditor information, time information and publishing information;
the step of obtaining the distribution data weight of the species distribution data of the various data structures according to the species distribution data of the target species in the various data structures and the data source information of the species distribution data of the various data structures comprises the following steps:
according to species number information recorded in the species distribution data of various data structures, acquiring first scores of the species distribution data of various data structures and first highest scores corresponding to the species number information;
obtaining second scores of species distribution data of various data structures and second highest scores corresponding to the auditor information according to the auditor information;
according to the time information, obtaining third scores of species distribution data of various data structures and third highest scores corresponding to the time information;
according to the publishing information, fourth scores of species distribution data of various data structures and fourth highest scores corresponding to the publishing information are obtained;
And acquiring the distribution data weight of species distribution data of various data structures according to the first score, the second score, the third score, the fourth score, the first highest score, the second highest score, the third highest score and the fourth highest score.
3. The method for fusing multi-source heterogeneous species distribution data according to claim 1, wherein the step of performing data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weights of the species distribution data of the various data structures to obtain a plurality of fused data distribution grids, and the probability that the target species appears in each fused data distribution grid comprises:
according to the distribution data weight of the species distribution data of various data structures, carrying out data fusion on the data distribution grids of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and fusion values of each fusion data distribution grid;
and obtaining the probability that the target species appears in each fusion data distribution grid according to the highest fusion value and the fusion value of each fusion data distribution grid.
4. The method according to claim 1, wherein the step of obtaining a data distribution grid of species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to ecological environment data, altitude data and climate data suitable for survival of the target species comprises:
according to the multi-source heterogeneous species distribution data and preset buffer data, a buffer area of species distribution data of various data structures is obtained;
acquiring a plurality of common grids from the buffer area according to the ecological environment data, the elevation data and the climate data;
and acquiring the data distribution grids of the species distribution data of the various data structures from the common grid according to a preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures.
5. The method of claim 4, wherein the multi-source heterogeneous species distribution data comprises punctate structure species distribution data of the target species;
the step of obtaining the buffer area of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data comprises the following steps:
Acquiring a plurality of initial distribution points of the point-like structure species distribution data, expanding each initial distribution point according to the diffusion capability of the target species, and acquiring a plurality of buffer areas;
the step of acquiring the data distribution grid of the species distribution data of the various data structures from the common grid according to the preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures comprises the following steps:
obtaining a first occurrence probability of the species of each common grid according to the shortest distance between each common grid corresponding to the point-like structure species distribution data and the plurality of initial distribution points;
and acquiring the data distribution grids from a plurality of common grids corresponding to the species distribution data of the dot-shaped structure according to the first occurrence probability of the species.
6. The method of claim 4, wherein the multi-source heterogeneous species distribution data comprises linear structure species distribution data of the target species;
the step of obtaining the buffer area of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data comprises the following steps:
Acquiring a distribution sample line of the linear structure species distribution data, expanding the distribution sample line according to the diffusion capability of the target species, and obtaining the buffer area;
the step of acquiring the data distribution grid of the species distribution data of the various data structures from the common grid according to the preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures comprises the following steps:
obtaining a second occurrence probability of the species of each common grid according to the shortest distance between each common grid corresponding to the linear structure species distribution data and the distribution sample line;
and acquiring the data distribution grids from a plurality of common grids corresponding to the linear structure species distribution data according to the second occurrence probability of the species.
7. The method of claim 4, wherein the multi-source heterogeneous species distribution data comprises planar structure species distribution data of the target species;
the step of obtaining the buffer area of the species distribution data of various data structures according to the multi-source heterogeneous species distribution data and preset buffer data comprises the following steps:
Acquiring a distribution range of the species distribution data of the planar structure, and determining the distribution range as the buffer area;
the step of acquiring the data distribution grid of the species distribution data of the various data structures from the common grid according to the preset data distribution grid acquisition method corresponding to the species distribution data of the various data structures comprises the following steps:
and acquiring the data distribution grids from the common grids corresponding to the species distribution data of the planar structure.
8. A multi-source heterogeneous species distribution data fusion device, comprising:
the multi-source heterogeneous species distribution data acquisition module is used for acquiring multi-source heterogeneous species distribution data of a target species, wherein the multi-source heterogeneous species distribution data comprise species distribution data of at least three data structures;
the data distribution grid acquisition module is used for acquiring the data distribution grids of the species distribution data of the target species in various data structures from the multi-source heterogeneous species distribution data according to the ecological environment data, the altitude data and the climate data of the target species suitable for survival;
the distributed data weight acquisition module is used for acquiring the distributed data weights of the species distribution data of various data structures according to the species distribution data of the target species in various data structures and the data source information of the species distribution data of various data structures;
And the data fusion module is used for carrying out data fusion on the data distribution grids of the species distribution data of the various data structures according to the distribution data weight of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and the probability that the target species appears in each fusion data distribution grid.
9. The multi-source heterogeneous species distribution data fusion device of claim 8, wherein the data source information includes auditor information, time information, and publishing information;
the distributed data weight acquisition module comprises:
the first score acquisition module is used for acquiring first scores of species distribution data of various data structures and first highest scores corresponding to the species number information according to the species number information recorded by the species distribution data of the various data structures;
the second score acquisition module is used for acquiring second scores of species distribution data of various data structures and second highest scores corresponding to the auditor information according to the auditor information;
the third score acquisition module is used for acquiring third scores of species distribution data of various data structures and third highest scores corresponding to the time information according to the time information;
A fourth score obtaining module, configured to obtain a fourth score of species distribution data of various data structures and a fourth highest score corresponding to the publishing information according to the publishing information;
and the data weight acquisition module is used for acquiring the distribution data weights of the species distribution data of various data structures according to the first score, the second score, the third score, the fourth score, the first highest score, the second highest score, the third highest score and the fourth highest score.
10. The multi-source heterogeneous species distribution data fusion device of claim 8, wherein the data fusion module comprises:
according to the distribution data weight of the species distribution data of various data structures, carrying out data fusion on the data distribution grids of the species distribution data of the various data structures to obtain a plurality of fusion data distribution grids and fusion values of each fusion data distribution grid;
and obtaining the probability that the target species appears in each fusion data distribution grid according to the highest fusion value and the fusion value of each fusion data distribution grid.
CN202310544496.8A 2023-05-16 2023-05-16 Multi-source heterogeneous species distribution data fusion method and device Active CN116304991B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310544496.8A CN116304991B (en) 2023-05-16 2023-05-16 Multi-source heterogeneous species distribution data fusion method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310544496.8A CN116304991B (en) 2023-05-16 2023-05-16 Multi-source heterogeneous species distribution data fusion method and device

Publications (2)

Publication Number Publication Date
CN116304991A true CN116304991A (en) 2023-06-23
CN116304991B CN116304991B (en) 2023-08-08

Family

ID=86803472

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310544496.8A Active CN116304991B (en) 2023-05-16 2023-05-16 Multi-source heterogeneous species distribution data fusion method and device

Country Status (1)

Country Link
CN (1) CN116304991B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103413017A (en) * 2013-05-16 2013-11-27 北京师范大学 Endangered wildlife habitat suitability distinguishing method based on GIS
CN106156756A (en) * 2016-07-28 2016-11-23 广州地理研究所 The Method of fast estimating of construction land efficiency spatial distribution
CN106844688A (en) * 2017-01-23 2017-06-13 环境保护部南京环境科学研究所 The plant habitat analyzed based on space overlapping and GAP protects red line demarcation method
CN111125285A (en) * 2019-12-25 2020-05-08 南京大学 Animal geographic zoning method based on species spatial distribution relation
CN111489092A (en) * 2020-04-15 2020-08-04 云南户外图科技有限公司 Method and system for evaluating suitable growing area of plant cultivation and planting environment
CN112434814A (en) * 2020-12-07 2021-03-02 中国人民解放军国防科技大学 Method for analyzing shipping economic potential based on multi-source heterogeneous information fusion algorithm
CN113220810A (en) * 2021-04-16 2021-08-06 昆明理工大学 Multi-source species distribution data processing method and device
US20210248370A1 (en) * 2020-02-11 2021-08-12 Hangzhou Glority Software Limited Method and system for diagnosing plant disease and insect pest
CN113610070A (en) * 2021-10-11 2021-11-05 中国地质环境监测院(自然资源部地质灾害技术指导中心) Landslide disaster identification method based on multi-source data fusion
CN115099315A (en) * 2022-06-10 2022-09-23 西安建筑科技大学 Multi-source heterogeneous geographic information data semantic fusion conversion method based on CityGML
CN115344657A (en) * 2022-08-23 2022-11-15 杭州睿胜软件有限公司 Species distribution data aggregation method, system and storage medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103413017A (en) * 2013-05-16 2013-11-27 北京师范大学 Endangered wildlife habitat suitability distinguishing method based on GIS
CN106156756A (en) * 2016-07-28 2016-11-23 广州地理研究所 The Method of fast estimating of construction land efficiency spatial distribution
CN106844688A (en) * 2017-01-23 2017-06-13 环境保护部南京环境科学研究所 The plant habitat analyzed based on space overlapping and GAP protects red line demarcation method
CN111125285A (en) * 2019-12-25 2020-05-08 南京大学 Animal geographic zoning method based on species spatial distribution relation
US20210248370A1 (en) * 2020-02-11 2021-08-12 Hangzhou Glority Software Limited Method and system for diagnosing plant disease and insect pest
CN111489092A (en) * 2020-04-15 2020-08-04 云南户外图科技有限公司 Method and system for evaluating suitable growing area of plant cultivation and planting environment
CN112434814A (en) * 2020-12-07 2021-03-02 中国人民解放军国防科技大学 Method for analyzing shipping economic potential based on multi-source heterogeneous information fusion algorithm
CN113220810A (en) * 2021-04-16 2021-08-06 昆明理工大学 Multi-source species distribution data processing method and device
CN113610070A (en) * 2021-10-11 2021-11-05 中国地质环境监测院(自然资源部地质灾害技术指导中心) Landslide disaster identification method based on multi-source data fusion
CN115099315A (en) * 2022-06-10 2022-09-23 西安建筑科技大学 Multi-source heterogeneous geographic information data semantic fusion conversion method based on CityGML
CN115344657A (en) * 2022-08-23 2022-11-15 杭州睿胜软件有限公司 Species distribution data aggregation method, system and storage medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
SHUTING WANG ET AL.: "The evolution and diversification of oakleaf butterflies", CELL *
李丹艳;任海;王俊;李平衡;吴建平;: "火烧和植造桉林对南亚热带退化草坡土壤种子库的影响", 生态环境学报, no. 01 *
李宗智 等: "白山原麝国家级自然保护区獐春夏生境选择", 生态学报 *

Also Published As

Publication number Publication date
CN116304991B (en) 2023-08-08

Similar Documents

Publication Publication Date Title
Comber et al. A route map for successful applications of geographically weighted regression
Sahin et al. The change detection in coastal settlements using image processing techniques: a case study of Korfez
Archer et al. Comparing TanDEM‐X data with frequently used DEMs for flood inundation modeling
KR102399089B1 (en) A system and method for flood damage detection using satellite image information
CN112861732B (en) Method, system and device for monitoring land in ecological environment fragile area
Congalton Assessing positional and thematic accuracies of maps generated from remotely sensed data
CN116304991B (en) Multi-source heterogeneous species distribution data fusion method and device
Dai et al. Assessment of karst rocky desertification from the local to regional scale based on unmanned aerial vehicle images: A case‐study of Shilin County, Yunnan Province, China
CN117314178A (en) Ecological security pattern construction method, device, equipment and storage medium
CN110472559B (en) Remote sensing image building area land utilization attribute space migration method
CN111412925B (en) POI position error correction method and device
Ciutea et al. Thermal inversions identification through the analysis of the vegetation inversions occurred in the forest ecosystems from the Eastern Carpathians
Ottichilo et al. Map updating using high resolution satelite imagery a case of the Kingdom of Swaziland
Cho et al. Construction of Spatiotemporal Big Data Using Environmental Impact Assessment Information
Howlin et al. Monitoring Black-Tailed Prairie Dogs in Colorado with the 2015 NAIP Imagery
Gujrathi et al. Improving the classification of Land use Objects using Dense Connectitvity of Convolutional Neural Networks
CN113591668B (en) Wide area unknown dam automatic detection method using deep learning and space analysis
Wu et al. Investigator accuracy: A center-weighted metric for evaluating the location accuracy of image segments in land cover classification
Hemakumara et al. Field verifications of the arc gis based automation landform model including the recommendations to enhance the automation system with ground reality
Anita et al. OIL PATTERN IDENTIFICATION ANALYSIS USING SEMANTIC DEEP LEARNING METHOD FROM PLEIADES-1B SATELIITE IMAGERY WITH ARCGIS PRO SOFTWARE (Case Study: Village “A”)
Divya et al. Assessing the spatial patterns of geotagged MGNREGA assets
CN117423013B (en) Ore potential prediction method based on geological big data
Gadakh et al. Land resource impact indicators of urban sprawl: A case study of Nashik city, Maharashtra
Fadillah et al. The Analysis of Angin Puting Beliung Risk Rate by Utilization of Remote Sensing and Geographic Information Systems in Semarang
Salama et al. A Computer Vision Approach for Detecting Discrepancies in Map Textual Labels

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