CN113807409A - Coastal zone classification method based on discriminant analysis - Google Patents
Coastal zone classification method based on discriminant analysis Download PDFInfo
- Publication number
- CN113807409A CN113807409A CN202110992630.1A CN202110992630A CN113807409A CN 113807409 A CN113807409 A CN 113807409A CN 202110992630 A CN202110992630 A CN 202110992630A CN 113807409 A CN113807409 A CN 113807409A
- Authority
- CN
- China
- Prior art keywords
- classification
- climate
- coastal zone
- data
- coastal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000012795 verification Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000007619 statistical method Methods 0.000 claims abstract description 6
- 230000003993 interaction Effects 0.000 claims description 24
- 230000008859 change Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000011002 quantification Methods 0.000 abstract description 2
- 239000010410 layer Substances 0.000 description 15
- 238000012545 processing Methods 0.000 description 9
- 238000011160 research Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 230000001808 coupling effect Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 239000013535 sea water Substances 0.000 description 2
- 239000002344 surface layer Substances 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 235000014653 Carica parviflora Nutrition 0.000 description 1
- 241000243321 Cnidaria Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 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
-
- 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 invention discloses a coastal zone classification method based on discriminant analysis, belonging to the technical field of meteorological information. Carrying out discriminant classification on the selected coastal zone characteristic climate factors by using a multivariate statistical analysis method, adopting the climate factors with coastal zone sea-land characteristic information as classification objects, and dynamically quantifying the coastal zone classification by using historical period and future predicted climate factor information; the coastal zone classification under different precision conditions is obtained by referring to the climate factors with different precisions, the technical problems that the precision and the accuracy are low, the quantification is difficult and the like in the existing coastal zone classification process are solved, and the classification result with high precision and good accuracy can be obtained. Meanwhile, the classification comprehensiveness of the coastal zone is improved, and the uncertainty risk in the classification process is reduced; after data are extracted, after a multivariate statistical relationship is established on the trained data, a classification result with a prejudgment rate of less than 5% is obtained, and the obtained classification is credible. The verification result has higher accuracy and lower false judgment rate.
Description
Technical Field
The invention belongs to the technical field of meteorological information, and particularly relates to a coastal zone classification method based on discriminant analysis.
Background
The coastal zone generally refers to a zone in which the edge of the sea extends to a certain range of the land, and the surface layers of the earth, sea, gas and growth circles interact in the range to generate a coupling effect. It is broadly defined as the intertidal zone affected by the tidal fluctuation of sea water every day and the land-sea transition zone of a certain range of land and shallow sea continent racks on both sides thereof. Since the region is deeply influenced by climate change and human activities, the coastal zone region has high dynamics, complexity and diversity. Meanwhile, the coastal zone is also a special ecological system with high productivity and high economic value.
The first step in the investigation of the changes in the influence of the coastal zone area is the isolation of this particular area from land and sea systems. However, during the development of the coastal zone, factors such as waves, tides, crustal movement, rock properties, sea-entering rivers, and intertidal zone organisms all affect the formation and development of the coastal zone. In this regard, a relatively comprehensive classification result cannot be obtained by using a single factor to classify the coastal zone. Due to complex terrain and confusion of land features, the extraction of relevant features of the coastal zone is difficult, and the quantitative, specific and accurate classification of the coastal zone is also difficult to a certain extent. The existing coastal zone classification technology is mainly based on experience, field investigation classification and a remote sensing data and image classification system. The traditional classification method mainly judges the approximate range of intertidal zone, continental shelf and continental part according to experience judgment and field investigation. In 6 months of 2001, the ' thousand years ecosystem assessment project ' defines a coastal zone as an ' interface between ocean and land, extends to the middle of a continental shelf towards the ocean and comprises all areas affected by ocean factors in the continental direction; specifically, the area is located between 50 meters of average sea depth and 50 meters above a tide line, or the low land extends from the coast to the continent within 100 kilometers, and comprises coral reefs, areas between high tide lines and low tide lines, estuaries, coastal aquatic product operation areas and aquatic weed communities'. In addition, in the field of comprehensive coastal zone management, the definition of the coastal zone needs to be determined according to the management purpose and the research need. The method is fuzzy in classification, is based on experience and field visit, does not quantitatively classify the coastal zone, and is difficult to guarantee accuracy. On the other hand, in the current coastal zone classification technology based on remote sensing data and images, land utilization raster data and vector data are adopted, so that the coastal zones can be classified according to different land utilization categories. Classification is generally made according to land resource utilization purposes. The method can divide the coastal zone into very detailed land types, but only static classification can be obtained, and meanwhile, the considered classification factors are not complete, no climate factor and index exist, dynamic, comprehensive and coupled classification can not be carried out under the climate change background, and the precision and accuracy in the classification process of the coastal zone are low and difficult to quantify; therefore, the precision and accuracy of the obtained classification result need to be further improved.
In addition, in the field of comprehensive coastal zone management, the definition of the comprehensive coastal zone needs to be determined according to the management purpose and research needs. The classification of the method is fuzzy, is based on experience and field visit, does not classify the coastal zone in a quantitative way, and simultaneously, the accuracy is difficult to ensure. In addition, the existing coastal zone classification technology based on remote sensing data and images adopts land utilization raster data and vector data, so that the coastal zones can be classified according to different land utilization categories. Classification is generally made according to land resource utilization purposes. This method can classify the coastal zone into very detailed land types, but classification is performed from the viewpoint of human development and utilization, and classification of the coastal zone category is not performed according to natural features inherent to the coastal zone. Meanwhile, the climate change causes significant changes in sea level, waves, storm surge, rainfall and other sea-related factors. The classification of the coastal zones can be made more comprehensive from a climatic factor point of view, and it is considered feasible to apply such classification to the sea itself and the changes of the sea-land interaction system in the context of future climate change. However, the coastal dynamic classification related to climate change has not been researched yet.
Disclosure of Invention
The invention aims to provide a coastal zone classification method based on discriminant analysis, which is characterized in that a multivariate statistical analysis method is used for discriminant analysis to perform discriminant classification on selected characteristic climate factors of the coastal zone, the climate factors with coastal zone sea-land characteristic information are used as classification objects, and historical period and future predicted climate factor information are used for dynamically quantifying the classification of the coastal zone; obtaining the classification of the coastal zones under different precision conditions by referring to the climate factors with different precisions, and obtaining a classification result with high precision and good accuracy; the method specifically comprises the following steps:
step 1, acquiring global climate model data in a typical continental climate target area and a marine climate target area, and dynamically dividing the selected area into a marine area, a land area and a coastal zone area according to climate factors;
step 2, global climate model data with distances of 200 kilometers from the left side and the right side of a coastline in a coastal zone interaction area are obtained, and climate factors with coastal zone sea-land characteristic information are extracted;
aiming at the grid points in the three selected target areas, dividing the climate factor data in the historical period into training data and verification data;
step 3, setting a discrimination type:
the judgment type I is set as a reference line of continental classification aiming at global climate model data in a typical continental climate target area;
the type II is judged, and a datum line for ocean category classification is set for global climate model data in a typical marine climate target area;
the type III is judged, and a datum line for classification of the coastal zone interaction area is set according to global climate model data in the coastal zone interaction target area;
step 4, establishing a multivariate statistical relationship by using the three types of climate factor training data through training, and performing a process of establishing a discriminant relationship based on a discriminant analysis method to obtain a discriminant function; verifying the actual position in the history period by using verification data, and calculating the misjudgment rate; the verification result has high accuracy and low false judgment rate;
step 5, regarding the climate factor data in the coastal zone interaction target area, taking the data of fifty years in the future as input quantity, and classifying the type of the area in the corresponding period in the future by judging the statistical relationship, namely the land type, the sea type or the coastal zone interaction type;
step 6, aiming at the performance of climate factor data in the coastal zone interaction target area under different time scale conditions, the method also comprises the steps of adopting the same spatial resolution, selecting data of different time step lengths of years, decades and fifty years from the climate factor data in the selected area, obtaining a plurality of sets of climate factor data of time scales of the area, and judging whether the category of the target area has obvious change under different time scales;
step 7, providing a method for preprocessing data aiming at climate factor data in the coastal zone interaction target area, wherein the method further comprises the following steps of (1) selecting at least three global climate models containing selected parameter data: the same spatial resolution and the same geographic and meteorological parameter data are adopted; (2) and after selecting a model with better simulation performance in the selected area, inputting the result obtained by ensemble prediction into a discrimination statistical relationship to obtain an ensemble classification result.
The extracted climate factor data is consistent with the climate factor data selected by the coastal zone;
the first judgment type is a datum line for continental classification, the second judgment type is a datum line for ocean classification, and the third judgment type is a datum line for coastal zone interaction area classification.
The climate factor of the coastal zone sea-land characteristic information comprises a boundary height layer and evapotranspiration;
the prediction of the historical period can be used for verifying the classification result and can also be used for comparing with the future classification result; through the change of the correlation factor related to the climate, the historical and future change trends of the coastal zone types can be observed.
The method has the advantages that the method utilizes a statistical method to visually classify the climatic factors with the sea-land characteristic information of the coastal zone in history and future periods, and does not need to carry out fuzzy classification by field visit or depending on experience; the coastal zones are dynamically divided, so that the technical problems that the precision and the accuracy are low, the quantification is difficult and the like in the existing coastal zone classification process are solved, meanwhile, the comprehensive property of the coastal zone classification is improved, and the uncertainty risk in the classification process is reduced; after data are extracted, after a multivariate statistical relationship is established on the trained data, a classification result with a prejudgment rate of less than 5% is obtained, and the obtained classification is credible. The verification result has higher accuracy and lower false judgment rate.
Drawings
FIG. 1 is a schematic flow chart of classification of coastal zones based on discriminant analysis.
FIG. 2 is a flow chart of a classification method of a coastal zone based on discriminant analysis.
FIG. 3 is a flow chart of a classification method of a coastal zone based on discriminant analysis.
Detailed Description
The invention provides a coastal zone classification method based on discriminant analysis, which is characterized in that a multivariate statistical analysis method is used for discriminant analysis to perform discriminant classification on selected coastal zone characteristic climate factors, the climate factors with coastal zone sea-land characteristic information are used as classification objects, and historical period and future predicted climate factor information are used for dynamically quantifying the classification of coastal zones; and obtaining the classification of the coastal zones under different precision conditions by referring to the climate factors with different precisions, and obtaining a classification result with high precision and good accuracy. The invention is explained below with reference to the drawings and examples.
The coastal zone generally refers to a zone in which the edge of the sea extends to a certain range of the land, and the surface layers of the earth, sea, gas and growth circles interact in the range to generate a coupling effect. The wide range is defined as the intertidal zone affected by the tide and the sea water, and the sea-land transition zone of the land and the shallow sea continent frame with a certain range on both sides of the intertidal zone, the width can reach dozens of meters to dozens of kilometers, and the wide range is generally divided into an upper zone, a middle zone (intertidal zone) and a lower zone. The region can be divided into five parts of coast, seashore, inner shore, outer shore and near shore. In addition, human activities are most concentrated in coastal zones due to their superior natural conditions. The length of the coastline around the world is about 44 kilometers, about two-third of large cities with more than 250 million people around the world are located near the coastline, and more than half of the population lives within 60 kilometers of the coastline. The region is therefore heavily influenced by human activities and the accompanying climate change. The research on the interaction, the cooperation and the coupling in coastal zone areas is of great significance for the comprehensive understanding of the influence of climate change and the sustainable development of human economy and society. The present invention will be described in detail below with reference to the accompanying drawings and examples.
FIG. 1 is a schematic flow chart of discriminant analysis of coastal zone classification. The method shown in fig. 1 specifically includes:
according to a certain spatial geographical distribution characteristic, acquiring global climate model data related to a coastal zone in a target area (within 200 kilometers from a coastline) of a typical continental climate target area, a typical marine climate target area and a coastal zone interaction area, wherein the global climate model data comprises climate factors with coastal zone sea-land characteristic information, typical land climate data and typical marine climate data;
the global climate model data comprises longitude, latitude, elevation, potential altitude, longitude wind, latitude wind, atmospheric boundary layer altitude, evapotranspiration and the like, and the parameters selected by the three types of areas are the same.
Specifically, the acquired data is month scale data. It should be understood that, in the present embodiment, the atmospheric boundary layer height data is taken as the month scale data without being specifically described.
And classifying the obtained two kinds of data after time sequencing, wherein the former part is used as training data, and the other part is used as verification data.
Specifically, the extracted height data of the atmospheric boundary layer is divided into training data according to 15-20 years of data, and 10-15 years of data are used as verification data for classification; the training data is used for establishing a model relation, and the verification data is used for verifying whether the established discriminant relation is reliable or not.
Alternatively, the length of time for which the data is classified may be case specific, with the general training data spanning longer than the validation data.
Atmospheric boundary layer height data within a typical continental climate target area is classified as discrimination type one. Accordingly, classifying the atmospheric boundary layer height data in the typical marine climate target area as discrimination type two; and classifying the atmospheric boundary layer height data in the coastal zone interaction target area into a discrimination type III.
Specifically, the first discrimination type is a reference line for continental classification, the second discrimination type is a reference line for ocean classification, and the third discrimination type is a reference line for coastal zone interaction area classification.
Discriminant Analysis (Discriminant Analysis) is a multivariate statistical Analysis method for discriminating the type assignment problem of a certain research object according to various feature values of the research object under the condition of classification determination. The method establishes a discrimination function according to a certain discrimination criterion, judges which category the sample belongs to and calculates the misjudgment rate.
The correlation distribution P (X | y ═ k) of the commonly used linear discriminant analysis model for each class k can be obtained by bayesian theorem:
wherein: k is a category to be determined, X is a known category, l is a category obtained by dividing X into l categories, P (X) is a probability of occurrence of the known category, P (X | y ═ k) is a probability of occurrence of X under a condition where k occurs, and P (X | y ═ 1) is a probability of occurrence of X under a condition where l occurs.
In the discrimination process, the samples are classified into class k, which maximizes the conditional probability. That is, for linear discriminant analysis, P (X | y ═ k) is modeled as a density multivariate gaussian distribution:
wherein: k is class, μ is mean variance, and d is dimension.
Classifying the climate factor training data of the three categories based on a discriminant analysis method to find multivariate statistical relationship verification data between the height of the atmospheric boundary layer and the three categories; and the actual position in the historical period is verified, and a misjudgment rate system is calculated.
Specifically, the sample regions are classified according to three categories known so far, and are classified into a land type, a sea type, and a coastal zone interaction type.
Aiming at the climate factor data in the coastal zone interaction target area, the data of the fifty years in the future is used as the input quantity, and the category of the area in the corresponding time period in the future, namely the land type, the sea type or the coastal zone interaction type, is obtained through the established distinguishing statistical relationship.
Specifically, future prediction data of a global climate model is selected, and research on future land type changes of coastal zone areas is conducted on the basis of well-established statistical relationships.
Fig. 2 is a flow chart of the classification method of the coastal zone based on discriminant analysis. In this embodiment, based on the embodiment described in fig. 1, the simulation operation based on different time scales is explained in detail; as shown in fig. 2, the average method was used to obtain data on a longer time scale (years, decades, fifty years, etc.) and to perform discriminant analysis.
The average value method is used for processing the height data of the atmospheric boundary layer of the target area to obtain data of different time scales including year, decade, fifty years and the like, and comprises the following steps:
generally, monthly scale data of atmospheric boundary layer height is acquired. And processing the data by adopting an average value method based on the same spatial resolution to obtain a plurality of time scale atmospheric boundary layer height data of the target area.
Specifically, taking the example of processing the month scale data into the year scale data, the weighted average of all month data points in the current year needs to be calculated as the year average data of the current year. The annual average data obtained by the average value method represent the average level of the atmospheric boundary layer height in the year and can reflect the general rule under the annual scale.
Optionally, when atmospheric boundary layer height data within the target region is processed into a ten-year, fifty-year scale, etc., the rationale for the processing is consistent with a monthly scale processing into a yearly scale. Average value method can be used to obtain average value data, and general rules of ten-year scale, century scale and the like can be obtained through analysis.
The remaining steps in this embodiment are the same as those in the embodiment of fig. 1, and are not described herein again.
The embodiment provides a method for processing raw data under different time scales. The average value method can be used for obtaining the average value data of the height of the atmospheric boundary layer, which is used for representing the corresponding boundary height layer data under each certain time scale and can be used for researching general rules. The embodiment provides a method for processing the original data into other multiple time scales on the basis of the method, and provides a reliable idea for researching the coastal zone type change under different time scales.
Fig. 3 is a flow chart of the classification method of the coastal zone based on discriminant analysis. Based on the embodiment shown in fig. 1, at least three (and more) global climate models including the selected parameter data are selected, a future coastal zone classification change research is performed, and the results of global climate model ensemble prediction are used to obtain more reliable and real classifications. The classification result after ensemble prediction processing adopted by the embodiment is more real and credible.
Specifically, in this embodiment, the HadCM3 developed by Hadley center of the british weather service, the national oceanic and atmospheric administration GFDL-CM2.1, and the north american multi-model ensemble prediction dataset CanCM4 are taken as examples. Geographic and meteorological parameter data of the target region in the historical period (1980-2020) and the future period (2021-2099) of each model are extracted, ensemble forecasting processing is carried out, and the obtained result is used as an input value of the multivariate statistical relationship obtained through discriminant analysis to obtain a classification result.
Alternatively, the method of ensemble forecasting may be selected from, but is not limited to, any of the following methods: monte Carlo Method (MCF), Singular vector methods (SVs), Conditional nonlinear optimal perturbation method (CNOP), averaging method, and the like. Preferably, the present invention is not based on the development of ensemble forecasting method, and because it is simple and fast, and can obtain better results, the present embodiment uses the mean value method for ensemble forecasting, and further description of other methods is omitted.
The remaining steps in this embodiment are the same as those in the embodiment of fig. 1, and are not described herein again.
The present embodiment provides a method of data post-processing. At least three sets of data which are good in performance and contain the same parameters are selected for the target area, and comprehensive classification results are obtained after ensemble prediction analysis. The embodiment improves the prediction accuracy and reduces the uncertainty on the basis of the method, and meanwhile, a classification result with high precision and good accuracy can be obtained for a thought of data post-processing.
Claims (5)
1. A classification method of a coastal zone based on discriminant analysis is characterized in that a multivariate statistical analysis method is used for discriminant analysis to perform discriminant classification on selected characteristic climate factors of the coastal zone, the climate factors with coastal zone sea-land characteristic information are used as classification objects, and historical period and future predicted climate factor information are used for dynamically quantifying classification of the coastal zone; obtaining classification of the coastal zones under different precision conditions by referring to climate factors with different precisions, and obtaining a classification result with high precision and good accuracy; the method specifically comprises the following steps:
step 1, acquiring global climate model data in a typical continental climate target area and a marine climate target area, and dynamically dividing the selected area into a marine area, a land area and a coastal zone area according to climate factors;
step 2, global climate model data with distances of 200 kilometers from the left side and the right side of a coastline in a coastal zone interaction area are obtained, and climate factors with coastal zone sea-land characteristic information are extracted;
aiming at the grid points in the three selected target areas, dividing the climate factor data in the historical period into two parts, namely training data and verification data;
step 3, setting a discrimination type:
the judgment type I is set as a reference line of continental classification aiming at global climate model data in a typical continental climate target area;
the type II is judged, and a reference line for ocean category classification is set for global climate model data in a typical ocean climate target area;
the type III is judged, and a datum line for classification of the coastal zone interaction area is set according to global climate model data in the coastal zone interaction target area;
step 4, establishing a multivariate statistical relationship by using the three types of climate factor training data through training, and performing a process of establishing a discriminant relationship based on a discriminant analysis method to obtain a discriminant function; verifying the actual position in the historical period by using verification data, and calculating the misjudgment rate; the verification result has high accuracy and low false judgment rate;
step 5, regarding the climate factor data in the coastal zone interaction target area, taking the data of fifty years in the future as input quantity, and classifying the type of the area in the corresponding period in the future by judging the statistical relationship, namely the land type, the sea type or the coastal zone interaction type;
step 6, aiming at the performance of climate factor data in the coastal zone interaction target area under different time scale conditions, the method also comprises the steps of adopting the same spatial resolution, selecting data of different time step lengths of years, decades and fifty years from the climate factor data in the selected area, obtaining multiple sets of climate factor data of the area in time scale, and judging whether the category of the target area has obvious change under different time scale;
step 7, providing a method for preprocessing data aiming at climate factor data in the coastal zone interaction target area, wherein the method further comprises the following steps of (1) selecting at least three global climate models containing selected parameter data: the same spatial resolution and the same geographic and meteorological parameter data are adopted; (2) and after selecting a model with better simulation performance in the selected area, inputting the result obtained by ensemble prediction into a discrimination statistical relationship to obtain an ensemble classification result.
2. The coastal zone classification method based on discriminant analysis according to claim 1, wherein the extracted climate factor data is consistent with the selected coastal zone category.
3. The coastal zone classification method based on discriminant analysis as claimed in claim 1, wherein the first discriminant type is a reference line for continental classification, the second discriminant type is a reference line for ocean classification, and the third discriminant type is a reference line for coastal zone interaction area classification.
4. The coastal zone classification method based on discriminant analysis according to claim 1, wherein the climate factor of the coastal zone sea-land feature information includes boundary height layer, evapotranspiration.
5. The coastal zone classification method based on discriminant analysis as claimed in claim 1, wherein the prediction of the historical period can be used to verify the classification result and compare with the future classification result; through the change of the correlation factor related to the climate, the historical and future change trends of the coastal zone types can be observed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110992630.1A CN113807409B (en) | 2021-08-27 | 2021-08-27 | Coastal zone classification method based on discriminant analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110992630.1A CN113807409B (en) | 2021-08-27 | 2021-08-27 | Coastal zone classification method based on discriminant analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807409A true CN113807409A (en) | 2021-12-17 |
| CN113807409B CN113807409B (en) | 2024-01-23 |
Family
ID=78941921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110992630.1A Active CN113807409B (en) | 2021-08-27 | 2021-08-27 | Coastal zone classification method based on discriminant analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807409B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999001843A1 (en) * | 1997-07-01 | 1999-01-14 | Applied Spectral Imaging Ltd. | Method for remote sensing analysis by decorrelation statistical analysis and hardware therefor |
| CN110991393A (en) * | 2019-12-17 | 2020-04-10 | 北京航天泰坦科技股份有限公司 | Method and device for remote sensing monitoring and analysis of coastline transition |
| CN112418506A (en) * | 2020-11-18 | 2021-02-26 | 厦门大学 | Coastal zone wetland ecological safety pattern optimization method and device based on machine learning |
| CN112579885A (en) * | 2020-11-27 | 2021-03-30 | 国家海洋环境预报中心 | Ocean forecast information service method based on user interest points and storage medium |
-
2021
- 2021-08-27 CN CN202110992630.1A patent/CN113807409B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999001843A1 (en) * | 1997-07-01 | 1999-01-14 | Applied Spectral Imaging Ltd. | Method for remote sensing analysis by decorrelation statistical analysis and hardware therefor |
| CN110991393A (en) * | 2019-12-17 | 2020-04-10 | 北京航天泰坦科技股份有限公司 | Method and device for remote sensing monitoring and analysis of coastline transition |
| CN112418506A (en) * | 2020-11-18 | 2021-02-26 | 厦门大学 | Coastal zone wetland ecological safety pattern optimization method and device based on machine learning |
| CN112579885A (en) * | 2020-11-27 | 2021-03-30 | 国家海洋环境预报中心 | Ocean forecast information service method based on user interest points and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| CHARLES W. FINKL; CHRISTOPHER MAKOWSKI: "Coastal Belt Linked Classification (CBLC): A System for Characterizing the Interface between Land and Sea Based on Large Marine Ecosystems, Coastal Ecological Sequences, and Terrestrial Ecoregions", JOURNAL OF COASTAL RESEARCH, vol. 36, no. 4 * |
| JUNHONG GUO, GUOHE HUANG, XIUQUAN WANG, YONGPING LI, QIANGUO LIN: "Investigating future precipitation changes over China through a high-resolution regional climate model ensemble", Retrieved from the Internet <URL:https://agupubs.onlinelibrary.wiley.com/doi/10.1002/2016EF000433> * |
| 黄博强: "陆海统筹视角下福建省海岸带土地利用变化过程与环境效应研究", 中国学位论文全文数据库 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807409B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ibbeken et al. | Source and sediment: a case study of provenance and mass balance at an active plate margin (Calabria, Southern Italy) | |
| Hengl et al. | Supervised Landform Classification to Enhance and Replace Photo‐Interpretation in Semi‐Detailed Soil Survey | |
| Zhao et al. | Mapping large-area tidal flats without the dependence on tidal elevations: A case study of Southern China | |
| Ojala et al. | Development of an ancient shoreline database to reconstruct the Litorina Sea maximum extension and the highest shoreline of the Baltic Sea basin in Finland. | |
| CN112800634B (en) | Rainfall estimation method and system coupling dry-wet state identification and multi-source information fusion | |
| Solaiman et al. | Development of probability based intensity-duration-frequency curves under climate change | |
| Gudmundsson et al. | Observation-based gridded runoff estimates for Europe (E-RUN version 1.1) | |
| Suprit et al. | Resolving orographic rainfall on the Indian west coast | |
| Kim et al. | Scale-dependent predictability of DEM-based landform attributes for soil spatial variability in a coastal dune system | |
| Friedland et al. | Isotropic and anisotropic kriging approaches for interpolating surface-level wind speeds across large, geographically diverse regions | |
| Kim et al. | Groundwater productivity potential mapping using frequency ratio and evidential belief function and artificial neural network models: focus on topographic factors | |
| Bharath et al. | Regionalization of extreme rainfall in India | |
| CN112381033A (en) | Satellite remote sensing quantitative evaluation method for intertidal zone erosion and deposition conditions caused by offshore wind turbine | |
| CN114254802B (en) | Prediction method for vegetation coverage space-time change under climate change drive | |
| Martínez et al. | Atlas of surface currents in the Mediterranean and Canary–Iberian–Biscay waters | |
| Ghanavati et al. | An assessment of whether long-term global changes in waves and storm surges have impacted global coastlines | |
| Athanasiou et al. | Global Coastal Characteristics (GCC): A global dataset of geophysical, hydrodynamic, and socioeconomic coastal indicators | |
| Carlón Allende et al. | Hydrogeographical regionalisation: An approach for evaluating the effects of land cover change in watersheds. A case study in the Cuitzeo Lake Watershed, Central Mexico | |
| CN109885808B (en) | Near-surface meteorological element calculation method | |
| Correa-Muñoz et al. | Determination of landslide susceptibility in linear infrastructure. Case: aqueduct network in Palacé, Popayan (Colombia) | |
| Corbella et al. | Assimilation of ocean wave spectra and atmospheric circulation patterns to improve wave modelling | |
| CN113807409B (en) | Coastal zone classification method based on discriminant analysis | |
| Ivanova et al. | Application of an integrated methodology for spatial classification of the environmental flow in the Bulgarian-Greek Rhodope Mountain Range | |
| Thakare et al. | Shoreline Change Detection Analysis along the Sindhudurg Coast of India using DSAS Technique | |
| Siervo et al. | Geomorphic analysis and semi-automated landforms extraction in different natural landscapes |
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 |