CN114722967B - Explosive cyclone classification method - Google Patents
Explosive cyclone classification method Download PDFInfo
- Publication number
- CN114722967B CN114722967B CN202210466639.3A CN202210466639A CN114722967B CN 114722967 B CN114722967 B CN 114722967B CN 202210466639 A CN202210466639 A CN 202210466639A CN 114722967 B CN114722967 B CN 114722967B
- Authority
- CN
- China
- Prior art keywords
- cyclone
- explosive
- type
- advection
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002360 explosive Substances 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011161 development Methods 0.000 claims abstract description 19
- 230000007246 mechanism Effects 0.000 claims abstract description 18
- 238000010438 heat treatment Methods 0.000 claims abstract description 12
- JTJMJGYZQZDUJJ-UHFFFAOYSA-N phencyclidine Chemical class C1CCCCN1C1(C=2C=CC=CC=2)CCCCC1 JTJMJGYZQZDUJJ-UHFFFAOYSA-N 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 238000003064 k means clustering Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 49
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000002301 combined effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000005437 stratosphere Substances 0.000 description 1
- 239000005436 troposphere Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Cyclones (AREA)
Abstract
The invention discloses a method for classifying explosive cyclones, which comprises the steps of firstly, identifying and tracking temperate zone cyclones and screening large sample explosive cyclones, secondly, calculating three forcing factors of vortex advection, temperature advection and non-adiabatic heating, thirdly, calculating contribution rates of the three forcing factors of vortex advection, temperature advection and non-adiabatic heating, fourthly, classifying and calculating according to the contribution rates and outputting classification results; the invention calculates the forcing factors and the contribution rates of the forcing factors of each case by using a Zwack-Okossi diagnosis equation based on the identified and tracked large sample explosive cyclone, classifies the development mechanism of the explosive cyclone by using a K-means clustering algorithm, classifies the development mechanism of the explosive cyclone from the view point of physical essence, and provides a new thought for the research of the explosive cyclone.
Description
Technical Field
The invention relates to the technical field of cyclone classification, in particular to a method for classifying explosive cyclones.
Background
The explosive cyclone is an extreme disaster weather frequently occurring in the middle latitude sea area in the cold season, the safety of maritime shipping, fishery production and military operation is seriously threatened, the development mechanism of the explosive cyclone is complex, and various explosive cyclones are carefully researched by classifying the explosive cyclone, so that the method is an effective method for clearing the development mechanism of the explosive cyclone;
the development mechanism of the explosive cyclone is complex, the diagnosis analysis is a research method commonly used in the analysis of the development mechanism of the explosive cyclone, in the diagnosis analysis, the used diagnosis equation mainly comprises an omega equation, a quasi-transposition potential trend equation, a Zwack-Okossi equation and the like, the development mechanism of the explosive cyclone is complex, the effect contributions of forcing factors of different cases have great difference, one case is single forcing factor dominant, the other case is two forcing factors jointly driven, and the other case is the result of the combined effect of a plurality of factors;
the current classification method classifies according to the burst intensity of the explosive cyclone, the focus is on the difference of the central air pressure reduction amplitude, the contribution of the forcing factors of the explosive cyclones with similar burst intensity is also obviously different, and the physical mechanism essential difference of the development of the explosive cyclone is difficult to grasp when classifying according to the burst intensity, so the invention provides a method for classifying the explosive cyclone to solve the problems in the prior art.
Disclosure of Invention
In view of the above, the present invention is directed to a method for classifying explosive cyclones, which classifies the development mechanism of the explosive cyclones by calculation and according to the difference of forcing factors.
In order to achieve the purpose of the invention, the invention is realized by the following technical scheme: a method of explosive cyclone classification comprising the steps of:
analyzing data again by using ERA5, identifying and tracking temperature zone cyclone cases by a cyclone identification method and a cyclone tracking method, and screening large sample explosive cyclones according to the explosive cyclone definition to form a sample set;
step two, calculating three forcing factors of vorticity advection A, temperature advection B and non-adiabatic heating C of each example in a sample set according to a Zwack-Okossi equation by using a finite difference method and ERA5 analysis data;
dividing the three forcing factors in the step two by the sum of A, B, C respectively, namely the vorticity advection A, the temperature advection B and the non-adiabatic heating C, and multiplying the sum by 100% to obtain the contribution rate a of the vorticity advection A, the contribution rate B of the temperature advection B and the contribution rate C of the non-adiabatic heating C, so as to form an input set;
and step four, classifying and calculating a development mechanism of explosive cyclone by using a K-means clustering algorithm and taking an input set as input to obtain a final cyclone classification result.
The further improvement is that: the cyclone identification in the first step requires that the minimum value of the sea level air pressure in the 5 degree by 5 degree area is lower than 1020hPa, and the position of the minimum value is not on the boundary of the 5 degree by 5 degree area; the duration of the identified cyclone life cycle is greater than or equal to 24 hours; the sea level pressure gradient in the 5 degree by 5 degree area is more than or equal to 2hPa; setting the altitude threshold value to 1500m; the 5×5 discrimination area moves throughout the investigation region and overlaps with the previous discrimination area.
The further improvement is that: in the first step, when the cyclone is tracked, the cyclone X exists at the moment t-delta t, the cyclone Y exists at the moment t, the distance between the two is delta d, and then the cyclone is tracked according to a limiting condition, wherein the limiting condition is that delta t is less than or equal to 24 hours; the cyclone Y at time t is the cyclone closest to the cyclone X at time t-deltat; the moving speed delta d/delta t of cyclone X to cyclone Y is less than 40m/s; Δd < Δdmax, where Δdmax is the maximum travel distance over a Δt time period, Δdmax=max (500 km,3×Δt×v), V represents the travel speed of cyclone X over a period of t-2 Δt to t- Δt; the change of the movement direction angle of the cyclone in the period from t-2 delta t to t-delta t to t is within a certain range.
The further improvement is that: in the second step, the Zwack-Okossi equation is calculated, the space difference and the time difference are in a second-order central difference format, the vertical integration is in a trapezoid integration method, the near-ground air pressure layer is 950hPa, and the air pressure of the atmosphere top layer is 100hPa.
The further improvement is that: the specific calculation method in the fourth step is as follows
S1, taking contribution rates a, b and c as input, and defining an explosive cyclone forcing factor contribution rate vector as K n ：(a n ，b n ，c n ) Wherein n represents a sample, and the explosive cyclone development mechanism of the black tide zone is divided into 7 types including type A, type B and type C3 single factor dominant type and type AB, type AC and type BC 3 double factor matched type and type ABC 1 multi factor combined type according to the contribution rate of the forcing factors;
s2, selecting K representative opposite directions as initial clustering centers, presetting 7 types of initial clustering center vectors according to the classification in S1, and marking the initial clustering center vectors as K m ：(a m ，b m ，c m ) Wherein m is as followsA class is shown;
s3, respectively calculating the distance between each object and each cluster center, and distributing the objects to the cluster centers closest to the object according to the principle of closest distance;
s4, calculating average vectors of the contribution rate vectors of the forcing factors, and taking the average vectors as new clustering center vectors;
s5, repeating the steps S3 and S4 to obtain K types after adjustment, stopping computing the output result when the sample classification is completely consistent with the previous classification, and continuing to repeat the steps S3 and S4 when the inconsistency occurs.
The further improvement is that: when the object distribution is performed in the step S3, the forced factor contribution rate vector K of the explosive cyclone sample is calculated n ：(a n ，b n ，c n ) Respectively and initially clustering the central vector K with 7 classes in S2 m ：(a m ，b m ，c m ) Subtracting, calculating the modulus |K of the two vector differences n -K m And the distribution is carried out according to the principle of minimum distance, namely the principle of minimum mode of two-vector difference.
The further improvement is that: and in the step S4, all acquired explosive cyclone samples are sequentially subjected to calculation in the step S3, namely 7 clustering center vectors are used as initial classification, and the average vector of all the contribution rate vectors of the forcing factors is obtained through calculation.
The beneficial effects of the invention are as follows: the invention calculates the forcing factors and the contribution rates of the forcing factors of each case by using a Zwack-Okossi diagnosis equation based on the identified and tracked large sample explosive cyclone, classifies the development mechanism of the explosive cyclone by using a K-means clustering algorithm, classifies the development mechanism of the explosive cyclone from the view point of physical essence, and provides a new thought for the research of the explosive cyclone.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the invention.
FIG. 2 is a flow chart of the classification calculation of the present invention.
Detailed Description
The present invention will be further described in detail with reference to the following examples, which are only for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Examples
According to the present embodiment, as shown in fig. 1 and 2, there is provided a method of explosive cyclone classification, comprising the steps of:
step one, re-analyzing data by using ERA5, identifying and tracking temperature zone cyclone cases by a cyclone identification method and a cyclone tracking method, and screening large sample explosive cyclones according to explosive cyclone definition to form a sample set so as to provide sample support for developing classification of development mechanisms of the sample set;
cyclone identification requires that the minimum value of sea level air pressure in the 5 DEG x 5 DEG zone is below 1020hPa and the location of the minimum value is not on the boundary of the 5 DEG x 5 DEG zone; the duration of the identified cyclone life cycle is greater than or equal to 24 hours; the sea level pressure gradient in the 5 degree by 5 degree area is more than or equal to 2hPa; setting a discrimination area with the altitude threshold value of 1500m,5 degrees multiplied by 5 degrees to move in the whole research area and overlap with the previous discrimination area so as to eliminate the interference of low heat pressure and ensure that the cyclone is positioned in the identification range;
during cyclone tracking, firstly, a cyclone X exists at the moment t-delta t, a cyclone Y exists at the moment t, the distance between the two is delta d, and then the cyclone is tracked according to the limiting condition, wherein the limiting condition is as follows: (1) Δt is 24 hours or less; (2) the cyclone Y at time t is the cyclone closest to the cyclone X at time t-deltat; (3) the moving speed delta d/delta t of cyclone X to cyclone Y is less than 40m/s; (4) Δd < Δdmax, where Δdmax is the maximum travel distance over a Δt time period, Δdmax=max (500 km,3×Δt×v), V represents the travel speed of cyclone X over a period of t-2 Δt to t- Δt; (5) the change of the movement direction angle of the cyclone in the period from t-2 delta t to t-delta t to t is within a certain range.
Step two, calculating three forcing factors of vorticity advection A, temperature advection B and non-adiabatic heating C of each example in a sample set according to a Zwack-Okossi equation by using a finite difference method and ERA5 analysis data;
calculating a space difference and a time difference of the Zwack-Okossi equation, adopting a second-order central difference format, adopting a trapezoid integration method for vertical integration, and selecting 950hPa for a near-ground air pressure layer, wherein the near-ground air pressure layer is an isobaric surface which is closest to the ground and can represent the development of ground cyclone; the atmospheric top pressure was chosen to be 100hPa, which includes the entire troposphere as well as a portion of the stratosphere.
Dividing the three forcing factors of the vorticity advection A, the temperature advection B and the non-adiabatic heating C in the step two by the sum of A, B, C respectively and multiplying by 100% to obtain the contribution rate a of the vorticity advection A, the contribution rate B of the temperature advection B and the contribution rate C of the non-adiabatic heating C, and forming an input set to provide data for cluster analysis.
Step four, classifying and calculating a development mechanism of explosive cyclone by using a K-means clustering algorithm and taking an input set as input to obtain a final cyclone classification result, wherein the specific calculation method is as follows
S1, taking contribution rates a, b and c as input, and defining an explosive cyclone forcing factor contribution rate vector as K n ：(a n ，b n ，c n ) Wherein n represents a sample, and the explosive cyclone development mechanism of the black tide zone is theoretically divided into 7 types including type A, type B and type C3 single factor dominant type and type AB, type AC and type BC 3 double factor matched type and type ABC 1 multi factor combined type according to the contribution rate of the forcing factors;
s2, selecting K representative opposite directions as initial clustering centers, presetting 7 types of initial clustering center vectors according to the classification in S1, and marking the initial clustering center vectors as K m ：(a m ，b m ，c m ) Wherein m represents a category;
setting the initial clustering center vector of single factor leading type A as K A : (1, 0) showing that the contribution rate of the vorticity advection A is 100%, the contribution rate of the temperature advection B and the non-adiabatic heating C are 0%, and similar preset other six types of initial clustering center vectors are respectively: the initial clustering center vector of B type of single factor dominant type is K B : the initial cluster center vectors of (0, 1, 0) and C type are K C : (0, 1); the initial clustering center vector of the AB type of the double-factor matching type is K AB : (0.5,0.5,0) initial clustering center vector of AC type is K AC : (0.5, 0, 0.5) and BC type initial clusteringThe center vector is K BC : (0,0.5,0.5); the initial clustering center vector of the multi-factor combined ABC type is K ABC ：(0.33，0.33，0.33)
S3, respectively calculating the distance between each object and each clustering center, and distributing the objects to the closest clustering centers according to the principle of closest distance, wherein when the objects are distributed, the forced factor contribution rate vector K of the explosive cyclone sample is distributed according to the following formula n ：(a n ，b n ，c n ) Respectively and initially clustering the central vector K with 7 classes in S2 m ：(a m ，b m ，c m ) Subtracting, calculating the modulus |K of the two vector differences n -K m |
Then distributing according to the principle of minimum distance, namely the principle of minimum two-vector difference;
s4, sequentially performing calculation in S3 on all acquired explosive cyclone samples, namely taking 7 clustering center vectors as initial classification, calculating to obtain average vectors of various compulsive factor contribution rate vectors, taking the average vectors as new clustering center vectors, and expressing the average vectors by the following formula
Wherein x is the number of samples of each type after clustering;
s5, repeating the steps S3 and S4 to obtain K types after adjustment, stopping computing the output result when the sample classification is completely consistent with the previous classification, and continuing to repeat the steps S3 and S4 when the inconsistency occurs.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (3)
1. A method of explosive cyclone classification comprising the steps of:
analyzing data again by using ERA5, identifying and tracking temperature zone cyclone cases by a cyclone identification method and a cyclone tracking method, and screening large sample explosive cyclones according to the explosive cyclone definition to form a sample set;
during cyclone tracking, firstly, supposing that a cyclone X exists at the time t-delta t, and a cyclone Y exists at the time t, wherein the distance between the two is delta d, and then, tracking the cyclone according to a limiting condition, wherein the limiting condition is that delta t is less than or equal to 24 hours; the cyclone Y at time t is the cyclone closest to the cyclone X at time t-deltat; the moving speed delta d/delta t of cyclone X to cyclone Y is less than 40m/s; Δd < Δdmax, where Δdmax is the maximum travel distance over a Δt time period, Δdmax=max (500 km,3×Δt×v), V represents the travel speed of cyclone X over a period of t-2 Δt to t- Δt; the change of the movement direction angle of the cyclone in the period from t-2 delta t to t-delta t to t is within a certain range;
step two, calculating three forcing factors of vorticity advection A, temperature advection B and non-adiabatic heating C of each example in a sample set according to a Zwack-Okossi equation by using a finite difference method and ERA5 analysis data;
calculating a space difference and a time difference of a Zwack-Okossi equation, adopting a second-order central difference format, adopting a trapezoid integration method for vertical integration, selecting 950hPa for a near-ground air pressure layer, and selecting 100hPa for an atmospheric top layer;
dividing the three forcing factors in the step two by the sum of A, B, C respectively, namely the vorticity advection A, the temperature advection B and the non-adiabatic heating C, and multiplying the sum by 100% to obtain the contribution rate a of the vorticity advection A, the contribution rate B of the temperature advection B and the contribution rate C of the non-adiabatic heating C, so as to form an input set;
step four, using a K-means clustering algorithm, taking an input set as input data, and carrying out classification calculation on a development mechanism of explosive cyclone to obtain a final cyclone classification result;
the specific calculation method is as follows:
s1, taking contribution rates a, b and c as input, and defining an explosive cyclone forcing factor contribution rate vector as K n ：(a n ，b n ，c n ) Wherein n represents a sample, and the explosive cyclone development mechanism of the black tide zone is divided into 7 types including type A, type B and type C3 single factor dominant type and type AB, type AC and type BC 3 double factor matched type and type ABC 1 multi factor combined type according to the contribution rate of the forcing factors;
s2, selecting K representative opposite directions as initial clustering centers, presetting 7 types of initial clustering center vectors according to the classification in S1, and marking the initial clustering center vectors as K m ：(a m ，b m ，c m ) Wherein m represents a category;
s3, respectively calculating the distance between each object and each cluster center, and distributing the objects to the cluster centers closest to the object according to the principle of closest distance;
in the process of object distribution, the forced factor contribution rate vector K of explosive cyclone samples n ：(a n ，b n ，c n ) Respectively and initially clustering the central vector K with 7 classes in S2 m ：(a m ，b m ，c m ) Subtracting, calculating the modulus |K of the two vector differences n -K m The I is distributed according to the principle of the nearest distance, namely the principle of the minimum of the modes of the two-vector difference;
s4, calculating average vectors of the contribution rate vectors of the forcing factors, and taking the average vectors as new clustering center vectors;
s5, repeating the steps S3 and S4 to obtain K types after adjustment, stopping operation and outputting a result when the sample classification is completely consistent with the previous classification, and continuing to repeat the steps S3 and S4 when inconsistency occurs.
2. A method of explosive cyclone classification according to claim 1, wherein: the cyclone identification in the first step requires that the minimum value of the sea level air pressure in the 5 degree by 5 degree area is lower than 1020hPa, and the position of the minimum value is not on the boundary of the 5 degree by 5 degree area; the duration of the identified cyclone life cycle is greater than or equal to 24 hours; the sea level pressure gradient in the 5 degree by 5 degree area is more than or equal to 2hPa; setting the altitude threshold value to 1500m; the 5×5 discrimination area moves throughout the investigation region and overlaps with the previous discrimination area.
3. A method of explosive cyclone classification according to claim 1, wherein: and in the step S4, all acquired explosive cyclone samples are sequentially subjected to calculation in the step S3, namely 7 clustering center vectors are used as initial classification, and the average vector of all the contribution rate vectors of the forcing factors is obtained through calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210466639.3A CN114722967B (en) | 2022-04-29 | 2022-04-29 | Explosive cyclone classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210466639.3A CN114722967B (en) | 2022-04-29 | 2022-04-29 | Explosive cyclone classification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114722967A CN114722967A (en) | 2022-07-08 |
| CN114722967B true CN114722967B (en) | 2024-04-12 |
Family
ID=82245636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210466639.3A Active CN114722967B (en) | 2022-04-29 | 2022-04-29 | Explosive cyclone classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114722967B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8224768B1 (en) * | 2008-04-18 | 2012-07-17 | Wsi, Corporation | Tropical cyclone prediction system and method |
| CN106250922A (en) * | 2016-07-22 | 2016-12-21 | 天津大学 | A kind of tropical cyclone objective classification method of the feature based factor |
| CN112883635A (en) * | 2021-01-24 | 2021-06-01 | 浙江大学 | Tropical cyclone full-path simulation method based on random forest algorithm |
| CN113837283A (en) * | 2021-09-26 | 2021-12-24 | 华北电力大学 | Tropical cyclone grade division method based on mean clustering and linear discrimination |
-
2022
- 2022-04-29 CN CN202210466639.3A patent/CN114722967B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8224768B1 (en) * | 2008-04-18 | 2012-07-17 | Wsi, Corporation | Tropical cyclone prediction system and method |
| CN106250922A (en) * | 2016-07-22 | 2016-12-21 | 天津大学 | A kind of tropical cyclone objective classification method of the feature based factor |
| CN112883635A (en) * | 2021-01-24 | 2021-06-01 | 浙江大学 | Tropical cyclone full-path simulation method based on random forest algorithm |
| CN113837283A (en) * | 2021-09-26 | 2021-12-24 | 华北电力大学 | Tropical cyclone grade division method based on mean clustering and linear discrimination |
Non-Patent Citations (1)
| Title |
|---|
| 爆发性气旋研究的回顾;傅刚 等;海洋气象学报;20170315(01);第13-22页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114722967A (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107909082B (en) | Sonar image target identification method based on deep learning technology | |
| Shen et al. | Detection of stored-grain insects using deep learning | |
| CN107862705B (en) | Unmanned aerial vehicle small target detection method based on motion characteristics and deep learning characteristics | |
| CN103871029B (en) | A kind of image enhaucament and dividing method | |
| CN111723693B (en) | Crowd counting method based on small sample learning | |
| CN108346159A (en) | A kind of visual target tracking method based on tracking-study-detection | |
| CN106529570B (en) | Image classification method based on depth ridge ripple neural network | |
| CN111582349B (en) | Improved target tracking algorithm based on YOLOv3 and kernel correlation filtering | |
| CN104680559A (en) | Multi-view indoor pedestrian tracking method based on movement behavior mode | |
| CN107491749A (en) | Global and local anomaly detection method in a kind of crowd's scene | |
| CN107992899A (en) | A kind of airdrome scene moving object detection recognition methods | |
| CN112288026B (en) | Infrared weak and small target detection method based on class activation diagram | |
| CN112149664A (en) | Target detection method for optimizing classification and positioning tasks | |
| CN111145145A (en) | Image surface defect detection method based on MobileNet | |
| CN104268574A (en) | SAR image change detecting method based on genetic kernel fuzzy clustering | |
| CN109977797B (en) | Optimization method of first-order target detector based on sorting loss function | |
| CN108960276A (en) | The sample for promoting spectrum picture supervised classification performance expands and consistency discrimination method | |
| Ren et al. | Research on infrared small target segmentation algorithm based on improved mask R-CNN | |
| Choi et al. | Rain-type classification from microwave satellite observations using deep neural network segmentation | |
| Lavanya et al. | Enhancing Real-time Object Detection with YOLO Algorithm | |
| CN110751671B (en) | Target tracking method based on kernel correlation filtering and motion estimation | |
| CN114722967B (en) | Explosive cyclone classification method | |
| Pillai et al. | Fine-Tuned EfficientNetB4 Transfer Learning Model for Weather Classification | |
| CN106529434A (en) | Fish swarm individual target tracking method based on visual attention model | |
| CN115240078B (en) | SAR image small sample target detection method based on light weight element learning |
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 |