CN114299377A - Vortex identification method and device based on width learning - Google Patents
Vortex identification method and device based on width learning Download PDFInfo
- Publication number
- CN114299377A CN114299377A CN202111675313.3A CN202111675313A CN114299377A CN 114299377 A CN114299377 A CN 114299377A CN 202111675313 A CN202111675313 A CN 202111675313A CN 114299377 A CN114299377 A CN 114299377A
- Authority
- CN
- China
- Prior art keywords
- vortex
- flow field
- target area
- determining
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000009826 distribution Methods 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000010410 layer Substances 0.000 claims description 51
- 238000004458 analytical method Methods 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 13
- 239000002344 surface layer Substances 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 21
- 238000011160 research Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 10
- 230000008901 benefit Effects 0.000 description 7
- 238000000605 extraction Methods 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 230000014509 gene expression Effects 0.000 description 5
- 239000013535 sea water Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000001556 precipitation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 239000004606 Fillers/Extenders Substances 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a vortex identification method and device based on width learning, and the method comprises the following steps: acquiring the sea surface flow field data of a target area, and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data; carrying out vortex distribution judgment on the target area, and determining a vortex distribution result of the target area; fitting the vortex distribution result through a quadric surface equation, and determining the three-dimensional structure type of the vortex; and after learning the characteristics of the identified vortex by adopting a width learning method, predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area to obtain a vortex identification result. The invention improves the accuracy of prediction and can be widely applied to the technical field of data processing.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a width learning-based vortex identification method and device.
Background
Vortices play a non-negligible role in the transport and distribution of global marine matter, energy, etc. Therefore, the identification and prediction of vortices are leading-edge hot spots in current marine science research, however, the sub-mesoscale vortices observed in the field are rare due to the uncertainty in the location and time of their generation, the relatively small scale, and the high cost of large-scale field observation of the sea. Therefore, the exploration and innovation of the identification and prediction method of the secondary mesoscale vortex have great significance for the development of marine science research.
In the existing vortex identification and prediction method, the method can be divided into an Euler method and a Lagrangian method according to different types of data, and the corresponding data types are Euler data and Lagrangian data respectively. The Euler data refers to snapshot data or spatial field data at a moment, and the Lagrangian data refers to trajectory data of water clusters or substance particles. Included in the euler method are: an OW parameter method, a WA algorithm, a VG algorithm, a detection method based on sea surface temperature data, an SAR image detection method aiming at three-dimensional vortex and a water color satellite detection method; included in the lagrangian method is a method for detecting a drift buoy based on a sea surface.
Although various methods are used for detecting ocean vortexes, none of the methods is suitable for vortexes with various dimensions and can accurately judge physical quantities such as the position and the structural dimension of each vortex, and the methods have respective advantages and disadvantages.
The OW algorithm, although widely used, still has 3 drawbacks in itself. Firstly, the selection of the optimal threshold value of the physical parameter W is difficult to determine; secondly, the derivation process of the physical parameters brings some noise items, which can increase the false detection rate of the vortex; third, physical criteria can cause vortex detection to fail or underestimate the size of the vortex size.
The VG algorithm gives four constraints, while sensitivity experiments need to be performed to determine the parameters a, b. When the search area is small, the number of velocity minima points will increase, and therefore the increased number of points for the fourth constraint detection will increase the probability of misidentifying the vortex center. Meanwhile, if the vortex size is small and is closer to islands or lands, the speed minimum point is very close to the lands, so that the speed minimum point is difficult to distinguish, and therefore the small vortex close to the coastline or between the islands is easy to miss detection. Furthermore, a flow sleeve that is elongated or about to completely break off may also be misdetected as a vortex.
When vortex is detected by using sea surface temperature data, the flow velocity vector is replaced by the thermal wind velocity vector, and the detection method still screens the vortex center by using four constraint conditions, so that the advantages and the disadvantages of the detection method are similar to those of a VG algorithm.
When vortex detection is performed based on the trajectory of a buoy drift buoy, the trajectory of the buoy may be very complex in the actual sea, and it is not an easy task to clearly identify all vortices by the buoy. Meanwhile, if the background flow velocity is greater than the tangential velocity of the vortex, the buoy cannot form a loop but a curve after encountering the vortex, and at the moment, the background flow field needs to be removed and a Lagrange locus needs to be reconstructed, so that the detection workload is increased undoubtedly. Furthermore, the float loops only inside the vortex, away from the vortex edge, so the vortex size estimated from the float data is small.
When the SAR image is used for detecting the sea surface vortex, only when the sea surface wind power is too strong and the wind speed is too high, the sea surface wave action is too strong, so that the sea surface is too rough and tends to be uniform, and the vortex cannot be clearly displayed on the SAR image. In addition, a clear SAR image can be obtained only under certain conditions in the detection process, for example, the radiation direction of vortex, the direction of wind-generated surface wave and the radar viewing direction all affect the definition of the image.
If the vortex is detected by using the water color satellite, the optical sensor is influenced by the cloud layer, effective ocean water color data cannot be obtained in a cloud area, and data of a plurality of sensors need to be fused, so that the detection cost is increased and the measurement error is increased. In addition, at present, the research on identifying the vortex by remote water color sensing is still few, and the influence of the vortex on the distribution of chlorophyll on the sea surface is more researched, so that the method for detecting the vortex needs further exploration and research.
Disclosure of Invention
In view of this, the embodiment of the present invention provides a method and an apparatus for vortex recognition based on width learning, which have high accuracy.
One aspect of the present invention provides a method for vortex identification based on width learning, including:
acquiring the sea surface flow field data of a target area, and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data;
carrying out vortex distribution judgment on the target area, and determining a vortex distribution result of the target area;
fitting the vortex distribution result through a quadric surface equation, and determining the three-dimensional structure type of the vortex;
and after learning the characteristics of the identified vortex by adopting a width learning method, predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area to obtain a vortex identification result.
Optionally, the obtaining of the sea surface flow field data of the target area and determining the flow field characteristics of the sea-air interface of the target area according to the sea surface flow field data include:
collecting the sea surface flow field data of the target area through a high-frequency ground wave radar;
and performing data analysis on the sea surface flow field data to obtain the flow field characteristics of the target area.
Optionally, the determining the vortex distribution of the target region by performing vortex distribution judgment on the target region includes:
determining the air pressure characteristic and the wind speed characteristic of an interface on an ocean vortex according to prior knowledge, and performing first analysis on the air pressure characteristic and the wind speed characteristic according to a satellite cloud picture and a wind speed field image;
converting data acquired by a high-frequency ground wave radar into a sea surface flow field speed vector field, and performing second analysis on the sea surface flow field speed vector field through a VG algorithm;
acquiring synchronous abnormal data of a sea surface temperature image in an infrared remote sensing image, and performing third analysis on the sea surface temperature image;
and determining the vortex distribution result of the target area according to the result of the first analysis, the result of the second analysis and the result of the third analysis.
Optionally, after fitting the vortex distribution result through a quadric equation, determining the three-dimensional structure type of the vortex includes:
converting sea surface flow field data acquired by a high-frequency ground wave radar into a regional field flow velocity vector, and performing vortex primary identification on the regional field flow velocity vector;
finding an area with abnormal temperature in the remote sensing image, identifying the vortex position by combining the initial vortex identification result and a VG algorithm, and judging whether the area has vortex;
after the vortex is judged to exist, taking the vortex surface layer as a starting point, layering downwards according to a preset spacing distance, and determining flow speed data of each layer in the vertical direction;
according to the direction of the flow velocity vector of each layer, whether vortex with the same polarity as that of the surface layer exists in each layer is searched;
if the vortex with the same polarity as the surface layer is found, detecting the boundary of the vortex, the central flow velocity of the vortex and the radius of the vortex according to the shape formed by the flow velocity vector;
establishing corresponding coordinate systems on each layer respectively, and fitting according to the vortex radius and the vortex boundary to obtain a boundary curve equation;
fitting according to a boundary curve equation of each layer to obtain a boundary surface equation of the three-dimensional vortex, wherein the boundary surface equation is used for representing the form of the three-dimensional vortex, and the form of the three-dimensional vortex comprises a hyperboloid vortex and a paraboloid vortex;
and (4) carrying out significance test on the boundary surface equation of the three-dimensional vortex obtained by fitting, and taking the quadric surface type with the best test result as the three-dimensional structure type of the vortex.
Optionally, after learning the features of the identified vortices by using a width learning method, predicting the offshore secondary mesoscale vortices according to the flow field features in the target region to obtain a vortex identification result, including:
extracting characteristics of vortex central flow velocity, vortex radius, vortex curved surface form and infrared remote sensing images to serve as input data;
dividing the input data into a training set and a validation set;
performing feature mapping on the training set to generate feature nodes, and obtaining an intermediate layer training matrix according to the feature nodes;
carrying out nonlinear transformation processing on the characteristic nodes to generate enhanced nodes, and obtaining an intermediate layer verification matrix according to the enhanced nodes;
splicing the characteristic nodes and the enhanced nodes to obtain a hidden layer;
outputting a predicted value according to the hidden layer, the middle layer training matrix and the middle layer verification matrix;
and determining the vortex identification result according to the predicted value.
Another aspect of the embodiments of the present invention further provides a vortex identification device based on width learning, including:
the device comprises a first module, a second module and a third module, wherein the first module is used for acquiring the sea surface flow field data of a target area and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data;
the second module is used for judging vortex distribution of the target area and determining a vortex distribution result of the target area;
the third module is used for determining the three-dimensional structure type of the vortex after fitting the vortex distribution result through a quadric surface equation;
and the fourth module is used for predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area after learning the characteristics of the identified vortex by adopting a width learning method, so as to obtain a vortex identification result.
Another aspect of the embodiments of the present invention further provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Still another aspect of embodiments of the present invention provides a computer-readable storage medium, which stores a program,
the program is executed by a processor to implement the method as described above.
Yet another aspect of embodiments of the present invention provides a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.
The method comprises the steps of obtaining sea surface flow field data of a target area, and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data; carrying out vortex distribution judgment on the target area, and determining a vortex distribution result of the target area; fitting the vortex distribution result through a quadric surface equation, and determining the three-dimensional structure type of the vortex; and after learning the characteristics of the identified vortex by adopting a width learning method, predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area to obtain a vortex identification result. The invention improves the accuracy of prediction.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flowchart illustrating the overall steps provided by an embodiment of the present invention;
FIG. 2 is a flow chart of a modeling of width learning provided by an embodiment of the present invention;
fig. 3 is a flowchart of an application based on width learning according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In view of the problems in the prior art, the invention provides a width learning-based vortex identification method, which comprises the following steps:
acquiring the sea surface flow field data of a target area, and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data;
carrying out vortex distribution judgment on the target area, and determining a vortex distribution result of the target area;
fitting the vortex distribution result through a quadric surface equation, and determining the three-dimensional structure type of the vortex;
and after learning the characteristics of the identified vortex by adopting a width learning method, predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area to obtain a vortex identification result.
Specifically, the basic idea of the present invention is summarized as follows: (1) acquiring meteorological data, remote sensing observation data, fixed station data and the like of a research area, and analyzing the data; (2) performing meteorological element feature identification, satellite infrared remote sensing image identification and surface wave radar observation sea flow field characteristic analysis according to the obtained data to obtain a secondary mesoscale vortex flow field and temperature features, and comprehensively identifying the existing region and range of the vortex; (3) carrying out three-dimensional structure judgment and classification on the identified vortex based on a quadric surface equation; (4) vortex prediction based on width learning.
Wherein, meteorological element characteristic identification means: the relationship between the sub-mesoscale vortices and the sea-gas interaction was analyzed. For most middle and small scale vortex active areas (such as the areas of the east Pacific and the black tide extender) the sea surface temperature and the sea surface wind speed have positive correlation on time scales of the weather, the day, the month, the season and the like. At the same time, the corresponding precipitation and cloud cover above the ocean's warm (cold) vortices also increases (decreases). Aiming at the specific sea-gas interaction relation, according to the existing abundant satellite cloud pictures and meteorological station wind speed precipitation data, whether a point with precipitation, cloud cover and wind speed abnormal with a background field exists at a certain point or not is judged based on observation data. If the point is compared with the background field, the rainfall and the cloud cover amount are increased, and meanwhile, the wind speed is increased, and the point is preliminarily judged to have warm vortexes; if the rainfall and the cloud cover amount of the point are reduced compared with the background field, and the wind speed is reduced, the cold vortex at the point is preliminarily judged. And judging whether the three meteorological element characteristics are correspondingly changed positively (negatively) or not, and further judging whether vortexes exist in the ground or not. VG algorithm results and infrared remote sensing image temperature abnormity discrimination method combined with high-frequency ground wave radar data are combined at the same time, comprehensive judgment is carried out
Optionally, the obtaining of the sea surface flow field data of the target area and determining the flow field characteristics of the sea-air interface of the target area according to the sea surface flow field data include:
collecting the sea surface flow field data of the target area through a high-frequency ground wave radar;
and performing data analysis on the sea surface flow field data to obtain the flow field characteristics of the target area.
Optionally, the determining the vortex distribution of the target region by performing vortex distribution judgment on the target region includes:
determining the air pressure characteristic and the wind speed characteristic of an interface on an ocean vortex according to prior knowledge, and performing first analysis on the air pressure characteristic and the wind speed characteristic according to a satellite cloud picture and a wind speed field image;
converting data acquired by a high-frequency ground wave radar into a sea surface flow field speed vector field, and performing second analysis on the sea surface flow field speed vector field through a VG algorithm;
acquiring synchronous abnormal data of a sea surface temperature image in an infrared remote sensing image, and performing third analysis on the sea surface temperature image;
and determining the vortex distribution result of the target area according to the result of the first analysis, the result of the second analysis and the result of the third analysis.
It should be noted that, for the second analysis, the invention uses the high-frequency ground wave radar to observe the characteristics of the sea surface flow field, and aims to use the shore-based high-frequency ground wave radar of the novel observation device to monitor the wind field, wave field and flow field in real time in the research area, the time resolution of the system can reach 1 hour, the space resolution can reach less than 1 kilometer, and the dynamic process and phenomenon of the secondary mesoscale can be monitored. And calculating the vortex characteristic quantity by adopting a VG algorithm aiming at the geometric characteristics of the flow field according to the flow velocity field data.
The VG algorithm gives four constraints, while sensitivity experiments need to be performed to determine the parameters a, b. When the search area is small, the number of velocity minima points will increase, and therefore the increased number of points for the fourth constraint detection will increase the probability of misidentifying the vortex center. Meanwhile, if the vortex size is small and is closer to islands or lands, the speed minimum point is very close to the lands, so that the speed minimum point is difficult to distinguish, and therefore the small vortex close to the coastline or between the islands is easy to miss detection. Furthermore, a flow sleeve that is elongated or about to completely break off may also be misdetected as a vortex. Therefore, the prior art only uses the VG algorithm for vortex prediction, which has the above disadvantages. The method and the device respectively perform the first analysis, the second analysis and the third analysis to assist in prediction, and are more accurate.
For the third analysis, the method aims to utilize an infrared satellite remote sensing sea surface temperature data set (such as GHRSST and the like) to automatically detect and identify vortex by adopting a characteristic extraction method, meanwhile, a hot wind speed field is obtained through calculation according to a hot wind algorithm (two-dimensional convolution is carried out on a Sobel operator and a matrix containing SST), important parameter information such as the vortex center position, the vortex boundary, the vortex strength and the like of the vortex is obtained by utilizing the geometric characteristics of the speed field, and the result and parameters obtained by two methods of data obtained by high-frequency ground wave radar detection and a satellite meteorological data set are mutually verified. And the infrared remote sensing image of the research area vortex is reserved to prepare for inputting the later width learning data.
Optionally, after fitting the vortex distribution result through a quadric equation, determining the three-dimensional structure type of the vortex includes:
converting sea surface flow field data acquired by a high-frequency ground wave radar into a regional field flow velocity vector, and performing vortex primary identification on the regional field flow velocity vector;
finding an area with abnormal temperature in the remote sensing image, identifying the vortex position by combining the initial vortex identification result and a VG algorithm, and judging whether the area has vortex;
after the vortex is judged to exist, taking the vortex surface layer as a starting point, layering downwards according to a preset spacing distance, and determining flow speed data of each layer in the vertical direction;
according to the direction of the flow velocity vector of each layer, whether vortex with the same polarity as that of the surface layer exists in each layer is searched;
if the vortex with the same polarity as the surface layer is found, detecting the boundary of the vortex, the central flow velocity of the vortex and the radius of the vortex according to the shape formed by the flow velocity vector;
establishing corresponding coordinate systems on each layer respectively, and fitting according to the vortex radius and the vortex boundary to obtain a boundary curve equation;
fitting according to a boundary curve equation of each layer to obtain a boundary surface equation of the three-dimensional vortex, wherein the boundary surface equation is used for representing the form of the three-dimensional vortex, and the form of the three-dimensional vortex comprises a hyperboloid vortex and a paraboloid vortex;
and (4) carrying out significance test on the boundary surface equation of the three-dimensional vortex obtained by fitting, and taking the quadric surface type with the best test result as the three-dimensional structure type of the vortex.
The obtaining of the quadratic surface equation of the vortex specifically refers to fitting a vortex boundary curve equation by using a surface layer of a vortex center determined by an infrared remote sensing image, a satellite meteorological data set and a high-frequency ground wave radar data set as a starting point and by a method of layering at equal intervals downwards and determining an inflection point from the center outwards, and then performing three-dimensional fitting by using a two-dimensional vortex boundary fitting equation of each layer to obtain the quadratic surface equation of the vortex. The curved surface equation comprises the types of an ellipsoid, a paraboloid, a hyperboloid, a conical surface and the like, and the respective expressions are as follows:
an ellipsoid surface:
(a, b, c are positive numbers)
Elliptic paraboloid:
(p, q is the same number)
Hyperbolic paraboloid:
(p, q is the same number)
Single-sheet hyperboloid:
(a, b, c are positive numbers)
Two-sheet hyperboloid:
(a, b, c are positive numbers)
An elliptical cone surface:
(a, b are positive numbers)
In this embodiment, the above quadric surface expressions are fitted one by one, then the significance tests are performed respectively, and the quadric surface type with the best significance test result is used as the three-dimensional structure type of the vortex.
The three-dimensional structure judgment refers to a quadric surface equation obtained by using a coordinate system established by taking the vortex center as an origin, and the judgment and classification are carried out on the three-dimensional structure of the vortex by comparing standard equations of various three-dimensional morphological structures (including an ellipsoid, an elliptic paraboloid and the like).
Optionally, after learning the features of the identified vortices by using a width learning method, predicting the offshore secondary mesoscale vortices according to the flow field features in the target region to obtain a vortex identification result, including:
extracting characteristics of vortex central flow velocity, vortex radius, vortex curved surface form and infrared remote sensing images to serve as input data;
dividing the input data into a training set and a validation set;
performing feature mapping on the training set to generate feature nodes, and obtaining an intermediate layer training matrix according to the feature nodes;
carrying out nonlinear transformation processing on the characteristic nodes to generate enhanced nodes, and obtaining an intermediate layer verification matrix according to the enhanced nodes;
splicing the characteristic nodes and the enhanced nodes to obtain a hidden layer;
outputting a predicted value according to the hidden layer, the middle layer training matrix and the middle layer verification matrix;
and determining the vortex identification result according to the predicted value.
It should be noted that the present invention employs a width learning system to learn the identified vortices. The width learning system automatically learns the implicit structure and the existence rule among data aiming at a large amount of data, so that corresponding prediction is made on newly input data. The method utilizes two advantages different from other machine learning systems, namely that the method is based on the RVFL network and has a simple structure. The invention takes a random vector function link neural network as a carrier, and realizes the transverse expansion of a design network by increasing the increment of a neural node instead of the number of structural layers so as to achieve the aim of prediction. The method takes vortex central flow velocity, vortex radius, vortex curved surface form and infrared remote sensing image extraction characteristics as input data, and the output data is a prediction result of vortex change radius, service life, moving path and the like. The model respectively generates characteristic nodes and enhanced nodes through characteristic mapping and nonlinear transformation, the characteristic nodes and the enhanced nodes are jointly used as hidden layers to output results, meanwhile, input data are divided into a training set and a verification set, and the model is trained and tested.
Another aspect of the embodiments of the present invention further provides a vortex identification device based on width learning, including:
the device comprises a first module, a second module and a third module, wherein the first module is used for acquiring the sea surface flow field data of a target area and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data;
the second module is used for judging vortex distribution of the target area and determining a vortex distribution result of the target area;
the third module is used for determining the three-dimensional structure type of the vortex after fitting the vortex distribution result through a quadric surface equation;
and the fourth module is used for predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area after learning the characteristics of the identified vortex by adopting a width learning method, so as to obtain a vortex identification result.
Another aspect of the embodiments of the present invention further provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Still another aspect of embodiments of the present invention provides a computer-readable storage medium, which stores a program,
the program is executed by a processor to implement the method as described above.
Yet another aspect of embodiments of the present invention provides a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.
The following detailed description of the specific implementation principles of the present invention is made with reference to the accompanying drawings:
the embodiment of the invention provides a novel vortex identification method, which mainly comprises the following steps: 1. predicting the vortex by adopting a width Learning method (Broad Learning System), and knowing related contents firstly; 2. starting from the characteristics of the sea-air interface, identifying the vortex by considering the characteristics of the air pressure and the wind speed characteristics (the interface on the ocean vortex); 3. and (4) carrying out prior judgment on the vortex form by combining a quadric surface equation.
Specifically, the overall implementation steps of the present invention are shown in fig. 1:
the first step is as follows: acquiring high-frequency ground wave radar observation sea surface flow field data of a research area, and processing and analyzing the data to obtain the flow field characteristics of a sea-air interface of the research area;
as a novel marine environment observation technology, the high-frequency ground wave radar can detect sea surface flow field information within an action range of 200km from the coast by utilizing the characteristic of small diffraction propagation attenuation on the surface of a conductive sea relative to a short wave (3-30 MHZ). The method has the advantages of over-the-horizon detection, large coverage area, high detection precision, moderate manufacturing cost, good real-time performance, no influence of severe weather and detected sea conditions, all-weather work and the like. The basic principle is as follows: a wave can be decomposed into a superposition of a number of simple sine wave train components with different amplitudes, periods, initial phases and propagation directions. All simple sine wave trains interact with high-frequency electromagnetic waves to generate scattering action, but contributions generated by different sine wave components are different, and only when the following two conditions are met, the radar can receive a stronger echo: the wavelength is equal to half of the wavelength of electric waves; secondly, the Bragg resonance occurs between the sea wave with the propagation direction close to the radar or far away from the radar and the radio wave transmitted by the radar. Therefore, the scheme adopts the high-frequency ground wave radar to collect the data information of the regional ocean current flow field, and is favorable for improving the precision of the data.
The second step is that: vortex is indirectly identified by using meteorological (wind speed field and satellite cloud picture) element data of satellite remote sensing, high-frequency ground wave radar data are processed by combining a VG algorithm, an infrared remote sensing image is analyzed by an automatic interpretation algorithm, and three methods are used for comprehensively judging whether vortex exists in a research area
1) The characteristics of air pressure and air speed of an upper interface of an ocean vortex are summarized in existing research data, comprehensive analysis is carried out according to existing abundant satellite cloud pictures and wind speed field images, the influence of the atmosphere on the ocean is shown relative to a large scale (such as a North Pacific ocean sea basin), namely, the negative correlation relation between the ocean surface temperature and the wind speed is shown, the influence of the ocean on the atmosphere is mainly shown in a local area where the vortex exists, namely, the obvious positive correlation relation exists between the ocean surface temperature and the wind speed and the cloud amount above the vortex, and meanwhile, the water vapor content and the rainfall can also respond (although the correlation is smaller than the wind speed and the cloud amount).
It has been shown that changes in the stability of the atmospheric boundary layer and changes in convection (enhancement/suppression) and water vapor supply are possible causes. The surface momentum vertical mixer is manufactured, the atmosphere of a boundary layer becomes unstable due to high sea temperature (warm vortex), vertical mixing is enhanced, high-rise high momentum in the boundary layer is caused to be transmitted downwards, the wind speed on the sea surface is increased, otherwise, the stability of the atmosphere is increased due to cold sea temperature (cold vortex), and turbulent mixing is inhibited.
2) And converting the high-frequency ground wave radar data into a sea surface flow field velocity vector field, and performing vortex identification analysis according to a VG algorithm.
The VG algorithm defines the vortex based on the geometric features of the flow field: a vortex can be intuitively defined as a region of clockwise or counterclockwise rotation of a velocity vector about a central point. Several studies have now pointed out certain typical features describing the vortex velocity field: the velocity near the center of the vortex is minimal; the magnitude of the tangential velocity increases nearly linearly with increasing distance from the center point and decays after reaching a maximum somewhere. The VG algorithm proposes four constraints corresponding to the definition of the vortex velocity field and the above features, and the point satisfying all the constraints is defined as the vortex center.
3) And based on SST abnormity in the infrared remote sensing image, performing image feature extraction and vortex identification by using a feature extraction method in an automatic interpretation algorithm of vortex infrared remote sensing.
The warm vortex and the cold vortex have positive and negative abnormities of seawater temperature with the vortex center as the center respectively, and the abnormities can reach the Surface of the sea under ideal conditions to form synchronous abnormities of sea Surface temperature SST (sea Surface temperature), so that the synchronous abnormities are detected by the satellite-borne infrared sensor. Therefore, vortex can be effectively identified based on the infrared remote sensing image.
With the increasing of SST data volume, the low efficiency of a visual interpretation method is gradually highlighted, and vortex infrared remote sensing gradually steps from manual interpretation to automatic interpretation. The feature extraction method utilizes a specific algorithm to calculate the feature velocity from continuous SST images and locate and identify vortex in a velocity vector field, and maximally contains more effective vortex information by using as few new features as possible. The characteristic extraction method can be used for vortex detection in the SST field sequence characteristics of the satellite, and can be further used for high-level expression of large-scale geophysical data, high-precision SST data reconstruction, marine big data mining analysis and the like.
And (3) respectively carrying out vortex identification in the research area by using the three methods 1) to 3), and carrying out comprehensive analysis on the identification result to obtain a final vortex distribution result of the research area.
According to the existing data, the ocean vortex characteristics are as follows: the flow of seawater inside the vortex can create a clockwise or counterclockwise rotational flow field and induce surface seawater turbulence (upwelling) or dispersion (downwelling) resulting in a vortex center sea level decrease or increase. Meanwhile, for most sea areas with active vortexes, an obvious positive correlation exists between the ocean surface temperature and the wind speed and cloud amount above the vortexes; the warm vortex and the cold vortex have positive and negative abnormities of the temperature of the seawater with the vortex center as the center, so that the air pressure on the surface of the vortex is reduced or increased; if the system movement speed of the air above the sea surface temperature abnormality caused by ocean vortex is low, the possibility of the phenomenon of strong convection of the generated ocean air is low; if the movement is faster relative to the ocean vortex atmosphere system, the ocean vortex influences the atmosphere through a vertical mixing mechanism, and strong radial rise is easily formed on the downstream side of the background wind of the warm vortex; meanwhile, the warm vortex can increase the sea surface wind speed, and the cold vortex can stabilize the sea surface atmosphere. According to the characteristics of the surface temperature, the air pressure and the wind speed of the vortex, the combination of a flow velocity vector of a sea surface flow field obtained by high-frequency ground wave radar data and a remote sensing image is considered, and the identification of the secondary mesoscale vortex is carried out.
The third step: fitting the identified vortex form by using a quadric surface equation, and carrying out prior judgment on the vortex form;
1) processing and converting sea surface flow data acquired by a high-frequency ground wave radar into a regional field flow velocity vector, and performing vortex identification on the sea surface flow velocity vector;
2) finding an area with abnormal temperature in the remote sensing image, and comprehensively judging whether the area has vortex or not by combining the vortex position identified by the VG algorithm;
3) taking the vortex surface layer as a starting point, layering downwards at a certain interval distance, and outputting flow speed data of each layer vertically by a result model;
4) searching whether vortexes with the same polarity as the surface layer exist in each layer according to the direction of the flow velocity vector of each layer;
5) if the corresponding vortex can be found, detecting elements such as the boundary of the vortex, the vortex central flow velocity, the vortex radius and the like according to the shape formed by the flow velocity vector, wherein the vortex boundary is defined as a connecting line of inflection points of which the velocity field is reduced from the center to the outside to a minimum value and then is increased, and the average value of the distance between the inflection points and the vortex central point is defined as the vortex radius; if no corresponding vortex can be found, the maximum depth of the vortex is considered to be smaller than the depth of the layer;
6) respectively establishing corresponding coordinate systems on each layer, fitting a boundary curve equation according to the measured vortex radius and the boundary form, and fitting a boundary surface equation of the three-dimensional vortex by the boundary curve equation of each layer so as to judge the form of the vortex (including hyperboloid vortex, paraboloid vortex and the like);
7) the quadric surface can be divided into ellipsoidal, paraboloidal, hyperboloid, conical and other types, and the respective expressions are as follows:
an ellipsoid surface:
(a, b, c are positive numbers)
Elliptic paraboloid:
(p, q is the same number)
Hyperbolic paraboloid:
(p, q is the same number)
Single-sheet hyperboloid:
(a, b, c are positive numbers)
Two-sheet hyperboloid:
(a, b, c are positive numbers)
An elliptical cone surface:
(a, b are positive numbers)
And firstly fitting the quadric surface expressions one by one, then respectively carrying out significance test, and taking the quadric surface type with the best significance test result as the three-dimensional structure type of the vortex.
The fourth step: learning the characteristics of the identified vortex by using a width learning method, and predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the research area;
the breadth learning is a neural network structure independent of a depth structure, and compared with a depth learning system widely used at present, the breadth learning has the advantages of high operation speed, simple system structure and the like. The invention can realize the training and learning of the known vortex data by using a width learning method, and further realize the prediction of the data, such as the prediction of the diameter, the service life, the moving path and the like of the vortex.
As shown in fig. 2 and fig. 3, the specific flow of the width learning method according to the embodiment of the present invention for processing data is as follows:
1) and extracting characteristics of vortex central flow velocity, vortex radius, vortex curved surface form and infrared remote sensing image as input data, wherein the vortex central flow velocity and the vortex radius are input numerical values, the vortex curved surface form is input as corresponding numerical values by respectively setting 1, 2, 3 and 4 to be an ellipsoid, a paraboloid, a hyperboloid and a conical surface, and the extraction characteristics of the infrared remote sensing image are similar to the input mode of the vortex curved surface form
2) Dividing input data into training sets Xtrain and Ytrain, verifying sets Xtest and Ytest, and expressing a width learning network output model as Y (HW);
3) and generating characteristic nodes by performing characteristic mapping on the training set data Xtrain to obtain an intermediate layer training matrix Htrain. By ZiRepresenting the i-th group of characteristic nodes containing q neurons, then
Wherein
As a linear or non-linear activation function, WeiAnd
respectively random weight and bias. Splicing n groups of characteristic nodes into Zn＝[Z1，Z2，…，Zn]；
4) Generating an enhanced node by the characteristic node through nonlinear transformation to obtain an intermediate layer verification matrix Htest. By HjRepresenting j groups of enhanced nodes containing r neurons, then
In which ξjA non-linear activation function, WhjAnd
respectively random weight and bias. Splicing m groups of enhanced nodes into Hm＝[H1，H2，...，Hm]；
5) Splicing the characteristic nodes and the enhanced nodes to form a hidden layer;
6) the output of the hidden layer is connected with the weight to obtain the final output, namely according to Ytest＝HtestW obtains a predicted value, and the output result is vortex change radius, service life, moving path and the like.
In summary, compared with the prior art, the embodiment of the invention has the following advantages:
the vortex detection method not only identifies the sea surface vortex aiming at the vortex surface characteristics of the sea surface barograph, but also can obtain the three-dimensional structure form of the sea surface barograph, adopts a numerical equation method to express the form characteristics of the sea surface barograph, simultaneously verifies the method with an infrared remote sensing image automatic interpretation algorithm and a data result of a high-frequency ground wave radar, and adopts a dynamics method, a velocity vector geometrical form method and vortex-based temperature anomaly characteristics to comprehensively identify the vortex. The method is not influenced by the cloud layer shielding and the like, and avoids the misjudgment of the vortex to a certain extent.
In addition, the existing various vortex detection methods focus on identifying the vortex, and the method also utilizes a width learning method to learn the characteristics of the identified vortex, and then predicts the offshore secondary mesoscale vortex according to the flow field characteristics in the research area, thereby having important significance for the research of the vortex.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A vortex identification method based on width learning is characterized by comprising the following steps:
acquiring the sea surface flow field data of a target area, and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data;
carrying out vortex distribution judgment on the target area, and determining a vortex distribution result of the target area;
fitting the vortex distribution result through a quadric surface equation, and determining the three-dimensional structure type of the vortex;
and after learning the characteristics of the identified vortex by adopting a width learning method, predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area to obtain a vortex identification result.
2. The method for vortex identification based on width learning according to claim 1, wherein the obtaining of the surface flow field data of the target area and the determining of the flow field characteristics of the sea-air interface of the target area according to the surface flow field data comprises:
collecting the sea surface flow field data of the target area through a high-frequency ground wave radar;
and performing data analysis on the sea surface flow field data to obtain the flow field characteristics of the target area.
3. The method for vortex identification based on width learning according to claim 1, wherein the determining vortex distribution of the target region and determining a vortex distribution result of the target region includes:
determining the air pressure characteristic and the wind speed characteristic of an interface on an ocean vortex according to prior knowledge, and performing first analysis on the air pressure characteristic and the wind speed characteristic according to a satellite cloud picture and a wind speed field image;
converting data acquired by a high-frequency ground wave radar into a sea surface flow field speed vector field, and performing second analysis on the sea surface flow field speed vector field through a VG algorithm;
acquiring synchronous abnormal data of a sea surface temperature image in an infrared remote sensing image, and performing third analysis on the sea surface temperature image;
and determining the vortex distribution result of the target area according to the result of the first analysis, the result of the second analysis and the result of the third analysis.
4. The method of claim 3, wherein the determining the three-dimensional structure type of the vortex after fitting the vortex distribution result by a quadric equation comprises:
converting sea surface flow field data acquired by a high-frequency ground wave radar into a regional field flow velocity vector, and performing vortex primary identification on the regional field flow velocity vector;
finding an area with abnormal temperature in the remote sensing image, identifying the vortex position by combining the initial vortex identification result and a VG algorithm, and judging whether the area has vortex;
after the vortex is judged to exist, taking the vortex surface layer as a starting point, layering downwards according to a preset spacing distance, and determining flow speed data of each layer in the vertical direction;
according to the direction of the flow velocity vector of each layer, whether vortex with the same polarity as that of the surface layer exists in each layer is searched;
if the vortex with the same polarity as the surface layer is found, detecting the boundary of the vortex, the central flow velocity of the vortex and the radius of the vortex according to the shape formed by the flow velocity vector;
establishing corresponding coordinate systems on each layer respectively, and fitting according to the vortex radius and the vortex boundary to obtain a boundary curve equation;
fitting according to a boundary curve equation of each layer to obtain a boundary surface equation of the three-dimensional vortex, wherein the boundary surface equation is used for representing the form of the three-dimensional vortex, and the form of the three-dimensional vortex comprises a hyperboloid vortex and a paraboloid vortex;
and (4) carrying out significance test on the boundary surface equation of the three-dimensional vortex obtained by fitting, and taking the quadric surface type with the best test result as the three-dimensional structure type of the vortex.
5. The method for vortex identification based on width learning according to claim 1, wherein after learning the features of the identified vortex by using the width learning method, predicting the offshore secondary mesoscale vortex according to the flow field features in the target region to obtain a vortex identification result, comprising:
extracting characteristics of vortex central flow velocity, vortex radius, vortex curved surface form and infrared remote sensing images to serve as input data;
dividing the input data into a training set and a validation set;
performing feature mapping on the training set to generate feature nodes, and obtaining an intermediate layer training matrix according to the feature nodes;
carrying out nonlinear transformation processing on the characteristic nodes to generate enhanced nodes, and obtaining an intermediate layer verification matrix according to the enhanced nodes;
splicing the characteristic nodes and the enhanced nodes to obtain a hidden layer;
outputting a predicted value according to the hidden layer, the middle layer training matrix and the middle layer verification matrix;
and determining the vortex identification result according to the predicted value.
6. The method of claim 5, wherein the vortex identification result includes, but is not limited to, a moving radius of a vortex, a life of the vortex, and a moving path of the vortex.
7. A vortex identification device based on width learning, comprising:
the device comprises a first module, a second module and a third module, wherein the first module is used for acquiring the sea surface flow field data of a target area and determining the flow field characteristics of a sea-air interface of the target area according to the sea surface flow field data;
the second module is used for judging vortex distribution of the target area and determining a vortex distribution result of the target area;
the third module is used for determining the three-dimensional structure type of the vortex after fitting the vortex distribution result through a quadric surface equation;
and the fourth module is used for predicting the offshore secondary mesoscale vortex according to the flow field characteristics in the target area after learning the characteristics of the identified vortex by adopting a width learning method, so as to obtain a vortex identification result.
8. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program realizes the method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the method of any of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675313.3A CN114299377B (en) | 2021-12-31 | 2021-12-31 | Vortex identification method and device based on width learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675313.3A CN114299377B (en) | 2021-12-31 | 2021-12-31 | Vortex identification method and device based on width learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114299377A true CN114299377A (en) | 2022-04-08 |
| CN114299377B CN114299377B (en) | 2024-03-22 |
Family
ID=80976039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111675313.3A Active CN114299377B (en) | 2021-12-31 | 2021-12-31 | Vortex identification method and device based on width learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299377B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116429374A (en) * | 2023-04-17 | 2023-07-14 | 中国人民解放军61540部队 | Mesoscale vortex characteristic determining method, mesoscale vortex characteristic determining system, electronic equipment and medium |
| CN116597085A (en) * | 2023-05-18 | 2023-08-15 | 中山大学 | Three-dimensional flow field reconstruction method, system, electronic equipment and storage medium |
| CN117175585A (en) * | 2023-11-02 | 2023-12-05 | 深圳航天科创泛在电气有限公司 | Wind power prediction method, device, equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097075A (en) * | 2019-03-21 | 2019-08-06 | 国家海洋信息中心 | Ocean mesoscale eddy classifying identification method based on deep learning |
| CN110298280A (en) * | 2019-06-20 | 2019-10-01 | 上海海洋大学 | A kind of ocean eddy recognition methods based on MKL multiple features fusion |
| US20200160568A1 (en) * | 2018-11-16 | 2020-05-21 | The Government Of The United States Of America, As Represented By The Secretary Of The Navy | Oceanic Eddy Detection from Two-Dimensional Sea Level Topography Gradients |
| JP6756889B1 (en) * | 2019-09-30 | 2020-09-16 | 東日本旅客鉄道株式会社 | Vortex detector, vortex detection method, program and trained model |
| CN111767827A (en) * | 2020-06-28 | 2020-10-13 | 中国人民解放军国防科技大学 | Mesoscale vortex identification method based on deep learning |
| CN111931409A (en) * | 2020-08-14 | 2020-11-13 | 南京大学 | Vortex three-dimensional posture recognition and tracking method based on high-resolution ocean mode data |
| CN112102325A (en) * | 2020-09-17 | 2020-12-18 | 中国科学院海洋研究所 | Ocean abnormal mesoscale vortex identification method based on deep learning and multi-source remote sensing data |
| CN112270294A (en) * | 2020-11-12 | 2021-01-26 | 中国海洋大学 | Underwater vehicle vortex identification method and device and underwater vehicle |
| CN112766194A (en) * | 2021-01-26 | 2021-05-07 | 上海海洋大学 | Detection method for mesoscale ocean eddy |
| CN113252010A (en) * | 2021-04-20 | 2021-08-13 | 中国海洋大学 | Marine long-time vortex-following observation system and design method |
| CN113420440A (en) * | 2021-06-22 | 2021-09-21 | 中国海洋大学 | Vortex identification method based on ocean vertical structure |
| CN113592786A (en) * | 2021-07-12 | 2021-11-02 | 浙江大学 | Deep learning-based detection method for mesoscale vortices in ocean |
| CN113743577A (en) * | 2021-06-25 | 2021-12-03 | 上海大学 | Fine grid data partition construction method and system for mesoscale vortex identification |
-
2021
- 2021-12-31 CN CN202111675313.3A patent/CN114299377B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200160568A1 (en) * | 2018-11-16 | 2020-05-21 | The Government Of The United States Of America, As Represented By The Secretary Of The Navy | Oceanic Eddy Detection from Two-Dimensional Sea Level Topography Gradients |
| CN110097075A (en) * | 2019-03-21 | 2019-08-06 | 国家海洋信息中心 | Ocean mesoscale eddy classifying identification method based on deep learning |
| CN110298280A (en) * | 2019-06-20 | 2019-10-01 | 上海海洋大学 | A kind of ocean eddy recognition methods based on MKL multiple features fusion |
| JP6756889B1 (en) * | 2019-09-30 | 2020-09-16 | 東日本旅客鉄道株式会社 | Vortex detector, vortex detection method, program and trained model |
| CN111767827A (en) * | 2020-06-28 | 2020-10-13 | 中国人民解放军国防科技大学 | Mesoscale vortex identification method based on deep learning |
| CN111931409A (en) * | 2020-08-14 | 2020-11-13 | 南京大学 | Vortex three-dimensional posture recognition and tracking method based on high-resolution ocean mode data |
| CN112102325A (en) * | 2020-09-17 | 2020-12-18 | 中国科学院海洋研究所 | Ocean abnormal mesoscale vortex identification method based on deep learning and multi-source remote sensing data |
| CN112270294A (en) * | 2020-11-12 | 2021-01-26 | 中国海洋大学 | Underwater vehicle vortex identification method and device and underwater vehicle |
| CN112766194A (en) * | 2021-01-26 | 2021-05-07 | 上海海洋大学 | Detection method for mesoscale ocean eddy |
| CN113252010A (en) * | 2021-04-20 | 2021-08-13 | 中国海洋大学 | Marine long-time vortex-following observation system and design method |
| CN113420440A (en) * | 2021-06-22 | 2021-09-21 | 中国海洋大学 | Vortex identification method based on ocean vertical structure |
| CN113743577A (en) * | 2021-06-25 | 2021-12-03 | 上海大学 | Fine grid data partition construction method and system for mesoscale vortex identification |
| CN113592786A (en) * | 2021-07-12 | 2021-11-02 | 浙江大学 | Deep learning-based detection method for mesoscale vortices in ocean |
Non-Patent Citations (3)
| Title |
|---|
| 张春华;安文韬;邵连军;赵钊;方乐;: "多源数据中尺度涡三维结构分析方法研究", 海洋技术学报, no. 02 * |
| 芦旭熠;单桂华;李观;: "基于深度学习的海洋中尺度涡识别与可视化", 计算机系统应用, no. 04 * |
| 董昌明;蒋星亮;徐广;季巾淋;林夏艳;孙文金;王森;: "海洋涡旋自动探测几何方法、涡旋数据库及其应用", 海洋科学进展, no. 04 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116429374A (en) * | 2023-04-17 | 2023-07-14 | 中国人民解放军61540部队 | Mesoscale vortex characteristic determining method, mesoscale vortex characteristic determining system, electronic equipment and medium |
| CN116597085A (en) * | 2023-05-18 | 2023-08-15 | 中山大学 | Three-dimensional flow field reconstruction method, system, electronic equipment and storage medium |
| CN116597085B (en) * | 2023-05-18 | 2023-12-12 | 中山大学 | Three-dimensional flow field reconstruction method, system, electronic equipment and storage medium |
| CN117175585A (en) * | 2023-11-02 | 2023-12-05 | 深圳航天科创泛在电气有限公司 | Wind power prediction method, device, equipment and storage medium |
| CN117175585B (en) * | 2023-11-02 | 2024-03-08 | 深圳航天科创泛在电气有限公司 | Wind power prediction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114299377B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114299377B (en) | Vortex identification method and device based on width learning | |
| Wick et al. | Description and validation of an automated objective technique for identification and characterization of the integrated water vapor signature of atmospheric rivers | |
| Gangeskar | An algorithm for estimation of wave height from shadowing in X-band radar sea surface images | |
| Nencioli et al. | A vector geometry–based eddy detection algorithm and its application to a high-resolution numerical model product and high-frequency radar surface velocities in the Southern California Bight | |
| CN103353988B (en) | Allos SAR scene Feature Correspondence Algorithm performance estimating method | |
| Huang et al. | Wave height estimation from X-band nautical radar images using temporal convolutional network | |
| Liu et al. | Comparison of algorithms for wind parameters extraction from shipborne X-band marine radar images | |
| Muste et al. | Modern digital instruments and techniques for hydrodynamic and morphologic characterization of river channels | |
| Wang et al. | A center location algorithm for tropical cyclone in satellite infrared images | |
| CN107369297A (en) | For tsunami detection and pre-warning system | |
| EP2848962A1 (en) | Method for identifying and classifying petroleum exuding areas at the bottom of the sea by reverse modelling | |
| Lai et al. | Submesoscale eddies in the Taiwan strait observed by high-frequency radars: Detection algorithms and eddy properties | |
| CN106199548B (en) | The detection method of the faint radar target of offshore floating based on the fusion of four POLARIZATION CHANNELs | |
| Muller et al. | Estimating the Lagrangian residual circulation in the Iroise Sea | |
| Wang et al. | Wind turbine wake detection with a single Doppler wind lidar | |
| Meng et al. | Remote Sensing for Subsurface and Deeper Oceans: An overview and a future outlook | |
| Viikmäe et al. | Quantification and characterization of mesoscale eddies with different automatic identification algorithms | |
| Malila et al. | On the groupiness and intermittency of oceanic whitecaps | |
| Wang et al. | An energy spectrum algorithm for wind direction retrieval from X-band marine radar image sequences | |
| Bao et al. | Application of lightning spatio-temporal localization method based on deep LSTM and interpolation | |
| CN109190182B (en) | Electromagnetic scattering modeling method for oil film coverage nonlinear sea surface | |
| KR101790482B1 (en) | Wave measurement system and method using marine rader | |
| Tang et al. | Simulation of the Doppler echoes from wind turbine based on scattered electric field calculation | |
| Redondo et al. | Eddy measurements, coastal turbulence and statistics in the gulf of Lions | |
| Potvin et al. | Using a low-order model to detect and characterize tornadoes in multiple-Doppler radar data |
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 |