CN114997267A - Ocean vortex evolution analysis method, device and equipment and readable storage medium - Google Patents
Ocean vortex evolution analysis method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN114997267A CN114997267A CN202210441847.8A CN202210441847A CN114997267A CN 114997267 A CN114997267 A CN 114997267A CN 202210441847 A CN202210441847 A CN 202210441847A CN 114997267 A CN114997267 A CN 114997267A
- Authority
- CN
- China
- Prior art keywords
- ocean
- vortex
- evolution
- information
- key
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an ocean vortex evolution analysis method, device and equipment and a readable storage medium, which relate to the technical field of ocean information and comprise the steps of constructing an ocean vortex process model; extracting key events in the ocean vortex evolution process, and identifying and tracking the ocean vortex according to a vortex detection method and a tracking method; and determining all key events in the ocean vortex evolution period according to the identified ocean vortex and the key events, and generating a key analysis result of the ocean vortex evolution by utilizing a model combining a recurrent neural network and a long-short term memory artificial neural network. The method has the advantages that the in-situ visualization is used for processing simulation analysis in a large-scale flow field; the vortex streamline structure with high precision can be generated in real time, and vortex statistical analysis and tracking analysis of different ocean areas and different scales are supported; the efficiency and the effectiveness of the system are proved; experts can be helped to track and analyze the evolution of ocean vortices.
Description
Technical Field
The invention relates to the technical field of ocean information technology, in particular to an ocean vortex evolution analysis method, device and equipment and a readable storage medium.
Background
Vortexes are one of the important subjects in marine simulations. The diameter of the mesoscale vortices in the ocean is typically between tens and hundreds of kilometers. The transport of ocean vortices often lasts for months and plays an important role in the transport of heat, salt, biological material and energy. Among them, vortex analysis is a key step of ocean flow field data analysis, and one of the commonly used methods for visualization is provided.
Currently, large scale flow field data and time series of vortices result in a huge scale of vortex data that needs to be analyzed. Experts need to obtain structured small-scale information, such as structural features of a particular vortex, from large-scale vortex data. The gap between them makes it difficult for a user to obtain the required vortex tracing information even if the user uses a high performance GPU for calculation. Furthermore, existing visualization schemes are unable to convert large-scale vectorized data into a usable information set, requiring compression of the large-scale data. Overall, large scale ocean vortex evolution analysis faces the following challenges: a huge difference exists between the time sequence of the ocean vortex data and the small-scale information; end-to-end visualization of the analysis requirements from vectorized data to structured information.
Disclosure of Invention
The invention aims to provide an ocean vortex evolution analysis method, device and equipment and a readable storage medium, so as to solve the problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides an ocean vortex evolution analysis method, including:
extracting process information in an ocean vortex historical sample library, and constructing an ocean vortex process model;
mining the ocean vortex flow model by using a heuristic workflow algorithm, and extracting key events in the ocean vortex evolution process, wherein the key events comprise merging, splitting, generating and eliminating of the ocean vortices;
inputting the obtained ocean flow field data into a preset high-performance computing cluster for analysis, and identifying and tracking ocean vortexes according to a vortex detection method and a tracking method;
determining all key events in an ocean vortex evolution period according to the identified ocean vortex and the key events, and storing time points of all the key events and high-precision streamline images of moments before and after the time points;
and generating a key analysis result of ocean vortex evolution by utilizing a model combining a cyclic neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all the key events.
In a second aspect, the present application further provides an ocean vortex evolution analysis apparatus, which includes an extraction module, an excavation module, an identification module, a determination module and a generation module, wherein:
the extraction module is used for extracting the process information in the ocean vortex historical sample library and constructing an ocean vortex process model;
the mining module is used for mining the ocean vortex flow model by utilizing a heuristic workflow algorithm and extracting key events in the ocean vortex evolution process, wherein the key events comprise merging, splitting, generating and eliminating of ocean vortices;
the identification module is used for inputting the obtained ocean flow field data into a preset high-performance computing cluster for analysis, and identifying and tracking ocean vortexes according to a vortex detection method and a tracking method;
the determining module is used for determining all key events in an ocean vortex evolution period according to the identified ocean vortices and the key events, and storing time points of all the key events and high-precision streamline images around the time points;
and the generation module is used for generating a key analysis result of the ocean vortex evolution by utilizing a model combining a cyclic neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all the key events.
In a third aspect, the present application further provides an ocean vortex evolution analysis device, including:
a memory for storing a computer program;
a processor for implementing the steps of the ocean vortex evolution analysis method when executing the computer program.
In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above method for analyzing evolution based on ocean vortex.
Currently, there are two common methods for analyzing the evolution of ocean vortices. The first is to detect ocean vortex evolution events using an event detection method by visually displaying all events and providing them to experts for analysis. Another approach is to minimize the size of the raw data by in situ visualization. Experts generally use data of compression ratio for research through a traditional ocean simulation analysis method. However, these two methods are relatively isolated and do not completely address the above challenges.
The invention has the beneficial effects that: processing simulation analysis in large-scale flow fields using in-situ visualization; in combination with narrative visual analysis, a large ocean flow field vortex evolution analysis system based on in-situ visualization is designed; the vortex streamline structure with high precision can be generated in real time, and vortex statistical analysis and tracking analysis of different ocean areas and different scales are supported; the efficiency and the effectiveness of the system are proved by analyzing the ocean simulation case data; the in-situ complex multivariable multi-center feature evolution-based visual analysis system can help experts to track and analyze the evolution of ocean vortexes and the statistics and analysis of regional vortexes.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of an ocean vortex evolution analysis method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an ocean vortex evolution analysis device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of the ocean vortex evolution analysis device according to the embodiment of the present invention.
In the figure, 701, an extraction module; 702. a digging module; 7021. selecting a unit; 7022. a first acquisition unit; 7023. a processing unit; 7024. a merging unit; 7025. a building unit; 703. an identification module; 7031. a first generation unit; 7032. a filtration unit; 7033. a visualization unit; 7034. a display unit; 7035. a recording unit; 7036. an identification unit; 7037. acquiring a second information unit; 7038. acquiring a third information unit; 7039. acquiring a fourth information unit; 7040. a data information unit; 704. a determination module; 705. a generation module; 7051. a determination unit; 7052. an extraction unit; 7053. a second generation unit; 7054. a conversion unit; 7055. a third generation unit; 706. establishing a data set module; 707. a calculation module; 708. an optimization module; 800. ocean vortex evolution analysis equipment; 801. a processor; 802. a memory; 803. a multimedia component; 804. an input/output (I/O) interface; 805. a communication component.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides an ocean vortex evolution analysis method.
Referring to fig. 1, it is shown that the method includes step S100, step S200, step S300, step S400 and step S500.
S100, extracting process information in the ocean vortex historical sample library, and constructing an ocean vortex process model.
It is understood that step S100 is preceded by steps S101, S102 and S103, wherein:
s101, identifying global ocean vortexes by adopting a narrative visualization method, and establishing an ocean vortex data set, wherein the ocean vortex data set comprises flow field vector information, temperature information and salinity information of the ocean vortexes;
s102, calculating to obtain an ocean vortex flow model according to a Heuritistics Miner algorithm and the ocean vortex data set;
s103, analyzing the ocean vortex flow model to obtain the optimized ocean vortex flow model.
The narrative visualization method and the Heuritics Miner algorithm are both the prior art, the story is simply explained by using a visual display form, and the Heuritics Miner algorithm is an inductive mining algorithm.
It should be noted that the narrative visualization method and the narrative-based interactive visualization analysis method are already applied to the field of information visualization, and a new idea is provided for scientific visualization. Hullman et al outlines how automatic ordering (order of rendering visualizations) is used when designing a system to help non-designers navigate the structured decisions when creating narrative visualizations. Fisher et al will describe as a new visualization technique based on topic detection, tracking and temporal visualization. Currently, narrative visualization methods are commonly used for information visualization, but are rarely used in the field of scientific visualization. However, the method still has a very high prospect in the aspect of improving the interaction and analysis effect of scientific visualization.
Therefore, it is necessary to describe key feature events based on feature detection and image generation to visualize event descriptions. These descriptions can be accomplished with a small number of words and sequences of events. Therefore, it is necessary to generate description information of key feature events; the main idea of workflow mining is to extract information about the process from the transaction log, obtain a process model and support analysis and optimization. The Heuristics Miner algorithm is used to generate event descriptions for processes that are less structured.
S200, mining the ocean vortex flow model by using a heuristic workflow algorithm, and extracting key events in the ocean vortex evolution process, wherein the key events comprise merging, splitting, generating and eliminating of the ocean vortex.
It is understood that step S200 includes steps S201, S202, S203, S204 and S205, where:
s201, selecting a first object as a case object;
s202, acquiring first information, wherein the first information comprises the information of the radius, the energy and the type of the ocean vortex of the first object;
s203, processing the first information through a heuristic workflow mining algorithm;
s204, deducing keywords of the key event according to the processed first information and merging and extinction information of the ocean vortexes in the first object;
s205, constructing a description table of the key event according to the key words.
It should be noted that the merging and splitting events in the vortex evolution process are as follows: the user can select deep exploration and enter a vortex evolution tracking interface of the local area. In vortex evolution tracking, experts typically focus on important events in the vortex evolution process.
According to a specific sea area selected by a user, streamline generation and vortex tracking are carried out on a high-performance computer, and all vortexes which are split and combined in the vortex evolution process are filtered out and serve as a visual object of a main view. The main view shows the events of each vortex over time in the trace map and shows the merging and splitting of vortices by branch merging and splitting. The direction of evolution of the tracking map is the time-duration direction. Each node may be selected to obtain detailed information. The width of each node represents the radius of the vortex. The user can select the vortex structure represented by a particular node, visualize the local flowsheet image at the corresponding time, and describe the event on the right.
In the present embodiment, the data set of the first information includes a common data set AVISO and a red sea simulation data set. The AVISO contains the global ocean data from 1993 to 2014, the grid scale is 1440 multiplied by 720, the time granularity is 1 day, the information of a speed field, longitude and latitude, temperature and the like of the global ocean is contained, and the overall scale is about 2 TB. The red sea simulation dataset covers a one month simulation time from bathymetry and regular grid (500 x 50,60 time steps) of the red sea. In each member, it contains five physical attributes: temperature, salinity and velocity field components in three directions, with 64-bit floating point data precision. In the visualization, we mainly used data of temperature and velocity attributes, each member being about 22.35GB (500 × 50 × 60 × 8KB × 4 (number of variables) $ 22.35 GB) in size, for a total of about 1.09 TB.
S300, inputting the obtained ocean flow field data to a preset high-performance computing cluster for analysis, and identifying and tracking the ocean vortexes according to a vortex detection method and a tracking method.
It is understood that step S300 includes steps S301, S302, S303, S304, S305, and S306, where:
s301, generating a streamline and vortex tracking according to a specific sea area to be selected;
s302, filtering out all the ocean vortexes which are split and combined in the ocean vortex evolution process;
s303, taking the filtered ocean vortexes as visualization objects;
s304, displaying the event of each ocean vortex in the visual object along with the change of time;
s305, recording each node data in the event as the ocean flow field data;
s306, analyzing and identifying the ocean flow field data through the high-performance computing cluster to obtain the identified ocean vortex data.
In the vortex detection method and the tracking method, vortex is mainly studied as an event, and the detection method is particularly critical. Commonly used vortex detection methods fall into two broad categories, mainly physical-based methods and geometry-based methods. The physics-based approach involves the computation of dynamic flow fields and requires a closed contour vortex definition based on thresholds. The SSH method, the eddy current method, the velocity gradient tensor method or the Okubo-Weiss parameter method are commonly used. Geometry-based methods mainly use the curvature or shape of the instantaneous flow field to detect vortices. They are mainly based on wrap angle, vector geometry, wavelets and lagrange pseudo-level structure detection, etc. Among them, the O-W method is simple and efficient, and is most widely applied.
Vortex tracking is an important component of vortex evolution analysis research. Trott judges the continuity of vortices by using the difference in radius, amplitude and kinetic energy of vortices according to the difference in characteristics of the two vortices at adjacent times, the two vortices with the smallest difference being continuous. Penven et al showed that the smaller the distance of the vortex nuclei, the greater the correlation between the two vortices.
The vortex detection method based on the physical and geometric characteristics of a flow field obtains Okubo-Weiss (OW) parameters, sea level height and velocity vectors through numerical simulation. The OW parameter describes the relative advantage of deformation versus flow rotation and is calculated as follows:
wherein s is n 、s s And ω is the normal component of the tension, the shear component, and the relative vorticity of the flow field, respectively. They are defined as follows:
s n ＝ux-vy,s s ＝vx+vy,ω＝vx-vy
where u and v represent velocity components and x and y represent directions.
Vortex tracking is performed by tracking distance (Δ D), radius (Δ R), shear deformation rate (Δ S) s ) Tensile deformation ratio (Δ S) n ) The difference and amplitude (Δ a) of (a) are carried out by the vortex core and the like. For example, if identified vortices e1 and e2 intersect at t1 and t2, then vortex e2 is a continuation of e1 from t1 to t2 when the difference in characteristics between e1 and e2 is minimal.
Where Δ f represents the above specific feature difference, and σ represents the number of features.
It should be noted that in this embodiment, the high performance computer CPU model used is intel (r) xeon (r) Gold 6248CPU @2.50GHz, and the GPU is Tesla V100. The scientific visualization algorithm toolkit VTK-m, which is mainly accelerated by a GPU, is used for supporting fine-grained concurrency of data analysis and visualization algorithms by providing an abstract model for data and execution. And deploying a VTK-m tool supporting GPU acceleration, and performing in-situ real-time streamline tracking and streamline image output according to the flow field area selected by the user.
Step S300 further includes S307, S308, S309, and S310, where:
s307, acquiring second information, wherein the second information comprises information of a normal component and a shearing component of an ocean velocity field and information of a relative vorticity of a flow field;
s308, obtaining third information through a numerical simulation method according to the second information, wherein the third information is an Okubo-Weiss parameter;
s309, according to the third information, fourth information is obtained through calculation, and the fourth information is ocean vortex parameters, sea level height and velocity vector information;
and S310, calculating to obtain ocean flow field data information according to the fourth information and the tracking method.
The vortex tracking is performed by comparing the distance (Δ D) passing through the vortex core, the radius (Δ R), and the shear deformation rate (Δ S) s ) Tensile deformation ratio (Δ S) n ) The difference and amplitude (Δ a) of (a), and when the characteristic difference is judged to be minimum by a formula, the vortexes have a sequential relationship (namely, the tracking of the vortexes).
S400, determining all key events in an ocean vortex evolution period according to the identified ocean vortex and the key events, and storing time points of all the key events and high-precision streamline images of the time points before and after the time points.
It can be understood that, in this step, high-precision streamline images of the vortex evolution key event time points and the moments before and after the time points are stored under in-situ simulation; where in-situ refers to running a program on a high performance computing cluster, saving only the image or data features of the intermediate or result, and not the original data set or the intermediate data set.
And S500, generating a key analysis result of ocean vortex evolution by utilizing a model combining a recurrent neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all the key events.
It is understood that S501, S502, S503, S504, and S505 are included in the S500 step, wherein:
s501, determining the event type of the key event according to the key event;
s502, extracting keyword information corresponding to the key event according to the event type and preset feature information;
s503, generating a keyword list according to the keyword information and the high-precision streamline image;
s504, converting the keyword list into a narrative character description result through a model combining a recurrent neural network and a long-short term memory artificial neural network;
and S505, generating a key analysis result of the ocean vortex evolution from the narrative character description result.
It should be noted that workflow mining uses the Heuristics Miner algorithm to generate event descriptions for less structured flows. The basic idea of the method is to mine dependency graphs, splits and join relationships. By setting a case mode and setting an object, processing key monitoring information such as the radius, the energy and the type of a vortex by a heuristic workflow mining algorithm. The description of the event can be derived using dimensional information of the event, such as merging and disappearing of vortices.
From workflow mining, the keywords of an event can be derived, and then an event description table is built, which usually consists of fields and values.
In general, generating natural language from tables is now a common method in machine learning. The work of generating natural language from tables is mainly accomplished using the machine learning model of Cao et al. The specific model mainly comprises a two-stage LSTM-RNN (Long Short-Term Memory, Current Neural Network) Convolutional Neural Network (CNN) and a Long Short-Term Memory artificial Neural Network (LSTM) combined encoder.
The entire system is controlled according to user interaction. And the in-situ calculation module is responsible for vortex identification and tracking, and outputs statistical data and a high-precision flow chart of a corresponding area according to the selection of a user. The workflow module extracts the keyword information of the corresponding event according to the corresponding event and the related characteristics to form a keyword list which is provided to the machine learning processing module. The machine learning processing module mainly uses the RNN + LSTM model to convert the keyword list into a narrative word description. The visual interaction module provides information such as images, texts, characteristics and the like of other modules for a user for visual analysis.
In the embodiment, vortex in the North Pacific region is identified and tracked by using an AVISO data set and our system, and the spatial-temporal characteristics of regional vortex distribution and evolution are analyzed.
Experts divided the north pacific region into 7 regions according to relevant laws in the marine field, including the tidal Ocean Current (OC), black tide extension (KE), subtropical counterflow (STCC), north equatorial ocean current (NEC), alaska ocean current (AC), california ocean current (CC), and northeastern tropical pacific (NETP).
Experts tracked and analyzed all vortexes generated in the north pacific region from 1993 to 2014. The conclusion is reached from the analysis of the histogram: more than half of the life of the vortex is less than 10 weeks. The gas vortices are smaller than the anti-cyclone vortices by 5km for the average radius of the vortices, and the average radius of all vortices is about 100 km. Experts analyze the generation of vortexes from a seasonal perspective, and find that obvious seasonal changes exist in the generation of vortexes, more vortexes in spring and less vortexes in autumn. Furthermore, by identifying and tracking the different regional vortexes in the North Pacific ocean, the number of vortexes generated by the STCC region was found to be the greatest. From this result, the expert, in combination with the field analysis, considers that the wind stress in the area is caused by the interaction with the ocean currents.
In the research of the embodiment, experts track the evolution of the life cycle of the vortex in the red sea through the analysis of the data of the red sea set, and intensively analyze the vortex of the splitting and merging events in the evolution process. In addition, experts find that the physical information such as the radius and the vorticity of the vortex are changed significantly when the corresponding event is generated through the comparison of vortex merging and splitting events. We select the evolution process of two vortices to show the visualization of our system on vortex tracking evolution.
Day 0, vortex No. 17, an anti-cyclonic vortex, evolved over 2 days, merging with the new vortex appearing at day 2. The pooled vortex was split into two vortexes on day five, which were combined into the same vortex after day one. Thereafter, the vortexes continued to evolve, with no vortexes splitting or merging with other vortexes. By day 39, vortexes disappeared. The scale (radius) of the vortex exhibited small scale fluctuations prior to the first coalescence. On day 3, there was a significant increase after vortex coalescence due to the same type of two vortexes. Subsequently, the vortex radius continues to increase. On day 6, the mean radius decreased significantly due to vortex breakdown. After splitting and second coalescence, the radii were relatively stable, decreasing on day 21, and then slowly disappeared. In addition, the local streamline characteristics of corresponding time are observed by selecting corresponding nodes of the tracking graph, and streamline state analysis is carried out. On day 4, the streamlines in the green region have not formed a vortex structure, but some of the streamlines have exhibited a different flow trend. On the fifth day, the vortexes started to divide substantially and the central core of new vortexes started to form. By day six, the division is substantially complete.
Day 0, cyclone 28 and 30 vortexes, each evolving over a period of time and merging at day 7. The pooled vortexes split into two vortexes one day later and are pooled again one vortex one day later. Thereafter, the vortices continued to evolve, splitting into two vortices at day 40, and then rapidly merging. On day 55, a similar situation reappeared.
Based on the visualization of multiple vortices, experts in the field considered that vortices were difficult to break apart again after merging due to red sea stenosis. Even if the vortex is split again, the split vortex is easy to merge quickly and is difficult to evolve and dissipate. In addition, experts have also found that each evolving vortex, when merged, typically merges and splits within a short time. Based on this, experts consider vortex coalescence to be a process in general in which energy collision and the like cause the vortex to become unstable in a short time.
The technical effects produced by the embodiment are as follows:
1, I O Properties: under the in-situ visualization framework, only 498KB is needed to store the north pacific region images with a resolution of 4160 x 1600 for one time step. Corresponding pipeline data are stored for comparison, and 381MB (adopting a VTK binary format) is needed for storing the pipeline data.
2. Time performance: the time required to store the corresponding image and the corresponding stream file is 0.974s and 9.533s, respectively.
3. Interaction performance: the interaction time for switching the flowgrams at different times is about 1 second, while if the original storage mode is used, the interaction time is at least 10 seconds.
Example 2:
as shown in fig. 2, the present embodiment provides an ocean vortex evolution analysis apparatus, referring to fig. 2, the apparatus includes an extraction module 701, an excavation module 702, an identification module 703, a determination module 704, and a generation module 705, where:
an extraction module 701, configured to extract process information in an ocean vortex historical sample library and construct an ocean vortex process model;
the mining module 702 is used for mining the ocean vortex flow model by utilizing a heuristic workflow algorithm and extracting key events in the ocean vortex evolution process, wherein the key events comprise merging, splitting, generating and eliminating of the ocean vortices;
the identification module 703 is used for inputting the acquired ocean flow field data into a preset high-performance computing cluster for analysis, and identifying and tracking ocean vortexes according to a vortex detection method and a tracking method;
the determining module 704 is used for determining all key events in the ocean vortex evolution period according to the identified ocean vortices and the key events, and storing time points of all the key events and high-precision streamline images of moments before and after the time points;
the generation module 705 is used for generating a key analysis result of the ocean vortex evolution by utilizing a model combining a recurrent neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all key events.
Preferably, the extraction module 701, previously comprising the data set creation module 706, the calculation module 707 and the optimization module 708, wherein:
the create data set module 706: the system is used for identifying global ocean vortexes by adopting a narrative visualization method, and establishing an ocean vortex data set, wherein the ocean vortex data set comprises flow field vector information, temperature information and salinity information of the ocean vortexes;
the calculation module 707: the method comprises the steps of calculating to obtain an ocean vortex flow model according to a Heuritistics Miner algorithm and an ocean vortex data set;
the optimization module 708: and the method is used for analyzing the ocean vortex flow model to obtain the optimized ocean vortex flow model.
Preferably, the mining module 702 includes a selecting unit 7021, a first obtaining unit 7022, a processing unit 7023, a merging unit 7024, and a constructing unit 7025, where:
a selecting unit 7021 for selecting the first object as a case object;
a first obtaining unit 7022, configured to obtain first information, where the first information includes information about a radius, energy, and a type of an ocean vortex of the first object;
the processing unit 7023 is configured to process the first information through a heuristic workflow mining algorithm;
a merging unit 7024, configured to derive keywords of the key event according to the processed first information and merging and extinction information of the ocean vortexes in the first object;
and a constructing unit 7025, configured to construct a description table of the key event according to the key.
Preferably, the recognition module 703 comprises a first generation unit 7031, a filtering unit 7032, a visualization unit 7033, a display unit 7034, a recording unit 7035, and a recognition unit 7036, wherein:
the first generating unit 7031 is configured to generate a streamline and a vortex tracking according to a specific sea area to be selected;
a filtering unit 7032 for filtering out all the ocean vortexes which are split and combined in the process of ocean vortex evolution;
a visualization unit 7033 for taking the filtered ocean vortices as visualization objects;
the display unit 7034 is used for displaying the time-varying events of each ocean vortex in the visual object;
the recording unit 7035 is configured to record each node data in the event as ocean flow field data;
and the identification unit 7036 is configured to analyze and identify the ocean flow field data by using the high-performance computing cluster to obtain identified ocean vortex data.
Preferably, the identifying module 703 further comprises an acquiring second information unit 7037, an acquiring third information unit 7038, an acquiring fourth information unit 7039 and a data information unit 7040, wherein:
retrieve second information element 7037: the system comprises a first information acquisition module, a second information acquisition module and a control module, wherein the first information acquisition module is used for acquiring first information which comprises information of a normal component and a shearing component of an ocean velocity field and information of a relative vorticity of the flow field;
acquiring third information unit 7038: the third information is obtained through a numerical simulation method according to the second information, and the third information is an Okubo-Weiss parameter;
acquire fourth information element 7039: the fourth information is obtained through calculation according to the third information, and the fourth information is ocean vortex parameters, sea level height and velocity vector information;
data information unit 7040: and calculating to obtain ocean flow field data information according to the fourth information and the tracking method.
Preferably, the generating module 705 includes a determining unit 7051, an extracting unit 7052, a second generating unit 7053, a transforming unit 7054, and a third generating unit 7055, wherein:
the determining unit 7051 is configured to determine, according to the key event, an event type to which the key event belongs;
the extracting unit 7052 is configured to extract keyword information corresponding to the key event according to the event type and preset feature information;
a second generating unit 7053 configured to generate a keyword table according to the keyword information and the high-precision streamline image;
a conversion unit 7054, configured to convert the keyword table into a narrative text description result through a model combining a recurrent neural network and a long-short term memory artificial neural network;
and a third generating unit 7055 for generating the narrative text description result into a key analysis result of the ocean vortex evolution.
It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
Example 3:
corresponding to the above method embodiment, the present embodiment further provides an ocean vortex evolution analysis device, and the ocean vortex evolution analysis device described below and the ocean vortex evolution analysis method described above may be referred to in correspondence.
FIG. 3 is a block diagram illustrating an ocean vortex evolution analysis device 800, according to an exemplary embodiment. As shown in fig. 3, the ocean vortex evolution analysis apparatus 800 may include: a processor 801, a memory 802. The ocean vortex evolution analysis device 800 may also include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the ocean vortex evolution analyzing apparatus 800, so as to complete all or part of the steps in the ocean vortex evolution analyzing method. The memory 802 is used to store various types of data to support the operation of the marine vortex evolution analysis device 800, which may include, for example, instructions for any application or method operating on the marine vortex evolution analysis device 800, as well as application-related data, such as contact data, transceived messages, pictures, audio, video, and so forth. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, and the like. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the ocean vortex evolution analyzing apparatus 800 and other apparatuses. Wireless communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: Wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the ocean vortex evolution analyzing Device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-mentioned ocean vortex evolution analyzing method.
In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the marine vortex evolution analysis method described above is also provided. For example, the computer readable storage medium may be the memory 802 described above comprising program instructions executable by the processor 801 of the ocean vortex evolution analysis device 800 to perform the ocean vortex evolution analysis method described above.
Example 4:
corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment, and a readable storage medium described below and an ocean vortex evolution analysis method described above may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the ocean vortex evolution analysis method of the above method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
In conclusion, the method has the advantages that the in-situ visualization is used for processing simulation analysis in a large-scale flow field; the vortex streamline structure with high precision can be generated in real time, and vortex statistical analysis and tracking analysis of different ocean areas and different scales are supported; the efficiency and the effectiveness of the system are proved; experts can be helped to track and analyze the evolution of ocean vortices.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An ocean vortex evolution analysis method, comprising:
extracting process information in an ocean vortex historical sample library, and constructing an ocean vortex process model;
mining the ocean vortex flow model by using a heuristic workflow algorithm, and extracting key events in the ocean vortex evolution process, wherein the key events comprise merging, splitting, generating and eliminating of the ocean vortices;
inputting the obtained ocean flow field data into a preset high-performance computing cluster for analysis, and identifying and tracking ocean vortexes according to a vortex detection method and a tracking method;
determining all key events in an ocean vortex evolution period according to the identified ocean vortices and the key events, and storing time points of all the key events and high-precision streamline images before and after the time points;
and generating a key analysis result of ocean vortex evolution by utilizing a model combining a cyclic neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all the key events.
2. The method for analyzing ocean vortex evolution according to claim 1, wherein the mining the ocean vortex flow model by using a heuristic workflow algorithm to extract key events in the ocean vortex evolution process comprises:
selecting a first object as a case object;
acquiring first information, wherein the first information comprises radius, energy and type information of an ocean vortex of the first object;
processing the first information through a heuristic workflow mining algorithm;
deducing keywords of the key events according to the processed first information and merging and extinction information of ocean vortexes in the first object;
and constructing a description table of the key event according to the key words.
3. The ocean vortex evolution analysis method according to claim 1, wherein the step of inputting the obtained ocean flow field data into a preset high-performance computing cluster for analysis, and identifying and tracking the ocean vortices according to a vortex detection method and a tracking method comprises the steps of:
generating a streamline and vortex tracking according to a specific sea area to be selected;
filtering out all ocean vortexes which are split and combined in the ocean vortex evolution process;
taking the filtered ocean vortexes as visual objects;
displaying events of each ocean vortex in the visual object changing along with time;
recording each node data in the event as the ocean flow field data;
and analyzing and identifying the ocean flow field data through the high-performance computing cluster to obtain the identified ocean vortex data.
4. The method for analyzing ocean vortex evolution according to claim 1, wherein the generating of the key analysis result of ocean vortex evolution by using a model combining a recurrent neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all the key events comprises:
determining the event type of the key event according to the key event;
extracting keyword information corresponding to the key event according to the event type and preset feature information;
generating a keyword list according to the keyword information and the high-precision streamline image;
converting the keyword list into a narrative character description result through a model combining a cyclic neural network and a long-short term memory artificial neural network;
and generating a key analysis result of the ocean vortex evolution by using the narrative text description result.
5. An ocean vortex evolution analysis device, comprising:
the extraction module is used for extracting the process information in the ocean vortex historical sample library and constructing an ocean vortex process model;
the mining module is used for mining the ocean vortex flow model by utilizing a heuristic workflow algorithm and extracting key events in the ocean vortex evolution process, wherein the key events comprise merging, splitting, generating and eliminating of ocean vortices;
the identification module is used for inputting the obtained ocean flow field data into a preset high-performance computing cluster for analysis, and identifying and tracking ocean vortexes according to a vortex detection method and a tracking method;
the determining module is used for determining all key events in an ocean vortex evolution period according to the identified ocean vortex and the key events and storing time points of all the key events and high-precision streamline images of the time points before and after the time points;
and the generation module is used for generating a key analysis result of the ocean vortex evolution by utilizing a model combining a cyclic neural network and a long-short term memory artificial neural network according to the high-precision streamline image and the types of all the key events.
6. The marine vortex evolution analysis device of claim 5, wherein the excavation module comprises:
the selecting unit is used for selecting the first object as a case object;
the first acquisition unit is used for acquiring first information, wherein the first information comprises the information of the radius, the energy and the type of the ocean vortex of the first object;
the processing unit is used for processing the first information through a heuristic workflow mining algorithm;
the merging unit is used for deducing keywords of the key events according to the processed first information and merging and extinction information of ocean vortexes in the first object;
and the construction unit is used for constructing the description table of the key event according to the key words.
7. The marine vortex evolution analysis device of claim 5, wherein the identification module comprises:
the first generation unit is used for generating a streamline and vortex tracking according to a specific sea area to be selected;
the filtering unit is used for filtering all the ocean vortexes which are split and combined in the ocean vortex evolution process;
the visualization unit is used for taking the filtered ocean vortexes as visualization objects;
the display unit is used for displaying the events of each ocean vortex in the visual object along with the change of time;
the recording unit is used for recording each node data in the event as the ocean flow field data;
and the identification unit is used for analyzing and identifying the ocean flow field data through the high-performance computing cluster to obtain the identified ocean vortex data.
8. The marine vortex evolution analysis device of claim 5, wherein the generation module comprises:
the determining unit is used for determining the event type of the key event according to the key event;
the extraction unit is used for extracting the keyword information corresponding to the key event according to the event type and preset characteristic information;
the second generation unit is used for generating a keyword list according to the keyword information and the high-precision streamline image;
the conversion unit is used for converting the keyword list into a narrative character description result through a model combining a recurrent neural network and a long-short term memory artificial neural network;
and the third generation unit is used for generating the narrative text description result into a key analysis result of the ocean vortex evolution.
9. An ocean vortex evolution analysis apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the marine vortex evolution analysis method of any one of claims 1 to 4 when executing the computer program.
10. A readable storage medium, characterized by: the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the marine vortex evolution analysis method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210441847.8A CN114997267A (en) | 2022-04-25 | 2022-04-25 | Ocean vortex evolution analysis method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210441847.8A CN114997267A (en) | 2022-04-25 | 2022-04-25 | Ocean vortex evolution analysis method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114997267A true CN114997267A (en) | 2022-09-02 |
Family
ID=83024503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210441847.8A Pending CN114997267A (en) | 2022-04-25 | 2022-04-25 | Ocean vortex evolution analysis method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997267A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115980773A (en) * | 2023-03-20 | 2023-04-18 | 中国海洋大学 | Evaluation and evolution analysis method for carbon circulation in ocean mesoscale vortex |
| CN117710834A (en) * | 2024-02-06 | 2024-03-15 | 中国水产科学研究院南海水产研究所 | Mesoscale vortex recognition analysis method, system and medium based on big data |
-
2022
- 2022-04-25 CN CN202210441847.8A patent/CN114997267A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115980773A (en) * | 2023-03-20 | 2023-04-18 | 中国海洋大学 | Evaluation and evolution analysis method for carbon circulation in ocean mesoscale vortex |
| CN115980773B (en) * | 2023-03-20 | 2023-07-04 | 中国海洋大学 | Estimation and evolution analysis method for internal carbon circulation of ocean mesoscale vortex |
| CN117710834A (en) * | 2024-02-06 | 2024-03-15 | 中国水产科学研究院南海水产研究所 | Mesoscale vortex recognition analysis method, system and medium based on big data |
| CN117710834B (en) * | 2024-02-06 | 2024-05-03 | 中国水产科学研究院南海水产研究所 | Mesoscale vortex recognition analysis method, system and medium based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Visual abstraction of large scale geospatial origin-destination movement data | |
| Zheng et al. | Visual analytics in urban computing: An overview | |
| Ver Hoef et al. | SSN: An R package for spatial statistical modeling on stream networks | |
| Woodring et al. | In situ eddy analysis in a high-resolution ocean climate model | |
| CN114997267A (en) | Ocean vortex evolution analysis method, device and equipment and readable storage medium | |
| Höllt et al. | Ovis: A framework for visual analysisof ocean forecast ensembles | |
| CN110287329A (en) | A kind of electric business classification attribute excavation method based on commodity text classification | |
| Deufemia et al. | Investigative analysis across documents and drawings: visual analytics for archaeologists | |
| CN108831442A (en) | Point of interest recognition methods, device, terminal device and storage medium | |
| Whittemore et al. | A participatory science approach to expanding instream infrastructure inventories | |
| CN116028798A (en) | Water damage early warning data processing method, device, computer equipment and storage medium | |
| CN114519356A (en) | Target word detection method and device, electronic equipment and storage medium | |
| CN112001435A (en) | Method and system for constructing training sample set in regional landslide early warning and storage medium | |
| Wang et al. | Overcoming bias in pretrained models by manipulating the finetuning dataset | |
| Palaniyappan Velumani et al. | AQX: Explaining air quality forecast for verifying domain knowledge using feature importance visualization | |
| CN114595635A (en) | Feature selection method, system and equipment for main steam temperature data of thermal power generating unit | |
| CN112529525B (en) | Method and system for extracting scene elements of power grid emergency and fusing all domains | |
| Asahara et al. | A mixed autoregressive hidden-markov-chain model applied to people's movements | |
| De Roo et al. | Bridging archaeology and GIS: influencing factors for a 4D archaeological GIS | |
| Yan et al. | Multilevel Robustness for 2D Vector Field Feature Tracking, Selection and Comparison | |
| Fatkhulin et al. | Analysis of the Basic Image Generation Methods by Neural Networks | |
| Han et al. | Narrative In Situ Visual Analysis for Large-Scale Ocean Eddy Evolution | |
| Abidin et al. | A Computerized Tool Based on Cellular Automata and Modified Game of Life for Urban Growth Region Analysis | |
| Palaniyappan et al. | AQX: Explaining Air Quality Forecast for Verifying Domain Knowledge using Feature Importance Visualization | |
| Popovici et al. | Clustering and visualization of geodetic array data streams using self-organizing maps |
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 |