KR102319145B1 - Method and device for generating high-resolution ocean data - Google Patents

Abstract

In the method for generating high-resolution ocean data, (a) training data including training ocean resource data, ocean weather data for training, and ocean physics data for training for each specific point in the ocean according to a specific latitude and a specific longitude is used In a state in which a machine learning-based ocean resource data prediction model for predicting the relationship between the ocean weather data for training and the ocean physical data for training and the ocean resource data for training is generated, the ocean data generating device is configured to: acquiring ocean meteorological data for testing and ocean physics data for testing for each of grid points in which regions are partitioned by latitude and longitude; (b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and (c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points. An apparatus for generating marine data is disclosed.

Description

Method for generating high-resolution ocean data and apparatus using the same

The present invention relates to a method for generating high-resolution ocean data and an apparatus using the same.

As the Ocean Spatial Planning and Management Act came into effect on April 18, 2019, the need for systematic integrated management of the entire ocean space is increasing.

However, as can be seen in FIG. 1 , conventionally, only marine resource information in the observed ocean area, which is built mainly for zenith and peak observation, exists, so a wide range of blank areas inevitably occur, and reliable in the non-observed ocean area. Since there was no marine resource information, there were difficulties in establishing a systematic policy for the entire ocean space.

Also, conventionally, a method of predicting marine resource information for an unobserved ocean area through linear interpolation is applied based on ocean observation information constructed mainly for stationary and vertex observations. However, the method by linear interpolation exists between two points. Because marine resource information is predicted only by a simple proportional expression derived from values observed at two points without considering the influence of various variables that There was a problem in that it was difficult to grasp accurate information about the unobserved ocean area.

For example, assuming that mackerel is not caught in areas above 25 degrees Celsius, a three-dimensional grid space including the sea level and the space below it is assumed, the observed water temperature in grid A is 20 degrees Celsius, and the observed water temperature in grid C is It is assumed that the temperature is 30 degrees Celsius, the unobserved water temperature in grid B located between grid A and grid C is 25 degrees Celsius, and the water temperature exceeds 25 degrees Celsius from grid B to grid C.

In the above situation, despite the fact that the catch of mackerel from grid B to grid C is inevitably reduced to 0 due to the water temperature, according to conventional linear interpolation, etc., the catch of mackerel from grid A to grid C decreases linearly. There was a problem in predicting data that was separated from the data.

or. According to the conventional linear interpolation, the water temperature of grid D, which is the midpoint of the physical distance between grid A and grid C, was predicted to be 25 degrees Celsius, and mackerel was expected to be caught only between grid A and grid D.

Therefore, there is a need for an improvement method to solve the above problems.

An object of the present invention is to solve all of the above problems.

In addition, the present invention grasps the relationship between marine meteorological data and marine physical data based on information actually observed at a wide range of points and marine resource data observed at a limited point, and thus provides an ocean view for an empty area where observation is restricted. It serves another purpose to produce resource data.

In addition, the present invention provides integrated ocean data for the entire ocean space by integrating ocean resource data for an actually observed point and ocean resource data for an empty area where observation is limited with ocean meteorological data and ocean physics data. for another purpose.

In order to achieve the object of the present invention as described above and to realize the characteristic effects of the present invention to be described later, the characteristic configuration of the present invention is as follows.

According to an aspect of the present invention, in a method for generating high-resolution ocean data, (a) ocean resource data for learning, ocean weather data for training, and ocean physics for learning for each specific point of the ocean according to a specific latitude and a specific longitude In a state in which a machine learning-based ocean resource data prediction model for predicting the relationship between the ocean weather data for training and the ocean physical data for training and the ocean resource data for training is generated by using the training data including the data, ocean data acquiring, by a generating device, ocean meteorological data for testing and ocean physics data for testing for each of the grid points dividing a predetermined area of the ocean by latitude and longitude; (b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and (c) generating, by the ocean data generating device, ocean data for the predetermined region of the ocean with reference to the test ocean resource data at the respective grid points. .

As an example, before step (a), (a0) when the learning data including the marine resource data for learning, the marine weather data for learning, and the marine physics data for learning for each of the specific points of the ocean is obtained , the ocean data generating device inputs the training ocean weather data and the training ocean physical data into the ocean resource data prediction model, so that the ocean resource data prediction model causes the ocean weather data for training at each of the specific points and generating output ocean resource data for training corresponding to the ocean physical data for training, and calculating a loss by comparing the output ocean resource data for training with the ocean resource data for training at each of the specific points, and generating the marine resource data prediction model for predicting the relationship between the marine weather data for learning, the marine physical data for learning, and the marine resource data for learning by performing back propagation using a loss; Disclosed is a method characterized in that it further comprises;

As an example, in the step (a), when some actual measurement data of marine weather variables generated by actually measuring at least some of the grid points are obtained, the ocean data generating apparatus may measure the partial ocean weather variables. Marine meteorological data prediction model for data - The marine weather data prediction model actually measures a specific ocean weather variable generated by actually measuring at a specific grid point among a plurality of grid points dividing an arbitrary area of the ocean by the latitude and the longitude It is generated to predict arbitrary marine weather data for each of the plurality of grid points using data - for the test by making the marine weather data prediction model refer to the actual measured data of some marine weather variables by inputting Disclosed is a method comprising generating marine meteorological data.

As an example, in the step (a), when the measured data of some marine meteorological variables and specific resolution information are obtained, the ocean data generating apparatus may predict the marine weather data by using the measured data of some marine weather variables and the specific resolution information. By inputting into a model, the marine meteorological data prediction model generates and transmits the test marine meteorological data matching the specific resolution information by referencing the actual measurement data of some ocean weather variables and the specific resolution information, and transmitting the specific information. Obtaining the marine meteorological data for the test and the marine physical data for the test corresponding to the resolution information, and in the step (b), the ocean data generating device sets the predetermined area of the ocean as the latitude and the longitude. By inputting the test ocean meteorological data and the test ocean physical data for each of the grid points partitioned to correspond to a specific resolution into the ocean resource data prediction model, the ocean resource data prediction model causes the each to predict and output the test marine resource data at each of the grid points corresponding to the test marine meteorological data for the grid points and the test marine physical data, and in the step (c), the A method is disclosed, wherein the ocean data generating apparatus generates the ocean data corresponding to the specific resolution for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points. do.

As an example, in the step (b), the ocean data generating device performs (i) a predetermined distance to each of the grid points as a predetermined pre-processing process for the test ocean meteorological data and the test ocean physical data. After determining sampling grid points with reference to a reference, (ii) generating ocean weather sampling data and ocean physical sampling data corresponding to each of the sampling grid points from among the test ocean weather data and the test ocean physical data , input the ocean weather sampling data and the ocean physics sampling data to the ocean resource data prediction model to cause the ocean resource data prediction model to output ocean resource sampling data at each of the sampling grid points, and In step (c), the method characterized in that the ocean data generating device generates ocean sampling data for the predetermined area of the ocean with reference to the ocean resource sampling data for each of the sampling grid points. is initiated.

As an example, the marine meteorological data for the test and the marine physical data for the test refer to each of the ocean weather observation data and the ocean physics observation data separately obtained for specific grid points that are at least some of the respective grid points, Disclosed is a method characterized in that each of the ocean weather forecast data and the ocean physics prediction data obtained for each of the grid points are corrected and generated.

As an example, the marine weather data for learning and the marine weather data for the test include information about at least some of atmospheric pressure, wind direction, wind speed, insolation, temperature, humidity, general weather, moon phase, wave height, and rainfall, and the learning ocean A method is disclosed, wherein the physical data and the marine physical data for the test include information about at least some of tidal, wave direction, wave velocity, sound velocity, density and surface sediments.

As an example, the marine resource data for learning and the marine resource data for testing include information on at least part of water temperature, salinity, dissolved oxygen, nutrient information, zooplankton information, and fish resource information. do.

As an example, (d) when a geographic information system (GIS) ocean data inquiry request is obtained from the user terminal, the ocean data generating device transmits the ocean data generated for the predetermined area of the ocean to the user terminal, , causing the user terminal to display the GIS ocean data corresponding to the ocean data; a method comprising further comprising is disclosed.

As an example, in the step (d), when a specific GIS ocean data inquiry request including information on a specific location in the specific area of the ocean is obtained from the user terminal, the ocean data generating device is configured to: Disclosed is a method characterized in that by transmitting specific ocean data generated for a specific location to the user terminal, the user terminal displays specific GIS ocean data corresponding to the specific ocean data.

According to another aspect of the present invention, there is provided an apparatus for generating marine data for generating high-resolution marine data, comprising: at least one memory storing instructions; and at least one processor configured to execute the instructions, wherein the processor comprises: (1) ocean resource data for training, ocean weather data for training, and ocean for training for each specific point of the ocean according to a specific latitude and a specific longitude. In a state in which a machine learning-based ocean resource data prediction model for predicting the relationship between the ocean weather data for training and the ocean physical data for training and the ocean resource data for training is generated by using learning data including physical data, the a process of acquiring ocean meteorological data for testing and ocean physics data for testing for each of grid points in which a predetermined area of the ocean is partitioned by latitude and longitude; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) an apparatus for generating ocean data that executes the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the ocean resource data for testing at each of the grid points. .

As an example, before the (1) process, the processor obtains the learning data including the marine resource data for learning, the marine weather data for learning, and the marine physics data for learning for each of the specific points in the ocean. When it is, the marine weather data for learning and the marine physical data for learning are input to the marine resource data prediction model, and the marine resource data prediction model causes the learning marine weather data and the learning marine physical data at each of the specific points. to generate the output marine resource data for learning corresponding to , and calculate a loss by comparing the output marine resource data for learning and the marine resource data for learning at each of the specific points, and backpropagation using the loss (back propagation), the process of generating the marine resource data prediction model for predicting the relationship between the marine weather data for learning, the marine physical data for learning, and the marine resource data for learning; Disclosed is an apparatus for generating marine data characterized by the present invention.

As an example, the processor, in the process (1), when some actual measured ocean weather variable data generated by actually measuring at least some of the respective grid points is obtained, converts the partial ocean weather variable actually measured data to the ocean Meteorological data prediction model - The marine weather data prediction model uses specific ocean weather variable measurement data generated by actually measuring at a specific grid point among a plurality of grid points dividing an arbitrary area of the ocean by the latitude and the longitude. It is generated to predict any ocean weather data for each of the plurality of grid points - by inputting the marine weather data prediction model to refer to the actual measured data of some ocean weather variables, and the test marine weather data Disclosed is an apparatus for generating ocean data, characterized in that it generates

As an example, in the process (1), when the partial ocean weather variable actual data and specific resolution information are obtained, the processor inputs the partial ocean weather variable actual data and the specific resolution information into the marine weather data prediction model. to generate and transmit the test marine meteorological data matching the specific resolution information by making the marine weather data prediction model refer to the actual measured data of some marine weather variables and the specific resolution information, and transmit the data to the specific resolution information Acquire the corresponding marine meteorological data for the test and the marine physical data for the test, and in the process (2), each By inputting the test marine meteorological data for the grid points and the test marine physical data into the marine resource data prediction model, the marine resource data prediction model causes the test marine weather data for each of the grid points predicting and outputting the test marine resource data at each of the grid points corresponding to the data and the test marine physical data, and in the (3) process, the test at each of the grid points Disclosed is an apparatus for generating ocean data characterized in that the ocean data corresponding to the specific resolution for the predetermined area of the ocean is generated with reference to ocean resource data.

As an example, in the process (2), the processor refers to (i) a predetermined distance criterion for each of the grid points as a predetermined pre-processing process for the test ocean weather data and the test ocean physical data. to determine sampling grid points, (ii) generating ocean weather sampling data and ocean physical sampling data corresponding to each of the sampling grid points from among the test ocean weather data and the test ocean physical data, and then (3) input the weather sampling data and the marine physical sampling data into the marine resource data prediction model, causing the marine resource data prediction model to output the marine resource sampling data at the respective sampling grid points; In the process, an apparatus for generating ocean data is disclosed, wherein ocean sampling data for the predetermined area of the ocean is generated by referring to the ocean resource sampling data for each of the sampling grid points.

As an example, the marine meteorological data for the test and the marine physical data for the test refer to each of the ocean weather observation data and the ocean physics observation data separately obtained for specific grid points that are at least some of the respective grid points, Disclosed is an apparatus for generating ocean data, characterized in that each of the ocean weather forecast data and ocean physics prediction data acquired for each of the grid points is corrected and generated.

As an example, the marine weather data for learning and the marine weather data for the test include information about at least some of atmospheric pressure, wind direction, wind speed, insolation, temperature, humidity, general weather, moon phase, wave height, and rainfall, and the learning ocean Disclosed is an apparatus for generating ocean data, characterized in that the physical data and the marine physical data for the test include information on at least a portion of an even, wave direction, wave velocity, sound velocity, density, and surface sediments.

As an example, the marine resource data for learning and the marine resource data for testing include information on at least a portion of water temperature, salinity, dissolved oxygen, nutrient information, zooplankton information, and fish resource information. The device is disclosed.

As an example, (4) the processor, when a geographic information system (GIS) ocean data inquiry request is obtained from the user terminal, transmits the ocean data generated for the predetermined area of the ocean to the user terminal, and the user A process for causing a terminal to display GIS ocean data corresponding to the ocean data; Disclosed is an apparatus for generating ocean data, characterized in that it further comprises.

As an example, the processor, in the process (4), when a specific GIS ocean data inquiry request including information on a specific location of the specific area of the ocean is obtained from the user terminal, the specific location of the ocean Disclosed is an apparatus for generating ocean data, characterized in that by transmitting specific ocean data generated for the user terminal to the user terminal, the user terminal displays specific GIS ocean data corresponding to the specific ocean data.

In addition to this, a computer-readable recording medium for recording a computer program for executing the method of the present invention is further provided.

The present invention identifies the relationship between marine meteorological data and ocean physical data based on information actually observed at a wide range of points and marine resource data observed at limited points, and thus provides marine resource data for an empty area where observation is restricted. has the effect of producing

In addition, the present invention provides an effect of providing integrated ocean data for the entire ocean space by integrating ocean resource data for an actually observed point and ocean resource data for an empty area where observation is limited with ocean meteorological data and ocean physics data. there is

The accompanying drawings for use in the description of the embodiments of the present invention are only a part of the embodiments of the present invention, and for those of ordinary skill in the art to which the present invention pertains (hereinafter "those skilled in the art"), the invention Other drawings may be obtained based on these drawings without any work being done.
1 schematically shows the problems of the ocean data generation method that relies on conventional stationary and vertex observations,
2 schematically shows an apparatus for generating ocean data for generating high-resolution ocean data according to an embodiment of the present invention;
3a and 3b schematically show a process of generating a marine resource data prediction model according to an embodiment of the present invention,
4a and 4b schematically show a process of generating high-resolution ocean data according to an embodiment of the present invention;
5 schematically illustrates ocean data generated for a grid corresponding to a non-observing point according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following detailed description of the present invention refers to the accompanying drawings, which show by way of illustration a specific embodiment in which the present invention may be practiced, in order to clarify the objects, technical solutions and advantages of the present invention. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention.

Also, throughout this description and claims, the word "comprises" and variations thereof are not intended to exclude other technical features, additions, components or steps. Other objects, advantages and characteristics of the present invention will appear to a person skilled in the art, in part from this description, and in part from practice of the present invention. The following illustrations and drawings are provided by way of illustration and are not intended to limit the invention.

Moreover, the invention encompasses all possible combinations of the embodiments indicated herein. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein with respect to one embodiment may be embodied in other embodiments without departing from the spirit and scope of the invention. In addition, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to enable those of ordinary skill in the art to easily practice the present invention.

FIG. 2 schematically shows an ocean data generating apparatus 200 for generating high-resolution ocean data according to an embodiment of the present invention. Referring to FIG. 2 , the ocean data generating device 200 generates high-resolution ocean data. It may include a memory 210 that stores instructions for generating and a processor 220 that performs an operation of generating high-resolution ocean data in response to the instructions stored in the memory 210 .

Specifically, the ocean data generating device 200 is typically a computing device (eg, a computer processor, memory, storage, input device and output device, a device that may include other components of existing computing devices; routers, switches, etc.) using a combination of electronic communication devices such as electronic information storage systems such as network attached storage (NAS) and storage area networks (SANs) and computer software (i.e., instructions that cause the computing device to function in a particular way). It may be to achieve the desired system performance.

In addition, the processor of the computing device may include a hardware configuration such as a micro processing unit (MPU) or a central processing unit (CPU), a cache memory, and a data bus. In addition, the computing device may further include an operating system and a software configuration of an application for performing a specific purpose.

However, a case in which the computing device includes an integrated processor in which a medium, a processor, and a memory are integrated for implementing the present invention is not excluded.

A method of generating high-resolution ocean data by the ocean data generating apparatus 200 configured as described above will be described below.

First, a marine weather data prediction model for generating marine weather data will be described, and a process by which the marine weather data prediction model generates marine weather data for training or marine weather data for testing will be described.

The marine meteorological data prediction model uses specific ocean weather variable measurement data generated by actually measuring at a specific grid point among a plurality of grid points partitioning an arbitrary area of the ocean by latitude and longitude for each of the plurality of grid points. It can be generated to predict any ocean weather data.

That is, the marine meteorological data prediction model is measured at a specific grid point that is at least a part of the entire grid point even if the ocean weather variable is not actually measured for all of the plurality of grid points partitioning an arbitrary area of the ocean by latitude and longitude. Any ocean weather data for all of the plurality of grid points may be predicted using the generated specific ocean weather variable actual measurement data.

For reference, the marine weather variable actual data may include information on at least a portion of air pressure, wind direction, wind speed, insolation, temperature, humidity, general weather, moon phase, wave height, and rainfall, but is not limited thereto. Various variables for predicting data may be included.

As such, in a state in which a marine weather data prediction model for predicting marine weather data is generated, some marine weather generated by actually measuring at least some of the grid points of each grid point partitioning a certain area of the ocean by latitude and longitude When the measured variable data is obtained, the marine data generating apparatus 200 inputs the measured marine weather variable data to the marine weather data prediction model, and causes the marine weather data prediction model to refer to the measured marine weather variable data for learning. It can generate marine weather data or marine weather data for testing. That is, the marine weather data prediction model may generate data at the remaining grid points including adjacent grid points with reference to data actually measured at some grid points.

Alternatively, for the test marine weather data and test marine physical data, each of the ocean weather observation data and the ocean physics observation data separately obtained for specific grid points that are at least some of the grid points are referenced, and each grid point Each of the marine weather forecast data and the marine physics prediction data obtained with respect to them may be corrected and generated. For example, the ocean data generating apparatus 200 may generate marine weather data for testing by correcting ocean weather data predicted for all grid points with ocean weather data observed for at least some of all grid points. have.

Next, a process of generating a marine resource data prediction model for predicting the relationship between the ocean meteorological data and ocean physical data generated through the process described above and the ocean resource data will be described.

For reference, the marine weather data for learning and the marine weather data for testing may include information on at least a portion of air pressure, wind direction, wind speed, insolation, temperature, humidity, general weather, moon phase, wave height, and rainfall.

In addition, the marine physics data for training and the marine physics data for testing may include information on at least a portion of an even, wave direction, wave velocity, sound velocity, density, and surface sediments. However, the present invention is not limited thereto, and flow velocity, water depth, current and tidal current information, sediment heavy metals, water depth flow data, suspended matter, branch, gravel, sand, coastal characteristics, bedrock characteristics, sedimentation environment, electrical conductivity, transparency, hydrogen ion concentration and the like.

In addition, the marine resource data for learning and the marine resource data for testing may include information on at least some of water temperature, salinity, dissolved oxygen, nutrient information, zooplankton information, and fish resource information.

Here, the fish resource information may include at least a part of information on the species, catch amount, size of the caught individual, the type of aquatic product, the yield of the aquatic product, the size of the harvested aquatic product individual, etc. in the grid area, but is not limited thereto. no.

In addition, the marine resource data for learning and the marine resource data for testing are data including information on at least part of water temperature, salinity, dissolved oxygen, nutrient information, zooplankton information, and fish resource information at the sea level, which is a two-dimensional plane. However, the present invention is not limited thereto.

That is, in a three-dimensional grid space that includes the sea level and the space below it, water temperature, salinity, dissolved oxygen amount, nutrient information, zooplankton information, and fish resource information change according to changes in latitude, longitude, and depth of seawater. can

On the other hand, since the machine learning method applied to the marine resource data prediction model is not limited to a specific method, linear regression, decision tree, multilayer perceptron, support vector machine, deep neural network ( A variety of methods such as a deep neural network, a convolutional neural network, a recurrent neural network (RNN), and a generative adversarial network (GAN) may be applied.

As an example, referring to the flowchart of FIG. 3A , when learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean is acquired ( S301 ), ocean data is generated The device 200 inputs the marine meteorological data for learning and the marine physical data for learning into the marine resource data prediction model (S302), so that the marine resource data prediction model causes the marine weather data for learning and the marine physics data for learning at each specific point. to generate the output marine resource data for learning corresponding to (S303), compare the output marine resource data for learning and the marine resource data for learning at each specific point to calculate a loss (S304), and use the loss By performing back propagation ( S305 ), it is possible to generate a marine resource data prediction model that predicts a relationship between the marine weather data for learning and the marine physical data for learning and the marine resource data for learning.

As another example, according to the boosting regression tree method, it is possible to learn the gradient of each individual tree and reduce the residual.

For example, referring to FIG. 3B , when the result of the point at which the water temperature is to be predicted is a hatched pattern box, tree 1 and tree 2 are generated as weak classifiers, and a large tree combined with each tree is selected as a strong classifier. , 2.3, which is the sum of the scores of each individual tree, can be the water temperature score of the point to be predicted.

In this way, in a state where the marine resource data prediction model for predicting the relationship between the marine meteorological data and the marine physical data and the marine resource data is generated, the flow chart of FIG. With reference to this will be described in detail below.

That is, the ocean data generating apparatus 200 may acquire ocean meteorological data for testing and ocean physical data for testing for each of the grid points dividing a predetermined area of the ocean by latitude and longitude ( S401 ).

Then, the ocean data generating device 200 inputs the marine meteorological data for testing and the ocean physical data for testing for each grid point dividing a certain area of the ocean by latitude and longitude into the marine resource data prediction model ( S402), the marine resource data prediction model can predict and output the test marine resource data at each grid point corresponding to the test marine meteorological data and the test marine physical data for each grid point There is (S403).

In addition, the ocean data generating apparatus 200 may generate ocean data for a certain area of the ocean with reference to the test ocean resource data at each grid point ( S404 ).

The overall process has been briefly reviewed with reference to the flowchart of FIG. 3A and the flowchart of FIG. 4A above, and a more detailed process will be described with reference to FIG. 4B below.

For example, when learning data at limited points where Jeongseon observation data and fisheries statistical data exist are acquired, the marine data generating apparatus 200 performs a data standardization process for the corresponding learning data to configure a dataset for machine learning. can be rough Such learning data may include, for example, (i) learning marine resource data including at least part of water temperature, salinity, dissolved oxygen content, nutrients, zooplankton population, aquatic product type and catch information, (ii) air pressure, wind direction, wind speed, insolation, Oceanic meteorological data for training that includes at least some of temperature, humidity, lunar phase, wave height and rainfall information, and (iii) ocean physics for training that includes at least part of information about even, wave direction, wave velocity, speed of sound, density, and surface sediments. data may be included.

Then, the marine data generating apparatus 200 inputs the learning data to the marine resource data prediction model, and causes the marine resource data prediction model to generate the learning output marine resource data corresponding to the marine weather data for learning and the marine physical data for learning. can make it

And, the marine data generating device 200 calculates the loss by comparing the marine resource data prediction model with the learning output marine resource data that is the predicted value and the learning marine resource data that is the correct value, and performs backpropagation using the loss. By doing so, it is possible to learn to predict the relationship between the marine weather data for learning, the marine physics data for learning, and the variables of the marine resource data for learning by analyzing the correlation between them.

In this way, in a state in which the marine resource data prediction model is generated, in order to generate actual marine resource data for each of the grid points dividing an arbitrary area of the ocean, the test marine weather data and test for each of the grid points When the marine physical data for use is obtained, the marine data generating apparatus 200 may cause the marine resource data prediction model to predict and output the marine resource data for testing at each grid point.

That is, unlike the existing reliance on stationary observation data and fishery statistical data at limited points to generate marine resource data, the ocean data generating device 200 is based on high-resolution ocean meteorological data and ocean physics data. It becomes possible to generate high-resolution marine resource data.

In addition, the marine data generating apparatus 200 may provide only the high-resolution marine resource data generated in this way to the service user, but complex marine data in which marine meteorological data and marine physical data are referenced through the GIS WEB development/expression service. may also provide

As an embodiment of the present invention as described above, the apparatus 200 for generating ocean data may generate ocean data to correspond to specific resolution information. That is, the ocean data generating apparatus 200 (i) corresponds to all of the grid points so as to correspond to the ocean meteorological data and the ocean physics data at all of the grid points dividing a certain area of the ocean by latitude and longitude. Ocean data may be generated, but (ii) ocean data at corresponding grid points may be generated by segmenting a certain area of the ocean to match specific resolution information.

More specifically, when the measured data of some marine meteorological variables and specific resolution information are obtained, the marine data generating apparatus 200 inputs the measured data of some marine weather variables and specific resolution information into the marine weather data prediction model to obtain marine meteorological data By making the prediction model refer to some ocean weather variable actual data and specific resolution information to generate and transmit test ocean weather data matching specific resolution information, marine weather data for testing corresponding to specific resolution information and test It is possible to acquire marine physics data.

In addition, the marine data generating apparatus 200 predicts marine resource data by using the marine meteorological data for testing and marine physical data for testing with respect to each grid point in which a certain area of the ocean is partitioned to correspond to a specific resolution by latitude and longitude. Input to the model, so that the marine resource data prediction model predicts and outputs the test ocean resource data at each grid point corresponding to the test ocean meteorological data and the test ocean physics data for each grid point can do.

In addition, the ocean data generating apparatus 200 may generate ocean data corresponding to a specific resolution for a certain area of the ocean with reference to the test ocean resource data at each grid point.

As another embodiment, a predetermined pre-processing process may be performed on the test ocean weather data and the test ocean physical data in order to reduce the amount of computation of the ocean resource data prediction model and increase the computation speed.

That is, the ocean data generating apparatus 200 (i) determines sampling grid points with reference to a predetermined distance reference for each grid point, and (ii) sampling of ocean weather data for testing and ocean physical data for testing. After generating ocean weather sampling data and ocean physical sampling data corresponding to each of the grid points, the ocean weather sampling data and ocean physical sampling data are input to the ocean resource data prediction model to cause the ocean resource data prediction model to each sample Ocean resource sampling data at grid points may be output, and ocean sampling data for a certain area of the ocean may be generated by referring to ocean resource sampling data for each sampling grid point.

On the other hand, when a GIS (geographic information system) marine data inquiry request is obtained from the user terminal, the marine data generating apparatus 200 transmits the marine data generated for a certain area of the ocean to the user terminal, so that the user terminal makes the marine It is possible to display GIS ocean data corresponding to the data.

For example, in a state in which the marine data generating apparatus 200 generates marine data covering the entire sea area near the Korean Peninsula and stores it in the GIS engine for each grid, when a GIS marine data inquiry request is obtained from the user terminal, the user allows the GIS It is possible to inquire marine data.

In this case, when a specific GIS ocean data inquiry request including information on a specific location in a certain area of the ocean is obtained from the user terminal, the ocean data generating apparatus 200 uses the specific ocean data generated for a specific location in the ocean to the user. By transmitting to the terminal and causing the user terminal to display the specific GIS ocean data corresponding to the specific ocean data at a specific location, the user can select the specific GIS ocean data that the user wants to inquire among high-resolution GIS ocean data composed of data from a plurality of grid points. You can also check GIS ocean data for your location.

Through this, as shown in FIG. 5, it is possible to check the high-resolution grid-specific ocean data produced in response to a certain area, rather than just checking the discontinuous ocean observation information that existed only at the existing observation point (black box). do. In addition, not only generates ocean data for the adjacent grid of the observed grid, but also generates ocean data for grids located far from the observed grid, such as grids in the ocean boundary region of neighboring countries, which have been difficult to observe in the past. You can also create

In addition, the embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM, a DVD, and a magneto-optical medium such as a floppy disk. media), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

In the above, the present invention has been described with specific matters such as specific components and limited embodiments and drawings, but these are provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , those of ordinary skill in the art to which the present invention pertains can make various modifications and variations from these descriptions.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and not only the claims described below, but also all modifications equivalently or equivalently to the claims described below belong to the scope of the spirit of the present invention. will do it

Claims (20)

A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
Before step (a),
(a0) When the learning data including the marine resource data for learning, the marine weather data for learning, and the marine physics data for learning for each of the specific points of the ocean is obtained, the ocean data generating device is configured to: By inputting the weather data and the marine physics data for learning into the marine resource data prediction model, the marine resource data prediction model causes the learning output corresponding to the marine weather data for learning and the marine physical data for learning at each of the specific points. to generate marine resource data, to calculate a loss by comparing the learning output marine resource data and the learning marine resource data at each of the specific points, and back propagation using the loss generating the marine resource data prediction model for predicting a relationship between the marine weather data for learning, the marine physical data for learning, and the marine resource data for learning;
Method, characterized in that it further comprises. delete A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
In step (a),
When the measured data of some ocean weather variables actually measured and generated at least some of the grid points are acquired, the ocean data generating device converts the part of the actually measured ocean weather variables into an ocean weather data prediction model - the ocean The meteorological data prediction model is configured to calculate the plurality of grid points by using specific ocean weather variable actual measurement data generated by actually measuring at a specific grid point among a plurality of grid points dividing an arbitrary area of the ocean by the latitude and the longitude. It is generated to predict any ocean weather data for each - input as - so that the ocean weather data prediction model refers to the actual measured data of some ocean weather variables to generate the ocean weather data for the test How to. 4. The method of claim 3,
In step (a),
When the measured data of some ocean weather variables and specific resolution information are obtained, the apparatus for generating ocean data inputs the measured data of some ocean weather variables and the specific resolution information into the ocean weather data prediction model to predict the ocean weather data. to generate and transmit the test marine meteorological data matching the specific resolution information by referring to the partial ocean weather variable actual measurement data and the specific resolution information, so that the test marine weather data corresponding to the specific resolution information Acquire data and marine physics data for the test,
In step (b),
The ocean data generating device is configured to generate the test ocean meteorological data and the test ocean physical data for each of the grid points in which the predetermined area of the ocean is partitioned to correspond to the specific resolution by the latitude and the longitude. By inputting into the marine resource data prediction model, the marine resource data prediction model causes the marine meteorological data for the test for each of the grid points and the marine physical data for the test at each of the grid points. To predict and output the marine resource data for the test,
In step (c),
The ocean data generating apparatus generates the ocean data corresponding to the specific resolution for the predetermined area of the ocean with reference to the test ocean resource data at each of the grid points. A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
In step (b),
As a predetermined pre-processing process for the marine meteorological data for the test and the marine physical data for the test, the ocean data generating device determines (i) sampling grid points with reference to a predetermined distance criterion for each of the grid points, , (ii) after generating the ocean weather sampling data and ocean physics sampling data corresponding to each of the sampling grid points among the ocean weather data for the test and the ocean physical data for the test, the ocean weather sampling data and the ocean physics data Input sampling data to the marine resource data prediction model, causing the marine resource data prediction model to output marine resource sampling data at each of the sampling grid points,
In step (c),
The method of claim 1, wherein the apparatus for generating ocean data generates ocean sampling data for the predetermined area of the ocean with reference to the ocean resource sampling data for each of the sampling grid points. A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
The marine weather data for the test and the marine physical data for the test refer to each of the ocean weather observation data and the ocean physical observation data separately obtained for specific grid points that are at least some of the respective grid points, respectively. A method characterized in that each of the marine weather forecast data and the marine physics prediction data obtained with respect to the grid points are corrected and generated. A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
The marine weather data for learning and the marine meteorological data for the test include information about at least some of atmospheric pressure, wind direction, wind speed, insolation, temperature, humidity, general conditions, moon phase, wave height, and rainfall,
The marine physics data for learning and the marine physics data for testing include information on at least a portion of an even, wave direction, wave velocity, sound velocity, density, and surface sediments. A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
The marine resource data for learning and the marine resource data for testing include information on at least part of water temperature, salinity, dissolved oxygen, nutrient information, zooplankton information, and fish resource information. A method for generating high-resolution ocean data, comprising:
(a) Learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each of specific points in the ocean according to a specific latitude and a specific longitude are used, so that the learning ocean weather data and the learning ocean physics data are used. In a state in which a machine learning-based ocean resource data prediction model for predicting a relationship between data and the training ocean resource data is generated, the ocean data generating apparatus divides a certain area of the ocean by latitude and longitude. acquiring ocean meteorological data for testing and ocean physics data for testing, respectively;
(b) the ocean data generating device generates the test ocean meteorological data and the test ocean physical data for each of the grid points dividing the predetermined area of the ocean by the latitude and the longitude as the ocean resource By inputting the data prediction model, the marine resource data prediction model causes the test ocean meteorological data for each of the grid points and the test ocean at each of the grid points corresponding to the test ocean physics data. predicting and outputting resource data; and
(c) generating, by the ocean data generating device, ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points;
including,
(d) when a geographic information system (GIS) ocean data inquiry request is obtained from the user terminal, the ocean data generating device transmits the ocean data generated for the predetermined area of the ocean to the user terminal, and the user causing the terminal to display GIS ocean data corresponding to the ocean data;
Method, characterized in that it further comprises. 10. The method of claim 9,
In step (d),
When a specific GIS ocean data inquiry request including information on a specific location in the certain area of the ocean is obtained from the user terminal, the ocean data generating device returns the specific ocean data generated for the specific location in the ocean By transmitting to the user terminal, the method characterized in that the display of the specific GIS ocean data corresponding to the specific ocean data by the user terminal. An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
Prior to the (1) process,
When the processor acquires the learning data including the marine resource data for learning, the marine weather data for learning, and the marine physics data for learning for each of the specific points of the ocean, the learning ocean weather data and the learning ocean By inputting physical data into the marine resource data prediction model, the marine resource data prediction model generates the training output ocean resource data corresponding to the training ocean weather data and the training ocean physical data at each of the specific points. By comparing the output marine resource data for learning and the marine resource data for learning at each of the specific points to calculate a loss and to perform back propagation using the loss, the learning for a process of generating the marine resource data prediction model for predicting a relationship between marine weather data, the marine physical data for training, and the marine resource data for training;
Marine data generating apparatus, characterized in that it further performs. delete An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
The processor is
In the process (1) above,
When the actual measured data of some ocean weather variables generated by being actually measured at at least some of the grid points of each of the grid points is obtained, the actual measured data of the partial ocean weather variables is used as an ocean weather data prediction model - the ocean weather data prediction model includes: Random ocean weather for each of the plurality of grid points using specific ocean weather variable actual measurement data generated by actually measuring at a specific grid point among a plurality of grid points dividing an arbitrary area of the ocean by the latitude and longitude It is generated to predict the data - by inputting the marine meteorological data prediction model to refer to the actual measured data of some of the marine weather variables to generate the marine meteorological data for the test. 14. The method of claim 13,
The processor is
In the process (1) above,
When the measured data of some marine weather variables and specific resolution information are obtained, the measured data of some ocean weather variables and the specific resolution information are input to the ocean weather data prediction model to cause the ocean weather data prediction model to cause the partial ocean weather variables By referring to the measured data and the specific resolution information to generate and transmit the test marine meteorological data matching the specific resolution information, the test marine meteorological data corresponding to the specific resolution information and the test marine meteorological data acquire data,
In the process (2) above,
The test ocean meteorological data and the test ocean physical data for each of the grid points in which the predetermined area of the ocean is partitioned to correspond to the specific resolution by the latitude and the longitude are added to the ocean resource data prediction model. By input, the marine resource data prediction model causes the test marine meteorological data for each of the grid points and the test marine resource data at each of the grid points corresponding to the test marine physical data. to predict and output
In the process (3) above,
Ocean data generating apparatus, characterized in that generating the ocean data corresponding to the specific resolution for the predetermined area of the ocean with reference to the test ocean resource data at each of the grid points. An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
The processor is
In the process (2) above,
As a predetermined pre-processing process for the marine meteorological data for the test and the marine physical data for the test, (i) determining sampling grid points with reference to a predetermined distance criterion for each of the grid points, (ii) for the test After generating ocean weather sampling data and ocean physical sampling data corresponding to each of the sampling grid points among ocean weather data and ocean physical data for the test, the ocean weather sampling data and the ocean physical sampling data are combined with the ocean resource data Input to the prediction model, causing the marine resource data prediction model to output the marine resource sampling data at each of the sampling grid points,
In the process (3) above,
Ocean data generating apparatus, characterized in that generating ocean sampling data for the predetermined area of the ocean by referring to the ocean resource sampling data for each of the sampling grid points. An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
The test ocean weather data and the test ocean physical data refer to each of the ocean weather observation data and ocean physics observation data separately acquired for specific grid points that are at least some of the respective grid points, respectively. Ocean data generating apparatus, characterized in that each of the marine weather forecast data and the ocean physics prediction data obtained with respect to the grid points are corrected and generated. An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
The marine weather data for learning and the marine meteorological data for the test include information about at least some of atmospheric pressure, wind direction, wind speed, insolation, temperature, humidity, general conditions, moon phase, wave height, and rainfall,
The marine physical data for learning and the marine physical data for testing include information on at least a portion of an even, wave direction, wave velocity, sound velocity, density, and surface sediments. An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physics data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
The marine resource data for learning and the marine resource data for testing include information on at least some of water temperature, salinity, dissolved oxygen, nutrient information, zooplankton information, and fish resource information. An apparatus for generating ocean data for generating high-resolution ocean data, the apparatus comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions;
The processor is configured to (1) use learning data including marine resource data for learning, marine weather data for learning, and ocean physics data for learning for each specific point in the ocean according to a specific latitude and a specific longitude, so that the learning ocean weather data and In a state in which a machine learning-based marine resource data prediction model for predicting the relationship between the marine physical data for learning and the marine resource data for learning is generated, each of the grid points dividing a certain area of the ocean by latitude and longitude a process of acquiring ocean meteorological data for testing and ocean physics data for testing; (2) by inputting the test ocean meteorological data and the test ocean physical data for each of the grid points that partitioned the predetermined area of the ocean by the latitude and the longitude into the ocean resource data prediction model, So that the marine resource data prediction model predicts and outputs the test marine resource data at each of the grid points corresponding to the test marine weather data and the test marine physical data for each of the grid points process; and (3) executing the instructions for performing a process of generating ocean data for the predetermined area of the ocean with reference to the test ocean resource data at the respective grid points,
(4) the processor, when a geographic information system (GIS) ocean data inquiry request is obtained from the user terminal, transmits the ocean data generated for the predetermined area of the ocean to the user terminal, causing the user terminal to a process for displaying GIS ocean data corresponding to the ocean data;
Marine data generating apparatus, characterized in that it further performs. 20. The method of claim 19,
The processor is
In the process (4) above,
When a specific GIS ocean data inquiry request including information on a specific location in the certain area of the ocean is obtained from the user terminal, the specific ocean data generated for the specific location in the ocean is transmitted to the user terminal, Ocean data generating apparatus, characterized in that the user terminal displays the specific GIS ocean data corresponding to the specific ocean data.

Images