Method and device for simulating isolated waves in ocean based on artificial intelligence

Abstract

The invention provides an artificial intelligence-based ocean internal solitary wave simulation method, which comprises the following steps of: identifying internal solitary wave feature information in a remote sensing image through a neural network, and substituting the internal solitary wave feature information into an inversion model to realize propagation simulation of an internal solitary wave; according to the method, artificial intelligence is used as a screening means, the neural network is trained to have the recognition capability, the internal solitary wave data can be rapidly and effectively obtained from a large number of remote sensing photos, then the internal solitary wave propagation process is inverted through an existing internal solitary wave simulation means, and the internal solitary wave research efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing measurement technology, and in particular to an artificial intelligence-based ocean internal solitary wave simulation method and device. Background Art

[0002] Internal ocean waves are a kind of fluctuation phenomenon that occurs in the interior of the stably stratified ocean, with a frequency between the inertial frequency and the buoyancy frequency, and its maximum amplitude occurs in the interior of the ocean. When the seawater density is stably stratified and there is a disturbance source, internal waves may be generated. The frequently observed ocean internal waves are a special type called internal solitary waves, which are usually generated by the interaction between the positive pressure tide and the terrain. During the propagation process, the internal tidal waves undergo nonlinear steep slopes, thereby splitting into internal solitary waves. There are many research materials on internal solitary waves at this stage, such as CN118607347A, CN115496004A, CN110110654B, CN118114030B and other patents, as well as articles such as "Numerical Simulation of the Interaction between Internal Solitary Waves and Submerged Bodies in Two-Layer Fluids" and "Experimental Study on the Propagation Evolution of Internal Solitary Waves and the Effect on Terrain", all of which have made relevant research on the technical fields such as the characteristics and simulation prediction of internal solitary waves. However, in the process of internal solitary wave research, the early internal solitary wave related identification process in the above-mentioned materials was all through manual identification, and manual work relied on experience to obtain relevant data, which was relatively inefficient and could not quickly screen out images with internal solitary wave data from massive remote sensing photos. Summary of the invention

[0003] In order to make up for the technical defect that the above-mentioned manual screening of images cannot quickly and effectively screen out internal solitary wave samples from a large number of photos and pictures, the present application proposes an ocean internal solitary wave simulation method and device based on artificial intelligence, which uses artificial intelligence combined with relevant hardware to quickly and effectively screen out internal solitary wave data from a large number of remote sensing photos and perform relevant simulations, thereby helping to improve the speed of internal solitary wave research.

[0004] The technical scheme of the method of the present application includes: a method for simulating internal solitary waves in the ocean based on artificial intelligence, which identifies characteristic information of internal solitary waves in remote sensing images through a neural network, and then substitutes the characteristic information of internal solitary waves into an inversion model to simulate the propagation of internal solitary waves; wherein the recognition process of the remote sensing image by the neural network includes: training the neural network so that it has the ability to identify strip-shaped areas with regular changes in light and dark in the image; converting the collected remote sensing image into a grayscale image and substituting it into the neural network, and the neural network determines whether there is a strip-shaped area with regular changes in light and dark in the grayscale image, and determines whether the strip-shaped area has a regular change in light and dark. Whether the light and dark pattern satisfies that the bright area is adjacent to the dark area, and the shape change trend of the bright area and the dark area is similar, if yes, the image is marked as the image to be extracted, and the strip area with the light and dark pattern change is marked as the waveform area, if not, the image recognition is terminated; after obtaining the image to be extracted, the brightest line in the waveform area is taken as the crest, the darkest line as the trough, and the horizontal distance between the crest and the trough is taken as the wavelength, and the propagation characteristic information of the internal solitary wave is calculated and extracted in combination with the buoyancy frequency of the sea area; after extracting the characteristic information of the internal solitary wave, the characteristic information of the internal solitary wave is substituted into the inversion model to realize the propagation simulation of the internal solitary wave.

[0005] Furthermore, before extracting the characteristic information of internal solitary wave propagation, it also includes a verification process for the image to be extracted, the verification process includes converting the grayscale image of the waveform area into a three-dimensional dot matrix image according to the position and grayscale value of the pixel points, dividing the three-dimensional dot matrix image into multiple layers of discrete point images according to the grayscale values ​​of each point of the three-dimensional dot matrix image according to preset values, projecting the discrete points of each layer of discrete point image onto a two-dimensional plane and fitting them to form contrast curves, judging whether the smoothness of each contrast curve is within a preset smoothness threshold, and whether the angles between all the contrast curves after being fitted into reference straight lines are less than a preset angle threshold, if so, confirming that the image to be extracted has passed the verification and entering the extraction step, if not, the image to be extracted is deemed to have failed and the extraction is abandoned.

[0006] Furthermore, the conversion process of the grayscale image of the waveform area into a three-dimensional dot matrix image includes: taking the plane where the pixels are located as a two-dimensional plane, assigning coordinate values ​​to the pixels at a clockwise angle of 45° to the strip area of ​​the waveform area as the X-axis and at a counterclockwise angle of 45° to the Y-axis, and taking the grayscale value as the Z-axis value.

[0007] Furthermore, in the process of dividing the three-dimensional dot matrix image into multiple layers of discrete dot images according to the gray value of each point of the three-dimensional dot matrix image according to a preset value, the preset value ranges from 5% to 20% of the maximum value of the Z axis.

[0008] Furthermore, when the image to be extracted passes the verification, the region with the maximum density of intersection points of the vertical lines of the reference straight lines is taken as the source region of the internal solitary wave.

[0009] Furthermore, the checking process also includes determining whether the number of light and dark stripes in the strip-shaped area with regular changes in light and dark patterns exceeds 5 pairs. If so, the image to be extracted is excluded; otherwise, the extraction process continues.

[0010] A device for simulating internal solitary waves in the ocean, wherein the device is configured to perform internal solitary wave simulation in the ocean using the above method.

[0011] This application uses artificial intelligence as a screening method to train a neural network so that it has recognition capabilities, can quickly and effectively obtain internal solitary wave data from a large number of remote sensing photos, and then invert the internal solitary wave propagation process through existing internal solitary wave simulation methods, thereby improving the efficiency of internal solitary wave research. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of a process for implementing the method of the present invention; Figure 2 A schematic diagram of an implementation of isolated wave peaks in a remote sensing image of the present invention; Figure 3 A schematic diagram of an implementation of the fish scale wave crest of a remote sensing image of the present invention; Figure 4 For the present invention Figure 2 A schematic diagram of an implementation of an image contrast curve; Figure 5 For the present invention Figure 3 A schematic diagram of an implementation of an image contrast curve. DETAILED DESCRIPTION

[0013] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0015] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0016] Combination Figure 1In one embodiment of the present application, the method of the present application includes: a method for simulating internal solitary waves in the ocean based on artificial intelligence, identifying the characteristic information of internal solitary waves in remote sensing images through a neural network, and then substituting the characteristic information of internal solitary waves into an inversion model to simulate the propagation of internal solitary waves; in the present application, based on the existing internal solitary wave inversion model, the remote sensing images are quickly screened by artificial intelligence, and images and related data with related characteristics of internal solitary waves are screened out, and then brought into the inversion model to obtain the propagation path and propagation process of internal solitary waves. In this embodiment, the recognition process of the remote sensing image by the neural network includes: training the neural network so that it has the ability to recognize the strip-shaped area with regular changes in light and dark in the image; in this step, since the internal solitary wave itself is an isolated waveform in the ocean, generally, there are relatively obvious boundaries before and after its propagation path, and the waveform light and dark changes in the remote sensing image are relatively regular, so this step uses the light and dark characteristics of the internal solitary wave as the acquisition feature to train the neural network, so that the neural network can quickly identify according to its isolated long strip wave mode, and the image with the above characteristics is screened out for verification and recognition extraction. In the actual acquisition and recognition process, the collected remote sensing image is converted into a grayscale image and substituted into the neural network. The neural network determines whether there is a strip area with regular changes in light and dark in the grayscale image, and whether the light and dark regularity of the strip area satisfies the condition that the bright area is adjacent to the dark area, and the shape change trend of the bright area and the dark area is similar. If yes, the image is marked as an image to be extracted, and the strip area with regular changes in light and dark is marked as a waveform area. If no, the image recognition is terminated. In the neural network recognition process, the parallel characteristics of the internal solitary waves and the characteristics that the peaks and troughs of the internal solitary waves are roughly parallel and adjacent, and the overall regular changes and the same change trend are used as extraction conditions to guide the neural network to perform recognition. After the image to be extracted is obtained by recognizing the image, the brightest line in the waveform area is taken as the crest, the darkest line is taken as the trough, the horizontal distance between the crest and the trough is taken as the wavelength, and the propagation characteristic information of the internal solitary wave is calculated and extracted in combination with the buoyancy frequency of the sea area; after the propagation characteristic information is obtained, according to the extracted characteristic information of the internal solitary wave, the characteristic information of the internal solitary wave is substituted into the inversion model to realize the propagation simulation of the internal solitary wave. The above-mentioned propagation characteristic information of the internal solitary wave includes wavelength, crest, trough, acquisition position of the internal solitary wave, acquisition time, source information and theoretical amplitude estimation information.

[0017] On the basis of the above embodiment, before extracting the propagation characteristic information of the internal solitary wave, a verification process for the extracted image is further included. Since there are many types and manifestations of waves in the ocean, although the screening method that the light and dark patterns change and the bright and dark areas are adjacent and the shape change trends of the bright and dark areas are similar can exclude most of the non-internal solitary wave images, the neural network may still be mixed with regular fish scale waves during the recognition process. Therefore, it is necessary to further exclude the above fish scale waves. Figure 2 Fish scale waves, Figure 3 The crest line expression of the two waves of the internal solitary wave (for the convenience of expression, this step Figure 2 , Figure 3 Only the brightest crest line in the remote sensing image with the highest grayscale value is used as the shape representative). The above two types of waves have relatively regular shape characteristics and brightness changes. The exclusion process of the present application utilizes the parallel and light and dark grayscale features of the internal solitary waves to exclude them. The verification process includes converting the grayscale image of the waveform area into a three-dimensional dot matrix image according to the position and grayscale value of the pixel points, dividing the three-dimensional dot matrix image into multiple layers of discrete point images according to the grayscale values ​​of each point of the three-dimensional dot matrix image according to a preset value, excluding the 1-3 layers with the most discrete points as the ocean background layer, retaining the crest layer with the highest grayscale value and the trough layer with the lowest grayscale and several other control layers, projecting the discrete points of each layer of the retained discrete point image onto a two-dimensional plane and fitting them to form a contrast curve. During the projection process of this step, since the overall shape of the wave is certain, but its crests and troughs cannot be completely parallel or completely within the same grayscale threshold range, and the coordinate values ​​of the fish scale wave in the two-dimensional plane after extracting the crest line, trough line and other lines are greatly different from the crest and trough of the internal solitary wave, the influence of the above-mentioned fish scale wave can be effectively excluded by judging the curvature and relative angle of the contrast curve, such as Figure 4 , Figure 5 . In this step, since the ocean background in the remote sensing image is relatively uniform, there may be several distributions within a grayscale threshold range. Therefore, this step will exclude the 1-3 layers with the most discrete points as the ocean background layer, and further exclude to improve the accuracy of the contrast curve extraction. This step further determines whether the smoothness of each contrast curve is within the preset smoothness threshold, and whether the angles between all contrast curves after fitting into reference straight lines are less than the preset angle threshold. If so, it is confirmed that the image to be extracted has passed the verification and enters the extraction step. Otherwise, the image to be extracted is deemed to have failed and the extraction is abandoned. During this verification process, Figure 3 Regular fish scale waves are projected Figure 5 After that, its smoothness and angle are Figure 2 Projection Figure 4 There are big differences in the images of internal solitary waves. The fish scale wave has a larger curvature and a larger line angle, while the internal solitary wave has a smoother line and a smaller angle. The above smoothing threshold and line angle are different in each sea area. It is necessary to convert the previous internal solitary waves through the above steps to obtain them. Generally, the maximum curvature and maximum angle of the internal solitary wave projection line after conversion are 120%.

[0018] On the basis of the above embodiment, the grayscale image of the waveform area is converted into a three-dimensional dot matrix image conversion process including: taking the plane where the pixel points are located as a two-dimensional plane, the direction of the clockwise 45° angle with the strip area of ​​the waveform area as the X-axis, and the direction of the counterclockwise 45° angle with the strip area of ​​the waveform area as the Y-axis to assign coordinate values ​​to the pixel points respectively, and taking the grayscale value as the Z-axis value. This embodiment discloses a projection method to determine the angle between the plane coordinate axis and the waveform area, so as to facilitate the recognition and calculation of the comparison curve after projection.

[0019] Based on one or more of the above embodiments, in the process of dividing the three-dimensional dot matrix image into multiple layers of discrete dot images according to the grayscale value of each point of the three-dimensional dot matrix image according to the preset value, the preset value range is 5%-20% of the maximum value of the Z axis. In this embodiment, the three-dimensional dot matrix image is divided into 5-20 layers according to the grayscale value range, that is, 5-20 contrast curves are obtained, which facilitates calculation while avoiding excessive calculation amount.

[0020] Based on one or more of the above embodiments, when the image to be extracted passes the verification, the region with the largest density of intersection points of the vertical lines of the reference straight lines is used as the source region of the internal solitary wave. In this embodiment, since the propagation path of the internal solitary wave is generally perpendicular to its source point, its waveform and path can still be well maintained after long-distance propagation, the source region of the internal solitary wave can be effectively extracted according to the direction of the waveform and path (i.e., the vertical line of the comparison curve of the internal solitary wave).

[0021] Based on one or more of the above embodiments, the checking process further includes determining whether the number of light and dark stripes in the strip-shaped area with light and dark regularity changes exceeds 5 pairs, if so, the image to be extracted is excluded, otherwise the extraction process continues. In this embodiment, although parallel waves are relatively rare, the present application also sets a parallel wave exclusion step to eliminate interference, so as to avoid interference with the extracted data.

[0022] A device for simulating internal solitary waves in the ocean, characterized in that the device uses the method described in any one of the above embodiments to simulate internal solitary waves.

[0023] This application uses artificial intelligence as a screening method to train a neural network so that it has recognition capabilities, can quickly and effectively obtain internal solitary wave data from a large number of remote sensing photos, and then invert the internal solitary wave propagation process through existing internal solitary wave simulation methods, thereby improving the efficiency of internal solitary wave research.

[0024] The above technical solutions only reflect the preferred technical solutions of the technical solutions of the present invention. Some changes that may be made to certain parts thereof by technicians in this technical field all reflect the principles of the present invention and fall within the protection scope of the present invention.

Claims

1. An artificial intelligence-based ocean internal solitary wave simulation method, characterized in that: The characteristic information of internal solitary waves in remote sensing images is identified through neural networks, and then the characteristic information of internal solitary waves is substituted into the inversion model to simulate the propagation of internal solitary waves. The recognition process of the remote sensing image by the neural network includes: Train the neural network to recognize the strip-like areas with regular changes in light and dark in the image; The collected remote sensing image is converted into a grayscale image and substituted into the neural network. The neural network determines whether there is a strip area with a regular change of light and dark in the grayscale image, and determines whether the light and dark rule of the strip area satisfies that the bright area and the dark area are adjacent, and the shape change trend of the bright area and the dark area is similar. If so, the image is marked as an image to be extracted, and the strip area with a regular change of light and dark is marked as a waveform area. If not, the image recognition is terminated. After the image to be extracted is obtained, the brightest line in the waveform area is taken as the wave crest, the darkest line is taken as the wave trough, the horizontal distance between the wave crest and the wave trough is taken as the wavelength, and the propagation characteristic information of the internal solitary wave is calculated and extracted in combination with the buoyancy frequency of the sea area; After extracting the characteristic information of the internal solitary wave, the characteristic information of the internal solitary wave is substituted into the inversion model to realize the propagation simulation of the internal solitary wave.

2. The method according to claim 1, characterized in that Before extracting the characteristic information of internal solitary wave propagation, the method also includes a verification process for the image to be extracted, the verification process includes converting the grayscale image of the waveform area into a three-dimensional dot matrix image according to the position and grayscale value of the pixel points, dividing the three-dimensional dot matrix image into multiple layers of discrete dot images according to the grayscale values ​​of each point of the three-dimensional dot matrix image according to a preset value, projecting the discrete points of each layer of discrete dot image onto a two-dimensional plane and fitting them to form contrast curves, judging whether the smoothness of each contrast curve is within a preset smoothness threshold, and whether the angles between all contrast curves after being fitted into reference straight lines are less than a preset angle threshold. If so, it is confirmed that the image to be extracted has passed the verification and enters the extraction step. Otherwise, the image to be extracted is deemed to have failed and the extraction is abandoned.

3. The method according to claim 2, characterized in that The process of converting the grayscale image of the waveform area into a three-dimensional dot matrix image includes: taking the plane where the pixels are located as a two-dimensional plane, assigning coordinate values ​​to the pixels in the direction of a 45° clockwise angle with the strip area of ​​the waveform area as the X-axis and in the direction of a 45° counterclockwise angle with the strip area of ​​the waveform area as the Y-axis, and taking the grayscale value as the Z-axis value.

4. The method according to claim 3, characterized in that In the process of dividing the three-dimensional dot matrix image into multiple layers of discrete dot images according to the gray value of each point of the three-dimensional dot matrix image according to a preset value, the preset value ranges from 5% to 20% of the maximum value of the Z axis.

5. The method according to claim 2, characterized in that: When the image to be extracted passes the verification, the region with the maximum density of the intersection points of the vertical lines of the reference straight lines is taken as the source region of the internal solitary wave.

6. The method according to claim 2, characterized in that The checking process also includes determining whether the number of light and dark stripes in the strip-shaped area with light and dark regular changes exceeds 5 pairs. If so, the image to be extracted is excluded. Otherwise, the extraction process continues.

7. An ocean internal solitary wave simulation device, characterized in that: The device uses the method described in any one of claims 1 to 6 to simulate internal solitary waves.

Images