An ocean subsurface temperature inversion method, device and terminal device

Abstract

The present application provides a method, device and terminal device for ocean subsurface temperature inversion, which are applicable to the field of data processing technology. The method includes: obtaining a plurality of ocean observation information; training an initial subsurface temperature inversion model according to the plurality of ocean observation information to obtain a plurality of target subsurface temperature inversion models; and calculating ocean subsurface temperature information based on the plurality of target subsurface temperature inversion models, the plurality of ocean observation information and a preset ocean observation depth threshold. The present application constructs a mapping relationship between deep temperatures and sea surface information through a subsurface temperature inversion model for performing inversion calculation on ocean subsurface temperature, providing accurate and effective data support for ocean underwater environment research work.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to a method, apparatus, and terminal device for retrieving the subsurface temperature of the ocean. Background Art

[0002] As the largest area on Earth, the ocean plays a central role in global climate regulation, energy transfer, and the water cycle. Its complex ocean circulation not only exchanges energy and matter with the atmosphere but also plays a crucial regulatory role in the global climate system. Behind these dynamic processes, the temperature distribution of seawater is one of the key driving factors. The ocean temperature field not only determines the density change of seawater, thereby affecting the flow pattern of the ocean, but also plays an important role in air-sea interaction, ocean circulation, and global climate change. Therefore, accurately estimating the three-dimensional temperature structure below the ocean surface has important scientific significance for studying these dynamic processes and their impact on the global climate system.

[0003] Traditional observation methods mainly rely on platforms such as buoys and ships for on-site observation. By inputting the sea surface information obtained from satellite remote sensing and on-site observation into a specific calculation network for analysis, the temperature data of the ocean surface can be calculated.

[0004] However, traditional observation methods for obtaining underwater temperature data over a large area. Satellite remote sensing technology can only obtain information on the ocean surface and cannot be used to determine the underwater dynamic environment and its three-dimensional temperature distribution. Most of the global ocean surface observation data obtained through the rapid development of satellite remote sensing technology is based on surface data, ignoring the correlation between temperatures at different depths. Only using surface data to retrieve the underwater environmental field, the inversion accuracy will decrease more and more significantly as the depth increases. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method, apparatus, and terminal device for retrieving the subsurface temperature of the ocean, aiming to solve the problem in the prior art that only the temperature of the ocean surface can be calculated, while the subsurface temperature of the ocean cannot be analyzed and calculated, and the underwater temperature distribution of the ocean cannot be determined.

[0006] The first aspect of the embodiments of this application provides a method for retrieving the subsurface temperature of the ocean, including:

[0007] Obtain multiple ocean observation information;

[0008] Train an initial subsurface temperature inversion model based on the multiple ocean observation information to obtain multiple target subsurface temperature inversion models;

[0009] Based on multiple target subsurface temperature inversion models, according to multiple ocean observation information and a preset ocean observation depth threshold, calculate the ocean subsurface temperature information.

[0010] The second aspect of the embodiments of the present application provides an ocean subsurface temperature inversion device, including:

[0011] An ocean observation information acquisition module, configured to acquire multiple ocean observation information;

[0012] A subsurface temperature inversion model training module, configured to train an initial subsurface temperature inversion model according to the multiple ocean observation information to obtain multiple target subsurface temperature inversion models; and

[0013] An ocean subsurface temperature information calculation module, configured to calculate the ocean subsurface temperature information based on the multiple target subsurface temperature inversion models, according to the multiple ocean observation information and the preset ocean observation depth threshold.

[0014] The third aspect of the embodiments of the present application provides a terminal device, the terminal device includes a memory and a processor, and a computer program that can run on the processor is stored on the memory. When the processor executes the computer program, the steps of the ocean subsurface temperature inversion method described in the first aspect above are implemented.

[0015] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, including: storing a computer program, and when the computer program is executed by a processor, the steps of the ocean subsurface temperature inversion method described in the first aspect above are implemented.

[0016] The beneficial effects of the embodiments of the present application compared with the prior art are: capturing the non-linear relationship between sea surface observation data and underwater temperature through the subsurface temperature inversion model, constructing the mapping relationship between deep temperature and sea surface parameters, establishing the connection between ocean temperatures at different depths, training the subsurface temperature inversion model through the obtained ocean observation data, and then using the correlation between ocean temperatures at different depths to inversely calculate the ocean subsurface temperature field layer by layer, thereby improving the efficiency of inversely calculating the ocean subsurface temperature. And compared with the inversion of a model that does not add the correlation between ocean temperatures at different depths, the mean square error is increased by 5.61%, overcoming the complexity of calculating the ocean underwater temperature field, and providing accurate and effective data support for ocean underwater environment research work. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of the implementation of the ocean subsurface temperature inversion method provided in the first embodiment of the present application;

[0019] Figure 2 It is a schematic flowchart of the implementation of the ocean subsurface temperature inversion method provided in the second embodiment of the present application;

[0020] Figure 3 It is a schematic flowchart of the implementation of the ocean subsurface temperature inversion method provided in the third embodiment of the present application;

[0021] Figure 4 It is a schematic flowchart of the implementation of the ocean subsurface temperature inversion method provided in the fourth embodiment of the present application;

[0022] Figure 5 It is a schematic flowchart of the implementation of the ocean subsurface temperature inversion method provided in the fifth embodiment of the present application;

[0023] Figure 6 It is a schematic structural diagram of the ocean subsurface temperature inversion device provided in the embodiments of the present application;

[0024] Figure 7 It is a schematic diagram of the terminal device provided in the embodiments of the present application. Detailed implementation manners

[0025] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0026] To illustrate the technical solutions described in the present application, the following will be described through specific embodiments.

[0027] Figure 1 The implementation flowchart of the ocean subsurface temperature inversion method provided in the first embodiment of the present application is shown and described in detail as follows:

[0028] Step S101, obtain multiple ocean observation information.

[0029] In this embodiment, the ocean observation information can be obtained through satellite remote sensing and in-situ observation. It can be understood that the ocean observation information needs to be preprocessed, and the preprocessed data can be used to train the initial subsurface temperature inversion model.

[0030] In this embodiment, preferably, the ocean observation information may include observation time information, observation area longitude and latitude information, sea surface height information, sea surface salinity information, sea surface wind speed information, sea surface temperature information, and multiple subsurface temperature observation information. It can be understood that the regions and times selected based on the monthly average observation data of sea surface height (SSH), sea surface salinity (SSS), sea surface temperature (SST), sea surface wind (SSW), and subsurface ocean temperature (ST) obtained by satellite remote sensing and in-situ observation are the same.

[0031] Step S102: Train the initial subsurface temperature inversion model according to the multiple ocean observation information to obtain multiple target subsurface temperature inversion models.

[0032] In this embodiment, the initial subsurface temperature inversion model can be a CNN model. The preprocessing process for the ocean observation information may include determining outliers for ST at a depth of 1000m. If the temperature is less than 0°C or greater than 10°C, it is determined as a temperature anomaly region, and the data in the temperature anomaly region is deleted and filled with nan values. If the boundary region exceeds the range selected by 9×9, the exceeded part is filled with zeros to indicate missing information. The preprocessed dataset can be divided into a training set and a validation set. The initial subsurface temperature inversion model after training is the target subsurface temperature inversion model, which is trained to minimize the mean square of the difference between the predicted value of the trained neural network and the actual observed value under the same conditions to obtain multiple target subsurface temperature inversion models. It can be understood that in this embodiment, a large amount of ocean observation information is divided into several homologous data to train multiple identical initial subsurface temperature inversion models respectively, and multiple target subsurface temperature inversion models can be obtained.

[0033] Step S103: Based on the multiple target subsurface temperature inversion models, calculate the ocean subsurface temperature information according to the multiple ocean observation information and the preset ocean observation depth threshold.

[0034] In this embodiment, the ocean subsurface temperature at different depths can be calculated by successively inverting the ocean observation information through multiple target subsurface temperature inversion models. Specifically, the sea surface data can be used as the input data first, and the ocean subsurface temperature at a depth of 5 meters can be inversely calculated through the first target subsurface temperature inversion model. Then, the temperature inversion value at a depth of 5 meters is combined with the sea surface data and used as the input of the second target subsurface temperature inversion model to inversely calculate the ocean subsurface temperature at a depth of 20 meters, and so on. It can be 5m, 20m, 40m, 60m, 70m, 80m, 90m, 100m, 125m, 150m, 175m, 200m, 225m, 250m, 275m, 300m, 350m, 400m, 500m, 600m, 700m, 800m, 900m, 1000m for each inverse calculation of the ocean subsurface temperature at these 24 depths. The preset ocean observation depth threshold can be set artificially and can be 1000m.

[0035] The ocean subsurface temperature inversion method provided by the embodiment of the present application captures the non-linear relationship between the sea surface observation data and the underwater temperature through the subsurface temperature inversion model, constructs the mapping relationship between the deep temperature and the sea surface parameters, establishes the connection between the ocean temperatures at different depths, trains the subsurface temperature inversion model through the obtained ocean observation data, and then inversely calculates the ocean subsurface temperature field layer by layer using the correlation between the ocean temperatures at different depths, thereby improving the efficiency of inversely calculating the ocean subsurface temperature. Compared with the model that does not add the correlation between the ocean temperatures at different depths for inversion, the mean square error has increased by 5.61%, overcoming the complexity of calculating the ocean underwater temperature field and providing accurate and effective data support for the research work of the ocean underwater environment.

[0036] Figure 2 The flowchart showing the implementation of the ocean subsurface temperature inversion method provided by the second embodiment of the present application is different from the first embodiment above in that: step S102 specifically includes:

[0037] Step S201, calculate multiple observed parameter variable values according to the sea surface height information, sea surface salinity information, sea surface temperature information, sea surface wind speed information, and multiple subsurface temperature observation information.

[0038] In this embodiment, the calculation formula for the intermediate variable value P of the observation parameter can be: P = 5(SSH + SSS + SST + USSW + VSSW) + q. Where SSH is the sea surface height, SSS is the sea surface salinity, SST is the sea surface temperature, SSW is the sea surface wind speed, USSW is the north component of the sea surface wind speed, VSSW is the east component of the sea surface wind speed, and q represents the number of depths. The subsurface temperature observation information can be represented by ST, which can be combined with the intermediate variable value P of the observation parameter to calculate the variable value of the observation parameter. The combination method can be an element value of the input tensor composed of the intermediate variable value P of the observation parameter and the variable value of the observation parameter, which is used for further inversion calculation of the ocean subsurface temperature.

[0039] Step S202, generate a plurality of ocean observation parameter tensors according to the plurality of variable values of the observation parameters, the observation time information, and the longitude and latitude information of the observation area.

[0040] In this embodiment, the variable value P of the observation parameter can be calculated from the sea surface height information, the sea surface salinity information, the sea surface temperature information, the sea surface wind speed information, and a plurality of subsurface temperature observation information. SSH is the sea surface height, SSS is the sea surface salinity, SST is the sea surface temperature, SSW is the sea surface wind speed, USSW is the north component of the sea surface wind speed, VSSW is the east component of the sea surface wind speed, and q represents the number of depths. The observation time information T can refer to the month length, and M and N represent the longitude and latitude span sizes of the selected area (for example, if the resolution is 0.25°, it means that the longitude and latitude spans of the selected area are M / 4° and N / 4° respectively). Then the generated tensor can be expressed as (T, M×N, L, L, P), where the size of the rectangular frame (L, L) is used as the area size of the data point input, and L is used to represent the horizontal and vertical coordinate values of the rectangular frame.

[0041] Step S203, train the initial subsurface temperature inversion model according to the plurality of ocean observation parameter tensors to obtain a plurality of target subsurface temperature inversion models.

[0042] In this embodiment, the input tensor size of the first initial subsurface temperature inversion model can be ((T - 12)×M×N, L, L, 5), where 5 represents the number of parameters, namely 5 ocean surface parameters: SSH, SSS, SST, USSW, and VSSW. Its output tensor size is ((T - 12)×M×N, L, L, 1), where 1 represents the ST at the corresponding depth. The input tensor size of the second initial subsurface temperature inversion model can be ((T - 12)×M×N, L, L, 6), where 6 represents the number of parameters, namely 6 ocean surface parameters: SSH, SSS, SST, USSW, VSSW, and the ST of the first layer. Its output tensor size can be ((T - 12)×M×N, L, L, 1), where 1 represents the ST at the corresponding depth. And so on, until the initial subsurface temperature inversion model for the ST at the last layer of depth is trained. The input tensor size of the trained initial subsurface temperature inversion model is ((T - 12)×M×N, L, L, P - 1), where 6 represents the number of parameters, namely P - 1 ocean surface parameters: SSH, SSS, SST, USSW, VSSW, and the ST of q - 1 layers above this layer. Its output tensor size is ((T - 12)×M×N, L, L, 1), where 1 represents the ST at the last layer of depth. Finally, q trained target subsurface temperature inversion models corresponding to q depths are obtained.

[0043] The ocean subsurface temperature inversion method provided by the embodiments of the present application trains the initial subsurface temperature inversion model through multiple ocean observation information, establishes the correlation between multiple sea surface observation information and ocean subsurface temperature information, and thus performs inversion calculation on the non-linearly changing ocean subsurface temperature through sea surface observation data, providing effective data support for the research work on the change of the ocean subsurface temperature field.

[0044] Figure 3 The flowchart of the implementation of the ocean subsurface temperature inversion method provided by Embodiment 3 of the present application is shown. The difference from Embodiment 1 above is that: Step S103 specifically includes:

[0045] Step S301, calculate the first surface layer temperature inversion information according to the multiple ocean observation information and the first target subsurface temperature inversion model.

[0046] In this embodiment, multiple pieces of ocean observation information can be converted into a tensor form as the input tensor of the first target subsurface temperature inversion model, and the output result is the first subsurface temperature inversion information. It can be understood that there are multiple target subsurface temperature inversion models. The first target subsurface temperature inversion model calculated in sequence is used to calculate the temperature of a shallower subsurface depth, such as performing an inversion calculation on the temperature at a depth of 5m.

[0047] Step S302: Calculate the second subsurface temperature inversion information according to the multiple pieces of ocean observation information, the first subsurface temperature inversion information, and the second target subsurface temperature inversion model.

[0048] In this embodiment, it can be to combine the output result of the previous target subsurface temperature inversion model with the sea surface parameter information to form the input tensor of the second target subsurface temperature inversion model. The calculation result output by the second target subsurface temperature inversion model is the second subsurface temperature inversion information. There are multiple pieces of target subsurface temperature inversion information. The second target subsurface temperature inversion model calculated in sequence is used to perform an inversion calculation on the input data formed by combining the output result of the previous target subsurface temperature inversion model with the sea surface parameter information, and can be used to calculate the subsurface temperature at a depth of 10m. It can be understood that only the first target subsurface temperature inversion model and the second target subsurface temperature inversion model are taken as examples here, and there can be a third target subsurface temperature inversion model, a fourth target subsurface temperature inversion model, etc., for performing inversion calculations on the subsurface temperatures of different depths of the ocean.

[0049] Step S303: Determine whether the ocean depth information corresponding to the second subsurface temperature inversion information is greater than or equal to a preset ocean observation depth threshold;

[0050] If so, determine the second subsurface temperature inversion information as the ocean subsurface temperature information;

[0051] If not, generate subsurface inversion temperature intermediate variable information according to the first subsurface temperature inversion information and the second subsurface inversion temperature information;

[0052] Use the subsurface inversion temperature intermediate variable information as the first subsurface temperature inversion information and return it to S302.

[0053] In this embodiment, the preset ocean observation depth threshold may be 1000 meters. It can be understood that the first target subsurface temperature inversion model can be used to calculate the subsurface temperature of the ocean at a depth of 5 meters, and the second target subsurface temperature inversion model can be used to calculate the subsurface temperature of the ocean at a depth of 10 meters. Through layer-by-layer calculation, finally, the subsurface temperature of the ocean at a depth of 1000 meters can be calculated by the last target subsurface temperature inversion model. Therefore, for each inversion of a target subsurface temperature inversion model, it is necessary to determine whether the depth value corresponding to the calculated subsurface temperature of the ocean has reached the preset ocean observation depth threshold. If it has reached, there is no need to perform the next inversion calculation, and the result is directly output as the subsurface temperature information of the ocean. If it has not reached, the next inversion calculation is required, that is, the output result of the target subsurface temperature inversion model calculated in this round is combined with the output results of the target subsurface temperature inversion models calculated in all previous inversion rounds and the sea surface parameters to generate an intermediate variable of the subsurface inversion temperature, which is used as the input of the next target subsurface temperature inversion model, so as to calculate the subsurface temperature of the ocean corresponding to the next depth, so as to realize the inversion calculation of the subsurface temperature of the ocean at different depths. It can be understood that regardless of whether the depth value corresponding to the calculated subsurface temperature of the ocean reaches the preset ocean observation depth threshold, the information obtained from these inversion calculations is part of the subsurface temperature information of the ocean, and can be combined with the subsurface temperature information obtained from the previous inversion calculations and the sea surface observation information to calculate the subsurface temperature information of the ocean at a greater depth.

[0054] The subsurface temperature inversion method provided by the embodiment of the present application adopts a method of layer-by-layer inversion of the subsurface deep temperature field of the ocean, and inversely calculates the temperature of different depths of the ocean through the target subsurface temperature inversion model. It can perform inversion in connection with the internal temperature characteristics of the ocean, avoiding the loss of connection information between the internal temperatures of the ocean when directly using characteristics such as sea surface temperature and height, thereby improving the accuracy of the inversion of the subsurface temperature of the ocean and ensuring the accuracy and effectiveness of the inversion calculation results.

[0055] Figure 4 The flowchart showing the implementation of the subsurface temperature inversion method provided in the fourth embodiment of the present application is different from that of the third embodiment above: The step S301 specifically includes:

[0056] Step S401, generating a plurality of ocean observation numerical tensors according to the plurality of ocean observation information.

[0057] In this embodiment, it may be to generate an input tensor from multiple numerical values in the ocean observation information. Specifically, SSH represents the sea surface height, SSS represents the sea surface salinity, SST represents the sea surface temperature, SSW represents the sea surface wind speed, USSW represents the north component of the sea surface wind speed, VSSW represents the east component of the sea surface wind speed, q represents the number of depths, the observation time information is T, M and N represent the longitude and latitude span sizes of the selected area (for example, if the resolution is 0.25°, it means that the longitude and latitude spans of the selected area are M / 4° and N / 4° respectively). The generated ocean observation numerical tensor can be expressed as (T, M×N, L, L, P), where the size of the rectangular frame (L, L) is used as the area size of the data point input, and L is used to represent the horizontal and vertical coordinate values of the rectangular frame.

[0058] Step S402: Based on the first target subsurface temperature inversion model, perform convolution calculations on the multiple ocean observation numerical tensors to obtain multiple ocean observation numerical multi-dimensional feature maps.

[0059] In this embodiment, the target subsurface temperature inversion model may be a trained CNN model. Then, convolution calculations can be performed on the ocean observation numerical tensors through multiple convolutional layers of the CNN model. It can be understood that the CNN model may include two convolutional layers, and the convolutional layers of the CNN model may contain convolutional kernels. Convolution calculations can be performed through the convolutional kernels and the ocean observation numerical tensors to obtain multiple ocean observation numerical multi-dimensional feature maps.

[0060] Step S403: Perform dimensionality reduction processing on the multiple ocean observation numerical multi-dimensional feature maps to obtain multiple ocean observation numerical one-dimensional feature maps.

[0061] In this embodiment, the dimensionality reduction processing of the ocean observation numerical multi-dimensional feature maps can be performed through the Flatten layer in the CNN model. The multiple ocean observation numerical multi-dimensional feature maps are processed into a one-dimensional matrix for reducing the complexity and computational amount of subsequent calculations. The matrix obtained after dimensionality reduction is the ocean observation numerical one-dimensional feature map.

[0062] Step S404: Based on the first target subsurface temperature inversion model, perform a non-linear transformation on the ocean observation numerical one-dimensional feature map to calculate the first subsurface temperature inversion information.

[0063] In this embodiment, the non-linear transformation of the ocean observation numerical one-dimensional feature map can be performed through the fully connected layer in the CNN model. Specifically, it can be through the activation function and bias term in the fully connected layer for non-linear mapping and calculation. It can be understood that there may be 3 fully connected layers in the CNN model, and the activation function may be ReLU, which is used to increase the non-linearity of the subsurface temperature inversion model so that it can handle the complex non-linear relationships between multiple subsurface depths in the ocean.

[0064] The ocean subsurface temperature inversion method provided by the embodiments of the present application performs convolution calculations on ocean observation information through a trained subsurface temperature inversion model, extracts features from the ocean observation information, and then performs dimensionality reduction processing on the extracted features to reduce the computational complexity and improve the solution efficiency. Then, the dimensionality-reduced features are mapped into a non-linear space for transformation, so as to realize the combination and transformation of features, avoid the overfitting phenomenon of the subsurface temperature inversion model, and improve the efficiency and accuracy of the inversion calculation of the ocean subsurface temperature.

[0065] Figure 5 The flowchart of the implementation of the ocean subsurface temperature inversion method provided in Embodiment 5 of the present application is shown. The difference from Embodiment 3 above is that the step S302 specifically includes:

[0066] Step S501, merge a plurality of the ocean observation information and the first surface temperature inversion information to obtain a subsurface temperature inversion input tensor.

[0067] In this embodiment, it may be to merge a plurality of values in the ocean observation information and the first surface temperature inversion information to generate an input tensor. Specifically, SSH is the sea surface height, SSS is the sea surface salinity, SST is the sea surface temperature, SSW is the sea surface wind speed, USSW is the north component of the sea surface wind speed, VSSW is the east component of the sea surface wind speed, q represents the number of depths, the observation time information T, M and N represent the longitude and latitude span sizes of the selected area, and ST represents the first surface temperature inversion information. The generated subsurface temperature inversion input tensor can be expressed as (T, M×N, L, L, P, ST), where the size of the rectangular frame (L, L) is used as the area size of the data point input, and L is used to represent the horizontal and vertical coordinate values of the rectangular frame.

[0068] Step S502, based on the second target subsurface temperature inversion model, perform convolution calculations on the subsurface temperature inversion input tensor to obtain a plurality of input tensor multi-dimensional feature maps.

[0069] In this embodiment, the second target subsurface temperature inversion model may be a trained CNN model. Then, convolution calculations can be performed on the subsurface temperature inversion input tensor through multiple convolutional layers of the CNN model. It can be understood that the CNN model may include two convolutional layers, and the convolutional layers of the CNN model may include convolutional kernels. Convolution calculations can be performed through the convolutional kernels and the subsurface temperature inversion input tensor to obtain a plurality of input tensor multi-dimensional feature maps.

[0070] Step S503, perform dimensionality reduction processing on the plurality of input tensor multi-dimensional feature maps to obtain a plurality of input tensor one-dimensional feature maps.

[0071] In this embodiment, the dimensionality reduction processing can be performed on the multi-dimensional feature map of the input tensor through the Flatten layer in the CNN model, and the multi-dimensional feature maps of multiple input tensors are processed into a one-dimensional matrix for reducing the complexity and computational amount of subsequent calculations. The matrix obtained after dimensionality reduction is the one-dimensional feature map of the input tensor.

[0072] Step S504: Based on the second target subsurface temperature inversion model, perform feature transformation processing on the one-dimensional feature map of the input tensor, and calculate the second subsurface temperature inversion information.

[0073] In this embodiment, the non-linear transformation can be performed on the one-dimensional feature map of the input tensor through the fully connected layer in the CNN model. Specifically, it can be through the activation function and bias term in the fully connected layer for non-linear mapping and calculation. It can be understood that there can be 3 fully connected layers in the CNN model, and the activation function can be ReLU, which is used to increase the non-linearity of the subsurface temperature inversion model so that it can handle the complex non-linear relationships between multiple subsurface depths of the ocean.

[0074] The ocean subsurface temperature inversion method provided by the embodiments of this application performs inversion calculations on ocean observation information and subsurface temperature information through multiple subsurface temperature inversion models. First, feature extraction is performed on the ocean observation information and the output result of the previous subsurface temperature inversion model through convolutional operations, and then the extracted features are processed for dimensionality reduction to reduce the computational complexity and improve the solution efficiency. Then, the features after dimensionality reduction are mapped into a non-linear space for transformation, thereby realizing the combination and transformation of features, avoiding the overfitting phenomenon of subsequent subsurface temperature inversion models, and improving the efficiency and accuracy of the layer-by-layer inversion calculation of the ocean subsurface temperature.

[0075] Corresponding to the method in the above embodiments, Figure 6 The structural block diagram of the ocean subsurface temperature inversion device provided by the embodiments of this application is shown. For the sake of convenience of description, only the parts related to the embodiments of this application are shown. Figure 6 The exemplary ocean subsurface temperature inversion device may be the execution subject of the ocean subsurface temperature inversion method provided in the foregoing Embodiment 1.

[0076] Referring to Figure 6 , the ocean subsurface temperature inversion device includes:

[0077] An ocean observation information acquisition module 610, configured to acquire multiple ocean observation information;

[0078] A subsurface temperature inversion model training module 620, configured to train an initial subsurface temperature inversion model according to the multiple ocean observation information to obtain multiple target subsurface temperature inversion models; and

[0079] The ocean subsurface temperature information calculation module 630 is configured to calculate the ocean subsurface temperature information based on multiple target subsurface temperature inversion models, according to multiple ocean observation information and a preset ocean observation depth threshold.

[0080] For the process of each module in the ocean subsurface temperature inversion device provided by the embodiments of the present application to implement its respective functions, reference may be specifically made to the description of the foregoing Figure 1 Example 1 shown, which will not be elaborated here.

[0081] The ocean subsurface temperature information calculation module 630 includes:

[0082] The first subsurface temperature inversion information calculation unit is configured to calculate the first subsurface temperature inversion information according to the multiple ocean observation information and the first target subsurface temperature inversion model;

[0083] The second subsurface temperature inversion information calculation unit is configured to calculate the second subsurface temperature inversion information according to the multiple ocean observation information, the first subsurface temperature inversion information, and the second target subsurface temperature inversion model;

[0084] The ocean subsurface temperature information determination unit is configured to determine whether the ocean depth information corresponding to the second subsurface temperature inversion information is greater than or equal to the preset ocean observation depth threshold;

[0085] If so, the second subsurface temperature inversion information is determined as the ocean subsurface temperature information;

[0086] If not, the subsurface inversion temperature intermediate variable information is generated according to the first subsurface temperature inversion information and the second subsurface inversion temperature information;

[0087] The subsurface inversion temperature intermediate variable information is used as the first subsurface temperature inversion information and returned to the second subsurface temperature inversion information calculation unit.

[0088] For the process of each unit in the ocean subsurface temperature information calculation module 630 provided by the embodiments of the present application to implement its respective functions, reference may be specifically made to the description of the foregoing Figure 3 Example 3 shown, which will not be elaborated here.

[0089] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0090] It should be understood that, as used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their combinations.

[0091] It should also be understood that the term "and / or" as used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0092] As used in the specification of this application and the appended claims, the term "if" can be interpreted, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted, depending on the context, as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0093] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are used only for descriptive distinction and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first", "second", etc. are used in the text in some embodiments of this application to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first table can be named a second table, and similarly, a second table can be named a first table, without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0094] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0095] The ocean subsurface temperature inversion method provided by the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0096] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication functions, a computing device or other processing devices connected to a wireless modem, a vehicle-mounted device, a vehicle-to-everything (V2X) terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a set top box (STB), a customer premise equipment (CPE), and / or other devices for communicating on a wireless system, as well as next-generation communication systems, such as mobile terminals in a 5G network or mobile terminals in a future evolved Public Land Mobile Network (PLMN) network.

[0097] By way of example and not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for devices that apply wearable technology to the intelligent design of daily wear and develop wearable devices, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is either worn directly on the body or integrated into the user's clothing or accessories. A wearable device is not just a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to cooperate with other devices such as smart phones, such as various smart bracelets and smart jewelry for monitoring physical signs.

[0098] Figure 7It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 7 shown, the terminal device 7 of this embodiment includes: at least one processor 70 ( Figure 7 only one is shown in the figure), and a memory 71. A computer program 72 that can run on the processor 70 is stored in the memory 71. When the processor 70 executes the computer program 72, the steps in the above-mentioned embodiments of various ocean subsurface temperature inversion methods are implemented, such as Figure 1 the steps S101 to S103 shown. Alternatively, when the processor 70 executes the computer program 72, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as Figure 6 the functions of the modules 610 to 630 shown.

[0099] The terminal device 7 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art can understand that Figure 7 merely examples of the terminal device 7 do not constitute a limitation on the terminal device 7, and may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the terminal device may further include an input and sending device, a network access device, a bus, etc.

[0100] The so-called processor 70 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0101] The memory 71 may be an internal storage unit of the terminal device 7 in some embodiments, such as the hard disk or memory of the terminal device 7. The memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk equipped on the terminal device 7, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 71 may also include both the internal storage unit and the external storage device of the terminal device 7. The memory 71 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 71 may also be used to temporarily store data that has been sent or will be sent.

[0102] In addition, in each embodiment of the present application, each functional unit may be integrated in a processing unit, may exist physically alone for each unit, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0103] An embodiment of the present application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, the terminal device implements the steps in any of the above method embodiments.

[0104] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments can be implemented.

[0105] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in any of the above method embodiments when executed.

[0106] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0107] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. An ocean subsurface temperature inversion method, characterized in that, Including: Obtaining multiple ocean observation information; The ocean observation information includes observation time information, observation area longitude and latitude information, sea surface height information, sea surface salinity information, sea surface wind speed information, sea surface temperature information, and multiple subsurface temperature observation information; Training an initial subsurface temperature inversion model according to the multiple ocean observation information to obtain multiple target subsurface temperature inversion models; the initial subsurface temperature inversion model is a CNN model; Based on the multiple target subsurface temperature inversion models, calculating the ocean subsurface temperature information according to the multiple ocean observation information and a preset ocean observation depth threshold, including: calculating the first subsurface temperature inversion information according to the multiple ocean observation information and the first target subsurface temperature inversion model, including: generating multiple ocean observation numerical tensors according to the multiple ocean observation information; performing convolution calculation on the multiple ocean observation numerical tensors based on the first target subsurface temperature inversion model to obtain multiple ocean observation numerical multi-dimensional feature maps; performing dimensionality reduction processing on the multiple ocean observation numerical multi-dimensional feature maps to obtain multiple ocean observation numerical one-dimensional feature maps; performing non-linear transformation on the ocean observation numerical one-dimensional feature maps based on the first target subsurface temperature inversion model to calculate the first subsurface temperature inversion information; Calculating the second subsurface temperature inversion information according to the multiple ocean observation information, the first subsurface temperature inversion information, and the second target subsurface temperature inversion model, including: performing merging processing on the multiple ocean observation information and the first subsurface temperature inversion information to obtain a subsurface temperature inversion input tensor; performing convolution calculation on the subsurface temperature inversion input tensor based on the second target subsurface temperature inversion model to obtain multiple input tensor multi-dimensional feature maps; performing dimensionality reduction processing on the multiple input tensor multi-dimensional feature maps to obtain multiple input tensor one-dimensional feature maps; performing feature transformation processing on the input tensor one-dimensional feature maps based on the second target subsurface temperature inversion model to calculate the second subsurface temperature inversion information; Judging whether the ocean depth information corresponding to the second subsurface temperature inversion information is greater than or equal to the preset ocean observation depth threshold; if so, determining the second subsurface temperature inversion information as the ocean subsurface temperature information; if not, generating subsurface inversion temperature intermediate variable information according to the first subsurface temperature inversion information and the second subsurface inversion temperature information; using the subsurface inversion temperature intermediate variable information as the first subsurface temperature inversion information, and returning to the step of obtaining the second subsurface temperature inversion information according to the multiple ocean observation information, the first subsurface temperature inversion information, and the second target subsurface temperature inversion model.

2. The ocean subsurface temperature inversion method according to claim 1, characterized in that The step of training an initial subsurface temperature inversion model according to the multiple ocean observation information to obtain multiple target subsurface temperature inversion models specifically includes: Calculating multiple observation parameter variable values according to the sea surface height information, sea surface salinity information, sea surface temperature information, sea surface wind speed information, and multiple subsurface temperature observation information; Generate multiple ocean observation parameter tensors according to the multiple values of the observation parameter variables, the observation time information, and the longitude and latitude information of the observation area. Train an initial subsurface temperature inversion model based on the multiple ocean observation parameter tensors to obtain multiple target subsurface temperature inversion models.

3. An ocean subsurface temperature inversion device, characterized in that, It includes: An ocean observation information acquisition module for acquiring multiple ocean observation information; The ocean observation information includes observation time information, longitude and latitude information of the observation area, sea surface height information, sea surface salinity information, sea surface wind speed information, sea surface temperature information, and multiple subsurface temperature observation information; A subsurface temperature inversion model training module for training an initial subsurface temperature inversion model based on the multiple ocean observation information to obtain multiple target subsurface temperature inversion models; the initial subsurface temperature inversion model is a CNN model; And An ocean subsurface temperature information calculation module for calculating ocean subsurface temperature information based on multiple target subsurface temperature inversion models, according to multiple ocean observation information and a preset ocean observation depth threshold, including: calculating the first subsurface temperature inversion information according to the multiple ocean observation information and the first target subsurface temperature inversion model, including: generating multiple ocean observation numerical tensors according to the multiple ocean observation information; performing convolution calculations on the multiple ocean observation numerical tensors based on the first target subsurface temperature inversion model to obtain multiple ocean observation numerical multi-dimensional feature maps; performing dimensionality reduction processing on the multiple ocean observation numerical multi-dimensional feature maps to obtain multiple ocean observation numerical one-dimensional feature maps; performing non-linear transformation on the ocean observation numerical one-dimensional feature maps based on the first target subsurface temperature inversion model to calculate the first subsurface temperature inversion information; Calculating the second subsurface temperature inversion information according to the multiple ocean observation information, the first subsurface temperature inversion information, and the second target subsurface temperature inversion model, including: combining the multiple ocean observation information and the first subsurface temperature inversion information to obtain a subsurface temperature inversion input tensor; performing convolution calculations on the subsurface temperature inversion input tensor based on the second target subsurface temperature inversion model to obtain multiple input tensor multi-dimensional feature maps; performing dimensionality reduction processing on the multiple input tensor multi-dimensional feature maps to obtain multiple input tensor one-dimensional feature maps; performing feature transformation processing on the input tensor one-dimensional feature maps based on the second target subsurface temperature inversion model to calculate the second subsurface temperature inversion information; Determine whether the ocean depth information corresponding to the second surface temperature inversion information is greater than or equal to a preset ocean observation depth threshold; if so, determine the second surface temperature inversion information as the ocean subsurface temperature information; if not, generate subsurface inversion temperature intermediate variable information according to the first surface temperature inversion information and the second surface inversion temperature information; use the subsurface inversion temperature intermediate variable information as the first surface temperature inversion information, and return it to the step of obtaining the second surface temperature inversion information according to the multiple ocean observation information, the first surface temperature inversion information, and the second target subsurface temperature inversion model.

4. A terminal device, characterized in that, The terminal device includes a memory and a processor, and a computer program that can run on the processor is stored on the memory. When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images