A joint reconstruction method of global ocean temperature and salinity profiles based on deep learning

Abstract

The present invention discloses a method for joint reconstruction of global ocean temperature and salinity profiles based on deep learning, which relates to the field of marine information technology. The key technical points are as follows: step S1, obtaining historical sea surface environmental parameter remote sensing data and underwater temperature and salinity profile data to construct a reconstruction model data set; step S2, demarcating global regions through K-means clustering according to temperature and salinity profile characteristics; step S3, constructing regional FFNN temperature and salinity profile reconstruction models according to the regions to obtain a joint reconstruction model of global ocean temperature and salinity profiles; step S4, obtaining real-time sea surface remote sensing data, and obtaining real-time temperature and salinity profile data based on the joint reconstruction model of global ocean temperature and salinity profiles. The present invention combines the properties of ocean temperature and salinity profiles, has superior performance, and has good applicability. It realizes the reconstruction of a global temperature and salinity model based on real-time sea surface remote sensing data, and provides new ideas and technical support for the rapid construction of global underwater temperature and salinity profiles.

Description

Technical Field

[0001] The present invention relates to the field of marine information technology, and in particular to a method for jointly reconstructing global ocean temperature and salinity profiles based on deep learning. Background Art

[0002] The underwater temperature and salinity structure of the ocean is an essential environmental factor for studying ocean processes and climate change, and plays a vital role in the study of multidimensional and multiscale dynamic processes within the ocean. However, due to the scarcity and difficulty in obtaining ocean observation data, the currently available cross-sectional data on the ocean's internal state are relatively sparse, and the temporal and spatial resolution is far from sufficient for the detailed study and application of underwater temperature and salinity structure. This has impacted and restricted my country's ability to understand and support marine environmental science in marine economics, marine engineering, shipping and transportation, and resource development and utilization.

[0003] Currently, ocean surface-subsurface reconstruction methods are primarily divided into dynamical and statistical reconstruction methods. Dynamical reconstruction methods are primarily based on surface quasigeostrophic (SQG) dynamics theory, projecting internal solutions onto the first baroclinic and barotropic modes. Using constraints from sea surface observations, they invert subsurface parameters such as sea surface height, sea surface temperature, and sea surface salinity. Statistical reconstruction methods aim to statistically or empirically combine satellite and in situ observations, exploring coupling relationships between the surface and deep layers or between different observations without involving dynamic equations, thereby reconstructing three-dimensional element fields. Their primary goal is to effectively utilize satellite remote sensing sea surface temperature and height data to rapidly estimate the dynamic three-dimensional ocean temperature and salinity field in real-time, when real-time underwater three-dimensional temperature and salinity profile observations are scarce or nonexistent. In recent years, significant progress has been made in this area, with methods such as multivariate linear regression, multivariate EOF reconstruction, coupled mode reconstruction, and the gravity empirical mode method being applied to the reconstruction of three-dimensional temperature and salinity fields.

[0004] However, most existing reconstruction methods tend to use the monthly average gridded temperature and salinity field as historical training labels to establish the monthly average temperature and salinity field reconstruction model. However, actual marine scientific research and marine environmental protection require daily, quasi-real-time underwater three-dimensional temperature and salinity fields. For the daily reconstruction model, it is necessary to use the measured scattered temperature and salinity profile as a label. However, the profile changes of the measured scattered data are more complex and contain more small and medium-scale information. The accuracy of the reconstruction method needs to be improved. Previous reconstruction models are mostly based on machine learning methods, and they rarely consider the contribution of deep learning algorithms to the improvement of reconstruction models. When performing statistical modeling on global zoning, the properties of the temperature and salinity profiles are not considered and the zoning is only performed by geographical location. At the same time, the existing reconstruction method adopts the technical approach of reconstructing and modeling temperature and salinity separately, which is not only inefficient, but also inevitably leads to poor coordination of temperature and salinity elements. Therefore, how to flexibly apply deep learning algorithms in the reconstruction model, further adapt to improve and optimize the reconstruction model effect, and provide a global temperature and salinity profile coordinated intelligent reconstruction method with high timeliness, easy execution and high accuracy is a technical problem that technicians in this field are extremely concerned about. Summary of the Invention

[0005] The purpose of the present invention is to solve the above problems and provide a global ocean temperature and salinity profile joint reconstruction method based on deep learning.

[0006] In order to achieve the above object, the technical solution of the present invention is as follows:

[0007] The present invention provides a method for jointly reconstructing global ocean temperature and salinity profiles based on deep learning, comprising the following steps:

[0008] Step S1: Acquire historical sea surface environmental parameter remote sensing data and underwater temperature and salinity profile data to construct a reconstruction model data set;

[0009] Step S2: Delineate global regions using K-means clustering based on the characteristics of the temperature-salinity profile;

[0010] Step S3, constructing a regional FFNN temperature-salinity profile reconstruction model according to the partitions to obtain a global ocean temperature-salinity profile joint reconstruction model;

[0011] Step S4: Acquire real-time sea surface remote sensing data, and obtain real-time temperature and salinity profile data based on the global ocean temperature and salinity profile joint reconstruction model.

[0012] The present invention is further configured as follows: the specific sub-steps of step S1 are:

[0013] Step S1.1: Collect historical temperature and salinity profile data as training data and independent verification data for inverted temperature and salinity profiles, and calculate the statistical regression relationship between the surface and subsurface layers. The selected historical temperature and salinity profile data must meet the following four conditions: (1) temperature and salinity are measured simultaneously; (2) the measurement depth reaches more than 1000m; (3) the minimum measurement depth is less than 5m; (4) the three data quality control flags Temperature_CODCflag, Depth_WODflag, and Salinity_CODCflag are all "0";

[0014] Step S1.2: Use cubic spline interpolation to vertically interpolate the temperature-salinity profile selected in S11 to 20 inhomogeneous layers of [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500, 600, 700, 800, 900, 1000] m;

[0015] Step S1.3: Select the delayed quality-controlled L4 level 0.25° daily gridded sea surface height anomaly data product released by the Copernicus Marine Environment Monitoring Service;

[0016] Step S1.4, interpolate the sky-averaged SLA data with a spatial resolution of 0.25° to the corresponding position of the historical temperature-salinity profile;

[0017] Step S1.5: Construct the reconstruction model dataset Y. The aggregation method of dataset Y is as follows:

[0018]

[0019] Among them, each sample in the data set Y is recorded as y (i,j)It is represented as the jth element of the i-th sample, and the longitude and latitude of all samples are consistent; i = [1, N] represents the 1st to Nth samples, one sample is a row in the matrix Y, each row contains 43 elements, j = [1, 43] represents the 1st to 43rd elements, corresponding to the 43 columns of the matrix Y; the first and second columns are longitude and latitude respectively, and the third column is the input data sea surface height; the ocean temperature and salinity profile data are divided into [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500 , 600, 700, 800, 900, 1000] m; j = [4, 23] represents the temperature of the 20 depth layers in sequence, and j = [24, 43] represents the salinity of the 20 depth layers in sequence; the paired data set Y is divided into training set Y1, validation set Y2 and test set Y3 in a ratio of 8:1:1; the specific division method is: select the first 0.8×N rows of samples as training set Y1, the remaining 0.1×N rows of samples as validation set X2, and the remaining 0.1×N rows of samples as test set Y3, and there is no intersection between the three;

[0020] Step S1.6: Normalize the input data. Select the MinMax normalization method to normalize the temperature, salinity, and sea surface height data in the input data set Y to the range [0, 1]. The normalization formula is as follows:

[0021]

[0022] The input dataset Y represents the dataset constructed in step S1.5, y j Represents an input sea surface feature in the dataset, Y ijmin is the minimum value of the i-th factor in the dataset Y, ijmax is the maximum value of the i-th factor in the data set Y. The set of factors normalized according to the formula is recorded as Y' j ; Y ijmin With Y ijmax Will be retained. During model validation and testing, the normalization of a batch of input data in the validation set and test set also uses Y ijmin With Y ijmax The calculation is performed because the statistical information contained in the training set is considered to be a known condition, while the statistical information of the test set and the validation set is considered to be an unknown condition. The purpose is to simulate the reasoning effect of the model on the unknown data set based on the existing information in most cases.

[0023] The present invention is further configured as follows: the specific sub-steps of step S2 are:

[0024] Step S2.1: Construct a cluster dataset and collect monthly average 1°×1° temperature and salinity profile data. The temperature and salinity data are sampled at depths of [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500, 600, 700, 800, 900, 1000] (unit: meter). Calculate the multi-year average and obtain the annual average temperature and salinity dataset at different longitudes and latitudes. The dataset is constructed as the training set X according to the following format:

[0025]

[0026] Among them, each element in the data set X is recorded as x i,j , x i,j represents the jth element of the ith sample, and the longitude and latitude of all samples are consistent; i = [1, N] represents the 1st to Nth samples, one sample is a row in the matrix X, and each row contains 42 elements. j = [1, 42] represents the 1st to 42nd elements, corresponding to the 42 columns of the matrix X: the first two columns are the longitude and latitude of the input data, the 3rd to 22nd columns are the temperature values of each sample profile in 20 depth layers, and the 23rd to 42nd columns are the salinity values of each sample profile in 20 depth layers;

[0027] Step S2.2, select the K value range: based on the characteristics of ocean water masses, the preset K value range is [2,20];

[0028] Step S2.3: Randomly select K samples from the training data set as the initial cluster centers:

[0029] Step S2.3.1: For each sample X i , calculate the Euclidean distance between it and the K cluster centers respectively, and record the distance between it and the j-th cluster center as d ij , j∈[1,K];

[0030] Step S2.3.2: Compare the distances between the sample and the cluster center to obtain D i =min{d ij} i , each sample can select a cluster center closest to it, and merge the samples with the same nearest cluster center into one cluster, thus obtaining K sample clusters;

[0031] Step S2.3.3: Calculate the mean of the samples in each cluster and use the mean as the new cluster center;

[0032] Step S2.3.4: If the new cluster center is different from the original cluster center, repeat steps S2.3.1-S2.3.3 until the cluster center no longer changes or the predetermined number of iterations m is reached;

[0033] Step S2.4: Output the cluster divisions and obtain the clustering results corresponding to different longitude and latitude sea areas as shown in the figure; calculate the silhouette coefficient of the entire data set. The silhouette coefficient is an indicator for evaluating clustering quality. Its value range is between [-1, 1]. The closer the value is to 1, the better the clustering effect.

[0034] Step S2.5, repeat steps S2.2-S2.4, compare the silhouette coefficients of the clustering results under different K values, obtain the optimal value of K value and its corresponding clustering result. After calculation, when K=7, the silhouette coefficient is the largest, which is 0.327; according to the clustering results, obtain the division of sea areas of different longitudes and latitudes according to the properties of temperature and salinity profiles, and divide the sea areas according to the clustering results.

[0035] The present invention is further configured as follows: the specific sub-steps of step S3 are:

[0036] Step S3.1, build the FFNN feedforward neural network reconstruction model. Assuming that n feature variables and m samples are input, the input layer X∈R m×n , construct a hidden layer with h neurons, then the weight and bias of the hidden layer can be expressed as W h ∈R n×h 、b h ∈R 1×h , if there are q output label values, the weight and bias parameters of the output layer are W o ∈R h×q 、b O ∈R 1 ×q , the output of the hidden layer and the output of the output layer are expressed as follows:

[0037] H=XW h +b h

[0038] O=HW o +b O

[0039] Build three hidden layers. The first hidden layer has h1 neurons, the second hidden layer has h2 neurons, and the third hidden layer has h3 neurons. Each layer is connected according to the above formula; each hidden layer is followed by a ReLU activation layer, the formula is as follows:

[0040] ReLU(input) = max(0, input)

[0041] Build two hidden layers. The first hidden layer has 128 neurons, and the second hidden layer has 64 neurons. Each layer is connected according to the above formula. Each hidden layer is followed by a ReLU activation layer. Adding an activation layer introduces nonlinear transformations to improve the expressiveness of the model.

[0042] Step S3.2: Select the mean square error (MSE) as the loss function of the FFNN reconstruction model to measure the difference between the reconstructed underwater temperature and salinity profile and the measured temperature and salinity profile. The formula is as follows:

[0043]

[0044] Among them, Y i Indicates the label of sample i, that is, the measured temperature and salinity profile data, Y' i Represents the value reconstructed by the model of sample i;

[0045] Step S3.3: Based on the partitioning results of S2, the dataset Y constructed in S1 is divided into seven regional datasets, which are respectively put into the FFNN reconstruction model built in S3.1 for training, and the hidden layer weights and bias W are fitted. h 、b h , the loss function is MSE, the number of initial iterations is epoch, epoch is a positive integer, the initial learning rate is lr, the initial batch size is batch size, and the optimizer is Adam;

[0046] Step S3.4: Save the trained FFNN models and model output parameters for the seven regions. The seven regional reconstruction models constitute a joint reconstruction model of the global ocean temperature and salinity profile.

[0047] The present invention is further configured as follows: the specific sub-steps of step S4 are:

[0048] Step S4.1, obtaining real-time sea surface remote sensing temperature and salinity data as model input;

[0049] Step S4.2: Input data into the global ocean temperature-salinity profile joint reconstruction model constructed in S3 to obtain the real-time global ocean temperature-salinity profile data field.

[0050] Compared with existing technologies, this solution offers significant advantages: Based on satellite remote sensing data and historical temperature-salinity profile data, this method divides the global ocean into seven regions according to the characteristics of these profiles, and constructs a FFNN temperature-salinity profile reconstruction model for each region. This method, incorporating the properties of ocean temperature-salinity profiles, offers superior performance and broad applicability. It reconstructs a global temperature-salinity model based on real-time sea surface remote sensing data, providing new insights and technical support for the rapid construction of global underwater temperature-salinity profiles. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a flowchart for implementing the joint reconstruction of global underwater temperature and salinity profiles based on deep learning in an embodiment of the present invention;

[0052] Figure 2: is a line graph of the silhouette coefficient of the clustering results under different K values in an embodiment of the present invention;

[0053] Figure 3 This is a global sea area division map for clustering temperature and salinity profile characteristics in an embodiment of the present invention;

[0054] Figure 4 This is a structural diagram of the global ocean temperature and salinity profile joint reconstruction model in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the present invention, the technical solution of the present invention will be further described in detail below in conjunction with the embodiments of the present invention and the accompanying drawings. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0056] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the embodiments.

[0057] Example:

[0058] A global ocean temperature and salinity profile joint reconstruction method based on deep learning, such as Figure 1-4 As shown, the following steps are included:

[0059] Step S1: Obtain historical sea surface environmental parameter remote sensing data and underwater temperature and salinity profile data to construct a reconstruction model dataset.

[0060] Step S2: Based on the characteristics of the temperature and salinity profiles, global regions are delineated through K-means clustering.

[0061] Step S3: Construct a regional FFNN temperature-salinity profile reconstruction model according to the partitions to obtain a global ocean temperature-salinity profile joint reconstruction model.

[0062] Step S4: Acquire real-time sea surface remote sensing data, and obtain real-time temperature and salinity profile data based on the global ocean temperature and salinity profile joint reconstruction model.

[0063] The specific steps for obtaining historical sea surface environmental parameter remote sensing data and underwater temperature and salinity profile data and constructing the reconstruction model dataset are as follows:

[0064] Step S1.1: Download the historical temperature and salinity profile dataset (IAP) from the website of the Institute of Atmospheric Physics, Chinese Academy of Sciences (http: / / www.ocean.iap.ac.cn / ftp / cheng / CODC-GOSD_database / ). The historical temperature and salinity profiles from 2002 to 2021 are used as training data to calculate the statistical regression relationship between the surface and subsurface layers, while the profiles from 2022 and 2023 are used as independent verification data and test data for the inverted temperature and salinity profiles. The selected profile data must meet the following four conditions: (1) simultaneous measurement of temperature and salinity; (2) measurement depth of more than 1000m; (3) minimum measurement depth of less than 5m; (4) the three data quality control flags Temperature_CODCflag, Depth_WODflag, and Salinity_CODCflag are all '0' (high quality).

[0065] Step S1.2: Use cubic spline interpolation to vertically interpolate the temperature-salinity profile selected in S1.1 to 20 inhomogeneous layers of [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500, 600, 700, 800, 900, 1000] m.

[0066] Step S1.3: Select the delayed quality-controlled L4 0.25° daily gridded sea surface anomaly (SLA) data product released by the Copernicus Marine Environment Monitoring Service (CMEMS) for the period 2002-2023.

[0067] Step S1.4: Interpolate the sky-averaged SLA data with a spatial resolution of 0.25° to the corresponding position of the historical temperature-salinity profile.

[0068] Step S1.5: Construct the reconstruction model dataset Y. The aggregation method of dataset Y is as follows:

[0069]

[0070] Among them, each sample in the data set Y is recorded as y (i,j)It is represented as the jth element of the i-th sample, and the longitude and latitude of all samples are consistent; i = [1, N] represents the 1st to Nth samples, one sample is a row in the matrix Y, each row contains 43 elements, j = [1, 43] represents the 1st to 43rd elements, corresponding to the 43 columns of the matrix Y; the first and second columns are longitude and latitude respectively, and the third column is the input data sea surface height; the ocean temperature and salinity profile data are divided into [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500 , 600, 700, 800, 900, 1000] m; j = [4, 23] represents the temperature of the 20 depth layers in sequence, and j = [24, 43] represents the salinity of the 20 depth layers in sequence; the paired data set Y is divided into training set Y1, validation set Y2 and test set Y3 in a ratio of 8:1:1; the specific division method is: select the first 0.8×N rows of samples as the training set Y1, the remaining 0.1×N rows of samples as the validation set X2, and the 0.1×N rows of samples as the test set Y3, and there is no intersection between the three.

[0071] Step S1.6: Normalize the input data. Select the MinMax normalization method to normalize the temperature, salinity, and sea surface height data in the input data set Y to the range [0, 1]. The normalization formula is as follows:

[0072]

[0073] Among them, the input dataset Y represents the dataset constructed in step 1.5, y j Represents an input ocean feature in the dataset, Y ijmin is the minimum value of the i-th factor in the dataset Y, ijmax is the maximum value of the i-th factor in the data set Y. The set of factors normalized according to the formula is recorded as Y' j ; Y ijmin With Y ijmax Will be retained. During model validation and testing, the normalization of a batch of input data in the validation set and test set also uses Y ijmin With Y ijmax The calculation is performed because the statistical information contained in the training set is considered to be a known condition, while the statistical information of the test set and the validation set is considered to be an unknown condition. The purpose is to simulate the reasoning effect of the model on the unknown data set based on the existing information in most cases.

[0074] Step S2: Based on the characteristics of the temperature-salinity profile, global regions are delineated through K-means clustering. The specific steps are as follows:

[0075] Step S2.1. Construct a clustering dataset. Download the monthly average 1°×1° temperature and salinity profile data from 2002 to 2023 from the website of the Institute of Atmospheric Physics, Chinese Academy of Sciences (http: / / www.ocean.iap.ac.cn / ftp / cheng / CODC-GOSD_database / ). The temperature and salinity data are sampled at depths of [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500, 600, 700, 800, 900, 1000] (unit: meters). Calculate the multi-year average to obtain a 20-year average temperature and salinity dataset at different longitudes and latitudes. The dataset is constructed as the training set X according to the following format:

[0076]

[0077] Among them, each element in the data set X is recorded as x i,j , x i,j represents the jth element of the ith sample, and the longitude and latitude of all samples are consistent; i = [1, N] represents the 1st to Nth samples, one sample is a row in the matrix X, and each row contains 42 elements. j = [1, 42] represents the 1st to 42nd elements, corresponding to the 42 columns of the matrix X: the first two columns are the longitude and latitude of the input data, the 3rd to 22nd columns are the temperature values of each sample profile in 20 depth layers, and the 23rd to 42nd columns are the salinity values of each sample profile in 20 depth layers;

[0078] Step S2.2. Select the K value range: Based on the characteristics of ocean water masses, the preset K value range is [2, 20];

[0079] Step S2.3. Randomly select K samples from the training data set as the initial cluster centers.

[0080] Step S2.3.1. For each sample X i , calculate the Euclidean distance between it and the K cluster centers respectively, and record the distance between it and the j-th cluster center as d ij , j∈[1,K];

[0081] Step S2.3.2. Compare the distances between the sample and the cluster center and get D i =min{d ij} i , each sample can select a cluster center closest to it, and merge the samples with the same nearest cluster center into one cluster, thus obtaining K sample clusters;

[0082] Step S2.3.3. Calculate the mean of the samples in each cluster and use the mean as the new cluster center;

[0083] Step S2.3.4. If the new cluster center is different from the original cluster center, repeat steps S2.3.1-S2.3.3 until the cluster center no longer changes or the predetermined number of iterations m is reached.

[0084] Step S2.4. Output the clustering results, obtaining the clustering results corresponding to different longitudes and latitudes of the ocean as shown in the figure. Calculate the silhouette coefficient for the entire dataset. The silhouette coefficient is an indicator of clustering quality, ranging from -1 to 1. Values closer to 1 indicate better clustering results.

[0085] Step S2.5. Repeat steps S2.2-S2.4, compare the silhouette coefficients of clustering results under different K values, and obtain the optimal value of K and its corresponding clustering results, see Figure 2 After calculation, when K=7, the silhouette coefficient is the largest, which is 0.327. According to the clustering results, the division of sea areas at different longitudes and latitudes is obtained according to the properties of the temperature and salinity profiles. The sea areas are divided according to the clustering results. Figure 3 .

[0086] Step S3: Construct a regional FFNN temperature-salinity profile reconstruction model according to the partitions to obtain a global ocean temperature-salinity profile joint reconstruction model. The specific steps are as follows:

[0087] Step S3.1: Build the FFNN feedforward neural network reconstruction model. Assuming that n feature variables and m samples are input, the input layer X∈R m×n , construct a hidden layer with h neurons, then the weight and bias of the hidden layer can be expressed as W h ∈R n×h 、b h ∈R 1×h , if there are q output label values, the weight and bias parameters of the output layer are W o ∈R h×q 、b O ∈R 1 ×q , the output of the hidden layer and the output of the output layer are expressed as follows:

[0088] H=XW h +b h

[0089] O=HW o +b O

[0090] Build three hidden layers. The first hidden layer has h1 neurons, the second hidden layer has h2 neurons, and the third hidden layer has h3 neurons. Each layer is connected according to the above formula; each hidden layer is followed by a ReLU activation layer, the formula is as follows:

[0091] ReLU(input) = max(0, input)

[0092] Reference Attachment Figure 4 , build two hidden layers. The first hidden layer has 128 neurons and the second hidden layer has 64 neurons. Each layer is connected according to the above formula; each hidden layer is followed by a ReLU activation layer. Adding the activation layer introduces nonlinear transformation to improve the expressive power of the model.

[0093] Step S3.2: Select the mean square error (MSE) as the loss function of the FFNN reconstruction model to measure the difference between the reconstructed underwater temperature and salinity profile and the measured temperature and salinity profile. The formula is as follows:

[0094]

[0095] Among them, Y i Indicates the label of sample i, that is, the measured temperature and salinity profile data, Y' i Represents the value reconstructed by the model for sample i.

[0096] Step S3.3: Based on the partitioning results of S2, the dataset Y constructed in S1 is divided into seven regional datasets, which are respectively put into the FFNN reconstruction model built in S3.1 for training, fitting the hidden layer weights and bias W h 、b h , the loss function is MSE, the number of initial iterations is epoch, epoch is a positive integer, the initial learning rate is lr, the initial batch size is batch size, and the optimizer is Adam.

[0097] Step S3.4: Save the trained FFNN models and model output parameters for the seven regions. The seven regional reconstruction models constitute the global ocean temperature and salinity profile joint reconstruction model.

[0098] Step S4: Acquire real-time sea surface remote sensing data and obtain real-time temperature and salinity profile data based on the global ocean temperature and salinity profile joint reconstruction model. The specific steps are as follows:

[0099] Step S4.1: Obtain real-time sea surface remote sensing temperature and salinity data as model input;

[0100] Step S4.2: Data is input into the global ocean temperature and salinity profile joint reconstruction model constructed in S3 to obtain the real-time global ocean temperature and salinity profile data field.

[0101] The above specific embodiments are merely explanations of the present invention and are not limitations of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the embodiments as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by patent law.

Claims

1. A method for joint reconstruction of global ocean temperature and salinity profiles based on deep learning, characterized by: The following steps are involved: Step S1: Acquire historical sea surface environmental parameter remote sensing data and underwater temperature and salinity profile data to construct a reconstruction model data set; Step S2: Delineate global regions using K-means clustering based on the characteristics of the temperature-salinity profile; The specific steps of step S2 are: Step S2.1: Construct a cluster dataset and collect monthly average 1°×1° temperature and salinity profile data. The temperature and salinity data are sampled at depths of [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500, 600, 700, 800, 900, 1000] (unit: meter). Calculate the multi-year average and obtain the annual average temperature and salinity dataset at different longitudes and latitudes. The dataset is constructed as the training set X according to the following format: Among them, each element in the data set X is recorded as x i,j , x i,j represents the jth element of the ith sample, and the longitude and latitude of all samples are consistent; i = [1, N] represents the 1st to Nth samples, one sample is a row in the matrix X, and each row contains 42 elements. j = [1, 42] represents the 1st to 42nd elements, corresponding to the 42 columns of the matrix X: the first two columns are the longitude and latitude of the input data, the 3rd to 22nd columns are the temperature values of each sample profile in 20 depth layers, and the 23rd to 42nd columns are the salinity values of each sample profile in 20 depth layers; Step S2.2, select the K value range: based on the characteristics of ocean water masses, the preset K value range is [2,20]; Step S2.3: Randomly select K samples from the training data set as the initial cluster centers: Step S2.3.1: For each sample X i , calculate the Euclidean distance between it and the K cluster centers respectively, and record the distance between it and the j-th cluster center as d ij , j∈[1,K]; Step S2.3.2: Compare the distances between the sample and the cluster center to obtain D i =min{d ij } i , each sample selects a cluster center closest to it, and merges the samples with the same nearest cluster center into one cluster, thus obtaining K sample clusters; Step S2.3.3: Calculate the mean of the samples in each cluster and use the mean as the new cluster center; Step S2.3.4: If the new cluster center is different from the original cluster center, repeat steps S2.3.1-S2.3.3 until the cluster center no longer changes or the predetermined number of iterations m is reached; Step S2.4: Output the cluster division and obtain the clustering results corresponding to different longitude and latitude sea areas; calculate the silhouette coefficient of the entire data set. The silhouette coefficient is an indicator for evaluating clustering quality. Its value range is between [-1, 1]. The closer the value is to 1, the better the clustering effect. Step S2.5: Repeat steps S2.2-S2.4, comparing the silhouette coefficients of the clustering results under different K values to obtain the optimal K value and its corresponding clustering result. After calculation, when K = 7, the silhouette coefficient is the largest, which is 0.

327. Based on the clustering results, the division of sea areas at different longitudes and latitudes according to the properties of the temperature and salinity profile is obtained, and the sea areas are divided according to the clustering results. Step S3, constructing a regional FFNN temperature-salinity profile reconstruction model according to the partitions to obtain a global ocean temperature-salinity profile joint reconstruction model; Step S4: Acquire real-time sea surface remote sensing data, and obtain real-time temperature and salinity profile data based on the global ocean temperature and salinity profile joint reconstruction model.

2. The method for joint reconstruction of global ocean temperature and salinity profiles based on deep learning according to claim 1, characterized in that: The specific steps of step S1 are: Step S1.1: Collect historical temperature and salinity profile data as training data, independent verification data for inverted temperature and salinity profiles, and test data, and calculate the statistical regression relationship between the surface and subsurface layers. The selected historical temperature and salinity profile data must meet the following four conditions: (1) simultaneous measurement of temperature and salinity; (2) measurement depth of more than 1000m; (3) minimum measurement depth of less than 5m; (4) three data quality control flags Temperature_CODCflag, Depth_WODflag, and Salinity_CODCflag are all "0"; Step S1.2: Use cubic spline interpolation to vertically interpolate the temperature-salinity profile selected in S1.1 to 20 inhomogeneous layers of [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500, 600, 700, 800, 900, 1000] m; Step S1.3: Select the delayed quality-controlled L4 level 0.25° daily gridded sea surface height anomaly data product released by the Copernicus Marine Environment Monitoring Service; Step S1.4, interpolate the sky-averaged SLA data with a spatial resolution of 0.25° to the corresponding position of the historical temperature-salinity profile; Step S1.5: Construct the reconstruction model dataset Y. The aggregation method of dataset Y is as follows: Among them, each sample in the data set Y is recorded as y (i,j) It is represented as the jth element of the i-th sample, and the longitude and latitude of all samples are consistent; i = [1, N] represents the 1st to Nth samples, one sample is a row in the matrix Y, each row contains 43 elements, j = [1, 43] represents the 1st to 43rd elements, corresponding to the 43 columns of the matrix Y; the first and second columns are longitude and latitude respectively, and the third column is the input data sea surface height; the ocean temperature and salinity profile data are divided into [5, 10, 20, 30, 40, 50, 75, 100, 125, 150, 200, 250, 300, 400, 500 , 600, 700, 800, 900, 1000] m; j = [4, 23] represents the temperature of the 20 depth layers in sequence, and j = [24, 43] represents the salinity of the 20 depth layers in sequence; the paired data set Y is divided into training set Y1, validation set Y2 and test set Y3 in a ratio of 8:1:1; the specific division method is: select the first 0.8×N rows of samples as training set Y1, the remaining 0.1×N rows of samples as validation set X2, and the remaining 0.1×N rows of samples as test set Y3, and there is no intersection between the three; Step S1.6: Normalize the input data. Select the MinMax normalization method to normalize the temperature, salinity, and sea surface height data in the input data set Y to the range [0, 1]. The normalization formula is as follows: The input dataset Y represents the dataset constructed in step S1.5, y j Represents an input ocean feature in the dataset, Y ijmin is the minimum value of the i-th factor in the dataset Y, ijmax is the maximum value of the i-th factor in the data set Y. The set of factors normalized according to the formula is recorded as Y' j ; Y ijmin With Y ijmax Will be retained. During model validation and testing, the normalization of a batch of input data in the validation set and test set also uses Y ijmin With Y ijmax The calculation is performed because the statistical information contained in the training set is considered to be a known condition, while the statistical information of the test set and the validation set is considered to be an unknown condition. The purpose is to simulate the reasoning effect of the model on the unknown data set based on the existing information in most cases.

3. The method for joint reconstruction of global ocean temperature and salinity profiles based on deep learning according to claim 1, characterized in that: The specific steps of step S3 are: Step S3.1, build the FFNN feedforward neural network reconstruction model. Assuming that n feature variables and m samples are input, the input layer X∈R m×n , construct a hidden layer with h neurons, then the weight and bias of the hidden layer can be expressed as W h ∈R n×h 、b h ∈R 1×h , if there are q output label values, the weight and bias parameters of the output layer are W o ∈R h×q 、b O ∈R 1×q , the output of the hidden layer and the output of the output layer are expressed as follows: H=XW h +b h O=HW o +b O Build three hidden layers. The first hidden layer has h1 neurons, the second hidden layer has h2 neurons, and the third hidden layer has h3 neurons. Each layer is connected according to the above formula; each hidden layer is followed by a ReLU activation layer, the formula is as follows: ReLU(input) = max(0, input) Build two hidden layers. The first hidden layer has 128 neurons, and the second hidden layer has 64 neurons. Each layer is connected according to the above formula. Each hidden layer is followed by a ReLU activation layer. Adding an activation layer introduces nonlinear transformations to improve the expressiveness of the model. Step S3.2: Select the mean square error (MSE) as the loss function of the FFNN reconstruction model to measure the difference between the reconstructed underwater temperature and salinity profile and the measured temperature and salinity profile. The formula is as follows: Among them, Y i Indicates the label of sample i, that is, the measured temperature and salinity profile data, Y' i Represents the value reconstructed by the model of sample i; Step S3.3: Based on the partitioning results of S2, the dataset Y constructed in S1 is divided into seven regional datasets, which are respectively put into the FFNN reconstruction model built in S3.1 for training, and the hidden layer weights and bias W are fitted. h 、b h , the loss function is MSE, the number of initial iterations is epoch, epoch is a positive integer, the initial learning rate is lr, the initial batch size is batchsize, and the optimizer is Adam; Step S3.4: Save the trained FFNN models and model output parameters for the seven regions. The seven regional reconstruction models constitute a joint reconstruction model of the global ocean temperature and salinity profile.

4. The method for joint reconstruction of global ocean temperature and salinity profiles based on deep learning according to claim 1, characterized in that: The specific steps of step S4 are: Step S4.1, obtaining real-time sea surface remote sensing temperature and salinity data as model input; Step S4.2: Input data into the global ocean temperature-salinity profile joint reconstruction model constructed in S3 to obtain the real-time global ocean temperature-salinity profile data field.

Images