CN115307780A - Sea surface temperature prediction method, system and application based on time-space information interaction fusion - Google Patents

Sea surface temperature prediction method, system and application based on time-space information interaction fusion Download PDF

Info

Publication number
CN115307780A
CN115307780A CN202211194484.9A CN202211194484A CN115307780A CN 115307780 A CN115307780 A CN 115307780A CN 202211194484 A CN202211194484 A CN 202211194484A CN 115307780 A CN115307780 A CN 115307780A
Authority
CN
China
Prior art keywords
time
matrix
space
spatial
surface temperature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202211194484.9A
Other languages
Chinese (zh)
Other versions
CN115307780B (en
Inventor
聂婕
宋宁
郑程予
魏志强
刘安安
宋丹
李文辉
孙正雅
张文生
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ocean University of China
Original Assignee
Ocean University of China
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ocean University of China filed Critical Ocean University of China
Priority to CN202211194484.9A priority Critical patent/CN115307780B/en
Publication of CN115307780A publication Critical patent/CN115307780A/en
Application granted granted Critical
Publication of CN115307780B publication Critical patent/CN115307780B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K13/00—Thermometers specially adapted for specific purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2474—Sequence data queries, e.g. querying versioned data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The invention belongs to the technical field of sea surface temperature prediction, and discloses a sea surface temperature prediction method, a sea surface temperature prediction system and application based on time-space information interactive fusion, wherein the sea surface temperature prediction system comprises an input module, a time-space matrix construction module, a time-space characteristic interactive fusion module, a time-space matrix aggregation module, a sea surface temperature data prediction module and an output module, a time-space matrix of each point in space is constructed through the time-space matrix construction module, and a time visual angle and a space visual angle characteristic expression are extracted from the time-space matrix; by constructing a space-time feature interactive fusion module and utilizing a self-attention mechanism and a mutual-attention mechanism in a Transformer, the mutual guidance relations of the time features at different moments, the mutual guidance relations of the space features in different spaces and the mutual guidance relations of the time features and the space features are fully excavated, so that the interactive fusion of the space-time information of the sea surface temperature data is realized, and the sea surface temperature prediction accuracy is improved.

Description

Sea surface temperature prediction method, system and application based on time-space information interaction fusion
Technical Field
The invention belongs to the technical field of sea surface temperature prediction, and particularly relates to a sea surface temperature prediction method and system based on space-time information interaction fusion and application.
Background
The sea surface temperature is the water temperature near the surface of the ocean, and the time-space change of the sea surface temperature reflects the dynamic evolution rule of the physical and chemical properties of the ocean, so that the prediction of the time-space distribution of the sea surface temperature data has important significance for guiding the ocean ecological environment. In the most advanced sea surface temperature data prediction method at present, the influences of time sequence characteristics, space structure characteristics and external factors on marine science data can be comprehensively considered, time sequence models such as long-term and short-term memory neural network models are generally adopted in the aspect of time characteristic data processing, and convolutional neural network models are generally adopted in the aspect of space characteristic data processing. In the space-time fusion strategy, space fusion is carried out firstly, and then time fusion is carried out, so that the time sequence characteristic and the space characteristic are fused, and the space-time distribution rule and the change trend of the sea surface temperature data can be mined to a certain extent. However, this method has the following problems:
firstly, the existing model structure can not realize the interactive fusion of the sea surface temperature data space-time information. The existing sea surface temperature data prediction model structure mostly adopts a method of performing time characteristic polymerization after spatial characteristic polymerization. Because the spatial dimension is fused before the time dimension, the spatial feature fusion cannot be guided by the spatial features at other moments, and thus the interactive fusion of the spatiotemporal information cannot be effectively realized.
Secondly, the characteristic that the physical process changes slowly exists in the marine physical field, so that the problem of ultra-long term dependence needs to be considered in time sequence prediction, for example, the marine element characteristics before one month can also influence the prediction of marine scientific data at the current moment. The existing method mostly adopts traditional time sequence prediction models such as a long-term and short-term memory neural network model, the previous time sequence information is lost in the time sequence characteristic transmission process, and although the long-term dependence problem is relieved to a certain extent by the structure of a gate mechanism in the model, the existing time sequence prediction method can not be used for the ultra-long-term dependence phenomenon.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a sea surface temperature prediction method, a sea surface temperature prediction system and sea surface temperature prediction application based on space-time information interaction fusion, wherein a space-time matrix of each point in a space is constructed through a space-time matrix construction module, and a time visual angle and a characteristic expression of the space visual angle are extracted from the space-time matrix; by constructing a space-time feature interactive fusion module and utilizing a self-attention mechanism and a mutual-attention mechanism in a Transformer, the mutual guidance relationship of time features at different moments, the mutual guidance relationship of space features in different spaces and the mutual guidance relationship of the time features and the space features are fully mined, the interactive fusion of the space-time information of the sea surface temperature data is realized, and the sea surface temperature prediction accuracy is improved.
In order to solve the technical problems, the invention adopts the technical scheme that:
the sea surface temperature prediction method based on the time-space information interactive fusion comprises the following steps:
s1, taking N sea surface temperature data matrixes with time dimensions of M N V
Figure 19390DEST_PATH_IMAGE001
Performing matrix averaging operation on the V dimension and aggregating the matrices to obtain a matrix S with the dimension of N M N; m, N, V is three dimensions;
s2, extracting a space-time matrix of each space point from the matrix S
Figure 840584DEST_PATH_IMAGE002
Wherein
Figure 141116DEST_PATH_IMAGE003
(ii) a The extraction method comprises extracting characteristic value of point i in t days and characteristic value of D-1 space points in neighborhood thereof as the characteristic value of the point
Figure 272145DEST_PATH_IMAGE004
Figure 819670DEST_PATH_IMAGE005
Dimension of
Figure 941210DEST_PATH_IMAGE006
(ii) a Then will be
Figure 468268DEST_PATH_IMAGE007
Performing matrix transformation to obtain a space-time grid with i point and dimension of t x D
Figure 483498DEST_PATH_IMAGE008
To obtain a space-time grid of all time instants
Figure 952656DEST_PATH_IMAGE009
；
S3, mixing
Figure 561492DEST_PATH_IMAGE010
Performing feature aggregation to obtain a time feature matrix
Figure 220138DEST_PATH_IMAGE011
，
Figure 902923DEST_PATH_IMAGE011
With dimensions M x N x t x D, M x N representing the presence of M x N spatial points, and for each spatial point there is a two-dimensional time signature matrix with dimensions t x D, wherein each row represents the time signature of the sea surface temperature, i.e. each spatial point
Figure 464354DEST_PATH_IMAGE012
The time characteristic of the moment has the dimension of 1*D;
s4, mixing
Figure 45639DEST_PATH_IMAGE011
The last two dimensions are transposed to obtain a space characteristic matrix
Figure 163768DEST_PATH_IMAGE013
，
Figure 294535DEST_PATH_IMAGE013
The dimension of (a) is M x N x D x t, M x N represents that M x N space points exist, and a two-dimensional space feature matrix with the dimension of D x t exists for each space point, wherein each row represents the space feature of the sea surface temperature, namely the space feature on each space point, and the dimension is 1*t;
s5, mixing
Figure 292447DEST_PATH_IMAGE011
And
Figure 275274DEST_PATH_IMAGE013
converting the time characteristic matrix into a two-dimensional time characteristic matrix and a two-dimensional space characteristic matrix of M points by N points, wherein the dimensionalities of the obtained time characteristic matrix and the obtained space characteristic matrix are t f and D f respectively;
s6, interactively fusing the time characteristics and the spatial characteristics obtained in the step S5 through four transform-based attention coding blocks, wherein the transform-based attention coding blocks are respectively based on a time self-attention module, a space self-attention module, a time guidance space attention module and a space guidance time attention module, and a time characteristic matrix is input
Figure 259410DEST_PATH_IMAGE011
And a spatial feature matrix
Figure 166055DEST_PATH_IMAGE013
Finally, four feature matrixes M of t x l, D x l, t x l and D x l of the M x N sample points are obtained respectively 1 、M 2 、M 3 、M 4 ；
S7, combining the four feature matrixes M 1 、M 2 、M 3 、M 4 Carrying out polymerization to obtain a polymerization space-time matrix M with dimension t x D;
s8, subjecting the aggregation space-time matrix M to LSTM operation to obtain the prediction result of the last M-N points
Figure 836333DEST_PATH_IMAGE014
(ii) a And performing loss calculation through the real data values y of the M x N space points, and performing back propagation operation to update the model parameters.
Further, in step S6, the time-based self-attention module only receives the time feature matrix
Figure 375899DEST_PATH_IMAGE011
And set the weight
Figure 350677DEST_PATH_IMAGE015
，
Figure 190457DEST_PATH_IMAGE016
，
Figure 31637DEST_PATH_IMAGE017
Respectively with
Figure 996182DEST_PATH_IMAGE011
Obtained by multiplying
Figure 836967DEST_PATH_IMAGE018
，
Figure 203358DEST_PATH_IMAGE019
，
Figure 215438DEST_PATH_IMAGE020
：
Figure 182126DEST_PATH_IMAGE021
Then calculating a relation weight matrix between the time characteristics
Figure 577336DEST_PATH_IMAGE022
：
Figure 860549DEST_PATH_IMAGE023
Finally utilize
Figure 43531DEST_PATH_IMAGE024
Weight of relationship between the intermediate features, calculating M 1 Assigning attention to different features:
Figure 231936DEST_PATH_IMAGE025
the resulting matrix M 1 Is a feature matrix of mutual guidance of temporal features.
Further, in step S6, the spatial self-attention module only receives the spatial feature matrix
Figure 899678DEST_PATH_IMAGE026
And set the weight
Figure 991393DEST_PATH_IMAGE027
，
Figure 109390DEST_PATH_IMAGE028
，
Figure 270244DEST_PATH_IMAGE029
Respectively with
Figure 757989DEST_PATH_IMAGE030
Obtained by multiplying
Figure 281374DEST_PATH_IMAGE031
，
Figure 117743DEST_PATH_IMAGE032
，
Figure 952844DEST_PATH_IMAGE033
：
Figure 978700DEST_PATH_IMAGE034
Then calculating a relation weight matrix between the spatial features
Figure 28695DEST_PATH_IMAGE035
：
Figure 488495DEST_PATH_IMAGE036
Finally utilize
Figure 374674DEST_PATH_IMAGE037
Weight of relationship between the intermediate features, calculating M 2 Assigning attention to different features:
Figure 719068DEST_PATH_IMAGE038
the resulting matrix M 2 Is a feature matrix of mutual guidance of spatial features.
Further, in step S6, the temporal guidance spatial attention module first receives the temporal feature matrix
Figure 951466DEST_PATH_IMAGE039
And set the weight
Figure 378905DEST_PATH_IMAGE040
And is and
Figure 955642DEST_PATH_IMAGE041
obtained by multiplying
Figure 306989DEST_PATH_IMAGE042
As a time guidance matrix:
Figure 580845DEST_PATH_IMAGE043
then inputting the spatial feature matrix
Figure 257814DEST_PATH_IMAGE044
And design the weights
Figure 56268DEST_PATH_IMAGE045
，
Figure 414568DEST_PATH_IMAGE046
Respectively with
Figure 605246DEST_PATH_IMAGE047
Obtained by multiplying
Figure 390800DEST_PATH_IMAGE048
，
Figure 676550DEST_PATH_IMAGE049
：
Figure 822229DEST_PATH_IMAGE050
Computing spatio-temporal relationship weight matrices
Figure 883726DEST_PATH_IMAGE051
：
Figure 263017DEST_PATH_IMAGE052
Finally utilize
Figure 331336DEST_PATH_IMAGE053
The weight of the relation between the intermediate features, calculating M 3 Namely, the attention of the time characteristic to the space characteristic is distributed:
Figure 359335DEST_PATH_IMAGE054
the resulting matrix M 3 Is a feature matrix of temporal feature guide spatial features.
Further, in step S6, the spatial guidance temporal attention module first receives a spatial feature matrix
Figure 275339DEST_PATH_IMAGE055
And set the weight
Figure 153427DEST_PATH_IMAGE056
And is and
Figure 912304DEST_PATH_IMAGE057
obtained by multiplying
Figure 150519DEST_PATH_IMAGE058
As a spatial guide matrix:
Figure 671761DEST_PATH_IMAGE059
then inputting the time characteristic matrix
Figure 970019DEST_PATH_IMAGE060
And design the weights
Figure 685034DEST_PATH_IMAGE061
，
Figure 54835DEST_PATH_IMAGE062
Respectively with
Figure 696163DEST_PATH_IMAGE063
Obtained by multiplying
Figure 165322DEST_PATH_IMAGE064
，
Figure 633212DEST_PATH_IMAGE065
：
Figure 987399DEST_PATH_IMAGE066
Computing spatio-temporal relationship weight matrices
Figure 732501DEST_PATH_IMAGE067
：
Figure 621829DEST_PATH_IMAGE068
Finally utilize
Figure 78480DEST_PATH_IMAGE069
Weight of relationship between the intermediate features, calculating M 4 Namely, the attention of the distributed space characteristic to the time characteristic:
Figure 258926DEST_PATH_IMAGE070
the resulting matrix M 4 Is a feature matrix of spatial feature guide temporal features.
Further, step S7 obtains an aggregation spatio-temporal matrix M according to the following formula,
Figure 311064DEST_PATH_IMAGE071
wherein the content of the first and second substances,
Figure 160508DEST_PATH_IMAGE072
combining the time characteristic after the time information self-fusion with the space characteristic after the time-space information fusion to obtain a multi-view space-time characteristic matrix；
Figure 494669DEST_PATH_IMAGE073
Combining the spatial features of the spatial information after self-fusion with the temporal features of the spatial information after fusion to obtain a spatial-temporal feature matrix with multiple visual angles; and T represents the transposition of the matrix, and finally cross multiplication operation is carried out to obtain a final space-time fusion characteristic matrix.
Further, in step S8, the prediction result is obtained by using M × N points
Figure 744384DEST_PATH_IMAGE074
And performing loss calculation on the real data values y of the M x N space points, as shown in formula (4):
Figure 152494DEST_PATH_IMAGE075
and (3) each time all samples in one batch are predicted and Loss is calculated, obtaining a final Loss value Loss through a formula (5), and performing back propagation operation to update model parameters:
Figure 321307DEST_PATH_IMAGE076
wherein m is the batch size.
The invention also provides a sea surface temperature prediction system based on the time-space information interactive fusion, which is used for realizing the sea surface temperature prediction method based on the time-space information interactive fusion, and comprises an input module, a time-space matrix construction module, a time-space characteristic interactive fusion module, a time-space matrix aggregation module, a sea surface temperature data prediction module and an output module,
the input module is used for inputting sea surface temperature data and acquiring N sea surface temperature data matrixes with time dimensions of M x N x V
Figure 337116DEST_PATH_IMAGE001
Performing matrix averaging operation on V dimension and aggregating the matrices to obtain a matrix with dimension N M NS；
The space-time matrix construction module is used for constructing a space-time matrix and extracting the space-time matrix of each space point from the matrix S
Figure 849000DEST_PATH_IMAGE002
Then will be
Figure 923135DEST_PATH_IMAGE002
Performing matrix transformation to obtain a space-time grid with i point and dimension of t x D
Figure 966309DEST_PATH_IMAGE008
To obtain a space-time grid of all time instants
Figure 557827DEST_PATH_IMAGE009
；
The space-time feature interactive fusion module is used for carrying out space-time feature interactive fusion and comprises four attention coding blocks based on a transformer, namely a time self-attention module, a time guidance space attention module, a space guidance time attention module and a space self-attention module,
firstly, the method is to
Figure 189797DEST_PATH_IMAGE009
Performing feature aggregation to obtain a time feature matrix
Figure 700412DEST_PATH_IMAGE011
Then will be
Figure 879548DEST_PATH_IMAGE011
The last two dimensions are transposed to obtain a space characteristic matrix
Figure 9178DEST_PATH_IMAGE013
(ii) a Will be provided with
Figure 744922DEST_PATH_IMAGE011
And
Figure 927904DEST_PATH_IMAGE013
converting the two-dimensional time characteristic matrix and the two-dimensional space characteristic matrix into M x N points, and finally obtaining four characteristic matrixes M of M x N sample points through four transform-based attention coding block processing 1 、M 2 、M 3 、M 4 ；
The space-time matrix aggregation module is used for aggregating four feature matrixes M 1 、M 2 、M 3 、M 4 Polymerizing to obtain a polymerization space-time matrix M;
the sea surface temperature data prediction module is used for carrying out LSTM operation on the polymerization space-time matrix M to obtain the prediction result of the last M points by N points
Figure 663779DEST_PATH_IMAGE074
；
And the output module is used for outputting the prediction result.
The invention also provides application of the sea surface temperature prediction system based on the time-space information interaction fusion, which is used for predicting the sea surface temperature, inputting the sea surface temperature data in a period of historical time A days, and outputting the sea surface temperature prediction result in a period of future time B days.
Compared with the prior art, the invention has the advantages that:
(1) And realizing the interactive fusion of the time-space information of the sea surface temperature data. The method constructs a space-time global space through a space-time matrix construction module, extracts a time characteristic matrix and a space characteristic matrix from a time visual angle and a space visual angle, interactively fuses the time characteristic matrix and the space characteristic matrix by utilizing a self-attention mechanism and an interactive attention mechanism in a Transformer, fully excavates the mutual guidance relation of the time characteristic and the space characteristic, realizes the interactive fusion of the space-time information of the sea surface temperature data, and improves the sea surface temperature prediction accuracy.
(2) The problem of the super-long-term dependence of the sea surface temperature time sequence prediction is solved. Through the space-time feature interaction fusion module, the time features at all moments can guide and interact any time feature, the distance and the like in the interaction process are guaranteed, the overall effective ultra-long term dependence relationship is effectively extracted, and the problem that the previous time sequence information is lost in the time sequence feature transmission process in the existing method is solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a block diagram of the temporal self-attention coding block of the present invention;
FIG. 3 is a block diagram of the spatial self-attention coding block of the present invention;
FIG. 4 is a block diagram of a time-guided spatial interactive attention code block of the present invention;
fig. 5 is a block diagram of a space-directed temporal interactive attention coding block of the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
Example 1
The embodiment designs a sea surface temperature prediction method based on space-time information interactive fusion, and the method replaces a convolution submodule in a traditional ConvLSTM model with a space-time matrix construction module and a space-time characteristic interactive fusion module. Firstly, sea surface temperature data is preprocessed, then a time-space matrix building module is built to obtain a time characteristic matrix and a space characteristic matrix, finally a time-space characteristic interactive fusion module is built to interactively fuse the time information of the time characteristic matrix and the space information of the space characteristic matrix to obtain four characteristic matrices and aggregate the four characteristic matrices, the aggregated time-space matrix is subjected to LSTM operation to obtain a prediction result, and the purpose is to predict the sea surface temperature in the same space area at the future n +1 moment. With reference to fig. 1-5, the method comprises the following steps:
s1, taking N sea surface temperature data matrixes with time dimensions of M N V
Figure 784050DEST_PATH_IMAGE001
Performing matrix averaging operation on the V dimension and aggregating the matrices to obtain a matrix S with the dimension of N M N; m, N, V is three-dimensional.
S2, extracting a space-time matrix of each space point from the matrix S
Figure 813449DEST_PATH_IMAGE002
Wherein
Figure 478916DEST_PATH_IMAGE003
(ii) a The extraction method comprises extracting characteristic value of point i in t days and characteristic value of D-1 space points in neighborhood thereof as the characteristic value of the point
Figure 233246DEST_PATH_IMAGE004
Figure 219525DEST_PATH_IMAGE005
Dimension of
Figure 415014DEST_PATH_IMAGE006
(ii) a Then will be
Figure 939799DEST_PATH_IMAGE007
Performing matrix transformation to obtain a space-time grid with i point and dimension of t x D
Figure 102796DEST_PATH_IMAGE008
To obtain a space-time grid of all time instants
Figure 377919DEST_PATH_IMAGE009
。
S3, mixing
Figure 850751DEST_PATH_IMAGE009
Performing feature aggregation to obtain a time feature matrix
Figure 372868DEST_PATH_IMAGE011
，
Figure 570631DEST_PATH_IMAGE011
With dimensions M x N x t x D, M x N representing the presence of M x N spatial points, and for each spatial point there is a two-dimensional time signature matrix with dimensions t x D, wherein each row represents the time signature of the sea surface temperature, i.e. each spatial point
Figure 337861DEST_PATH_IMAGE012
The time characteristic of the time instant has the dimension of 1*D.
S4, mixing
Figure 429314DEST_PATH_IMAGE011
The last two dimensions are transposed to obtain a space characteristic matrix
Figure 200961DEST_PATH_IMAGE013
，
Figure 823703DEST_PATH_IMAGE013
M x N x D x t, M x N representing the presence of M x N spatial points, and for each spatial point there is a two-dimensional spatial feature matrix of dimension D x t, wherein each row represents a spatial feature of the sea surface temperature, i.e. a spatial feature at each spatial point, of dimension 1*t.
S5, mixing
Figure 191362DEST_PATH_IMAGE011
And
Figure 215950DEST_PATH_IMAGE013
and converting the two-dimensional time characteristic matrix and the two-dimensional space characteristic matrix into M-N points, namely taking each space point as an independent sample, and taking the two-dimensional time characteristic matrix and the two-dimensional space characteristic matrix as the characteristic input of the sample. The invention designs two full-connection layers, and the dimensions of the time characteristic matrix and the space characteristic matrix of the M × N sample points are t × f and D × f respectively.
And S6, interactively fusing the time features and the spatial features obtained in the step S5 through four transform-based attention coding blocks.
Wherein, the attention coding block based on the transformer is respectively based on a time self-attention module and a space self-attention moduleAn intention module, a time guidance space attention module and a space guidance time attention module, and finally four feature matrixes M of t x l, D x l, t x l and D x l of the M x N sample points are obtained respectively 1 、M 2 、M 3 、M 4 。
As shown in connection with FIG. 2, the time-based self-attention module accepts only the time feature matrix
Figure 751973DEST_PATH_IMAGE011
And sets the weight
Figure 675061DEST_PATH_IMAGE015
，
Figure 33361DEST_PATH_IMAGE016
，
Figure 99406DEST_PATH_IMAGE017
Respectively with
Figure 212856DEST_PATH_IMAGE011
Obtained by multiplying
Figure 560923DEST_PATH_IMAGE018
，
Figure 519651DEST_PATH_IMAGE019
，
Figure 768099DEST_PATH_IMAGE020
：
Figure 147390DEST_PATH_IMAGE021
Then calculating a relation weight matrix between the time characteristics
Figure 28758DEST_PATH_IMAGE022
：
Figure 978129DEST_PATH_IMAGE023
Finally utilize
Figure 520231DEST_PATH_IMAGE024
The weight of the relation between the intermediate features, calculating M 1 Assigning attention to different features:
Figure 975483DEST_PATH_IMAGE025
the resulting matrix M 1 Is a feature matrix of mutual guidance of temporal features.
The spatial self-attention module, shown in connection with FIG. 3, accepts only the spatial feature matrix
Figure 281830DEST_PATH_IMAGE026
And set the weight
Figure 831629DEST_PATH_IMAGE027
，
Figure 805402DEST_PATH_IMAGE028
，
Figure 792074DEST_PATH_IMAGE029
Respectively with
Figure 834986DEST_PATH_IMAGE030
Obtained by multiplying
Figure 939208DEST_PATH_IMAGE031
，
Figure 190323DEST_PATH_IMAGE032
，
Figure 908749DEST_PATH_IMAGE033
：
Figure 252006DEST_PATH_IMAGE034
Then calculating the relation weight between the spatial featuresWeight matrix
Figure 582755DEST_PATH_IMAGE035
：
Figure 452491DEST_PATH_IMAGE036
Finally utilize
Figure 420447DEST_PATH_IMAGE037
The weight of the relation between the intermediate features, calculating M 2 Assigning attention to different features:
Figure 188683DEST_PATH_IMAGE038
the resulting matrix M 2 Is a feature matrix of mutual guidance of spatial features.
As shown in FIG. 4, the time feature matrix is first accepted
Figure 385440DEST_PATH_IMAGE039
And set the weight
Figure 922732DEST_PATH_IMAGE040
And is and
Figure 655064DEST_PATH_IMAGE041
obtained by multiplying
Figure 723646DEST_PATH_IMAGE042
As a time guidance matrix:
Figure 911045DEST_PATH_IMAGE043
then inputting the spatial feature matrix
Figure 489793DEST_PATH_IMAGE044
And design the weights
Figure 245826DEST_PATH_IMAGE045
，
Figure 316550DEST_PATH_IMAGE046
Respectively with
Figure 104378DEST_PATH_IMAGE047
Obtained by multiplying
Figure 865529DEST_PATH_IMAGE048
，
Figure 706708DEST_PATH_IMAGE049
：
Figure 733570DEST_PATH_IMAGE050
Computing spatio-temporal relationship weight matrices
Figure 246460DEST_PATH_IMAGE051
：
Figure 301266DEST_PATH_IMAGE052
Finally utilize
Figure 890510DEST_PATH_IMAGE053
The weight of the relation between the intermediate features, calculating M 3 Namely, the attention degree of the time characteristic to the space characteristic is distributed:
Figure 670247DEST_PATH_IMAGE054
the resulting matrix M 3 Is a feature matrix of temporal feature guide spatial features.
As shown in connection with FIG. 5, the spatial guidance temporal attention module first accepts a spatial feature matrix
Figure 49145DEST_PATH_IMAGE055
Andsetting weights
Figure 535621DEST_PATH_IMAGE056
And is and
Figure 718603DEST_PATH_IMAGE057
obtained by multiplying
Figure 907008DEST_PATH_IMAGE058
As a spatial guide matrix:
Figure 840329DEST_PATH_IMAGE059
then inputting the time characteristic matrix
Figure 604148DEST_PATH_IMAGE060
And design the weights
Figure 518883DEST_PATH_IMAGE061
，
Figure 273212DEST_PATH_IMAGE062
Respectively with
Figure 744645DEST_PATH_IMAGE063
Obtained by multiplying
Figure 690866DEST_PATH_IMAGE064
，
Figure 979765DEST_PATH_IMAGE065
：
Figure 893495DEST_PATH_IMAGE066
Computing spatio-temporal relationship weight matrices
Figure 653771DEST_PATH_IMAGE067
：
Figure 969346DEST_PATH_IMAGE068
Finally utilize
Figure 897988DEST_PATH_IMAGE069
The weight of the relation between the intermediate features, calculating M 4 Namely, the attention of the distributed space characteristic to the time characteristic:
Figure 112063DEST_PATH_IMAGE070
the resulting matrix M 4 Is a feature matrix of spatial feature guide temporal features.
S7, combining the four feature matrixes M 1 、M 2 、M 3 、M 4 And (5) carrying out polymerization to obtain a polymerization space-time matrix M with dimension of t x D.
An aggregate spatio-temporal matrix M is obtained according to the following equation,
Figure 862981DEST_PATH_IMAGE071
wherein the content of the first and second substances,
Figure 360959DEST_PATH_IMAGE072
combining the time characteristics after the time information self-fusion with the space characteristics after the time-space information fusion to obtain a multi-view space-time characteristic matrix;
Figure 991660DEST_PATH_IMAGE073
combining the spatial features after spatial information self-fusion with the temporal features after spatial-temporal information fusion to obtain a spatial-temporal feature matrix with multiple visual angles; and T represents the transposition of the matrix, and finally cross multiplication operation is carried out to obtain a final space-time fusion characteristic matrix.
S8, subjecting the polymerization space-time matrix M of t x D to LSTM operation to obtain the prediction result of the last M x N points
Figure 365135DEST_PATH_IMAGE074
(ii) a The loss calculation is performed by the true data values y of M × N spatial points, as shown in equation (4). And (3) each time all the samples in one batch (the batch size is defined as m) are predicted and Loss is calculated, obtaining a final Loss value Loss through a formula (5), and carrying out back propagation operation to update the model parameters.
Figure 982061DEST_PATH_IMAGE078
Example 2
The embodiment provides a sea surface temperature prediction system based on spatio-temporal information interaction fusion, which is used for realizing the sea surface temperature prediction method based on spatio-temporal information interaction fusion as described in embodiment 1.
The input module is used for inputting sea surface temperature data and acquiring N sea surface temperature data matrixes with time dimensions of M x N x V
Figure 255916DEST_PATH_IMAGE001
And carrying out matrix averaging operation on the V dimension and aggregating the matrices to obtain a matrix S with the dimension of N M N.
The space-time matrix construction module is used for constructing a space-time matrix and extracting the space-time matrix of each space point from the matrix S
Figure 558984DEST_PATH_IMAGE002
Then will be
Figure 465760DEST_PATH_IMAGE002
Performing matrix transformation to obtain a space-time grid with i point and dimension of t x D
Figure 807749DEST_PATH_IMAGE008
To obtain a space-time grid of all time instants
Figure 640838DEST_PATH_IMAGE009
。
The space-time feature interactive fusion module is used for carrying out space-time feature interactive fusion and comprises four attention coding blocks based on a transformer, namely a time self-attention module, a time guidance space attention module, a space guidance time attention module and a space self-attention module,
firstly, the first step is to
Figure 426391DEST_PATH_IMAGE009
Performing feature aggregation to obtain a time feature matrix
Figure 351622DEST_PATH_IMAGE011
Then will be
Figure 559618DEST_PATH_IMAGE011
The last two dimensions are transposed to obtain a space characteristic matrix
Figure 293219DEST_PATH_IMAGE013
(ii) a Will be provided with
Figure 938089DEST_PATH_IMAGE011
And
Figure 271987DEST_PATH_IMAGE013
converting the two-dimensional time characteristic matrix and the two-dimensional space characteristic matrix into M x N points, and finally obtaining four characteristic matrixes M of M x N sample points through four transform-based attention coding block processing 1 、M 2 、M 3 、M 4 ；
The space-time matrix aggregation module is used for aggregating four feature matrixes M 1 、M 2 、M 3 、M 4 And polymerizing to obtain a polymerization space-time matrix M.
The sea surface temperature data prediction module is used for carrying out LSTM operation on the polymerization space-time matrix M to obtain the prediction result of the last M points by N points
Figure 34407DEST_PATH_IMAGE014
。
And the output module is used for outputting the prediction result.
The data processing process of each module can refer to the record in embodiment 1, and is not described herein again.
Example 3
The embodiment provides an application of a sea surface temperature prediction system based on space-time information interactive fusion, which is used for predicting sea surface temperature, inputting sea surface temperature data in a period of historical time A days, and outputting a sea surface temperature prediction result in a period of future time B days.
A specific method of predicting the sea surface temperature is described below by way of example.
Step one, establishing a training data set:
(1) Sea surface temperature data of 42 years from 1981 to 2022 and the like in the world are acquired, sea surface temperature data of a prediction region are extracted from two dimensions of time and space, and sea surface temperature data sets on different space-time dimensions in the region are constructed.
(2) The constructed sea surface temperature space-time data set is divided into a training sample, a verification sample and a test sample according to the proportion of 70%, 20% and 10%, and the data are processed according to a method for predicting B days every A days.
Step two, establishing a sea surface temperature prediction model:
(1) And constructing a deep learning framework by adopting a Pythroch.
(2) A Transformer mechanism-based spatio-temporal information interactive fusion prediction model is constructed, and comprises a spatio-temporal matrix construction module, a spatio-temporal feature interactive fusion module (four Transformer-based attention coding blocks), a spatio-temporal matrix aggregation module and a sea surface temperature data prediction module. The model inputs the sea surface temperature data of the previous A days and outputs the sea surface temperature prediction data of the future B days.
(3) Inputting the training sample obtained in the first step into a model for training, detecting the model prediction effect after each training by using a verification sample, and evaluating the model by using a test sample after the model is trained for 100 times.
Step three, model application:
(1) And setting a B-day parameter to be predicted, and inputting the sea surface temperature data of the previous A-day into the trained model to obtain a final B-day sea surface temperature prediction result.
In summary, the invention (1) constructs a spatio-temporal matrix of each point in the space in a spatio-temporal matrix construction module, and extracts feature expressions of a temporal view and a spatial view from the spatio-temporal matrix. (2) The time-space feature interactive fusion module utilizes a self-attention mechanism and a mutual attention mechanism in a transformer to construct a time self-attention coding block which fully excavates the mutual guidance relationship of time features at different moments, a space self-attention coding block which excavates the mutual guidance relationship of space features in different spaces, and a time guidance space interactive attention coding block and a space guidance time interactive attention coding block which fully excavate the mutual guidance relationship of the time features and the space features, and the time-space data ultra-long term dependency relationship is constructed through the four coding blocks, so that the interactive fusion of the time-space information of the sea surface temperature data is realized.
In addition, it should be noted that, in practical application, the method and system of the present invention can also be applied to the space-time variation of other marine scientific data (e.g., time-space data fields such as chlorophyll concentration, wind speed, wind direction, etc.) to obtain the space-time distribution prediction, and reflect the dynamic evolution law of the physical and chemical properties of the marine field. For example, the method and the system of the invention are applied to process, obtain the prediction of the concentration of the offshore chlorophyll a, input the offshore chlorophyll a data in a period of historical time period A (the offshore chlorophyll a data with N time dimensions M N V is obtained through the original chlorophyll a remote sensing data, the meteorological remote sensing data and the buoy chlorophyll a monitoring data), and output the chlorophyll a prediction result in a period of time period B in the future (a whole offshore area chlorophyll a prediction graph which is continuous in a long time sequence).
It is understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art should understand that they can make various changes, modifications, additions and substitutions within the spirit and scope of the present invention.

Claims (9)

1. The sea surface temperature prediction method based on the time-space information interactive fusion is characterized by comprising the following steps of:
s1, taking t time dimensions as M N V sea surface temperature data matrix
Figure 805462DEST_PATH_IMAGE001
Performing matrix averaging operation on the V dimension and aggregating the matrices to obtain a matrix S with the dimension of t M N; m, N, V is three dimensions;
s2, extracting a space-time matrix of each space point from the matrix S
Figure 925865DEST_PATH_IMAGE002
Wherein
Figure 158132DEST_PATH_IMAGE003
(ii) a The extraction method comprises extracting characteristic value of point i in t days and characteristic value of D-1 space points in neighborhood thereof as the characteristic value of the point
Figure 38494DEST_PATH_IMAGE004
Figure 321708DEST_PATH_IMAGE005
Dimension of
Figure 973532DEST_PATH_IMAGE006
(ii) a Then will be
Figure 693095DEST_PATH_IMAGE007
Performing matrix transformation to obtain a space-time grid with i point and dimension of t x D
Figure 95257DEST_PATH_IMAGE008
To obtain a space-time grid of all time instants
Figure 741568DEST_PATH_IMAGE009
；
S3, mixing
Figure 62828DEST_PATH_IMAGE010
Performing feature aggregation to obtain a time feature matrix
Figure 817158DEST_PATH_IMAGE011
，
Figure 757432DEST_PATH_IMAGE011
Of (D) represents the presence of M N spatial points, and for each spatial point there is a two-dimensional time signature matrix of dimension t D, in which each row represents the time signature of the sea surface temperature, i.e. each spatial point
Figure 234812DEST_PATH_IMAGE012
The time characteristic of the moment has the dimension of 1*D;
s4, mixing
Figure 258131DEST_PATH_IMAGE011
The last two dimensions are transposed to obtain a space characteristic matrix
Figure 703019DEST_PATH_IMAGE013
，
Figure 932137DEST_PATH_IMAGE013
M × N × D × t, where M × N represents the presence of M × N spatial points, and for each spatial point there is a two-dimensional spatial feature matrix with a dimension D × t, where each row represents a spatial feature of the sea surface temperature, i.e., a spatial feature at each spatial point, with a dimension of 1*t;
s5, mixing
Figure 778871DEST_PATH_IMAGE011
And
Figure 441933DEST_PATH_IMAGE013
converting the time characteristic into a two-dimensional time characteristic matrix and a two-dimensional space characteristic matrix of M points by N points to obtain time characteristicsThe dimensions of the matrix and the spatial feature matrix are t x f and D x f respectively;
s6, interactively fusing the time characteristics and the spatial characteristics obtained in the step S5 through four transform-based attention coding blocks, wherein the transform-based attention coding blocks are respectively based on a time self-attention module, a space self-attention module, a time guidance space attention module and a space guidance time attention module, and a time characteristic matrix is input
Figure 124850DEST_PATH_IMAGE011
And a spatial feature matrix
Figure 406926DEST_PATH_IMAGE013
Finally, four feature matrixes M of t x l, D x l, t x l and D x l of the M x N sample points are obtained respectively 1 、M 2 、M 3 、M 4 ；
S7, combining the four feature matrixes M 1 、M 2 、M 3 、M 4 Carrying out polymerization to obtain a polymerization space-time matrix M with dimension t x D;
s8, subjecting the aggregation space-time matrix M to LSTM operation to obtain the prediction result of the last M-N points
Figure 904904DEST_PATH_IMAGE014
(ii) a And performing loss calculation through the real data values y of the M x N space points, and performing back propagation operation to update the model parameters.
2. The method for sea table temperature prediction based on spatio-temporal information interaction fusion of claim 1, wherein in step S6, the time-based self-attention module only accepts the time feature matrix
Figure 129081DEST_PATH_IMAGE011
And set the weight
Figure 174659DEST_PATH_IMAGE015
，
Figure 260427DEST_PATH_IMAGE016
，
Figure 65441DEST_PATH_IMAGE017
Respectively with
Figure 837350DEST_PATH_IMAGE011
Obtained by multiplying
Figure 478547DEST_PATH_IMAGE018
，
Figure 351694DEST_PATH_IMAGE019
，
Figure 856887DEST_PATH_IMAGE020
：
Figure 422866DEST_PATH_IMAGE021
Then calculating a relation weight matrix between the time characteristics
Figure 816938DEST_PATH_IMAGE022
Figure 870607DEST_PATH_IMAGE023
Figure 384634DEST_PATH_IMAGE024
Finally utilize
Figure 872247DEST_PATH_IMAGE025
The weight of the relation between the intermediate features, calculating M 1 Assigning attention to different features:
Figure 238769DEST_PATH_IMAGE026
the resulting matrix M 1 Is a feature matrix of mutual guidance of temporal features.
3. The method for sea table temperature prediction based on spatio-temporal information interaction fusion of claim 1, wherein in step S6, the spatial self-attention module only accepts spatial feature matrix
Figure 594664DEST_PATH_IMAGE027
And set the weight
Figure 979509DEST_PATH_IMAGE028
，
Figure 169182DEST_PATH_IMAGE029
，
Figure 22999DEST_PATH_IMAGE030
Respectively with
Figure 182585DEST_PATH_IMAGE031
Obtained by multiplying
Figure 687516DEST_PATH_IMAGE032
，
Figure 2085DEST_PATH_IMAGE033
，
Figure 592466DEST_PATH_IMAGE034
：
Figure 290164DEST_PATH_IMAGE035
Then calculating a relation weight matrix between the spatial features
Figure 790546DEST_PATH_IMAGE036
Figure 494639DEST_PATH_IMAGE037
Finally utilize
Figure 120662DEST_PATH_IMAGE038
The weight of the relation between the intermediate features, calculating M 2 Assigning attention to different features:
Figure 960704DEST_PATH_IMAGE039
the resulting matrix M 2 Is a feature matrix of mutual guidance of spatial features.
4. The method for sea surface temperature prediction based on spatio-temporal information interaction fusion of claim 1, wherein in step S6, the time-directed spatial attention module first receives the time feature matrix
Figure 131922DEST_PATH_IMAGE040
And set the weight
Figure 680584DEST_PATH_IMAGE041
And is and
Figure 595451DEST_PATH_IMAGE042
obtained by multiplying
Figure 460638DEST_PATH_IMAGE043
As a time guidance matrix:
Figure 428857DEST_PATH_IMAGE044
then inputting the spatial feature matrix
Figure 464815DEST_PATH_IMAGE045
And design the weights
Figure 183372DEST_PATH_IMAGE046
，
Figure 998007DEST_PATH_IMAGE047
Respectively with
Figure 760295DEST_PATH_IMAGE048
Obtained by multiplying
Figure 34282DEST_PATH_IMAGE049
，
Figure 18245DEST_PATH_IMAGE050
：
Figure 185922DEST_PATH_IMAGE051
Computing spatio-temporal relationship weight matrices
Figure 417314DEST_PATH_IMAGE052
Figure 913017DEST_PATH_IMAGE053
Figure 724110DEST_PATH_IMAGE054
Finally utilize
Figure 621659DEST_PATH_IMAGE055
The weight of the relation between the intermediate features, calculating M 3 Namely, the attention degree of the time characteristic to the space characteristic is distributed:
Figure 601116DEST_PATH_IMAGE056
the resulting matrix M 3 Is a feature matrix of temporal feature guide spatial features.
5. The method for sea table temperature prediction based on spatio-temporal information interaction fusion of claim 1, wherein in step S6, the spatial guidance time attention module firstly receives a spatial feature matrix
Figure 600427DEST_PATH_IMAGE057
And set the weight
Figure 198899DEST_PATH_IMAGE058
And is and
Figure 200221DEST_PATH_IMAGE059
obtained by multiplying
Figure 383203DEST_PATH_IMAGE060
As a spatial guide matrix:
Figure 853499DEST_PATH_IMAGE061
then inputting the time characteristic matrix
Figure 504929DEST_PATH_IMAGE062
And design the weights
Figure 737590DEST_PATH_IMAGE063
，
Figure 199795DEST_PATH_IMAGE064
Respectively with
Figure 406654DEST_PATH_IMAGE065
Obtained by multiplying
Figure 346928DEST_PATH_IMAGE066
，
Figure 699675DEST_PATH_IMAGE067
：
Figure 582049DEST_PATH_IMAGE068
Computing spatio-temporal relationship weight matrices
Figure 26937DEST_PATH_IMAGE069
：
Figure 567639DEST_PATH_IMAGE070
Finally utilize
Figure 40471DEST_PATH_IMAGE071
The weight of the relation between the intermediate features, calculating M 4 Namely, the attention of the distributed space characteristic to the time characteristic:
Figure 828168DEST_PATH_IMAGE072
the resulting matrix M 4 Is a feature matrix of spatial feature guide temporal features.
6. The sea table temperature prediction method based on spatio-temporal information interaction fusion of claim 1, characterized in that step S7 obtains an aggregation spatio-temporal matrix M according to the following formula,
Figure 760351DEST_PATH_IMAGE073
wherein the content of the first and second substances,
Figure 793161DEST_PATH_IMAGE074
combining the time characteristics after the time information self-fusion with the space characteristics after the time-space information fusion to obtain a multi-view space-time characteristic matrix;
Figure 619034DEST_PATH_IMAGE075
combining the spatial features of the spatial information after self-fusion with the temporal features of the spatial information after fusion to obtain a spatial-temporal feature matrix with multiple visual angles; and T represents the transposition of the matrix, and finally cross multiplication operation is carried out to obtain a final space-time fusion characteristic matrix.
7. The method for sea table temperature prediction based on spatio-temporal information interaction fusion of claim 1, wherein in step S8, the prediction results of M x N points are obtained
Figure 328364DEST_PATH_IMAGE076
And the real data values y of the M x N spatial points are subjected to a loss calculation, as shown in equation (4):
Figure 544582DEST_PATH_IMAGE077
and (3) each time all samples in one batch are predicted and Loss is calculated, obtaining a final Loss value Loss through a formula (5), and performing back propagation operation to update model parameters:
Figure 381082DEST_PATH_IMAGE078
wherein m is the batch size.
8. The sea surface temperature prediction system based on the time-space information interactive fusion is characterized by comprising an input module, a time-space matrix construction module, a time-space characteristic interactive fusion module, a time-space matrix aggregation module, a sea surface temperature data prediction module and an output module,
the input module is used for inputting sea surface temperature data and acquiring N sea surface temperature data matrixes with time dimensions of M x N x V
Figure 630109DEST_PATH_IMAGE001
Performing matrix averaging operation on the V dimension and aggregating the matrices to obtain a matrix S with the dimension of N × M × N;
the space-time matrix construction module is used for constructing a space-time matrix and extracting the space-time matrix of each space point from the matrix S
Figure 395940DEST_PATH_IMAGE080
Then will be
Figure 770551DEST_PATH_IMAGE080
Performing matrix transformation to obtain a space-time grid with i point and dimension of t x D
Figure 446383DEST_PATH_IMAGE008
To obtain a space-time grid of all time instants
Figure 746784DEST_PATH_IMAGE009
；
The space-time feature interactive fusion module is used for carrying out space-time feature interactive fusion and comprises four attention coding blocks based on a transformer, namely a time self-attention module, a time guidance space attention module, a space guidance time attention module and a space self-attention module,
firstly, the first step is to
Figure 766954DEST_PATH_IMAGE009
Carrying out characteristic polymerization to obtain time characteristicsSign matrix
Figure 194525DEST_PATH_IMAGE011
Then will be
Figure 521601DEST_PATH_IMAGE011
The last two dimensions are transposed to obtain a space characteristic matrix
Figure 258482DEST_PATH_IMAGE013
(ii) a Will be provided with
Figure 500369DEST_PATH_IMAGE011
And
Figure 466051DEST_PATH_IMAGE013
converting the two-dimensional time characteristic matrix and the two-dimensional space characteristic matrix into M x N points, and finally obtaining four characteristic matrixes M of M x N sample points through four transform-based attention coding block processing 1 、M 2 、M 3 、M 4 ；
The space-time matrix aggregation module is used for aggregating four feature matrixes M 1 、M 2 、M 3 、M 4 Polymerizing to obtain a polymerization space-time matrix M;
the sea surface temperature data prediction module is used for carrying out LSTM operation on the polymerization space-time matrix M to obtain the prediction result of the last M points by N points
Figure 100164DEST_PATH_IMAGE081
；
And the output module is used for outputting the prediction result.
9. The application of the sea surface temperature prediction system based on spatio-temporal information interaction fusion as defined in claim 8, which is used for predicting sea surface temperature, inputting sea surface temperature data in a historical time period of A days, and outputting sea surface temperature prediction results in a future time period of B days.
CN202211194484.9A 2022-09-29 2022-09-29 Sea surface temperature prediction method, system and application based on time-space information interaction fusion Active CN115307780B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211194484.9A CN115307780B (en) 2022-09-29 2022-09-29 Sea surface temperature prediction method, system and application based on time-space information interaction fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211194484.9A CN115307780B (en) 2022-09-29 2022-09-29 Sea surface temperature prediction method, system and application based on time-space information interaction fusion

Publications (2)

Publication Number Publication Date
CN115307780A true CN115307780A (en) 2022-11-08
CN115307780B CN115307780B (en) 2023-01-06

Family

ID=83866567

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211194484.9A Active CN115307780B (en) 2022-09-29 2022-09-29 Sea surface temperature prediction method, system and application based on time-space information interaction fusion

Country Status (1)

Country Link
CN (1) CN115307780B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115984281A (en) * 2023-03-21 2023-04-18 中国海洋大学 Multi-task completion method of time sequence sea temperature image based on local specificity deepening
CN116246213A (en) * 2023-05-08 2023-06-09 腾讯科技（深圳）有限公司 Data processing method, device, equipment and medium
CN116822382A (en) * 2023-08-30 2023-09-29 中国海洋大学 Sea surface temperature prediction method and network based on space-time multiple characteristic diagram convolution

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019216449A1 (en) * 2018-05-09 2019-11-14 주식회사 알고리고 Method and apparatus for time series artificial neural network electric vehicle power demand prediction, using spatio-temporal fusion of power demand data and heterogeneous data
US20210201010A1 (en) * 2019-12-31 2021-07-01 Wuhan University Pedestrian re-identification method based on spatio-temporal joint model of residual attention mechanism and device thereof
US20210232588A1 (en) * 2020-01-23 2021-07-29 Beijing Baidu Netcom Science And Technology Co., Ltd. Parking lot free parking space predicting method, apparatus, electronic device and storage medium
CN113326981A (en) * 2021-05-26 2021-08-31 北京交通大学 Atmospheric environment pollutant prediction model based on dynamic space-time attention mechanism
US20210342722A1 (en) * 2020-12-23 2021-11-04 Beijing Baidu Netcom Science And Technology Co., Ltd. Air quality prediction model training method, air quality prediction method, electronic device and storage medium
CN113705880A (en) * 2021-08-25 2021-11-26 杭州远眺科技有限公司 Traffic speed prediction method and device based on space-time attention diagram convolutional network
US11222217B1 (en) * 2020-08-14 2022-01-11 Tsinghua University Detection method using fusion network based on attention mechanism, and terminal device
CN114399073A (en) * 2021-11-26 2022-04-26 中国石油大学(华东) Ocean surface temperature field prediction method based on deep learning
CN114492992A (en) * 2022-01-25 2022-05-13 重庆邮电大学 Self-adaptive space-time graph neural network traffic flow prediction method and system based on Transformer
CN114936691A (en) * 2022-05-06 2022-08-23 河北工业大学 Temperature forecasting method integrating relevance weighting and space-time attention

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019216449A1 (en) * 2018-05-09 2019-11-14 주식회사 알고리고 Method and apparatus for time series artificial neural network electric vehicle power demand prediction, using spatio-temporal fusion of power demand data and heterogeneous data
US20210201010A1 (en) * 2019-12-31 2021-07-01 Wuhan University Pedestrian re-identification method based on spatio-temporal joint model of residual attention mechanism and device thereof
US20210232588A1 (en) * 2020-01-23 2021-07-29 Beijing Baidu Netcom Science And Technology Co., Ltd. Parking lot free parking space predicting method, apparatus, electronic device and storage medium
US11222217B1 (en) * 2020-08-14 2022-01-11 Tsinghua University Detection method using fusion network based on attention mechanism, and terminal device
US20210342722A1 (en) * 2020-12-23 2021-11-04 Beijing Baidu Netcom Science And Technology Co., Ltd. Air quality prediction model training method, air quality prediction method, electronic device and storage medium
CN113326981A (en) * 2021-05-26 2021-08-31 北京交通大学 Atmospheric environment pollutant prediction model based on dynamic space-time attention mechanism
CN113705880A (en) * 2021-08-25 2021-11-26 杭州远眺科技有限公司 Traffic speed prediction method and device based on space-time attention diagram convolutional network
CN114399073A (en) * 2021-11-26 2022-04-26 中国石油大学(华东) Ocean surface temperature field prediction method based on deep learning
CN114492992A (en) * 2022-01-25 2022-05-13 重庆邮电大学 Self-adaptive space-time graph neural network traffic flow prediction method and system based on Transformer
CN114936691A (en) * 2022-05-06 2022-08-23 河北工业大学 Temperature forecasting method integrating relevance weighting and space-time attention

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
JITAOCAI 等: "Prediction of gas leakage and dispersion in utility tunnels based on CFD-EnKF coupling model: A 3D full-scale application", 《SUSTAINABLE CITIES AND SOCIETY VOLUME 80, MAY 2022, 103789》 *
XING GUO等: "Prediction of Sea Surface Temperature by Combining Interdimensional and Self-Attention with Neural Networks", 《REMOTE SENSING》 *
ZIKUN CHEN等: "Study of LSTM Model in Sea Surface Temperature Prediction of the Yellow Sea Cold Water Mass Area", 《2019 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTING, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI)》 *
张守文 等: "基于CESM预测系统对全球关键海区海温主要模态后报能力评估", 《海洋学报》 *
王成贺 等: "基于时空演变多重特性建模的近海叶绿素浓度时序预测", 《信号处理》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115984281A (en) * 2023-03-21 2023-04-18 中国海洋大学 Multi-task completion method of time sequence sea temperature image based on local specificity deepening
CN116246213A (en) * 2023-05-08 2023-06-09 腾讯科技（深圳）有限公司 Data processing method, device, equipment and medium
CN116246213B (en) * 2023-05-08 2023-07-28 腾讯科技（深圳）有限公司 Data processing method, device, equipment and medium
CN116822382A (en) * 2023-08-30 2023-09-29 中国海洋大学 Sea surface temperature prediction method and network based on space-time multiple characteristic diagram convolution
CN116822382B (en) * 2023-08-30 2023-11-21 中国海洋大学 Sea surface temperature prediction method and network based on space-time multiple characteristic diagram convolution

Also Published As

Publication number Publication date
CN115307780B (en) 2023-01-06

Similar Documents

Publication Publication Date Title
CN115307780B (en) Sea surface temperature prediction method, system and application based on time-space information interaction fusion
Shiri et al. Estimation of daily suspended sediment load by using wavelet conjunction models
CN111784041B (en) Wind power prediction method and system based on graph convolution neural network
CN109635763B (en) Crowd density estimation method
CN110119854A (en) Voltage-stablizer water level prediction method based on cost-sensitive LSTM Recognition with Recurrent Neural Network
Hou et al. D2CL: A dense dilated convolutional LSTM model for sea surface temperature prediction
CN113627093B (en) Underwater mechanism trans-scale flow field characteristic prediction method based on improved Unet network
CN111242351A (en) Tropical cyclone track prediction method based on self-encoder and GRU neural network
CN115222163A (en) Multi-factor medium-long term real-time forecasting method and system for harbor basin inlet waves and application
Kambekar et al. Wave prediction using genetic programming and model trees
Shao et al. Ocean reanalysis data‐driven deep learning forecast for sea surface multivariate in the South China Sea
Manepalli et al. Emulating numeric hydroclimate models with physics-informed cGANs
Bento et al. Ocean wave power forecasting using convolutional neural networks
CN116050595A (en) Attention mechanism and decomposition mechanism coupled runoff amount prediction method
CN112949944B (en) Intelligent groundwater level prediction method and system based on space-time characteristics
CN115604131B (en) Link flow prediction method, system, electronic device and medium
CN110648030A (en) Method and device for predicting seawater temperature
CN114169646B (en) Water bloom prediction method, device, electronic equipment and computer readable storage medium
Bosma et al. Estimating solar and wind power production using computer vision deep learning techniques on weather maps
CN111626472B (en) Scene trend judgment index computing system and method based on depth hybrid cloud model
CN112508170A (en) Multi-correlation time sequence prediction system and method based on generation countermeasure network
CN111444614B (en) Flow field reconstruction method based on graph convolution
CN114202091A (en) Indian ocean dipole index prediction method
CN114661874A (en) Visual question-answering method based on multi-angle semantic understanding and self-adaptive dual channels
El‐Shazly et al. Improved appearance loss for deep estimation of image depth

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant