CN-116245018-B - Sea wave missing measurement data forecasting method based on bivariate long-short-term memory algorithm

CN116245018BCN 116245018 BCN116245018 BCN 116245018BCN-116245018-B

Abstract

The invention discloses a sea wave missing measurement data forecasting method based on a double-variable long-short-term memory algorithm, which comprises the specific steps of firstly obtaining buoy data A, interpolating continuously lost buoy data by a machine learning method, interpolating single lost buoy data by a regression model method to form a new buoy data set B, and finding out and forecasting variable in the buoy data set B by utilizing a sea wave variable association database And inputting the training set data of each bivariate into a long-short-time memory algorithm for training to obtain a corresponding bivariate LSTM model, and finally, checking the model result by using the verification set data and determining an optimal prediction model. The method can interpolate and correct short-term missing data of the buoy, can predict long-term missing variables, and effectively improves accuracy of buoy data.

Inventors

WANG JIN
XIE WENHONG
DONG CHANGMING
LI CHUNHUI
JI JINLIN

Assignees

南京信息工程大学

Dates

Publication Date: 20260508
Application Date: 20230112

Claims (7)

1. A sea wave missing measurement data forecasting method based on a bivariate long-short-term memory algorithm is characterized by comprising the following steps: Acquiring a buoy data set A; interpolating single lost buoy data by using a regression model method, and interpolating continuously lost buoy data by using a machine learning method, so as to form a new buoy data set B; using sea wave variable associated database to find and forecast variable in buoy data set B The matched variables form a bivariate set V, and a training set and a verification set of each bivariate in the bivariate set V are determined at the same time; Substituting the training set of each bivariate into a long short-time memory algorithm to train so as to obtain a corresponding bivariate LSTM model; Inputting the verification set of each variable into a corresponding bivariate LSTM model to conduct missing variable prediction, comparing and analyzing each prediction result with corresponding verification set data, evaluating the prediction performance of each bivariate LSTM model to obtain a prediction result, and determining an optimal prediction model according to preset conditions and the prediction result; the determining process of the training set of each bivariate is as follows: Querying sea wave variable association database for forecast variable Associated variable sets ; The variables in the buoy data set B are collected Matching the variables in the set to construct a set In (3) forecast variable And aggregate with Each element in the two-variable combination is combined to form a double-variable set Wherein is aggregated Representing buoy data set B and variable set A set of the matched variables in the set, Represented as the I-th and forecast variables in buoy dataset B The variable(s) associated with the variable(s), Represented as the I-th bivariate; front of buoy data set corresponding to bivariate As a bivariate training set; The determining process of the verification set of each bivariate is as follows: Querying sea wave variable association database for forecast variable Associated variable sets ; The variables in the buoy data set B are collected Matching the variables in the set to construct a set In (3) forecast variable And aggregate with Each element in the two-variable combination is combined to form a double-variable set Wherein is aggregated Representing buoy data set B and variable set A set of the matched variables in the set, Represented as the I-th and forecast variables in buoy dataset B The variable(s) associated with the variable(s), Represented as the I-th bivariate; Post-processing of corresponding buoy data sets in bivariate As a bivariate verification set, and concentrating the bivariate verification set And The corresponding buoy data are respectively put into Verification set A verification set, wherein, Representing buoy dataset B find and forecast variables Number of variables with high correlation.
2. The ocean wave missing measurement data forecasting method based on the bivariate long-short-term memory algorithm of claim 1, wherein the regression model is: ; Wherein, the For the single interpolated buoy data at time t, Represented as And (3) with A hidden function between the two, Representing time; represented as The float data of the moment in time, Represented as The float data of the moment in time, Is an error term.
3. The ocean wave missing measurement data forecasting method based on the bivariate long-short-term memory algorithm of claim 1, wherein the interpolation process of the continuously lost buoy data is as follows: To be used for As input, with continuously missing buoy data For target labels, in artificial masks In-region calculation of losses and use of a hybrid loss function Supervising the network training, after the training is completed, the method Carry-in In the method, interpolation of continuously missing buoy data is realized; Wherein, the Representing buoy data containing two consecutive missing blocks, Represented as an artificial mask, In order for the focal point frequency to be lost, Denoted as the loss of the L1 norm, In order to mask the operator(s), In order to continuously miss the interpolation result of the buoy data, In order to train the network, In order to continuously miss the buoy data, In order to optimize the parameters of the device, Is a complete buoy data set.
4. The ocean wave missing measurement data forecasting method based on the bivariate long-short-term memory algorithm of claim 1, wherein the training set of the bivariate is a matrix of n rows and 2 columns; The first column is denoted as Buoy data of (2), second column expressed as forecast variable Buoy data of (a) is provided.
5. The ocean wave missing measurement data forecasting method based on the bivariate long-short-term memory algorithm of claim 1, wherein the determining step of the optimal forecasting model comprises the following steps: Will each be Data in the verification set is input into a corresponding bivariate LSTM model to obtain a corresponding forecast variable Is a forecast result of (1); Respectively calculating correlation coefficient, root mean square error and average absolute percentage error of the forecast results obtained by each bivariate model, and putting the calculation results of the correlation numbers into a newly constructed set In which the root mean square error calculation result is put into a newly constructed set In the method, the average absolute percentage error calculation result is put into a newly constructed set In (a) and (b); respectively judging the set by using if function Maximum value and set of (a) Sum set To thereby determine the set Maximum value and set of (a) Sum set The bivariate LSTM model corresponding to the minimum value in the model, and the corresponding bivariate LSTM model is put into a newly constructed set In (a) and (b); Determining a set The bivariate LSTM model with highest occurrence number is used for judging the set by using if function Whether the bivariate LSTM model with highest occurrence number is unique; If set up The double-variable LSTM model with the highest occurrence frequency is unique, and the double-variable LSTM model is proved to be an optimal prediction model; If set up The bivariate LSTM model with highest occurrence number is not unique, and the bivariate LSTM model is assembled The bivariate LSTM model corresponding to the middle maximum value is considered as an optimal prediction model; Wherein, the collection Maximum value and set of (a) Sum set Minimum value of (2) not the only one.
6. A system for realizing the sea wave missing measurement data forecasting method based on the bivariate long-short-term memory algorithm as set forth in claim 1, which is characterized by comprising A data acquisition module for acquiring a buoy data set A, The data interpolation module is used for interpolating the continuously lost buoy data by a machine learning method, and interpolating the single lost buoy data by a regression model method so as to form a new buoy data set B; the related variable determining module is used for finding out and forecasting variables in the buoy data set B by utilizing the sea wave variable related database The matched variables form a bivariate set V, and a training set and a verification set of each bivariate are determined at the same time; the bivariate model building module is used for substituting each bivariate training set into a long-short-time memory algorithm to train, so as to build a corresponding bivariate LSTM model; And the optimal prediction model determining module is used for inputting the verification set of each variable into the corresponding bivariate LSTM model to perform missing variable prediction, comparing and analyzing each prediction result with the corresponding verification set data, and evaluating the prediction performance of each bivariate LSTM model to obtain an optimal prediction model.
7. The sea wave missing measurement data forecasting device based on the bivariate long-short-time memory algorithm is characterized by comprising a processor and a memory, wherein the memory stores a computer program, and the steps of the sea wave missing measurement data forecasting method based on the bivariate long-short-time memory algorithm are realized when the processor executes the computer program.

Description

Sea wave missing measurement data forecasting method based on bivariate long-short-term memory algorithm Technical Field The invention relates to the technical field of sea wave missing measurement data forecasting, in particular to a sea wave missing measurement data forecasting method based on a bivariate long-short-term memory algorithm. Background Ocean waves are one of the common ocean phenomena, and the energy source of ocean waves is mainly wind. The wind direction transmits energy to the sea surface, so that the sea water moves in a fluctuant manner, and waves on the sea surface are formed. Besides wind, the formation of sea waves is influenced by other sea and atmospheric factors, the propagation process of the sea waves is very complex, and certain constraint relations among the sea wave elements are met. The sea wave has huge destructive power and has close relation to human life, so that the understanding of the distribution characteristics and the change rule is very important. The real and reliable sea surface data can be obtained through buoy, radar and other observation methods, and further the space-time distribution and the change process of sea waves are restored. In addition to observing sea waves, it is more important to forecast sea waves. The first developed wave numerical forecast is based on observation data and theoretical research, and the future wave state of the area is calculated and forecasted by combining the current wave state in the area. Wave numerical forecasting has become a widely adopted method in wave forecasting research. Based on wave generation and elimination and propagation rules, the wave numerical model can simulate and forecast waves in the research area. The calculation is performed using partial differential equations in numerical mode. Partial differential equations describing the ocean process are complex. If the accuracy of the pattern forecast is to be improved, more influencing factors need to be added in the pattern, which makes the pattern more complex and increases the calculation time. Although researchers at home and abroad commonly adopt numerical mode to study ocean processes, physical modeling is unfavorable for improving the forecasting efficiency. With the development of science and technology, the performance of the computer is greatly improved, and a favorable development environment is created for a machine learning algorithm. On one hand, the artificial intelligence calculation is simpler than the numerical method, the change mechanism of the physical process is not required to be clearly understood, the defect of the numerical mode is overcome to a certain extent, the numerical mode can complement each other, the method is greatly helpful for improving the timeliness and the accuracy of sea wave forecasting, on the other hand, the artificial intelligence method provides a new sea wave forecasting means, expands the thinking of sea research, and has long-term significance for sea observation and sea disaster early warning. At present, many researchers at home and abroad apply the research means to sea wave forecasting work, and find many aspects, for example Gao Li trains buoy data in an LSTM model by using wave height, wind speed, wind direction and wind speed at the moment of forecasting as four input factors in Taiwan strait and surrounding sea area wave forecasting research based on deep learning, and the result shows that the more input variables, the more input period (historical time sequence) and the best forecasting result are obtained, but if the buoy data are lost, the forecasting result is greatly reduced. Meanwhile, a great deal of researches show that the generation of the sea waves has close relation with wind speed and the like, wherein the generated waves and the period meet the dispersion relation of the sea waves, for example, the relation of wind wave growth is considered in a Venturi wind wave spectrum, the dissipation problem of the sea wave mode is overcome by adding external conditions, the strong mutual relation of the sea waves and the wind is shown, the influence of the wind cannot be ignored in researching the change of the waves, and the like. Therefore, how to process the buoy data missing so as to improve the accuracy of the forecasting result, how to utilize the correlation between the factors influencing the generation of the sea waves and the sea waves according to the sea wave generation characteristics, excavate and autonomously analyze the change rule of the data through a machine learning algorithm, and acquire a series of complex and nonlinear ocean characteristics through training and learning, so that the reliability of forecasting the sea wave missing measurement data becomes important. Disclosure of Invention The invention aims to provide a sea wave missing measurement data forecasting method based on a bivariate long-short-term memory algorithm, which is used for realizing reliable forecasting of