CN112465203A - Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium - Google Patents

Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium Download PDF

Info

Publication number
CN112465203A
CN112465203A CN202011298616.3A CN202011298616A CN112465203A CN 112465203 A CN112465203 A CN 112465203A CN 202011298616 A CN202011298616 A CN 202011298616A CN 112465203 A CN112465203 A CN 112465203A
Authority
CN
China
Prior art keywords
data
neural network
sea level
level height
tensor
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.)
Pending
Application number
CN202011298616.3A
Other languages
Chinese (zh)
Inventor
宋弢
李颖
徐丹亚
江璟瑜
孟凡
谢鹏飞
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.)
China University of Petroleum East China
Original Assignee
China University of Petroleum East 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 China University of Petroleum East China filed Critical China University of Petroleum East China
Priority to CN202011298616.3A priority Critical patent/CN112465203A/en
Publication of CN112465203A publication Critical patent/CN112465203A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to an intelligent sea level height prediction system based on a recurrent neural network, and belongs to the field of ocean numerical prediction and deep learning. The system comprises: a gated cyclic unit neural network model, the network model comprising: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.

Description

Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium
Technical Field
The invention relates to the field of ocean numerical prediction and deep learning, in particular to an intelligent sea level height prediction system based on a gate control cycle unit neural network, computer equipment and a storage medium.
Background
Under the large background of global warming, the phenomenon of sea level rising is increasingly highlighted, and the sea level rising is gradually a focus of public attention. The harm brought by the rise of sea level restricts the sustainable development of marine economy in China, and meanwhile, certain negative effects are brought to the production and life of local people. And a proper prediction method is selected to accurately and reasonably predict the height change of the sea level, so that the coastal region can be effectively helped to preset relevant policies according to the prediction condition of the sea level, and corresponding disaster prevention and reduction measures are taken.
The change rule for accurately predicting the sea level height has important significance in ocean research, and due to the complexity and uncertainty of the ocean environment, the accuracy of sea level height prediction is still to be improved. Methods for predicting sea level height are mainly classified into two types, one is a mode prediction method based on a differential equation, and the other is a method based on data driving.
Pattern prediction is a complex process requiring a significant amount of time and computational processing. These models contain inherent bias due to parameterization and linearization of differential equations, which reduces prediction accuracy. The data-driven method mainly focuses on statistical methods, but the traditional statistical methods may not well describe the nonlinearity and randomness of the sea level height data, resulting in large prediction errors.
Disclosure of Invention
Based on the above problems, the embodiment of the invention provides an intelligent sea level height prediction system based on a gated cyclic unit neural network, computer equipment and a storage medium, which can effectively improve the accuracy of sea level height prediction. The following presents a simplified summary in order to provide a basic understanding of the disclosure of the embodiments.
According to a first aspect of the embodiments of the present invention, an intelligent sea level height prediction system based on a gated cyclic unit neural network is provided.
In some optional embodiments, the system comprises a gated cyclic unit neural network prediction model, the network prediction model comprising: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
Optionally, the performing missing value complementation and normalization processing on the input historical sea level height data by using a data preprocessor specifically includes: the default value in the ocean history data is retrieved by the isnull function of the pandas library in python and padded to 0. The data is then linearly varied by dispersion normalization, mapping it between [0,1 ].
Optionally, the segmenting and integrating the data by using the sequence builder with a certain step length to form a sequence tensor specifically includes: and carrying out tensor form segmentation on the historical data through a keras framework, wherein the tensor form segmentation is in the form of (samples, timeframes, features), and an input format required by the neural network is formed. Wherein samples refers to the sample size of the historical data, timestamp refers to the prediction step size, and features refers to the characteristic factors.
Optionally, the selection of the timeframe is determined by performing feature learning and extraction by using the historical data of the sea level height of the previous n days so as to perform sea level height prediction of the (n + 1) th day.
Optionally, the system includes a gated recurrent neural network prediction model, and the step of establishing includes:
(1) establishing a neural network basic structure comprising an input layer, a hidden layer and a full connection layer (output layer), and determining the neuron number, the activation function, the loss function and the initial value of the hidden layer of each layer.
(2) Inputting the processed historical sea level height data into a prediction model for forward propagation training, inputting from an input layer, performing deep feature learning and extraction on the data through a hidden layer, and finally performing dimension transformation and output on a full-connection layer (an output layer) to obtain a predicted value result.
(3) And comparing the error between the predicted value and the true value through the loss function, and judging whether the error reaches the precision error.
(4) If not, the error is subjected to back propagation training, the weight connection parameters between layers are adjusted, and the error between the predicted value and the true value is continuously reduced.
(5) And if the error precision is met, determining the optimal weight connection parameter corresponding to the minimum error.
Optionally, error back-propagation and adam algorithms are employed for the propagation training.
Optionally, the number of neurons in the hidden layer is determined to be 128, the RELU is selected as the activation function, the MSE is selected as the loss function, and the initial parameter of the hidden layer is randomly determined.
According to a second aspect of embodiments of the present invention, there is provided a computer apparatus.
In some optional embodiments, the computer device comprises: a memory, a processor, and a program stored on the memory and executable by the processor, the processor implementing the steps of, when executing the program: constructing a neural network prediction model of a gated cyclic unit, wherein the network prediction model comprises the following steps: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
Optionally, the performing missing value complementation and normalization processing on the input historical sea level height data by using a data preprocessor specifically includes: the default value in the ocean history data is retrieved by the isnull function of the pandas library in python and padded to 0. The data is then linearly varied by dispersion normalization, mapping it between [0,1 ].
Optionally, the segmenting and integrating the data by using the sequence builder with a certain step length to form a sequence tensor specifically includes: and carrying out tensor form segmentation on the historical data through a keras framework, wherein the tensor form segmentation is in the form of (samples, timeframes, features), and an input format required by the neural network is formed. Wherein samples refers to the sample size of the historical data, timestamp refers to the prediction step size, and features refers to the characteristic factors.
Optionally, the selection of the timeframe is determined by performing feature learning and extraction by using the historical data of the sea level height of the previous n days so as to perform sea level height prediction of the (n + 1) th day.
Optionally, the system includes a gated recurrent neural network prediction model, and the step of establishing includes:
(1) establishing a neural network basic structure comprising an input layer, a hidden layer and a full connection layer (output layer), and determining the neuron number, the activation function, the loss function and the initial value of the hidden layer of each layer.
(2) Inputting the processed historical sea level height data into a prediction model for forward propagation training, inputting from an input layer, performing deep feature learning and extraction on the data through a hidden layer, and finally performing dimension transformation and output on a full-connection layer (an output layer) to obtain a predicted value result.
(3) And comparing the error between the predicted value and the true value through the loss function, and judging whether the error reaches the precision error.
(4) If not, the error is subjected to back propagation training, the weight connection parameters between layers are adjusted, and the error between the predicted value and the true value is continuously reduced.
(5) And if the error precision is met, determining the optimal weight connection parameter corresponding to the minimum error.
Optionally, error back-propagation and adam algorithms are employed for the propagation training.
Optionally, the number of neurons in the hidden layer is determined to be 128, the RELU is selected as the activation function, the MSE is selected as the loss function, and the initial parameter of the hidden layer is randomly determined.
According to a third aspect of embodiments of the present invention, there is provided a storage medium.
In some alternative embodiments, the storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of: constructing a neural network prediction model of a gated cyclic unit, wherein the network prediction model comprises the following steps: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
Optionally, the performing missing value complementation and normalization processing on the input historical sea level height data by using a data preprocessor specifically includes: the default value in the ocean history data is retrieved by the isnull function of the pandas library in python and padded to 0. The data is then linearly varied by dispersion normalization, mapping it between [0,1 ].
Optionally, the segmenting and integrating the data by using the sequence builder with a certain step length to form a sequence tensor specifically includes: and carrying out tensor form segmentation on the historical data through a keras framework, wherein the tensor form segmentation is in the form of (samples, timeframes, features), and an input format required by the neural network is formed. Wherein samples refers to the sample size of the historical data, timestamp refers to the prediction step size, and features refers to the characteristic factors.
Optionally, the selection of the timeframe is determined by performing feature learning and extraction by using the historical data of the sea level height of the previous n days so as to perform sea level height prediction of the (n + 1) th day.
Optionally, the system includes a gated recurrent neural network prediction model, and the step of establishing includes:
(1) establishing a neural network basic structure comprising an input layer, a hidden layer and a full connection layer (output layer), and determining the neuron number, the activation function, the loss function and the initial value of the hidden layer of each layer.
(2) Inputting the processed historical sea level height data into a prediction model for forward propagation training, inputting from an input layer, performing deep feature learning and extraction on the data through a hidden layer, and finally performing dimension transformation and output on a full-connection layer (an output layer) to obtain a predicted value result.
(3) And comparing the error between the predicted value and the true value through the loss function, and judging whether the error reaches the precision error.
(4) If not, the error is subjected to back propagation training, the weight connection parameters between layers are adjusted, and the error between the predicted value and the true value is continuously reduced.
(5) And if the error precision is met, determining the optimal weight connection parameter corresponding to the minimum error.
Optionally, error back-propagation and adam algorithms are employed for the propagation training.
Optionally, the number of neurons in the hidden layer is determined to be 128, the RELU is selected as the activation function, the MSE is selected as the loss function, and the initial parameter of the hidden layer is randomly determined.
The embodiment of the invention has the following beneficial effects and advantages:
at present, the sea level rising phenomenon of China is increasingly prominent, immeasurable influence is caused on coastal areas, and accurate sea level height prediction means is needed for prediction, so that certain preventive measures are taken. The invention provides a sea level height intelligent prediction system based on a gated cyclic unit neural network, computer equipment and a storage medium, aiming at the problems of long calculation time, large resource consumption and inaccurate precision of some existing prediction methods. By utilizing the technology such as the gate control cycle unit neural network in deep learning, the characteristics of the sea level height data are mined from historical data, so that a new form for predicting the sea level height is realized. Compared with the traditional methods such as ocean numerical mode and statistics, the method can fully excavate the deep-level characteristics of the sea level height data, summarize the trend rule of the sea level height change, and perform more accurate prediction with less calculation time and resources.
Drawings
FIG. 1 is a schematic diagram illustrating an overall workflow of an intelligent sea level height prediction system based on a gated cyclic unit neural network according to an exemplary embodiment
FIG. 2 is a schematic flow diagram illustrating the creation of a gated recurrent neural network prediction model in accordance with an exemplary embodiment
Detailed Description
The technical solution of the present invention is further explained below with reference to the accompanying drawings and the detailed description.
It should be noted in advance that the following description is intended to provide further detailed description of the present application, and is exemplary. The technical means and terms of art used in the present invention are consistent with those skilled in the art described in the present application. In this specification, the terms "comprises," "comprising," or any combination thereof, are used to specify the presence of stated features, steps, operations, devices, components, and/or groups thereof.
In an optional embodiment, the system comprises a gated cyclic unit neural network prediction model, the network prediction model comprising: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
Fig. 1 is a schematic diagram illustrating an overall workflow of a sea level height intelligent prediction and forecasting system based on a gated cyclic unit neural network according to an exemplary embodiment.
Optionally, the performing missing value complementation and normalization processing on the input historical sea level height data by using a data preprocessor specifically includes: the default value in the ocean history data is retrieved by the isnull function of the pandas library in python and padded to 0. The data is then linearly varied by dispersion normalization, mapping it between [0,1 ].
Optionally, the segmenting and integrating the data by using the sequence builder with a certain step length to form a sequence tensor specifically includes: and carrying out tensor form segmentation on the historical data through a keras framework, wherein the tensor form segmentation is in the form of (samples, timeframes, features), and an input format required by the neural network is formed. Wherein samples refers to the sample size of the historical data, timestamp refers to the prediction step size, and features refers to the characteristic factors.
Optionally, the selection of the timeframe is determined by performing feature learning and extraction by using the historical data of the sea level height of the previous n days so as to perform sea level height prediction of the (n + 1) th day.
Optionally, the system includes a gated recurrent neural network prediction model, and the step of establishing includes:
(1) establishing a neural network basic structure comprising an input layer, a hidden layer and a full connection layer (output layer), and determining the neuron number, the activation function, the loss function and the initial value of the hidden layer of each layer.
(2) Inputting the processed historical sea level height data into a prediction model for forward propagation training, inputting from an input layer, performing deep feature learning and extraction on the data through a hidden layer, and finally performing dimension transformation and output on a full-connection layer (an output layer) to obtain a predicted value result.
(3) And comparing the error between the predicted value and the true value through the loss function, and judging whether the error reaches the precision error.
(4) If not, the error is subjected to back propagation training, the weight connection parameters between layers are adjusted, and the error between the predicted value and the true value is continuously reduced.
(5) And if the error precision is met, determining the optimal weight connection parameter corresponding to the minimum error.
FIG. 2 is a schematic flow diagram illustrating the creation of a gated recurrent neural network prediction model in accordance with an exemplary embodiment.
Optionally, error back-propagation and adam algorithms are employed for the propagation training.
Optionally, the number of neurons in the hidden layer is determined to be 128, the RELU is selected as the activation function, the MSE is selected as the loss function, and the initial parameter of the hidden layer is randomly determined.
In the above embodiment example, there is also provided a non-transitory computer readable storage medium comprising instructions executable by a processor to perform the steps of: establishing a gated cyclic unit neural network prediction model, wherein the network prediction model comprises: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
The non-transitory computer readable storage medium may be a read-only memory, a random access memory, a magnetic tape, an optical storage device, and the like.
The invention predicts the sea level height data by the deep learning technology, can reduce a large amount of calculation time and resources compared with the traditional methods such as ocean numerical mode, statistics and the like, has high processing speed and quite accurate accuracy, and is convenient for integration and large-scale application.
Although the preferred embodiments of the present invention have been described above, the present invention is only one of the preferred embodiments of the present invention, and is not limited thereto. It will be apparent to those skilled in the art that various changes and modifications can be made in the above embodiments without departing from the scope of the invention, and it is intended to cover all such modifications, equivalents and modifications as fall within the true spirit of the invention.

Claims (10)

1. The sea level height intelligent prediction forecasting system based on the recurrent neural network is characterized by comprising a gated recurrent unit neural network prediction model, wherein the network prediction model comprises: the system comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor. Firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
2. The system of claim 1, wherein the utilizing of the data preprocessor to perform missing value complementation and normalization on the input historical sea level altitude data specifically comprises: the default value in the ocean history data is retrieved by the isnull function of the pandas library in python and padded to 0. The data is then linearly varied by dispersion normalization, mapping it between [0,1 ].
3. The system of claim 1, wherein the step of slicing and integrating the data by using the sequence builder to form the sequence tensor comprises: and carrying out tensor form segmentation on the historical data through a keras framework, wherein the tensor form segmentation is in the form of (samples, timeframes, features), and an input format required by the neural network is formed. Wherein samples refers to the sample size of the historical data, timestamp refers to the prediction step size, and features refers to the characteristic factors.
4. The system of claim 3, wherein said timemap is selected based on the n +1 th day sea level height prediction using historical data of sea level heights from the previous n days for feature learning and extraction.
5. The system of claim 1, wherein the step of building a gated recurrent neural network prediction model comprises:
(1) establishing a neural network basic structure comprising an input layer, a hidden layer and a full connection layer (output layer), and determining the neuron number, the activation function, the loss function and the initial value of the hidden layer of each layer.
(2) Inputting the processed historical sea level height data into a prediction model for forward propagation training, inputting from an input layer, performing deep feature learning and extraction on the data through a hidden layer, and finally performing dimension transformation and output on a full-connection layer (an output layer) to obtain a predicted value result.
(3) And comparing the error between the predicted value and the true value through the loss function, and judging whether the error reaches the precision error.
(4) If not, the error is subjected to back propagation training, the weight connection parameters between layers are adjusted, and the error between the predicted value and the true value is continuously reduced.
(5) And if the error precision is met, determining the optimal weight connection parameter corresponding to the minimum error.
6. The system of claim 5, wherein error back propagation and adam algorithms are employed for the propagation training.
7. The system of claim 5, wherein the number of hidden layer neurons is determined to be 128, the RELU is selected as the activation function, the MSE is selected as the loss function, and the initial hidden layer parameters are randomly determined.
8. The system of claim 7, wherein the number of hidden layer neurons is established without any particular theory, and is generally determined empirically or by multiple experiments in the system.
9. A computer device comprising a memory, a processor, and a program stored on the memory and executable by the processor, wherein the processor implements the following steps when executing the program: constructing a neural network prediction model of a gated cyclic unit, wherein the network prediction model comprises the following steps: the data preprocessing device comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor; firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
10. A storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of: constructing a neural network prediction model of a gated cyclic unit, wherein the network prediction model comprises the following steps: the data preprocessing device comprises a data preprocessor, a tensor sequence builder and a gated cyclic unit neural network predictor; firstly, carrying out missing value complementation and normalization pretreatment on the input historical sea level height data by using a data preprocessor; then, a sequence builder is used for segmenting and integrating data in a certain step length to form a tensor sequence; and finally, establishing a gate control cycle neural network prediction model in a gate control cycle unit neural network predictor, and predicting the characteristic tensor by performing deep feature learning and extraction on the input historical sea level height data to finally obtain a predicted value of the sea level height.
CN202011298616.3A 2020-11-19 2020-11-19 Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium Pending CN112465203A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011298616.3A CN112465203A (en) 2020-11-19 2020-11-19 Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011298616.3A CN112465203A (en) 2020-11-19 2020-11-19 Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112465203A true CN112465203A (en) 2021-03-09

Family

ID=74836816

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011298616.3A Pending CN112465203A (en) 2020-11-19 2020-11-19 Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112465203A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070050142A1 (en) * 2005-08-23 2007-03-01 Pamela Posey System and method for estimating ocean height and current on a personal computer with location adjustment
CN109614742A (en) * 2018-12-25 2019-04-12 中国海洋大学 A kind of sea level height duration prediction algorithm
CN110503231A (en) * 2019-05-29 2019-11-26 中国石油大学(华东) A kind of sea level height intelligent Forecasting based on ConvLSTM
CN111210089A (en) * 2020-01-17 2020-05-29 大连大学 Stock price prediction method of gated cyclic unit neural network based on Kalman filtering
CN111680784A (en) * 2020-05-27 2020-09-18 上海大学 Sea surface temperature deep learning prediction method based on time-space multidimensional influence

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070050142A1 (en) * 2005-08-23 2007-03-01 Pamela Posey System and method for estimating ocean height and current on a personal computer with location adjustment
CN109614742A (en) * 2018-12-25 2019-04-12 中国海洋大学 A kind of sea level height duration prediction algorithm
CN110503231A (en) * 2019-05-29 2019-11-26 中国石油大学(华东) A kind of sea level height intelligent Forecasting based on ConvLSTM
CN111210089A (en) * 2020-01-17 2020-05-29 大连大学 Stock price prediction method of gated cyclic unit neural network based on Kalman filtering
CN111680784A (en) * 2020-05-27 2020-09-18 上海大学 Sea surface temperature deep learning prediction method based on time-space multidimensional influence

Similar Documents

Publication Publication Date Title
CN114422381A (en) Communication network flow prediction method, system, storage medium and computer equipment
CN116049719B (en) Fault detection and estimation method, system and medium based on migration type generation model
CN113065703A (en) Time series prediction method combining multiple models
CN116562156B (en) Training method, device, equipment and storage medium for control decision model
CN112558185A (en) Bidirectional GRU typhoon track intelligent prediction and forecast system based on attention mechanism, computer equipment and storage medium
CN111898746B (en) Deep learning method for continuous relevance of broken flight path
CN116522594A (en) Time self-adaptive transient stability prediction method and device based on convolutional neural network
Ye et al. Hydrologic time series anomaly detection based on flink
Feng et al. Stream-flow forecasting based on dynamic spatio-temporal attention
Wang et al. Vessel traffic flow forecasting based on BP neural network and residual analysis
CN117034657A (en) Geophysical data processing module based on priori information constraint
CN112465203A (en) Sea level height intelligent prediction and forecast system based on gate control circulation unit neural network, computer equipment and storage medium
CN116680639A (en) Deep-learning-based anomaly detection method for sensor data of deep-sea submersible
CN114970674A (en) Time sequence data concept drift adaptation method based on relevance alignment
CN114943328A (en) SARIMA-GRU time sequence prediction model based on BP neural network nonlinear combination
CN111027680B (en) Monitoring quantity uncertainty prediction method and system based on variational self-encoder
Chen et al. GCN-Seq2Seq: A Spatio-Temporal feature-fused model for surface water quality prediction
LU504816B1 (en) Interpretable deep learning model for extreme climate prediction
CN118247512B (en) Point cloud semantic segmentation model building method and point cloud semantic segmentation method
CN118013635B (en) Design method, device and equipment of building drainage pipeline and storage medium
CN113688774B (en) Advanced learning-based high-rise building wind induced response prediction and training method and device
Chen et al. Resident Load Disaggregation Based on Dilated Causal Convolution and Variational Autoencoder
CN115878783B (en) Text processing method, deep learning model training method and sample generation method
CN114036948B (en) Named entity identification method based on uncertainty quantification
CN116910682B (en) Event detection method and device, electronic equipment and storage medium

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210309