Sea wave height prediction method and system based on deep learning model

A technology of deep learning and prediction methods, applied in biological neural network models, character and pattern recognition, instruments, etc., can solve the problems of large amount of calculation, long calculation time, high cost, etc., and achieve improved prediction accuracy, fast and accurate prediction, and low cost The effect of cost forecasting

Pending Publication Date: 2022-05-06
NANJING UNIV OF INFORMATION SCI & TECH
View PDF11 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Existing technologies often only perform time-series prediction of a single observation point in ocean wave prediction, and seldom directly process two-dimensional observation data; moreover, the existing prediction technology also has the disadvantages of large amount of calculation, long calculation time, and difficulty in converg

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sea wave height prediction method and system based on deep learning model
  • Sea wave height prediction method and system based on deep learning model
  • Sea wave height prediction method and system based on deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] The embodiment of the present invention discloses a method for predicting the wave height of ocean waves based on a deep learning model, such as figure 1 shown, including the following steps:

[0079] (1) Obtain the original two-dimensional effective wave height data of ocean waves;

[0080] The geographical range of the significant wave height data used in this example is from 105° to 126° east longitude and 4° to 43° north latitude in the coastal waters of China, which contains a two-dimensional map composed of observation values ​​of 79×43 observation points data with a spatial resolution of 0.5 × 0.5.

[0081] (2) Preprocessing the original two-dimensional ocean wave significant wave height data, and using the preprocessed ocean wave significant wave height data as a training data set; wherein, the preprocessing process specifically includes the following steps:

[0082] (2-1) Eliminate abnormal wave values, such as negative values, abnormal high values, etc.;

...

Embodiment 2

[0130] The embodiment of the present invention discloses an ocean wave height prediction system based on a deep learning model, see Figure 7 ,include:

[0131] The collection module is used to obtain the image data of the wave height;

[0132] The preprocessing module is used to preprocess the image data of the wave height, and use the preprocessed image data of the wave height as a training data set;

[0133] A building block for constructing a data prediction model for significant wave height of ocean waves;

[0134] The training module is used to input the training data set into the ocean wave significant wave height data prediction model for deep learning training until the preset accuracy is reached, and the optimal prediction model is obtained;

[0135] The prediction module predicts the significant wave height of sea waves through the optimal prediction model, and denormalizes the prediction results to obtain the predicted value of significant wave height of sea wave...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a sea wave height prediction method and system based on a deep learning model, and relates to the technical field of ocean prediction, and the method comprises the following steps: obtaining the picture data of the sea wave height; preprocessing the picture data of the sea wave height, and taking the preprocessed picture data of the sea wave height as a training data set; constructing a sea wave significant wave height data prediction model, inputting the training data set into the sea wave significant wave height data prediction model for deep learning training until preset precision is reached, and obtaining an optimal prediction model; and carrying out sea wave significant wave height prediction through the optimal prediction model, and carrying out reverse normalization on a prediction result to obtain a prediction value of the sea wave significant wave height. According to the method, the defects of large calculation amount, high cost, incapability of rapid prediction, dependence on feature engineering and the like in the existing prediction technology can be overcome, and then low-cost rapid and accurate prediction is realized.

Description

technical field [0001] The present invention relates to the technical field of ocean prediction, and more specifically relates to a method and system for predicting ocean wave height based on a deep learning model. Background technique [0002] According to the mechanism of wave formation, ocean waves can be divided into wind waves and swell waves. Since the sea surface wave is actually an irregular combination of various waves with different wave heights, periods, and directions, the wave height value of a wave is not representative. Effective wave height refers to the actual wave height value calculated according to certain rules, such as average wave height, root mean square wave height, maximum wave height, certain guaranteed rate wave height, average wave height of a certain part of the wave, etc. Significant wave height has a major impact on marine engineering construction, maritime navigation, and transportation, and is also an important parameter for marine disaster...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06V10/40
CPCG06N3/045G06F18/214
Inventor 王丽娜邓熙麟董昌明
Owner NANJING UNIV OF INFORMATION SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap