Cargando…
Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions
This research introduces a deep learning method for ocean wave height estimation utilizing a Convolutional Neural Network (CNN) based on the VGGNet. The model is trained on a dataset comprising buoy wave heights and radar images, both critical for marine engineering. The dataset features X-band rada...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10615293/ https://www.ncbi.nlm.nih.gov/pubmed/37903150 http://dx.doi.org/10.1371/journal.pone.0292884 |
_version_ | 1785129191113490432 |
---|---|
author | Kwon, Ji-Woo Chang, Won-Du Yang, Young Jun |
author_facet | Kwon, Ji-Woo Chang, Won-Du Yang, Young Jun |
author_sort | Kwon, Ji-Woo |
collection | PubMed |
description | This research introduces a deep learning method for ocean wave height estimation utilizing a Convolutional Neural Network (CNN) based on the VGGNet. The model is trained on a dataset comprising buoy wave heights and radar images, both critical for marine engineering. The dataset features X-band radar images sourced from Sokcho, Republic of Korea, spanning from June 1, 2021, to August 13, 2021. This collection amounts to 72,180 three-dimensional images, gathered at intervals of approximately 1.43 seconds. The data collected was highly unbalanced in terms of wave heights, with images of lower wave heights being more common. To deal with data imbalances in the wave height datasets, we categorized the data into three groups based on wave heights and applied stratified random sampling at each level. This approach balances the data patches for each training iteration, reducing the risk of overfitting and promoting learning from diverse data. We also implemented a system to protect data in groups with fewer instances, ensuring fair representation across all categories. This study presents a deep learning regression model for predicting wave height values from radar images. The model extracts features from sequences of 64 radar images using three-dimensional convolutions for both temporal and spatial learning. Using three-dimensional convolutions, the model captures temporal features in radar image sequences and provides accurate wave height estimates with an RMSE of 0.3576 m. The study derived results using radar images under different wave height conditions for 74 days to ensure reliability. |
format | Online Article Text |
id | pubmed-10615293 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-106152932023-10-31 Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions Kwon, Ji-Woo Chang, Won-Du Yang, Young Jun PLoS One Research Article This research introduces a deep learning method for ocean wave height estimation utilizing a Convolutional Neural Network (CNN) based on the VGGNet. The model is trained on a dataset comprising buoy wave heights and radar images, both critical for marine engineering. The dataset features X-band radar images sourced from Sokcho, Republic of Korea, spanning from June 1, 2021, to August 13, 2021. This collection amounts to 72,180 three-dimensional images, gathered at intervals of approximately 1.43 seconds. The data collected was highly unbalanced in terms of wave heights, with images of lower wave heights being more common. To deal with data imbalances in the wave height datasets, we categorized the data into three groups based on wave heights and applied stratified random sampling at each level. This approach balances the data patches for each training iteration, reducing the risk of overfitting and promoting learning from diverse data. We also implemented a system to protect data in groups with fewer instances, ensuring fair representation across all categories. This study presents a deep learning regression model for predicting wave height values from radar images. The model extracts features from sequences of 64 radar images using three-dimensional convolutions for both temporal and spatial learning. Using three-dimensional convolutions, the model captures temporal features in radar image sequences and provides accurate wave height estimates with an RMSE of 0.3576 m. The study derived results using radar images under different wave height conditions for 74 days to ensure reliability. Public Library of Science 2023-10-30 /pmc/articles/PMC10615293/ /pubmed/37903150 http://dx.doi.org/10.1371/journal.pone.0292884 Text en © 2023 Kwon et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Kwon, Ji-Woo Chang, Won-Du Yang, Young Jun Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions |
title | Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions |
title_full | Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions |
title_fullStr | Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions |
title_full_unstemmed | Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions |
title_short | Significant wave height prediction from X-band marine radar images using deep learning with 3D convolutions |
title_sort | significant wave height prediction from x-band marine radar images using deep learning with 3d convolutions |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10615293/ https://www.ncbi.nlm.nih.gov/pubmed/37903150 http://dx.doi.org/10.1371/journal.pone.0292884 |
work_keys_str_mv | AT kwonjiwoo significantwaveheightpredictionfromxbandmarineradarimagesusingdeeplearningwith3dconvolutions AT changwondu significantwaveheightpredictionfromxbandmarineradarimagesusingdeeplearningwith3dconvolutions AT yangyoungjun significantwaveheightpredictionfromxbandmarineradarimagesusingdeeplearningwith3dconvolutions |