A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image

Xudong Zhang; Haoyu Wang; Shuo Wang; Yanliang Liu; Weidong Yu; Xiaofeng Li

doi:10.1109/PIERS55526.2022.9792885

A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image

Xudong Zhang, Haoyu Wang, Shuo Wang, Yanliang Liu, Weidong Yu, Xiaofeng Li

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Internal solitary wave (ISW) has a large amplitude and spreads widely in the global oceans. Amplitude is an important parameter for ISW studies, while the accuracy of state-of-the-art models is limited. Here we show our study of ISW amplitude inversion using synchronous ISW observations from in-situ data and satellite images combined with machine learning techniques. The ISW amplitude can be inversed based on satellite extracted information. Four different machine learning techniques are applied, and results are compared. The results show that the XGBoost has the best performance with a root mean square of 22.08 m on an independent dataset. The proposed amplitude inversion model may shed light on the ISW energy studies.

Original language	English
Title of host publication	2022 Photonics & Electromagnetics Research Symposium (PIERS)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	269-272
Number of pages	4
ISBN (Electronic)	9781665460231
ISBN (Print)	9781665460248 (PoD)
DOIs	https://doi.org/10.1109/PIERS55526.2022.9792885
Publication status	Published - 16 Jun 2022
Event	2022 Photonics and Electromagnetics Research Symposium, PIERS 2022 - Hangzhou, China Duration: 25 Apr 2022 → 29 Apr 2022

Publication series

Name	Progress in Electromagnetics Research Symposium
ISSN (Print)	1559-9450
ISSN (Electronic)	2694-5053

Conference

Conference	2022 Photonics and Electromagnetics Research Symposium, PIERS 2022
Country/Territory	China
City	Hangzhou
Period	25/04/22 → 29/04/22

Bibliographical note

Funding Information:
This study was supported by the National Natural Science Foundation for Young Scientists of China [grant number 41906157]. The buoy data were provided by the regional international cooperation project Monsoon Onset Monitoring and its Social and Ecosystem Impact (MOMSEI).

Publisher Copyright:
© 2022 IEEE.

Keywords

Training
Satellites
Machine learning algorithms
Inverse problems
Oceans
Machine learning
Data models

ASJC Scopus subject areas

Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials

Access to Document

10.1109/PIERS55526.2022.9792885

Cite this

Zhang, X., Wang, H., Wang, S., Liu, Y., Yu, W., & Li, X. (2022). A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image. In 2022 Photonics & Electromagnetics Research Symposium (PIERS) (pp. 269-272). (Progress in Electromagnetics Research Symposium). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/PIERS55526.2022.9792885

@inproceedings{42f46e8f199b43fc8e6d0ed696a21944,

title = "A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image",

abstract = "Internal solitary wave (ISW) has a large amplitude and spreads widely in the global oceans. Amplitude is an important parameter for ISW studies, while the accuracy of state-of-the-art models is limited. Here we show our study of ISW amplitude inversion using synchronous ISW observations from in-situ data and satellite images combined with machine learning techniques. The ISW amplitude can be inversed based on satellite extracted information. Four different machine learning techniques are applied, and results are compared. The results show that the XGBoost has the best performance with a root mean square of 22.08 m on an independent dataset. The proposed amplitude inversion model may shed light on the ISW energy studies.",

keywords = "Training, Satellites, Machine learning algorithms, Inverse problems, Oceans, Machine learning, Data models",

author = "Xudong Zhang and Haoyu Wang and Shuo Wang and Yanliang Liu and Weidong Yu and Xiaofeng Li",

note = "Funding Information: This study was supported by the National Natural Science Foundation for Young Scientists of China [grant number 41906157]. The buoy data were provided by the regional international cooperation project Monsoon Onset Monitoring and its Social and Ecosystem Impact (MOMSEI). Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 Photonics and Electromagnetics Research Symposium, PIERS 2022 ; Conference date: 25-04-2022 Through 29-04-2022",

year = "2022",

month = jun,

day = "16",

doi = "10.1109/PIERS55526.2022.9792885",

language = "English",

isbn = "9781665460248 (PoD)",

series = "Progress in Electromagnetics Research Symposium",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "269--272",

booktitle = "2022 Photonics & Electromagnetics Research Symposium (PIERS)",

}

Zhang, X, Wang, H, Wang, S, Liu, Y, Yu, W & Li, X 2022, A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image. in 2022 Photonics & Electromagnetics Research Symposium (PIERS). Progress in Electromagnetics Research Symposium, Institute of Electrical and Electronics Engineers (IEEE), pp. 269-272, 2022 Photonics and Electromagnetics Research Symposium, PIERS 2022, Hangzhou, China, 25/04/22. https://doi.org/10.1109/PIERS55526.2022.9792885

A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image. / Zhang, Xudong; Wang, Haoyu; Wang, Shuo et al.
2022 Photonics & Electromagnetics Research Symposium (PIERS). Institute of Electrical and Electronics Engineers (IEEE), 2022. p. 269-272 (Progress in Electromagnetics Research Symposium).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image

AU - Zhang, Xudong

AU - Wang, Haoyu

AU - Wang, Shuo

AU - Liu, Yanliang

AU - Yu, Weidong

AU - Li, Xiaofeng

N1 - Funding Information: This study was supported by the National Natural Science Foundation for Young Scientists of China [grant number 41906157]. The buoy data were provided by the regional international cooperation project Monsoon Onset Monitoring and its Social and Ecosystem Impact (MOMSEI). Publisher Copyright: © 2022 IEEE.

PY - 2022/6/16

Y1 - 2022/6/16

N2 - Internal solitary wave (ISW) has a large amplitude and spreads widely in the global oceans. Amplitude is an important parameter for ISW studies, while the accuracy of state-of-the-art models is limited. Here we show our study of ISW amplitude inversion using synchronous ISW observations from in-situ data and satellite images combined with machine learning techniques. The ISW amplitude can be inversed based on satellite extracted information. Four different machine learning techniques are applied, and results are compared. The results show that the XGBoost has the best performance with a root mean square of 22.08 m on an independent dataset. The proposed amplitude inversion model may shed light on the ISW energy studies.

AB - Internal solitary wave (ISW) has a large amplitude and spreads widely in the global oceans. Amplitude is an important parameter for ISW studies, while the accuracy of state-of-the-art models is limited. Here we show our study of ISW amplitude inversion using synchronous ISW observations from in-situ data and satellite images combined with machine learning techniques. The ISW amplitude can be inversed based on satellite extracted information. Four different machine learning techniques are applied, and results are compared. The results show that the XGBoost has the best performance with a root mean square of 22.08 m on an independent dataset. The proposed amplitude inversion model may shed light on the ISW energy studies.

KW - Training

KW - Satellites

KW - Machine learning algorithms

KW - Inverse problems

KW - Oceans

KW - Machine learning

KW - Data models

UR - http://www.scopus.com/inward/record.url?scp=85132771895&partnerID=8YFLogxK

U2 - 10.1109/PIERS55526.2022.9792885

DO - 10.1109/PIERS55526.2022.9792885

M3 - Conference contribution

AN - SCOPUS:85132771895

SN - 9781665460248 (PoD)

T3 - Progress in Electromagnetics Research Symposium

SP - 269

EP - 272

BT - 2022 Photonics & Electromagnetics Research Symposium (PIERS)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2022 Photonics and Electromagnetics Research Symposium, PIERS 2022

Y2 - 25 April 2022 through 29 April 2022

ER -

A Machine-learning-based Model to Inverse Internal Solitary Wave Amplitude from Satellite Image

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this