Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data

Sea surface height (SSH) is of great significance in oceanography and meteorology. Traditional physical altimetry methods based on delay–Doppler mapping (DDM) are subject to errors that are difficult to correct computationally. The current deep-learning-based SSH inversion techniques prim...

Full description

Saved in:
Bibliographic Details
Main Authors: Yun Zhang, Ganyao Qin, Shuhu Yang, Yanling Han, Zhonghua Hong
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10974576/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138175751585792
author Yun Zhang
Ganyao Qin
Shuhu Yang
Yanling Han
Zhonghua Hong
author_facet Yun Zhang
Ganyao Qin
Shuhu Yang
Yanling Han
Zhonghua Hong
author_sort Yun Zhang
collection DOAJ
description Sea surface height (SSH) is of great significance in oceanography and meteorology. Traditional physical altimetry methods based on delay–Doppler mapping (DDM) are subject to errors that are difficult to correct computationally. The current deep-learning-based SSH inversion techniques primarily relying on single-modal data are unable to fully leverage the rich feature information from global navigation satellite system reflectometry (GNSS-R) remote sensing data, therefore limiting the potential accuracy improvement. This study proposes a physics-informed multimodal deep-learning framework, physical-informed multimodal heterogeneous altimetry network (PIMFA-Net), to fuse heterogeneous spaceborne GNSS-R data to retrieve SSH. The GNSS-R data are acquired from the GNOS II instrument onboard the Fengyun-3E satellite, which can receive reflected signals from both global positioning system (GPS) and BeiDou navigation satellite system (BDS). GNSS-R parameters are used to construct the PIMFA-Net, which includes cropped DDM images, signal parameters, and system parameters in combination with environmental parameters (wind speed and convective rain rate from the European Centre for Medium-Range Weather Forecast, and SSH derived from physical altimetry models). The global sea surface dataset Danmarks Tekniske Universitet 2018 is used as ground truth for model training and evaluation. Data from 1 to 31 July 2022 are used to train PIMFA-Net, while data from August to October 2022 are used to evaluate the general ability of PIMFA-Net. Results demonstrate that the PIMFA-Net not only improves the accuracy and generalization by integrating heterogeneous data sources but also achieves all-weather, all-day, and wide-area SSH inversion with a precision of less than 40 cm for both GPS and BDS signals. This outcome holds significant potential for applications in marine ecological security monitoring and research.
format Article
id doaj-art-cd8df58968674e419fc08b71921dd33e
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-cd8df58968674e419fc08b71921dd33e2025-08-20T02:30:38ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118119791199510.1109/JSTARS.2025.356274110974576Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R DataYun Zhang0https://orcid.org/0000-0003-4367-8674Ganyao Qin1Shuhu Yang2https://orcid.org/0000-0001-9967-7756Yanling Han3https://orcid.org/0000-0002-0682-9157Zhonghua Hong4https://orcid.org/0000-0003-0045-1066College of Information Technology, Shanghai Ocean University, Shanghai, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai, ChinaSea surface height (SSH) is of great significance in oceanography and meteorology. Traditional physical altimetry methods based on delay–Doppler mapping (DDM) are subject to errors that are difficult to correct computationally. The current deep-learning-based SSH inversion techniques primarily relying on single-modal data are unable to fully leverage the rich feature information from global navigation satellite system reflectometry (GNSS-R) remote sensing data, therefore limiting the potential accuracy improvement. This study proposes a physics-informed multimodal deep-learning framework, physical-informed multimodal heterogeneous altimetry network (PIMFA-Net), to fuse heterogeneous spaceborne GNSS-R data to retrieve SSH. The GNSS-R data are acquired from the GNOS II instrument onboard the Fengyun-3E satellite, which can receive reflected signals from both global positioning system (GPS) and BeiDou navigation satellite system (BDS). GNSS-R parameters are used to construct the PIMFA-Net, which includes cropped DDM images, signal parameters, and system parameters in combination with environmental parameters (wind speed and convective rain rate from the European Centre for Medium-Range Weather Forecast, and SSH derived from physical altimetry models). The global sea surface dataset Danmarks Tekniske Universitet 2018 is used as ground truth for model training and evaluation. Data from 1 to 31 July 2022 are used to train PIMFA-Net, while data from August to October 2022 are used to evaluate the general ability of PIMFA-Net. Results demonstrate that the PIMFA-Net not only improves the accuracy and generalization by integrating heterogeneous data sources but also achieves all-weather, all-day, and wide-area SSH inversion with a precision of less than 40 cm for both GPS and BDS signals. This outcome holds significant potential for applications in marine ecological security monitoring and research.https://ieeexplore.ieee.org/document/10974576/Global navigation satellite system reflectometry (GNSS-R)multimodal deep learningphysics-informed enhancementsea surface height (SSH) inversion
spellingShingle Yun Zhang
Ganyao Qin
Shuhu Yang
Yanling Han
Zhonghua Hong
Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Global navigation satellite system reflectometry (GNSS-R)
multimodal deep learning
physics-informed enhancement
sea surface height (SSH) inversion
title Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data
title_full Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data
title_fullStr Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data
title_full_unstemmed Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data
title_short Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data
title_sort sea surface height inversion model based on multimodal deep learning for the fusion of heterogeneous fy 3e gnss r data
topic Global navigation satellite system reflectometry (GNSS-R)
multimodal deep learning
physics-informed enhancement
sea surface height (SSH) inversion
url https://ieeexplore.ieee.org/document/10974576/
work_keys_str_mv AT yunzhang seasurfaceheightinversionmodelbasedonmultimodaldeeplearningforthefusionofheterogeneousfy3egnssrdata
AT ganyaoqin seasurfaceheightinversionmodelbasedonmultimodaldeeplearningforthefusionofheterogeneousfy3egnssrdata
AT shuhuyang seasurfaceheightinversionmodelbasedonmultimodaldeeplearningforthefusionofheterogeneousfy3egnssrdata
AT yanlinghan seasurfaceheightinversionmodelbasedonmultimodaldeeplearningforthefusionofheterogeneousfy3egnssrdata
AT zhonghuahong seasurfaceheightinversionmodelbasedonmultimodaldeeplearningforthefusionofheterogeneousfy3egnssrdata