Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning

This study aims to enhance the spatial resolution and accuracy of bathymetric prediction by integrating Gravity Anomaly (GA) and Vertical Gravity Gradient Anomaly (VGG) data with a dual-channel Backpropagation Neural Network (BPNN). The seafloor topography of the Izu-Ogasawara Trench in the Western...

Full description

Saved in:
Bibliographic Details
Main Authors: Junhui Li, Nengfang Chao, Houpu Li, Gang Chen, Shaofeng Bian, Zhengtao Wang, Aoyu Ma
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Marine Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmars.2024.1520401/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121004930170880
author Junhui Li
Nengfang Chao
Nengfang Chao
Houpu Li
Gang Chen
Gang Chen
Shaofeng Bian
Zhengtao Wang
Aoyu Ma
author_facet Junhui Li
Nengfang Chao
Nengfang Chao
Houpu Li
Gang Chen
Gang Chen
Shaofeng Bian
Zhengtao Wang
Aoyu Ma
author_sort Junhui Li
collection DOAJ
description This study aims to enhance the spatial resolution and accuracy of bathymetric prediction by integrating Gravity Anomaly (GA) and Vertical Gravity Gradient Anomaly (VGG) data with a dual-channel Backpropagation Neural Network (BPNN). The seafloor topography of the Izu-Ogasawara Trench in the Western Pacific will be constructed and evaluated using depth models and single-beam data. The BPNN improved the accuracy of seafloor topography prediction by 0.17% and 0.35% using the 1 arc-minute SIO and GEBCO depth models, respectively, in areas without in-situ data. When single-beam data was utilized, the BPNN improved prediction accuracy by 64.93%, 70.29%, and 68.78% compared to the Gravity Geological Method (GGM), SIO v25.1, and GEBCO 2023, respectively. When single-beam, GA, and VGG data were all combined, the root mean square error (RMSE) was reduced to 19.12 m, representing an improvement of 60.92% and 61.13% compared to using only GA or VGG data, respectively. Comparing bathymetric predictions at different depths, the BPNN achieved a mean relative error (MRE) as low as 0.5%. Across various terrains—such as trench areas, seamounts, and deep-sea plains—the accuracy of seafloor topography predicted by the BPNN improved by 88.36%, 87.42%, and 84.39% compared to GGM, SIO and GEBCO depth models, respectively. These findings demonstrate that BPNN can integrate GA and VGG data to enhance both the accuracy and spatial resolution of seafloor topography in regions with and without in-situ data, and across various depths and terrains. This study provides new data and methodological support for constructing high-precision global seafloor topography.
format Article
id doaj-art-1af23de35a3946bbbf4ea186f86c95bd
institution Kabale University
issn 2296-7745
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Marine Science
spelling doaj-art-1af23de35a3946bbbf4ea186f86c95bd2024-12-16T06:18:34ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-12-011110.3389/fmars.2024.15204011520401Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learningJunhui Li0Nengfang Chao1Nengfang Chao2Houpu Li3Gang Chen4Gang Chen5Shaofeng Bian6Zhengtao Wang7Aoyu Ma8College of Marine Science and Technology, Hubei Key Laboratory of Marine Geological Resources, China University of Geosciences, Wuhan, ChinaCollege of Marine Science and Technology, Hubei Key Laboratory of Marine Geological Resources, China University of Geosciences, Wuhan, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan, ChinaCollege of Marine Science and Technology, Hubei Key Laboratory of Marine Geological Resources, China University of Geosciences, Wuhan, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan, ChinaSchool of Geodesy and Geomatics, Key Laboratory of Geospace Environment and Geodesy, Wuhan University, Wuhan, ChinaCollege of Marine Science and Technology, Hubei Key Laboratory of Marine Geological Resources, China University of Geosciences, Wuhan, ChinaThis study aims to enhance the spatial resolution and accuracy of bathymetric prediction by integrating Gravity Anomaly (GA) and Vertical Gravity Gradient Anomaly (VGG) data with a dual-channel Backpropagation Neural Network (BPNN). The seafloor topography of the Izu-Ogasawara Trench in the Western Pacific will be constructed and evaluated using depth models and single-beam data. The BPNN improved the accuracy of seafloor topography prediction by 0.17% and 0.35% using the 1 arc-minute SIO and GEBCO depth models, respectively, in areas without in-situ data. When single-beam data was utilized, the BPNN improved prediction accuracy by 64.93%, 70.29%, and 68.78% compared to the Gravity Geological Method (GGM), SIO v25.1, and GEBCO 2023, respectively. When single-beam, GA, and VGG data were all combined, the root mean square error (RMSE) was reduced to 19.12 m, representing an improvement of 60.92% and 61.13% compared to using only GA or VGG data, respectively. Comparing bathymetric predictions at different depths, the BPNN achieved a mean relative error (MRE) as low as 0.5%. Across various terrains—such as trench areas, seamounts, and deep-sea plains—the accuracy of seafloor topography predicted by the BPNN improved by 88.36%, 87.42%, and 84.39% compared to GGM, SIO and GEBCO depth models, respectively. These findings demonstrate that BPNN can integrate GA and VGG data to enhance both the accuracy and spatial resolution of seafloor topography in regions with and without in-situ data, and across various depths and terrains. This study provides new data and methodological support for constructing high-precision global seafloor topography.https://www.frontiersin.org/articles/10.3389/fmars.2024.1520401/fullseafloor topographyBPNNgravity anomalyvertical gravity gradientIzu-Ogasawara Trenchdeep learning
spellingShingle Junhui Li
Nengfang Chao
Nengfang Chao
Houpu Li
Gang Chen
Gang Chen
Shaofeng Bian
Zhengtao Wang
Aoyu Ma
Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
Frontiers in Marine Science
seafloor topography
BPNN
gravity anomaly
vertical gravity gradient
Izu-Ogasawara Trench
deep learning
title Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
title_full Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
title_fullStr Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
title_full_unstemmed Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
title_short Enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
title_sort enhancing bathymetric prediction by integrating gravity and gravity gradient data with deep learning
topic seafloor topography
BPNN
gravity anomaly
vertical gravity gradient
Izu-Ogasawara Trench
deep learning
url https://www.frontiersin.org/articles/10.3389/fmars.2024.1520401/full
work_keys_str_mv AT junhuili enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT nengfangchao enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT nengfangchao enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT houpuli enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT gangchen enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT gangchen enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT shaofengbian enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT zhengtaowang enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning
AT aoyuma enhancingbathymetricpredictionbyintegratinggravityandgravitygradientdatawithdeeplearning