SWOT Global Bathymetry Modeling Using Deep Neural Networks Trained on Multiple Geophysical Features Article Swipe
Farshad Salajegheh
,
Xiaoli Deng
,
Ole Andersen
,
Richard Coleman
,
Mehdi Khaki
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1029/2025ea004545
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1029/2025ea004545
This paper presents BathDNN25, a global bathymetry model developed using gravity data derived from wide‐swath altimetry collected by the Surface Water and Ocean Topography (SWOT) mission, with shipborne bathymetry serving as training data in a deep neural network (DNN) framework. BathDNN25 integrates multiple geophysical inputs, including gravity anomalies , vertical gravity gradients , their band‐pass filtered forms , the north and east components derived from the deflection of the vertical (, ), their band‐pass versions (, ), low‐pass filtered bathymetry , and both low‐pass and band‐pass filtered gravity (, ), to capture both large‐scale trends and fine‐scale bathymetric features. A key innovation lies in its use of multi‐scale geophysical features, enabling enhanced sensitivity to morphological complexity such as ridges, escarpments, and seamounts, while adapting well to varying geological conditions and data sparsity. Model performance was assessed using residual statistics against independent data sets, including global shipborne soundings and seamount summits, with BathDNN25 achieving residual standard deviations of 99 and 167 m, respectively. Compared to existing methods (Harper & Sandwell, 2024, https://doi.org/10.1029/2023ea003199 ), this represents reductions in residual error of over 51% and 113%. SHAP analysis across 14 regions and ablation tests using four model variants further confirmed the complementary value of SWOT‐derived gravity features. Overall, BathDNN25 demonstrates accuracy, robustness, and scalability, underscoring the importance of high‐quality geophysical inputs and the potential of SWOT‐derived data and artificial intelligence in advancing global bathymetric modeling.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1029/2025ea004545
- OA Status
- gold
- References
- 27
- OpenAlex ID
- https://openalex.org/W4415884997
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415884997Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1029/2025ea004545Digital Object Identifier
- Title
-
SWOT Global Bathymetry Modeling Using Deep Neural Networks Trained on Multiple Geophysical FeaturesWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-01Full publication date if available
- Authors
-
Farshad Salajegheh, Xiaoli Deng, Ole Andersen, Richard Coleman, Mehdi KhakiList of authors in order
- Landing page
-
https://doi.org/10.1029/2025ea004545Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1029/2025ea004545Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
27Number of works referenced by this work
Full payload
| id | https://openalex.org/W4415884997 |
|---|---|
| doi | https://doi.org/10.1029/2025ea004545 |
| ids.doi | https://doi.org/10.1029/2025ea004545 |
| ids.openalex | https://openalex.org/W4415884997 |
| fwci | |
| type | article |
| title | SWOT Global Bathymetry Modeling Using Deep Neural Networks Trained on Multiple Geophysical Features |
| biblio.issue | 11 |
| biblio.volume | 12 |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list.value | 1800 |
| apc_list.currency | USD |
| apc_list.value_usd | 1800 |
| apc_paid.value | 1800 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 1800 |
| language | en |
| locations[0].id | doi:10.1029/2025ea004545 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2764679394 |
| locations[0].source.issn | 2333-5084 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2333-5084 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Earth and Space Science |
| locations[0].source.host_organization | https://openalex.org/P4310315809 |
| locations[0].source.host_organization_name | American Geophysical Union |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310315809 |
| locations[0].source.host_organization_lineage_names | American Geophysical Union |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Earth and Space Science |
| locations[0].landing_page_url | https://doi.org/10.1029/2025ea004545 |
| locations[1].id | pmh:oai:doaj.org/article:20558cbf57c54077ba8543e067ac94f6 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Earth and Space Science, Vol 12, Iss 11, Pp n/a-n/a (2025) |
| locations[1].landing_page_url | https://doaj.org/article/20558cbf57c54077ba8543e067ac94f6 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5011262627 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9812-0243 |
| authorships[0].author.display_name | Farshad Salajegheh |
| authorships[0].countries | AU |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I78757542 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Engineering University of Newcastle Callaghan NSW Australia |
| authorships[0].institutions[0].id | https://openalex.org/I78757542 |
| authorships[0].institutions[0].ror | https://ror.org/00eae9z71 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I78757542 |
| authorships[0].institutions[0].country_code | AU |
| authorships[0].institutions[0].display_name | University of Newcastle Australia |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Farshad Salajegheh |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Engineering University of Newcastle Callaghan NSW Australia |
| authorships[1].author.id | https://openalex.org/A5054988629 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9595-8032 |
| authorships[1].author.display_name | Xiaoli Deng |
| authorships[1].countries | AU |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I78757542 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Engineering University of Newcastle Callaghan NSW Australia |
| authorships[1].institutions[0].id | https://openalex.org/I78757542 |
| authorships[1].institutions[0].ror | https://ror.org/00eae9z71 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I78757542 |
| authorships[1].institutions[0].country_code | AU |
| authorships[1].institutions[0].display_name | University of Newcastle Australia |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xiaoli Deng |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Engineering University of Newcastle Callaghan NSW Australia |
| authorships[2].author.id | https://openalex.org/A5064774963 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6685-3415 |
| authorships[2].author.display_name | Ole Andersen |
| authorships[2].countries | DK |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I96673099 |
| authorships[2].affiliations[0].raw_affiliation_string | DTU Space Technical University of Denmark Lyngby Denmark |
| authorships[2].institutions[0].id | https://openalex.org/I96673099 |
| authorships[2].institutions[0].ror | https://ror.org/04qtj9h94 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I96673099 |
| authorships[2].institutions[0].country_code | DK |
| authorships[2].institutions[0].display_name | Technical University of Denmark |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ole Baltazar Andersen |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | DTU Space Technical University of Denmark Lyngby Denmark |
| authorships[3].author.id | https://openalex.org/A5018602235 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-9731-7498 |
| authorships[3].author.display_name | Richard Coleman |
| authorships[3].countries | AU |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I129801699 |
| authorships[3].affiliations[0].raw_affiliation_string | Institute for Marine and Antarctic Studies (IMAS) University of Tasmania Dynnyrne TAS Australia |
| authorships[3].institutions[0].id | https://openalex.org/I129801699 |
| authorships[3].institutions[0].ror | https://ror.org/01nfmeh72 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I129801699 |
| authorships[3].institutions[0].country_code | AU |
| authorships[3].institutions[0].display_name | University of Tasmania |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Richard Coleman |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Institute for Marine and Antarctic Studies (IMAS) University of Tasmania Dynnyrne TAS Australia |
| authorships[4].author.id | https://openalex.org/A5036054765 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-3718-2843 |
| authorships[4].author.display_name | Mehdi Khaki |
| authorships[4].countries | AU |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I78757542 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Engineering University of Newcastle Callaghan NSW Australia |
| authorships[4].institutions[0].id | https://openalex.org/I78757542 |
| authorships[4].institutions[0].ror | https://ror.org/00eae9z71 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I78757542 |
| authorships[4].institutions[0].country_code | AU |
| authorships[4].institutions[0].display_name | University of Newcastle Australia |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Mehdi Khaki |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Engineering University of Newcastle Callaghan NSW Australia |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1029/2025ea004545 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-04T00:00:00 |
| display_name | SWOT Global Bathymetry Modeling Using Deep Neural Networks Trained on Multiple Geophysical Features |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1029/2025ea004545 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2764679394 |
| best_oa_location.source.issn | 2333-5084 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2333-5084 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Earth and Space Science |
| best_oa_location.source.host_organization | https://openalex.org/P4310315809 |
| best_oa_location.source.host_organization_name | American Geophysical Union |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310315809 |
| best_oa_location.source.host_organization_lineage_names | American Geophysical Union |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Earth and Space Science |
| best_oa_location.landing_page_url | https://doi.org/10.1029/2025ea004545 |
| primary_location.id | doi:10.1029/2025ea004545 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2764679394 |
| primary_location.source.issn | 2333-5084 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2333-5084 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Earth and Space Science |
| primary_location.source.host_organization | https://openalex.org/P4310315809 |
| primary_location.source.host_organization_name | American Geophysical Union |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310315809 |
| primary_location.source.host_organization_lineage_names | American Geophysical Union |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Earth and Space Science |
| primary_location.landing_page_url | https://doi.org/10.1029/2025ea004545 |
| publication_date | 2025-11-01 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W2961971513, https://openalex.org/W2060405276, https://openalex.org/W4405306574, https://openalex.org/W2111101932, https://openalex.org/W1994870724, https://openalex.org/W4362659713, https://openalex.org/W2073621729, https://openalex.org/W4392821114, https://openalex.org/W4234985135, https://openalex.org/W1990730786, https://openalex.org/W4402133569, https://openalex.org/W4405113495, https://openalex.org/W2790313440, https://openalex.org/W4243207591, https://openalex.org/W2102234201, https://openalex.org/W6893197477, https://openalex.org/W2974741142, https://openalex.org/W2047018904, https://openalex.org/W1980872241, https://openalex.org/W2021959819, https://openalex.org/W1968311195, https://openalex.org/W2968914048, https://openalex.org/W4317653900, https://openalex.org/W3088705535, https://openalex.org/W4405306560, https://openalex.org/W4399702641, https://openalex.org/W4401972859 |
| referenced_works_count | 27 |
| abstract_inverted_index., | 49, 53, 58, 81 |
| abstract_inverted_index.A | 100 |
| abstract_inverted_index.a | 5, 35 |
| abstract_inverted_index.(, | 71, 76, 89 |
| abstract_inverted_index.), | 72, 77, 90, 172 |
| abstract_inverted_index.14 | 187 |
| abstract_inverted_index.99 | 158 |
| abstract_inverted_index.as | 31, 118 |
| abstract_inverted_index.by | 18 |
| abstract_inverted_index.in | 34, 104, 176, 228 |
| abstract_inverted_index.m, | 161 |
| abstract_inverted_index.of | 68, 107, 157, 179, 201, 215, 222 |
| abstract_inverted_index.to | 91, 114, 126, 164 |
| abstract_inverted_index.167 | 160 |
| abstract_inverted_index.51% | 181 |
| abstract_inverted_index.and | 22, 61, 82, 85, 96, 121, 130, 148, 159, 182, 189, 210, 219, 225 |
| abstract_inverted_index.its | 105 |
| abstract_inverted_index.key | 101 |
| abstract_inverted_index.the | 19, 59, 66, 69, 198, 213, 220 |
| abstract_inverted_index.use | 106 |
| abstract_inverted_index.was | 135 |
| abstract_inverted_index.SHAP | 184 |
| abstract_inverted_index.This | 1 |
| abstract_inverted_index.both | 83, 93 |
| abstract_inverted_index.data | 12, 33, 131, 142, 224 |
| abstract_inverted_index.deep | 36 |
| abstract_inverted_index.east | 62 |
| abstract_inverted_index.four | 193 |
| abstract_inverted_index.from | 14, 65 |
| abstract_inverted_index.lies | 103 |
| abstract_inverted_index.over | 180 |
| abstract_inverted_index.such | 117 |
| abstract_inverted_index.this | 173 |
| abstract_inverted_index.well | 125 |
| abstract_inverted_index.with | 27, 151 |
| abstract_inverted_index.& | 168 |
| abstract_inverted_index.(DNN) | 39 |
| abstract_inverted_index.113%. | 183 |
| abstract_inverted_index.2024, | 170 |
| abstract_inverted_index.Model | 133 |
| abstract_inverted_index.Ocean | 23 |
| abstract_inverted_index.Water | 21 |
| abstract_inverted_index.error | 178 |
| abstract_inverted_index.forms | 57 |
| abstract_inverted_index.model | 8, 194 |
| abstract_inverted_index.north | 60 |
| abstract_inverted_index.paper | 2 |
| abstract_inverted_index.sets, | 143 |
| abstract_inverted_index.tests | 191 |
| abstract_inverted_index.their | 54, 73 |
| abstract_inverted_index.using | 10, 137, 192 |
| abstract_inverted_index.value | 200 |
| abstract_inverted_index.while | 123 |
| abstract_inverted_index.(SWOT) | 25 |
| abstract_inverted_index.across | 186 |
| abstract_inverted_index.global | 6, 145, 230 |
| abstract_inverted_index.inputs | 218 |
| abstract_inverted_index.neural | 37 |
| abstract_inverted_index.trends | 95 |
| abstract_inverted_index.(Harper | 167 |
| abstract_inverted_index.Surface | 20 |
| abstract_inverted_index.against | 140 |
| abstract_inverted_index.capture | 92 |
| abstract_inverted_index.derived | 13, 64 |
| abstract_inverted_index.further | 196 |
| abstract_inverted_index.gravity | 11, 47, 51, 88, 203 |
| abstract_inverted_index.inputs, | 45 |
| abstract_inverted_index.methods | 166 |
| abstract_inverted_index.network | 38 |
| abstract_inverted_index.regions | 188 |
| abstract_inverted_index.ridges, | 119 |
| abstract_inverted_index.serving | 30 |
| abstract_inverted_index.varying | 127 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.Compared | 163 |
| abstract_inverted_index.Overall, | 205 |
| abstract_inverted_index.ablation | 190 |
| abstract_inverted_index.adapting | 124 |
| abstract_inverted_index.analysis | 185 |
| abstract_inverted_index.assessed | 136 |
| abstract_inverted_index.enabling | 111 |
| abstract_inverted_index.enhanced | 112 |
| abstract_inverted_index.existing | 165 |
| abstract_inverted_index.filtered | 56, 79, 87 |
| abstract_inverted_index.mission, | 26 |
| abstract_inverted_index.multiple | 43 |
| abstract_inverted_index.presents | 3 |
| abstract_inverted_index.residual | 138, 154, 177 |
| abstract_inverted_index.seamount | 149 |
| abstract_inverted_index.standard | 155 |
| abstract_inverted_index.summits, | 150 |
| abstract_inverted_index.training | 32 |
| abstract_inverted_index.variants | 195 |
| abstract_inverted_index.versions | 75 |
| abstract_inverted_index.vertical | 50, 70 |
| abstract_inverted_index.BathDNN25 | 41, 152, 206 |
| abstract_inverted_index.Sandwell, | 169 |
| abstract_inverted_index.accuracy, | 208 |
| abstract_inverted_index.achieving | 153 |
| abstract_inverted_index.advancing | 229 |
| abstract_inverted_index.altimetry | 16 |
| abstract_inverted_index.anomalies | 48 |
| abstract_inverted_index.collected | 17 |
| abstract_inverted_index.confirmed | 197 |
| abstract_inverted_index.developed | 9 |
| abstract_inverted_index.features, | 110 |
| abstract_inverted_index.features. | 99, 204 |
| abstract_inverted_index.gradients | 52 |
| abstract_inverted_index.including | 46, 144 |
| abstract_inverted_index.modeling. | 232 |
| abstract_inverted_index.potential | 221 |
| abstract_inverted_index.shipborne | 28, 146 |
| abstract_inverted_index.soundings | 147 |
| abstract_inverted_index.sparsity. | 132 |
| abstract_inverted_index.BathDNN25, | 4 |
| abstract_inverted_index.Topography | 24 |
| abstract_inverted_index.artificial | 226 |
| abstract_inverted_index.bathymetry | 7, 29, 80 |
| abstract_inverted_index.complexity | 116 |
| abstract_inverted_index.components | 63 |
| abstract_inverted_index.conditions | 129 |
| abstract_inverted_index.deflection | 67 |
| abstract_inverted_index.deviations | 156 |
| abstract_inverted_index.framework. | 40 |
| abstract_inverted_index.geological | 128 |
| abstract_inverted_index.importance | 214 |
| abstract_inverted_index.innovation | 102 |
| abstract_inverted_index.integrates | 42 |
| abstract_inverted_index.low‐pass | 78, 84 |
| abstract_inverted_index.reductions | 175 |
| abstract_inverted_index.represents | 174 |
| abstract_inverted_index.seamounts, | 122 |
| abstract_inverted_index.statistics | 139 |
| abstract_inverted_index.band‐pass | 55, 74, 86 |
| abstract_inverted_index.bathymetric | 98, 231 |
| abstract_inverted_index.geophysical | 44, 109, 217 |
| abstract_inverted_index.independent | 141 |
| abstract_inverted_index.performance | 134 |
| abstract_inverted_index.robustness, | 209 |
| abstract_inverted_index.sensitivity | 113 |
| abstract_inverted_index.demonstrates | 207 |
| abstract_inverted_index.escarpments, | 120 |
| abstract_inverted_index.fine‐scale | 97 |
| abstract_inverted_index.intelligence | 227 |
| abstract_inverted_index.scalability, | 211 |
| abstract_inverted_index.underscoring | 212 |
| abstract_inverted_index.wide‐swath | 15 |
| abstract_inverted_index.complementary | 199 |
| abstract_inverted_index.large‐scale | 94 |
| abstract_inverted_index.morphological | 115 |
| abstract_inverted_index.multi‐scale | 108 |
| abstract_inverted_index.respectively. | 162 |
| abstract_inverted_index.SWOT‐derived | 202, 223 |
| abstract_inverted_index.high‐quality | 216 |
| abstract_inverted_index.https://doi.org/10.1029/2023ea003199 | 171 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |