Articles | Volume 17, issue 1
https://doi.org/10.5194/essd-17-165-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/essd-17-165-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
SDUST2023BCO: a global seafloor model determined from a multi-layer perceptron neural network using multi-source differential marine geodetic data
Shuai Zhou
College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
State Key Laboratory of Geodesy and Earth's Dynamics, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan 430077, China
College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
Huiying Zhang
College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
Yongjun Jia
National Satellite Ocean Application Service, Ministry of Natural Resources, Beijing 100812, China
Heping Sun
State Key Laboratory of Geodesy and Earth's Dynamics, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan 430077, China
Xin Liu
College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
Dechao An
School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai 519082, China
Related authors
No articles found.
Yixiang Liu, Jinyun Guo, Bin Guan, Shaofeng Bian, Heping Sun, and Xin Liu
EGUsphere, https://doi.org/10.5194/egusphere-2025-2585, https://doi.org/10.5194/egusphere-2025-2585, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
This study refines the coastal gravity anomaly model by constructing a residual terrain model using high-resolution topographic and bathymetric data. In the spatial domain, the RTM (residual terrain model) gravity forward modeling method is applied to effectively compensate for the missing high-frequency information in the XGM2019e-2159 gravity anomaly model. As a result, an RTM-corrected XGM2019e-2159 gravity anomaly model for the study area is obtained.
Yong Wang, Shengjun Zhang, and Yongjun Jia
Ocean Sci., 21, 931–944, https://doi.org/10.5194/os-21-931-2025, https://doi.org/10.5194/os-21-931-2025, 2025
Short summary
Short summary
The distance-weighted averaging method was used to calculate the along-orbit sea surface height (SSH) wavenumber spectra of four satellites and to evaluate the along-track resolution capability of the four satellites. The results show that the resolution of Surface Water and Ocean Topography (SWOT) in the Kuroshio region is 25 km, which is twice the resolution of conventional satellites. A parameter was defined using the cross-power-spectrum approach and used to analyse the global ocean.
Ruichen Zhou, Jinyun Guo, Shaoshuai Ya, Heping Sun, and Xin Liu
Earth Syst. Sci. Data, 17, 817–836, https://doi.org/10.5194/essd-17-817-2025, https://doi.org/10.5194/essd-17-817-2025, 2025
Short summary
Short summary
SDUST2023VGGA is a high-resolution (1' × 1') model developed to map the ocean's vertical gradient of gravity anomaly. By using multidirectional mean sea surface data, it reduces the impact of ocean dynamics and provides detailed global gravity anomaly change rates. This model provides critical insights into seafloor structures and ocean mass distribution, contributing to research in marine geophysics and oceanography. The dataset is freely available on Zenodo.
Shengjun Zhang, Xu Chen, Runsheng Zhou, and Yongjun Jia
Geosci. Model Dev., 18, 1221–1239, https://doi.org/10.5194/gmd-18-1221-2025, https://doi.org/10.5194/gmd-18-1221-2025, 2025
Short summary
Short summary
NSOAS24, a new global marine gravity model derived from multi-satellite altimetry missions, represents a significant advancement over its predecessor, NSOAS22. Through optimized processing procedures, NSOAS24 resolves previous issues and demonstrates improved accuracy. Compared to NSOAS22, NSOAS24 shows a reduction of approximately 0.7 mGal in standard deviation when validated against recent shipborne data. Notably, its accuracy now rivals internationally recognized models DTU21 and V32.1.
Xin Liu, Yang Yang, Menghao Song, Xiaofeng Dai, Yurong Ding, Gaoying Yin, and Jinyun Guo
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2025-2, https://doi.org/10.5194/essd-2025-2, 2025
Revised manuscript not accepted
Short summary
Short summary
This study tackles the challenge of measuring sea surface height in the Arctic Ocean, where ice coverage makes accurate modeling difficult. Using advanced satellite data and innovative methods, a new high-resolution mean sea surface model was created. It achieves greater precision than previous models and offers valuable insights into Arctic oceanography. This research provides an important tool for understanding changes in the Arctic environment and their global impacts.
Zhen Li, Jinyun Guo, Chengcheng Zhu, Xin Liu, Cheinway Hwang, Sergey Lebedev, Xiaotao Chang, Anatoly Soloviev, and Heping Sun
Earth Syst. Sci. Data, 16, 4119–4135, https://doi.org/10.5194/essd-16-4119-2024, https://doi.org/10.5194/essd-16-4119-2024, 2024
Short summary
Short summary
A new global marine gravity model, SDUST2022GRA, is recovered from radar and laser altimeter data. The accuracy of SDUST2022GRA is 4.43 mGal on a global scale, which is at least 0.22 mGal better than that of other models. The spatial resolution of SDUST2022GRA is approximately 20 km in a certain region, slightly superior to other models. These assessments suggest that SDUST2022GRA is a reliable global marine gravity anomaly model.
Fengshun Zhu, Jinyun Guo, Huiying Zhang, Lingyong Huang, Heping Sun, and Xin Liu
Earth Syst. Sci. Data, 16, 2281–2296, https://doi.org/10.5194/essd-16-2281-2024, https://doi.org/10.5194/essd-16-2281-2024, 2024
Short summary
Short summary
We used multi-satellite altimeter data to construct a high-resolution marine gravity change rate (MGCR) model on 5′×5′ grids, named SDUST2020MGCR. The spatial distribution of SDUST2020MGCR and GRACE MGCR are similar, such as in the eastern seas of Japan (dipole), western seas of the Nicobar Islands (rising), and southern seas of Greenland (falling). The SDUST2020MGCR can provide a detailed view of long-term marine gravity change, which will help to study the seawater mass migration.
Dechao An, Jinyun Guo, Xiaotao Chang, Zhenming Wang, Yongjun Jia, Xin Liu, Valery Bondur, and Heping Sun
Geosci. Model Dev., 17, 2039–2052, https://doi.org/10.5194/gmd-17-2039-2024, https://doi.org/10.5194/gmd-17-2039-2024, 2024
Short summary
Short summary
Seafloor topography, as fundamental geoinformation in marine surveying and mapping, plays a crucial role in numerous scientific studies. In this paper, we focus on constructing a high-precision seafloor topography and bathymetry model for the Philippine Sea (5° N–35° N, 120° E–150° E), based on shipborne bathymetric data and marine gravity anomalies, and evaluate the reliability of the model's accuracy.
Zhaoqing Dong, Lijian Shi, Mingsen Lin, Yongjun Jia, Tao Zeng, and Suhui Wu
The Cryosphere, 17, 1389–1410, https://doi.org/10.5194/tc-17-1389-2023, https://doi.org/10.5194/tc-17-1389-2023, 2023
Short summary
Short summary
We try to explore the application of SGDR data in polar sea ice thickness. Through this study, we find that it seems difficult to obtain reasonable results by using conventional methods. So we use the 15 lowest points per 25 km to estimate SSHA to retrieve more reasonable Arctic radar freeboard and thickness. This study also provides reference for reprocessing L1 data. We will release products that are more reasonable and suitable for polar sea ice thickness retrieval to better evaluate HY-2B.
Jiajia Yuan, Jinyun Guo, Chengcheng Zhu, Zhen Li, Xin Liu, and Jinyao Gao
Earth Syst. Sci. Data, 15, 155–169, https://doi.org/10.5194/essd-15-155-2023, https://doi.org/10.5194/essd-15-155-2023, 2023
Short summary
Short summary
The mean sea surface (MSS) is a relative steady-state sea level within a finite period with important applications in geodesy, oceanography, and other disciplines. In this study, the Shandong University of Science and Technology 2020 (SDUST2020), a new global MSS model, was established with a 19-year moving average method from multi-satellite altimetry data. Its global coverage is from 80 °S to 84 °N, the grid size is 1'×1', and the reference period is from January 1993 to December 2019.
Chengcheng Zhu, Jinyun Guo, Jiajia Yuan, Zhen Li, Xin Liu, and Jinyao Gao
Earth Syst. Sci. Data, 14, 4589–4606, https://doi.org/10.5194/essd-14-4589-2022, https://doi.org/10.5194/essd-14-4589-2022, 2022
Short summary
Short summary
Accurate marine gravity anomalies play an important role in the fields of submarine topography, Earth structure, and submarine exploitation. With the launch of different altimetry satellites, the density of altimeter data can meet the requirements of inversion of high-resolution and high-precision gravity anomaly models. We construct the global marine gravity anomaly model (SDUST2021GRA) from altimeter data (including HY-2A). The accuracy of the model is high, especially in the offshore area.
Cited articles
An, D., Guo, J., Li, Z., Ji, B., Liu, X., and Chang, X.: Improved gravity-geologic method reliably removing the long-wavelength gravity effect of regional seafloor topography: A case of bathymetric prediction in the South China Sea, IEEE T. Geosci. Remote, 60, 4211912, https://doi.org/10.1109/TGRS.2022.3223047, 2022.
An, D., Guo, J., Chang, X., Wang, Z., Jia, Y., Liu, X., Bondur, V., and Sun, H.: High-precision 1′ × 1′ bathymetric model of Philippine Sea inversed from marine gravity anomalies, Geosci. Model Dev., 17, 2039–2052, https://doi.org/10.5194/gmd-17-2039-2024, 2024.
Annan, R. F. and Wan, X.: Mapping seafloor topography of Gulf of Guinea using an adaptive meshed gravity-geologic method, Arab. J. Geosci., 13, 301, https://doi.org/10.1007/s12517-020-05297-8, 2020.
Fan, D., Li, S., Meng, S., Lin, Y., Xing, Z., Zhang, C., Yang, J., Wan, X., and Qu, Z.: Applying iterative method to solving high-order terms of seafloor topography, Mar. Geod., 43, 63–85, https://doi.org/10.1080/01490419.2019.1670298, 2020.
Hirt, C. and Rexer, M.: Earth2014: 1 arc-min shape, topography, bedrock and ice-sheet models – Available as gridded data and degree-10,800 spherical harmonics, Int. J. Appl. Earth Obs., 39, 103–112, https://doi.org/10.1016/j.jag.2015.03.001, 2015.
Hu, M., Li, J., Li, H., and Xin, L.: Bathymetry predicted from vertical gravity gradient anomalies and ship soundings, Geod. Geodyn., 5, 41–46, https://doi.org/10.3724/SP.J.1246.2014.01041, 2014.
Hu, M., Li, J., Li, H., and Shen, C.: A program for bathymetry prediction from vertical gravity gradient anomalies and ship soundings, Arab. J. Geosci., 8, 4509–4515, https://doi.org/10.1007/s12517-014-1570-0, 2015.
Hu, M., Li, L., Jin, T., Jiang, W., Wen, H., and Li, J.: A new 1′ × 1′ global seafloor topography model predicted from satellite altimetric vertical gravity gradient anomaly and ship soundings BAT_VGG2021, Remote Sens., 13, 3515, https://doi.org/10.3390/rs13173515, 2021.
Hu, Q., Huang, X., Zhang, Z., Zhang, X., Xu, X., Sun, H., Zhou, C., Zhao, W., and Tian, J.: Cascade of internal wave energy catalyzed by eddy-topography interactions in the deep South China Sea, Geophys. Res. Lett., 47, e2019GL086510, https://doi.org/10.1029/2019GL086510, 2020.
Jin, X., Guo, J., Shen, Y., Liu, X., and Zhao, C. M.: Application of singular spectrum analysis and multilayer perceptron in the mid-long-term polar motion prediction, Adv. Space Res., 68, 3562–3573, https://doi.org/10.1016/j.asr.2021.06.039, 2021.
Kim, J. W., von Frese, R. R. B., Lee, B. Y., Roman, D. R., and Doh, S.: Altimetry-derived gravity predictions of bathymetry by the gravity-geologic method, Pure Appl. Geophy., 168, 815–826, https://doi.org/10.1007/s00024-010-0170-5, 2011.
Kuremoto, T., Kimura, S., Kobayashi, K., and Obayashi, M.: Time series forecasting using a deep belief network with restricted Boltzmann machines, Neurocomputing, 137, 47–56, https://doi.org/10.1016/j.neucom.2013.03.047, 2014.
Kuster, G. T. and Toksoz, M. N.: Velocity and attenuation of seismic waves in two-phase media: Part I. Theoretical formulations, Geophysics, 39, 587–606, https://doi.org/10.1190/1.1440450, 1974.
Lee, S., Mohr, N. M., Street, W. N., and Nadkarni, P.: Machine learning in relation to emergency medicine clinical and operational scenarios: an overview, West. J. Emerg. Med., 20, 219–227, https://doi.org/10.5811/westjem.2019.1.41244, 2019.
Li, Z., Guo, J., Zhu, G., Liu, X., Hwang, C., Lebedev, S., Chang, X., Soloviev, A., and Sun, H.: The global marine free air gravity anomaly model SDUST2022GRA, Zenodo [data set], https://doi.org/10.5281/zenodo.8337387, 2023.
Li, Z., Guo, J., Zhu, C., Liu, X., Hwang, C., Lebedev, S., Chang, X., Soloviev, A., and Sun, H.: The SDUST2022GRA global marine gravity anomalies recovered from radar and laser altimeter data: contribution of ICESat-2 laser altimetry, Earth Syst. Sci. Data, 16, 4119–4135, https://doi.org/10.5194/essd-16-4119-2024, 2024.
Marks, K. M. and Smith, W. H. F.: Radially symmetric coherence between satellite gravity and multibeam bathymetry grids, Mar. Geophys. Res., 33, 223–227, https://doi.org/10.1007/s11001-012-9157-1, 2012.
Mulet, S., Rio, M.-H., Etienne, H., Artana, C., Cancet, M., Dibarboure, G., Feng, H., Husson, R., Picot, N., Provost, C., and Strub, P. T.: The new CNES-CLS18 global mean dynamic topography, Ocean Sci., 17, 789–808, https://doi.org/10.5194/os-17-789-2021, 2021.
Pujol, M., Schaeffer, P., Faugère, Y., Raynal, M., Dibarboure, G., and Picot, N.: Gauging the improvement of recent mean sea surface models: a new approach for identifying and quantifying their errors, J. Geophys. Res.-Oceans, 123, 5889–5911, https://doi.org/10.1029/2017JC013503, 2018.
Ramillien, G. and Wright, I. C.: Predicted seafloor topography of the New Zealand region: A nonlinear least squares inversion of satellite altimetry data, J. Geophys. Res.-Sol. Ea., 105, 16577–16590, https://doi.org/10.1029/2000JB900099, 2000.
Sandwell, D. T., Goff, J. A., Gevorgian, J., Harper, H., Kim, S., Yu, Y., Tozer, B., Wessel, P., and Smith, W. H. F.: Improved bathymetric prediction using geological information: SYNBATH, Earth Space Sci., 9, e2021EA002069, https://doi.org/10.1029/2021EA002069, 2022.
Smith, W. H. F. and Sandwell D. T.: Global sea floor topography from satellite altimetry and ship depth soundings, Science, 277, 1956–1962, https://doi.org/10.1126/science.277.5334.1956, 1997.
Sun, Y., Zheng, W., Li, Z., and Zhou, Z.: Improved the accuracy of seafloor topography from altimetry-derived gravity by the topography constraint factor weight optimization method, Remote Sens., 13, 2277, https://doi.org/10.3390/rs13122277, 2021.
Sun, Y., Zheng, W., Li, Z., Zhou, Z., Zhou, X., and Wen, Z.: Improving the accuracy of bathymetry using the combined neural network and gravity wavelet decomposition method with altimetry derived gravity data, Mar. Geod., 46, 271–302, https://doi.org/10.1080/01490419.2023.2179140, 2023.
Sunil, M., Pallikkavaliyaveetil, N., Mithun, N., Gopinath, A., Chidangil, S., Kumar, S., and Lukose, J.: Machine learning assisted Raman spectroscopy: A viable approach for the detection of microplastics. J. Water Process Eng., 60, 105150, https://doi.org/10.1016/j.jwpe.2024.105150, 2024.
Wang, Y.: Predicting bathymetry from the Earth's Gravity Gradient Anomalies, Mar. Geod., 23, 251–258, https://doi.org/10.1080/01490410050210508, 2000.
Woodworth, P. L., Gravelle, M., Marcos, M., Guy, W., and Hughes, C. W.: The status of measurement of the mediterranean mean dynamic topography by geodetic techniques, J. Geodesy, 89, 811–827, https://doi.org/10.1007/s00190-015-0817-1, 2015.
Xing, J., Chen, X. X., and Ma, L.: Bathymetry inversion using the modified gravity-geologic method: application of the rectangular prism model and Tikhonov regularization, Appl. Geophys., 17, 377–389, https://doi.org/10.1007/s11770-020-0821-y, 2020.
Yang, J., Jekeli, C., and Liu, L.: Seafloor topography estimation from gravity gradients using simulated annealing, J. Geophys. Res.-Sol. Ea., 123, 6958–6975, https://doi.org/10.1029/2018JB015883, 2018.
Yeu, Y., Yee, J., Yun, H. S., and Kim K. B.: Evaluation of the accuracy of bathymetry on the nearshore coastlines of western Korea from satellite altimetry, multi-beam, and airborne bathymetric LiDAR, Sensors, 18, 2926, https://doi.org/10.3390/s18092926, 2018.
Zhou, S., Liu, X., Guo, J., Jin, X., Yang, L., Sun, Y., and Sun, H.: Bathymetry of the Gulf of Mexico predicted with multilayer perceptron from multisource marine geodetic data. IEEE T. Geosci. Remote, 61, 4208911, https://doi.org/10.1109/TGRS.2023.3328035, 2023.
Zhou, S., Guo, J., Zhang, H., Jia, Y., Bian, S., Sun, H., Liu, X., and An, D.: SDUST2023BCO: a global seafloor model determined from multi-layer perceptron neural network using multi-source differential marine geodetic data, Zenodo [data set], https://doi.org/10.5281/zenodo.13341896, 2024.
Zhu, C., Guo, J., Yuan, J., Jin, X., Gao, J., and Li, C.: Refining altimeter-derived gravity anomaly model from shipborne gravity by Multi-Layer Perceptron Neural Network: A case in the South China Sea, Remote Sens., 13, 607, https://doi.org/10.3390/rs13040607, 2021.
Zhu, C., Yang, L., Bian, H., Li, H., Guo, J., Liu, N., and Lin, L.: Recovering gravity from satellite altimetry data using deep learning network. IEEE T. Geosci. Remote, 61, 5911311, https://doi.org/10.1109/TGRS.2023.3280261, 2023.
Short summary
Our research focuses on using machine learning to enhance the accuracy and efficiency of bathymetric models. In this paper, a multi-layer perceptron (MLP) neural network is used to integrate multi-source marine geodetic data. And a new bathymetric model of the global ocean, spanning 0–360° E and 80° S–80° N, known as the Shandong University of Science and Technology 2023 Bathymetric Chart of the Oceans (SDUST2023BCO), has been constructed, with a grid size of 1′ × 1′.
Our research focuses on using machine learning to enhance the accuracy and efficiency of...
Altmetrics
Final-revised paper
Preprint