Dynamic Nautical Chart Depth Contours Generation Based on Super-Resolution DEM and Real-Time Water Level Interaction&nbsp;

PDF(12848 KB)

Journal of Dalian Maritime University ›› 2026, Vol. 52 ›› Issue (1) : 12-20.

Dynamic Nautical Chart Depth Contours Generation Based on Super-Resolution DEM and Real-Time Water Level Interaction

LI Zhi-hao¹, PAN Ming-yang^1*, LI Shao-xi¹, WANG Mo², HU Jing-feng¹, HAO Jiang-ling¹, ZHANG Ruo-lan¹

Author information +

History +

Abstract

The IHO S-98 standard defines the interoperability between electronic navigational charts (ENCs) and multi-source hydrographic data as a future application trend. This study aims to explore intelligent techniques for generating dynamic depth contours by integrating ENC products with real-time water level data. In scenarios where S-102 bathymetric surface data are incomplete, the sparse depth data contained in ENC products are insufficient to directly support high-reliability dynamic depth computations. To address this limitation, we propose a deep learning-based super-resolution solution. Specifically, an improved TSE-EDSR model is employed to reconstruct a high-fidelity digital elevation model (DEM) of the seabed from sparse chart soundings. By further integrating real-time water level data, dynamic depth contours are generated. Experimental results demonstrate that the proposed method produces DEMs and dynamic depth contours with significantly higher accuracy and morphological authenticity compared to traditional interpolation approaches. This work provides technical support for S-98 interoperability applications and holds substantial theoretical and practical value for advancing the development and application of next-generation electronic navigational charts.

Key words

Depth Contours / Electronic Navigational Chart (ENC) / Deep Learning / Super-Resolution / Digital Elevation Model (DEM)

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LI Zhi-hao, PAN Ming-yang, LI Shao-xi, WANG Mo, HU Jing-feng, HAO Jiang-ling, ZHANG Ruo-lan. Dynamic Nautical Chart Depth Contours Generation Based on Super-Resolution DEM and Real-Time Water Level Interaction [J]. Journal of Dalian Maritime University. 2026, 52(1): 12-20

References

[1]惠大涛,王如政,白亭颖,等.一种面向海图生产的等深线及深度区生成方法研究[J].测绘与空间地理信息,2025,48(05):163-166.

HUI D T, WANG R Z, BAI T Y, et al. Research on a generation method of isobaths and depth areas for nautical chart production[J]. Geomatics and Spatial Information Technology, 2025, 48(05):163-166.(in Chinese)

[2]缪锦根,白亭颖,姜悦,等.数字化浪潮下的海图转型：从纸质到电子的演变[J].中国海事,2025,(02):21-26.DOI:10.16831/j.cnki.issn1673-2278.2025.02.006.

MIAO J G, BAI T Y, JIANG Y, et al. Transformation of nautical charts in the digital wave: Evolution from paper to electronic[J]. China Maritime, 2025,(02):21-26. (in Chinese)

[3]International Hydrographic Organization. S-98: Data Product Interoperability in S-100 Navigation SystemsSSS. Edition 1.0.0, 2021.

[4]ZHANG Y F, YU W H. Comparison of DEM super-resolution methods based on interpolation and neural networks[J]. Sensors, 2022, 22(3): 745.

[5]CHEN Z X, WANG X W, XU Z K, et al. Convolutional neural network based dem super resolution[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, 41: 247-250.

[6]XU Z K, ChEN Z X, YI W W, et al. Deep gradient prior network for DEM super-resolution: Transfer learning from image to DEM[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150: 80-90.

[7]LI Z J, MI D Y, LI C H, et al. EF-TSR: edge feature transformer-based DEM super-resolution network[J]. Remote Sensing Letters, 2025, 16(4): 389-399.

[8]LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]//Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2017: 136-144.

[9]LIANG J Y, CAO J Z, SUN G L, et al. Swinir: Image restoration using swin transformer[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 1833-1844.

[10]CHEN X Y, WANG X T, ZHANG W L, et al. Hat: Hybrid attention transformer for image restoration[J]. arXiv preprint arXiv:2309.05239, 2023.

[11]JIAO D L, WANG D J, LV H Y, et al. Super-resolution reconstruction of a digital elevation model based on a deep residual network[J]. Open Geosciences, 2020, 12(1): 1369-1382.

[12]HU J, LI S, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.

[13]ZHANG Y J, ZHENG Z, LUO Y M, et al. A CNN-based subpixel level DSM generation approach via single image super-resolution[J]. Photogrammetric Engineering & Remote Sensing, 2019, 85(10): 765-775.

[14]HANIN B. Universal function approximation by deep neural nets with bounded width and relu activations[J]. Mathematics, 2019, 7(10): 992.

[15]WU Z, MA P F. ESRGAN-based DEM super-resolution for enhanced slope deformation monitoring in lantau island of Hong Kong[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020, 43: 351-356.

[16]ZHAO H, GALLO O, FROSIO I, et al. Loss functions for image restoration with neural networks[J]. IEEE Transactions on computational imaging, 2016, 3(1): 47-57.

[17]International Hydrographic Organization. S-104: Water Level Information for Surface NavigationSSS. Edition 1.0.0, 2021.

[18]LOSHCHILOV I, HUTTER F. Sgdr: Stochastic gradient descent with warm restarts[J]. arXiv preprint arXiv:1608.03983, 2016.

[19]REUTER H, NELSON A, JARVIS A. An evaluation of void‐filling interpolation methods for SRTM data[J]. International Journal of Geographical Information Science, 2007, 21(9): 983-1008.