Abstract
Seafloor mapping to create bathymetric charts of the oceans is important for various applications. However, making high-resolution bathymetric charts requires measuring underwater depths at many points in sea areas, and thus, is time-consuming and costly. In this work, treating gridded bathymetric data as digital images, we employ the image-processing technique known as superresolution to enhance the resolution of bathymetric charts by estimating high-resolution images from low-resolution ones. Specifically, we use the recently-developed deep-learning methodology to automatically learn the geometric features of ocean floors and recover their details. Through an experiment using bathymetric data around Japan, we confirmed that the proposed method outperforms naive interpolation both qualitatively and quantitatively, observing an eight-dB average improvement in peak signal-to-noise ratio. Deep-learning-based bathymetric image superresolution can significantly reduce the number of sea areas or points that must be measured, thereby accelerating the detailed mapping of the seafloor and the creation of high-resolution bathymetric charts around the globe.
Highlights
Bathymetric charts of the oceans describe the underwater depths of ocean floors
We used General Bathymetric Chart of the Oceans (GEBCO) 2014 and 2019 data, whose resolutions are 30 arc-seconds and 15 arc-seconds, as low-resolution input and high-resolution output images, respectively. From these two sets of data, we first cropped corresponding sea areas with no overlaps around Japan, each of which is a square with sides of length 3,840 arc-seconds in latitude or longitude; here, each area was cropped only if it resided within the range between (N 20;25;31, E 122;55;57) and (N 45;33;26, E 153;59;12), with its corners’ latitudes and longitudes being powers of 3,840 arc-seconds, and contained no lands in both of the low- and high-resolution sets
Note that we used GEBCO data based on real measurement for both high-resolution outputs and low-resolution inputs; this is different from the standard experimental scheme in learningbased image superresolution [8], where artificially downsampled versions of high-resolution images are used as low-resolution images, which might have different statistical properties from real observations
Summary
Bathymetric charts of the oceans describe the underwater depths of ocean floors. Today, they have a wide range of applications, e.g., ship navigation, submarine infrastructure (e.g., pipeline and cable) construction, fishery resource protection, seabed resource (e.g., mineral, oil, and gas) exploration, and seismic hazard (e.g., earthquake and tsunami) assessment. The General Bathymetric Chart of the Oceans (GEBCO) project [1] has been attempting to create global terrain models of the oceans and lands for more than 100 years. According to the Seabed 2030 project [2], whose aim is to integrate all available bathymetric data into an improved global seafloor map, more than 80 percent of the seafloor is yet to be mapped.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
