Abstract
Sand waves constitute ubiquitous geomorphology distribution in the ocean. In this paper, we quantitatively investigate the sand wave variation of topology, morphology, and evolution from the high-resolution mapping of a side scan sonar (SSS) in an Autonomous Underwater Vehicle (AUV), in favor of online sequential Extreme Learning Machine (OS-ELM). We utilize echo intensity directly derived from SSS to help accelerate detection and localization, denote a collection of Gaussian-type morphological templates, with one integrated matching criterion for similarity assessment, discuss the envelope demodulation, zero-crossing rate (ZCR), cross-correlation statistically, and estimate the specific morphological parameters. It is demonstrated that the sand wave detection rate could reach up to 95.61% averagely, comparable to deep learning such as MobileNet, but at a much higher speed, with the average test time of 0.0018 s, which is particularly superior for sand waves at smaller scales. The calculation of morphological parameters primarily infer a wave length range and composition ratio in all types of sand waves, implying the possible dominant direction of hydrodynamics. The proposed scheme permits to delicately and adaptively explore the submarine geomorphology of sand waves with online computation strategies and symmetrically integrate evidence of its spatio-temporal responses during formation and migration.
Highlights
The submarine sand wave, one type of ubiquitous geomorphology distributed widely in the ocean, is highly correlative with multivariate marine environmental factors in their formation and migration process [1,2,3,4]
Where (vi + vi+1)∆ti/2 refers to the actual distance of Autonomous Underwater Vehicle (AUV) in the along-track directions, and w/2Rs represents the mapping coefficient between the width of the echo intensity and the actual across-track distance in the seabed, ∆ti is the time difference between the ith ping and the (i+1)th ping that the side scan sonar (SSS) receives echoes, vi is the instantaneous sailing speed of AUV in the ith ping, vi+1 is the instantaneous speed of AUV in the (i+1)th ping, Rs is the slant length of the sonar, w is the width of echo intensity in the ith ping
We statistically investigate the envelope demodulation, zero-crossing rate (ZCR) spectrum, and cross-correlation coefficients to examine the high variability of sand waves regarding their size, shape, and spacing and further potentially estimate the specific morphological parameters, including wave length, wave height, and asymmetric index, by means of echo intensity in the SSS profile
Summary
The submarine sand wave, one type of ubiquitous geomorphology distributed widely in the ocean, is highly correlative with multivariate marine environmental factors in their formation and migration process [1,2,3,4]. In this paper, starting from the inspiration to quantitatively investigate the geomorphology in sand wave profiles along a AUV’s track, we directly extract the echo intensity of each ping from SSS imaging through time varying gain (TVG) correction, speed correction, blind zone removal, and ensemble empirical mode decomposition (EEMD) denoising to compensate the frequent motion variation in an AUV as well as the noise interference, energy attenuation, and multi-path effects over time. Both ELM learning and some classical approaches have been jointly employed and aim to potentially provide a mutually reinforcing and complementary, related solution. The basic parameters describing the morphological characteristics of sand waves will be elaborately discussed and finely grained in the study region, with the help of the statistics in the envelope demodulation, zero-crossing rate (ZCR) spectrum, and the cross-correlation coefficient; and the specific morphological parameters, including wave length, wave height, asymmetric index, will be further estimated, so as to explore the topology, morphology, and evolution in sand waves at a higher resolution with online computation strategies and provide insights into the spatial-temporal evidence in the formation and migration process
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
