Underwater acoustic echosounding for surface roughness parameters retrieval is studied in a frequency band that is relatively new for such purposes. During the described 2-weeks sea experiment, 1–3 kHz tonal pulses were emitted from an oceanographic platform, located on the northern Black Sea shelf. Doppler spectra of the resulting reverberation were studied. The frequency band of the acoustic system, selected for this study, is chosen due to the fact that the sound propagation range is large enough for remote sensing in a coastal zone, and the resolution cell size does not limit the research. Backscattering of acoustical signals was received for distances around two nautical miles. However, it turned to be quite difficult to interpret the obtained data since backscattering spectrum shape was influenced by a series of effects, resulting in a complicated link to wind waves and currents’ parameters. Significant wave height and dominant wave frequency were estimated as the result of such signals processed with the use of machine learning tools. A decision-tree-based mathematical regression model was trained to solve the inverse problem. Wind waves prediction is in a good agreement with direct measurements, made on the platform, and machine learning results allow physical interpretation.

This paper is devoted to an acoustical method of measuring mesoscale sea and ocean currents. Due to the fact that such currents exhibit variability, long-term studies are of great interest. The aim of this study is to prepare a physical foundation to organize current measurements in an automated way using stationary mounted underwater echosounding systems. An acoustic system operating at a frequency of 1–3 kHz (lower than commercial frequencies) that is capable of sensing echo signals from natural inhomogeneities located at distances of 1 to 10 km was tested. The test was conducted during a two-week marine experiment on the northern shelf of the Black Sea. The acoustic system was mounted on a platform together with a weather station and other tools that provided reference values for further comparison. Scattering from moving particles, as well as from wind waves, provides a general opportunity for sensing of currents at remote points. Since most scatterers exist at a depth of at least 2 m or on the surface, the proposed sensing method is going specialized for currents in upper layers. However, analysis of Doppler spectra of the actual returning (reverberation) signal showed that this kind of scattering was mixed with bottom reverberation (which contains no additional frequency shift), and other signal distortions were present. Thus, we proposed a new method of signal processing that is aware of the regional environment. The described method is based on machine learning, namely on gradient boosting to build decision trees, which compute water current properties. Such a computational routine is preceded by an original acoustic signal feature extraction process. Finally, a precision of an order of magnitude was achieved, and a sensing distance of at least 2 km was proven as a result of this study carried out with available instruments.