A ray approach is used to simulate subcritical scattering from a buried target at low-to-high frequencies (100 Hz–15 kHz). A penetrating wave at a subcritical angle decays along the depth at the bottom (i.e., evanescent wave) and propagates horizontally at a subcritical angle-dependent speed lower than the sound speed of the bottom. The corresponding target strength (TS) is distinguished from that of a standard plane wave. Its pattern is asymmetric by the evanescent wave including for symmetric targets and is more complicated owing to the higher wavenumber induced by the lower speed of the evanescent wave. A scattered signal is simulated by considering the features of the penetrating wave with the TS and then verified using the finite element method. In the ray approach, once the TS is computed, a scattered field is efficiently derived with low computational complexity. Strong peaks are observed in the scattered signal via mid-frequency enhancement; however, their amplitudes are less than those yielded by the free-field target owing to the more diminished penetrating waves at higher frequencies. The peaks indicate the possibility of detecting the buried target using a receiver near the target (bistatic sonar) with a broadband source signal that includes low-to-mid frequencies.

Artificial Intelligence (AI) is widely used in various fields, but obtaining sufficient underwater acoustic data for AI training remains challenging. Even if simulation data are used for training, the classification accuracy could be lowered due to changes in the environment around the target. This study presents the research findings on training neural networks for target classification using data generated through simulations. We trained neural networks using target scattering signals obtained through finite element analysis for various environments. Subsequently, we utilized trained neural networks to classify the spherical shells on the seabed acquired in water tank experiments. To solve the problem of lack of data for AI training, we generated training data by applying realistic variations of parameters such as sound speed of water, target material properties, and thickness. Such training data provide more meaningful information than noise-added data. The targets considered were spherical shells with and without internal spaces. Although the target classification accuracy is not yet high enough, it is expected to be used to overcome the lack of data by applying to untrained targets. [Work supported by KIMST funded by the Agency of Korea Coast Guard (KIMST-20210547) and by KRISO funded by Ministry of Oceans and Fisheries (PES4380).]