Integrating modeled environmental variability into neural network training for underwater source localization.

Supervised machine learning (ML) is a powerful tool that has been applied to many fields of underwater acoustics, including acoustic inversion. ML algorithms depend on the existence of extensive labeled datasets, which are difficult to obtain for the task of underwater source localization. A feed-forward neural network (FNN) trained on imbalanced or biased data may end up suffering from a problem analogous to model mismatch in matched field processing (MFP), that is, producing incorrect results due to a difference between the environment sampled by the training data and the actual environment. To overcome this issue, physical and numerical propagation models can act as data augmentation tools to compensate for the lack of comprehensive acoustic data. This paper examines how modeled data can be effectively used for training FNNs. Mismatch tests compare the output from a FNN and MFP and show that the network becomes more robust to various kinds of mismatches when trained on diverse environments. A systematic analysis of how the training dataset's variability impacts a FNN's localization performance on experimental data is carried out. Results show that networks trained with synthetic data achieve better and more robust performance than regular MFP when environment variability is taken into account.

Simplex based three-dimensional eigenray search for underwater predictions.

A solution for the calculation of three-dimensional (3D) eigenrays based on Simplex optimization, implemented in a 3D Gaussian beam model, is investigated in this paper. The validation and performance of the solution were analyzed through comparisons against an equivalent (flat) two-dimensional waveguide, and against results of a tank scale experiment presented in Sturm and Korakas [(2013). J. Acoust. Soc. Am. 133(1), 108-118], in which cross-slope propagation in a wedge waveguide with a mild slope was considered. It was found that the search strategy based on Simplex optimization was able to calculate efficiently and accurately 3D eigenrays, thus providing predictions of arrival patterns along cross-slope range, which replicated elaborate patterns of mode shadow zones, intra-mode interference, and mode arrivals. A remarkable aspect of the search strategy was its ability to provide accurate values of initial eigenray elevation and azimuth, within the accuracy defined for the eigenray to arrive at the location of a given hydrophone.