Testing transfer learning for source ranging in a laboratory tank

Abstract

One difficulty in applying deep learning techniques to ocean acoustics is the spatially and temporally varying environmental properties. Another challenge is the lack of labeled data for training large networks. The overall goal of this work is to develop deep learning approaches that can be adaptable to different conditions. For example, a trained neural network will fail to generalize when the appropriate environmental variability is not included in the training data. To improve network performance, transfer learning can modify a pre-trained network to make predictions on data that was recorded under different conditions than the original dataset. In this work, a convolutional neural network was trained on acoustic data measured in a water tank, while the water was at room temperature, to predict source-receiver range. Transfer learning was used to update the pre-trained model with a smaller set of data measured at different water temperatures. The resulting model better generalizes to measurements at different temperatures. This approach illustrates how transfer learning can be used in ocean acoustics to improve generalizability in a specific area with less labeled data and lower computational cost. [Work supported by the Office of Naval Research, Grant N00014-22-12402.]