Seabed classification using physics-based modeling and machine learning
arXiv:2003.11156 · doi:10.1121/10.0001728
Abstract
In this work model-based methods are employed along with machine learning techniques to classify sediments in oceanic environments based on the geoacoustic properties of a two-layer seabed. Two different scenarios are investigated. First, a simple low-frequency case is set up, where the acoustic field is modeled with normal modes. Four different hypotheses are made for seafloor sediment possibilities and these are explored using both various machine learning techniques and a simple matched-field approach. For most noise levels, the latter has an inferior performance to the machine learning methods. Second, the high-frequency model of the scattering from a rough, two-layer seafloor is considered. Again, four different sediment possibilities are classified with machine learning. For higher accuracy, 1D Convolutional Neural Networks (CNNs) are employed. In both cases we see that the machine learning methods, both in simple and more complex formulations, lead to effective sediment characterization. Our results assess the robustness to noise and model misspecification of different classifiers.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Scikit-learn: Machine Learning in Python
- Explaining and Harnessing Adversarial Examples
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Machine learning in acoustics: theory and applications
- Source localization in an ocean waveguide using supervised machine learning
- Do CIFAR-10 Classifiers Generalize to CIFAR-10?
- A hybrid approach to solve the high-frequency Helmholtz equation with source singularity in smooth heterogeneous media
- Seafloor identification in sonar imagery via simulations of Helmholtz equations and discrete optimization