Bayesian optimization improves underwater source location and acoustic analysis
Bayesian optimization with kernel ensembles and disagreement-based acquisition for source localization and acoustic inversion
Machine Learning
Summary
Finding underwater sound sources and understanding ocean conditions involves running slow and complex simulations. The authors developed a method that combines several ways to predict outcomes, making the search for the best solution more reliable and efficient. Their approach adjusts itself based on early tests and chooses the next data points to check wisely. Tests on both fake and real ocean data show it usually finds better answers faster than previous methods.
What this means in practice
- •For ocean engineers: Improve the accuracy and efficiency of locating underwater sound sources and estimating sea floor properties using limited simulation runs.
- •For sensor system designers: Design sensor placement strategies that use adaptive sampling to better characterize underwater acoustic environments.
Authors
Heng Zhang, Haotian Xiang, Florian Meyer, Qin Lu
Abstract
Joint source localization and geoacoustic inversion requires optimizing an objective built from an expensive normal mode propagation model. Bayesian optimization (BO) with a Gaussian process (GP) surrogate can obtain accurate parameter estimates within a limited number of forward model evaluations, but its performance depends on the choice of kernel family. With few observations in a seven-dimensional search space, no single kernel can be expected to perform consistently well across individual inversions. To reduce this dependence, we use a weighted ensemble of GPs with different kernel families, allowing the surrogate to adapt to the observed objective without committing to one kernel in advance. The ensemble is combined with an optimum-conditioned acquisition function that determines where the expensive objective should be evaluated next. Experiments on simulated and measured SWellEx-96 data show that the resulting method achieves the lowest mean final objective among the considered BO strategies and reduces parameter estimation error on most coordinates. Ablation results further show that the ensemble provides robustness to kernel choice, while the acquisition function accounts for most of the optimization gain.