贝叶斯优化结合核集成与基于分歧的采集函数用于声源定位与声学反演

中文摘要 AI 辅助

联合声源定位与地声反演需要优化一个基于昂贵的简正波传播模型构建的目标函数。使用高斯过程（GP）代理的贝叶斯优化（BO）能够在有限的模型评估次数内获得准确的参数估计，但其性能依赖于核函数族的选择。在七维搜索空间中观测点稀少的情况下，没有任何单一核函数能够期望在每次单独反演中表现一致良好。为减少这种依赖性，我们使用不同核函数族的加权高斯过程集成，使代理能够适应观测到的目标函数，而无需预先承诺使用某一种核函数。该集成与一个最优条件采集函数相结合，该函数决定下一步应在何处评估昂贵的目标函数。在模拟和实测的SWellEx-96数据上的实验表明，所提出的方法在所考虑的BO策略中实现了最低的平均最终目标值，并在大多数坐标上减少了参数估计误差。消融结果进一步表明，集成提供了对核函数选择的鲁棒性，而采集函数则贡献了大部分的优化增益。

英文摘要

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.

发表机构

• University of Georgia（佐治亚大学）
• University of California, San Diego（加利福尼亚大学圣迭戈分校）

机构由 AI 辅助整理，请以论文原文为准。