Reconstructing Ocean Flow from Observed Lagrangian Trajectories

Accurate and computationally efficient modeling of ocean currents is important for understanding and monitoring the dispersion of marine pollution. Passive floating Lagrangian drifters, equipped with GPS, are a low-cost approach to tracking surface flow. However, assimilating drifter observations into comprehensive ocean models remains challenging, and these models are often too computationally intensive for real-time or operational use. In this work, we introduce a novel Lagrangian data assimilation method that leverages machine learning techniques to enable computationally efficient ocean flow modeling. We first train an autoencoder using existing snapshots of the flow field to create a reduced-order model, which extracts low-dimensional representations of the high-dimensional data. We then apply Bayesian optimization to minimize a cost function, defined in the low-dimensional latent space, that measures the discrepancy between observed trajectories and model-generated trajectories. Our approach is demonstrated to efficiently reconstruct regional ocean flow from sparse drifter data, with results obtained in minutes. The method can be used to identify the minimum number of drifters needed for accurate flow modeling and to determine optimal drifter launch locations.