Convolutional Neural Networks for Sea Surface Data Assimilation in Operational Ocean Models: Test Case in the Gulf of Mexico

Abstract. Deep learning models have demonstrated remarkable success in fields such as language processing and computer vision, routinely employed for tasks like language translation, image classification, and anomaly detection. Recent advancements in ocean sciences, particularly in data assimilation (DA), suggest that machine learning can emulate dynamical models, replace traditional DA steps to expedite processes, or serve as hybrid surrogate models to enhance forecasts. However, these studies often rely on ocean models of intermediate complexity, which involve significant simplifications that present challenges when transitioning to full-scale operational ocean models. This work explores the application of Convolutional Neural Networks (CNNs) in assimilating sea surface height and sea surface temperature data using the Hybrid Coordinate Ocean Model (HYCOM) in the Gulf of Mexico. The CNNs are trained to correct model errors from a two-year, high-resolution (1/25°) HYCOM dataset, assimilated using the Tendral Statistical Interpolation System (TSIS). We assess the performance of the CNNs across five controlled experiments, designed to provide insights into their application in environments governed by full primitive equations, real observations, and complex topographies. The experiments focus on evaluating: 1) the architecture and complexity of the CNNs, 2) the type and quantity of observations, 3) the type and number of assimilated fields, 4) the impact of training window size, and 5) the influence of coastal boundaries. Our findings reveal significant correlations between the chosen training window size—a factor not commonly examined—and the CNNs' ability to assimilate observations effectively. We also establish a clear link between the CNNs' architecture and complexity and their overall performance.