Observational Insights of Nearshore Wind Stress and Parameterizations From Gaussian Process Regressions.

The nearshore wind stress, u∗2 ${u}_{\ast }^{2}$, is examined using machine‐learning models for air‐ocean data collected via new flux buoys deployed across four experiments. Consistent with prior nearshore studies, existing open‐ocean models predict nearshore u∗2 ${u}_{\ast }^{2}$ with a large error of 0.0152 m2/s2. Gaussian Process Regression (GPR) for nearshore u∗BM2 ${u}_{\ast \text{BM}}^{2}$ is developed, reducing errors to 0.0108 m2/s2. Nearshore air‐sea parameterizations are examined with wind speed (61%) and the wind‐wave frequency of encounters (16%) being the most important. A simpler nearshore, GPR‐derived, wind‐dependent‐only model (u∗NSU2 ${u}_{\ast \text{NSU}}^{2}$) is developed, with errors of 0.0135 m2/s2. GPRs, evaluated using identical variables, were applied to nearshore observations, and these observations modeled with open‐ocean formulations for an initial comparison of parameterizations between these two regimes. The parameterizations are similar, though with subtle nonlinear differences. The new nearshore data set and machine‐learning models enhance the accuracy of predictions and understanding of differences from the open‐ocean. Plain Language Summary: Understanding and accurately parameterizing wind stress on the ocean surface is crucial for modeling oceanic and atmospheric phenomena. Despite its significance, nearshore wind stress and its influencing factors remain inadequately understood due to limited in situ observations and the complexity of the problem. To address this gap, ten shallow‐water air‐sea buoys were developed and deployed alongside directional wave buoys in four field experiments, yielding a substantial data set of nearshore wind stress and associated variables. Discrepancies between nearshore and open‐ocean models were observed, with open‐ocean models exhibiting large errors. Machine‐learning models enhance the accuracy of predictions and understanding of the input variables. A new data‐informed machine‐learning model for nearshore wind stress significantly reduced the error by 30%. Each variable parameterization is described, and a simple model for wind stress based solely on wind speed is provided. Furthermore, an examination of wind stress parameterizations revealed similarities and differences between nearshore and open‐ocean, primarily attributed to wind speeds. These findings significantly enhance the accuracy of weather and ocean forecasts, particularly for nearshore regions. Key Points: Ten air‐sea buoys for winds and fluxes, deployed with wave buoys in four experiments, improve nearshore wind stress observation gapsSupervised machine learning enhances nearshore wind stress predictions, yielding parameterized variable responses without preconceptionsNearshore wind stress parameterizations relative to the open‐ocean have similar variable responses though with small nonlinear differences [ABSTRACT FROM AUTHOR]