Bayesian optimization of ocean mixed layer parameterizations

Global climate is highly sensitive to tropical sea surface temperature. Accurately representing the tropical SST remains a significant challenge for general circulation and climate models. One of the largest sources of uncertainty is the vertical turbulent mixing. To accurately represent the distribution of ocean mixed layer depths, turbulence closure schemes necessitate careful tuning. This is most commonly done manually by comparing with mixed layer depth climatologies. Advancements in machine learning research introduce a new strategy: automated tuning. Veropt, an add-on to the python ocean model Veros, uses Gaussian processes to emulate an objective function in a multi-dimensional parameter space. We present a surprising combination of changes to the default parameters of the commonly used turbulent kinetic energy (TKE) closure scheme that minimise the model bias in tropical mixed layer depth.