Autonomous underwater vehicles (AUVs) have changed the way marine environment is surveyed, monitored and mapped. Autonomous underwater vehicles have a wide range of applications in research, military, and commercial settings. AUVs not only perform a given task but also adapt to changes in the environment, e.g., sudden side currents, downdrafts, and other effects which are extremely unpredictable. To navigate properly and allow simultaneous localisation and mapping (SLAM) algorithms to be used, these effects need to be detected. With current navigation systems, these disturbances in the water flow are not measured directly. Only the indirect effects are observed. It is proposed to detect the disturbances directly by placing pressure sensors on the surface of the AUV and processing the pressure data obtained. Within this study, the applicability of different learning methods for determining flow parameters of a surrounding fluid from pressure on an AUV body are tested. This is based on CFD simulations using pressure data from specified points on the surface of the AUV. It is shown that support vector machines are most suitable for the given task and yield excellent results.