Abstract: A computer-implemented method for forecasting weather uses a trained machine learning model to determine the error in a weather forecast, e.g., for a selected ocean region. The machine learning model is configured to determine the predicted forecasting error given the weather forecast and a set of existing conditions. The weather forecast is adjusted using the predicted forecasting error to produce an augmented weather forecast. Training the machine learning model may include the utilization of hindcasting methods. Determination of existing conditions and other modeling may include the use of data from an array of metocean sensor nodes dispersed on a body of water.

Abstract: A real-time metocean sensor array system may include a one or more floating instruments each including geolocation capabilities and connected to a satellite communication network. In some examples, the floating instruments may further include an omnidirectional hydrophone. Motion and acoustical data gathered by the instruments may be converted by onboard processing logic into wave, current, and/or wind-related observations that may be communicated in real time and analyzed via a cloud-based system.

Abstract: A real-time metocean sensor array system may include a one or more floating instruments each including geolocation capabilities and connected to a satellite communication network. In some examples, the floating instruments may further include an omnidirectional hydrophone. Motion and acoustical data gathered by the instruments may be converted by onboard processing logic into wave, current, and/or wind-related observations that may be communicated in real time and analyzed via a cloud-based system.