Climatological Observations for Maritime Prediction and Analysis Support Service (COMPASS)

Current US Navy forecasting systems and mission-planning tools cannot easily incorporate extended-range forecasts that can improve mission readiness and effectiveness; ensure safety; and reduce cost, labor, and resource requirements. If Navy operational planners and decision makers had tools and systems that incorporated these extended-range forecasts, they could plan missions using more reliable and longer-term weather and climate predictions. The Climatological Observations for Maritime Prediction and Analysis Support Service (COMPASS) uses machine learning to create operationally relevant and mission-specific probabilistic forecasts up to a year in advance for regions and time periods of interest. COMPASS integrates extended-range multi-model forecast ensemble data to generate general and mission-specific probabilistic forecasts; the skill of COMPASS forecasts is superior to the skill of individual forecast models and commonly used weighted forecasts that integrate several forecast models. COMPASS forecasts can be produced and visualized in the Advanced Climatological Analysis and Forecasting (ACAF) system or any other existing forecasting or decision-support product.