The Offshore Precipitation Capability

Effective air traffic management requires forecasting the potential impact of convective weather on the capacity of air routes, and rerouting traffic or implementing traffic management initiatives to compensate. Within the CONUS, real-time convective weather information is provided to air traffic controllers either through radar display systems, such as the Weather and Radar Processor (WARP), or the Corridor Integrated Weather System (CIWS). Outside radar coverage, air traffic managers do not have access to any system that provides accurate and timely radar-like precipitation estimates.

In this work, machine learning and image processing methods are applied to develop a system that estimates radar-like precipitation intensity and echo top heights beyond the range of weather radar. The technology, called the Offshore Precipitation Capability (OPC), combines global lightning data with existing radar mosaics, five GOES satellite channels, and several fields from the Rapid Refresh (RAP) 13 km numerical weather prediction model to create precipitation and echo top fields similar to those provided by WARP or CIWS. Preprocessing and feature extraction techniques are used to construct inputs for model training and a variety of machine learning algorithms are investigated to identify which provides the most accuracy. Output from the machine learning model is blended with existing radar mosaics to create a seamless weather radar-like image in offshore regions. Motion tracking and compensation are applied to the estimated precipitation fields to provide timely updates. The resulting fields are validated using land radars and satellite precipitation measurements provided by the NASA Tropical Rainfall Measuring Mission (TRMM). This capability is initially being developed for the Miami Oceanic airspace and will directly benefit the FAA by providing improved situational awareness for offshore air traffic control.