Publications

In this work, machine learning and image processing methods are used to estimate 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 Geostationary Operational Environmental Satellite (GOES) 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 existing Federal Aviation Administration (FAA) weather systems. Preprocessing and feature extraction methods are described to construct inputs for model training. 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 weather radar-like analyses that extend into offshore regions. The resulting fields are validated using land radars and satellite precipitation measurements provided by the National Aeronautics and Space Administration (NASA) Global Precipitation Measurement Mission (GPM) core observatory satellite. This capability is initially being developed for the Miami Oceanic airspace with the goal of providing improved situational awareness for offshore air traffic control.

Accurate wind information is of fundamental importance to some of the critical future air traffic concepts under the FAA's Next Generation Air Transportation System (NextGen) initiative. Concepts involving time elements, such as Four-Dimensional Trajectory Based Operations (4D-TBO) and Interval Management (IM), are especially sensitive to wind information accuracy. There is a growing need to establish appropriate concepts of operation and target performance requirements accounting for wind information accuracy for these types of procedure, and meeting these needs is the purpose of this project. In the first phase of this work, a Wind Information Analysis Framework was developed to help explore the relationship of wind information to NextGen application performance. A refined version of the framework has been developed for the Phase 2 work that highlights the role stakeholders play in defining Air Traffic Control (ATC) scenarios, distinguishes wind scenarios into benign, moderate, severe, and extreme categories, and more clearly identifies what and how wind requirements recommendations are developed from the performance assessment trade-spaces. This report documents how this refined analysis framework has been used in Phase 2 of the work in terms of: -Refined wind information metrics and wind scenario selection process applicable to a broader range of NextGen applications, with particular focus on 4D-TBO and IM. -Expanded and refined studies of 4D-TBO applications with current Flight Management Systems (FMS) (with MITRE collaboration) to identify more accurate trade-spaces using operational FMS capabilities with higher-fidelity aircraft models. -Expansion of the 4D-TBO study using incremental enhancements possible in future FMSs (with Honeywell collaboration), specifically in the area of wind blending algorithms to quantify performance improvement potential from near-term avionics refinements. -Demonstrating the adaptability of the Wind Information Analysis Framework by using it to identify initial wind information needs for IM applications.

Accurate wind information is of fundamental importance to some of the critical future air traffic concepts envisioned under the FAA’s Next Generation Air Transportation System (NextGen) initiative. In the first phase of this work, a Wind Information Analysis Framework was developed to help explore the relationship of wind information to NextGen application performance. A refined version of the framework has been developed for the Phase 2 work.

Storm initiation is a very challenging aspect of nowcasting. Rapidly forming storms that appear in areas of little to no pre-existing convection can pose a danger to aircraft, and have the potential to cause unforeseen delays in the national airspace system (NAS). As such, detection and prediction of the initial development of convective storms is critical to NAS operations and planning. The Corridor Integrated Weather System (CIWS) currently provides deterministic 0-2 hour storm forecasts over the NAS, and represents the 0-2 hour portion of the 0-8 hour deterministic CoSPA storm forecasts. CIWS includes a convective initiation (CI) module, however this module has difficulty initiating convection in areas of little or no pre-existing convection. In this study, we seek to improve the capabilities of the CI module using machine learning methods to detect regions of imminent convection and enhance the storm initiation to the 0-2 hour forecast. Improvements to the current CI detection capabilities will prove to be a benefit in the short term, as well in the longer term plans of the Federal Aviation Administration's (FAA) Next Generation Air Transportation System (NextGen). In order to improve the capabilities of the CI module in CIWS, data from a variety of sources are fused together to produce a forecast of CI. Data incorporated into the CI algorithm include: Satellite fields from NASA's Satellite Convective Analysis and Tracking (SATCAST), convective instability fields, and a collection of numerical models which includes NOAA's North America Rapid Refresh Ensemble Time Lag System (NARRE-TL), the Localized Aviation MOS Program (LAMP), Short Range Ensemble Forecasts (SREF), and High Resolution Rapid Refresh (HRRR) model forecasts. These fields are brought together in a machine learning framework to create a probabilistic model which is used to initiate new growth in the deterministic CIWS 0-2 hour forecast. A variety of machine learning classifiers, including logistic regression, neural networks, support vector machines, and random forests, are used to investigate which technique works best with the data available. The skill of this updated CI capability is being assessed over the summer of 2012 using multiple skill metrics including CSI, bias and fraction skill score.

Air traffic congestion in the United States (US) is a serious national problem resulting in a critical need for timely, reliable and high quality forecasts of precipitation and echo tops with forecast time horizons of up to 8 hours. In order to address the short-term needs of the Federal Aviation Administration (FAA) as well as the long-term goals of the US's Next Generation Airspace System (NextGen), MIT Lincoln Laboratory, NCAR Research Applications Laboratory and NOAA Earth Systems Research Laboratory (ESRL) Global Systems Division (GSD) are collaborating on developing a forecast system under funding from the FAA's Aviation Weather Research Program (AWRP). The CoSPA system combines the latest technologies in heuristic nowcasting, extrapolation, statistical techniques and numerical weather prediction to produce rapidly updating (15 min) 0-8 hour forecasts of storm locations, echo tops and intensities. The system blends highly-skillful heuristic nowcasts with output from NOAA's High Resolution Rapid Refresh (HRRR) using phase correction and statistical weighting functions. The CoSPA 0-8 hour forecasts are accessible to the aviation community via an operational situation display and a website that builds upon the FAA's Corridor Integrated Weather System (CIWS) and shows current time situational awareness products including: VIL, echo tops, lightning, growth and decay, forecasts and verification contours, as well as an animation of the weather from 8 hours in the past to 8 hours into the future. This presentation will include a brief description of the CoSPA forecast system and display, examples of forecast performance, and provide an overview of recent enhancements to CoSPA as well as ongoing research.