In the control tower simulation facility, an Air Traffic Control Systems staff member uses integrated electronic flight data and surveillance systems to direct an aircraft to taxi toward the runway.

Air Traffic Control Systems

The safe and efficient flow of aircraft in today's skies depends on a suite of weather sensing and traffic management technologies. Our group aims to improve air transportation by developing sensors, weather tracking and forecasting systems, and decision support automation that assists pilots and air traffic controllers in routing aircraft out of harm's way and maintaining smooth traffic patterns. To ensure user acceptance and the effectiveness of our technologies, we rely on extensive analysis and field evaluations and draw upon diverse areas of expertise, including signal processing, meteorology, software engineering, machine learning, human factors, and more. The systems our researchers have developed currently operate nationwide to minimize weather-related delays and protect aircraft against accidents. In addition to air traffic management, we are conducting initiatives in transportation logistics, the reduction of aircraft noise and environmental impacts, and cyber-secure information systems.

Featured Projects

Two photos are shown of the same landscape. The left hand photo shows a clear day, with a mountain in the distance. The right hand side shows a foggy view, with the mountain obscured.
air traffic control
An algorithm uses camera imagery to estimate visibility for pilots flying in remote areas that lack weather sensors.
a screenshot of a user interface shows a world map with radar-like depictions of rain bands, colored blue, green, and yellow.
aviation weather
By compiling lightning data, satellite imagery, and numerical weather models, the GSWR provides radar-like analyses and forecasts over regions not observed by actual weather radars.
A photo show radar returns of a thunderstorm and black lines showing tornado paths.
We are developing deep learning models to detect and predict tornadoes in real time.
A large KC-135R tanker aircraft refuels an F-15 Eagle aircraft while they in mid air.
artificial intelligence
Our model optimizes the scheduling of aerial refueling missions, saving fuel and costs for the Department of Defense.
The LASSOS display screen highlights the laser strike event in live sensor imagery on the left and generates a 3D model of the laser streak in Google Earth, right.
optical systems
A system that detects laser beams being shone into the sky and alerts police of their source can help protect pilots and aircraft.

Advancing Our Research


Apr 30 -
May 1
MIT Lincoln Laboratory, Lexington, Massachusetts

Featured Publications

WSR-88D microburst detection performance evaluation

Nov 28
MIT Lincoln Laboratory Report ATC-455

A deep learning-based velocity dealiasing algorithm derived from the WSR-88D open radar product generator

Jul 1
Artificial Intelligence for the Earth Systems, Vol. 2, Issue 3, July 2023.
A 3D illustration of a pilot cockpit.

Foundational AI Concepts

Our group applies artificial intelligence (AI) and machine learning (ML) techniques to improve air traffic safety and collision avoidance systems. The video linked below provides an overview of how AI/ML capabilities are incorporated into operational workflows and describes several applications of this technology.

Combined photo view of an Alaskan weather tower camera, showing ideal aerial conditions vs. overcast conditions.

Transforming Cameras into Weather Sensors

The Visibility Estimation through Image Analytics (VEIA) technology provides an inexpensive and robust way to extract meteorological visibility from cameras – thus transforming cameras into weather sensors.  The VEIA algorithm uses the presence and strength of edges in an image to provide an estimation of the meteorological visibility within the scene.  The algorithm compares the overall edge strength of the current image to those from a clear day representation generated by creating a composite image from several days of imagery.