Deeper Dive
My project, ForeCAT, aims to improve aviation safety by better predicting Clear Air Turbulence (CAT), which can occur even when there are no clouds or storms in the sky. I became interested in this problem after experiencing sudden and frightening turbulence myself on flights. I started wondering why something that can be so dangerous is still so difficult to predict. So, I developed ForeCAT as a system that combines information about the atmosphere with machine learning to predict the likelihood and severity of CAT. Through this project, I explored whether understanding the physics of the atmosphere and correlating it with turbulence events could help make better predictions. The results were encouraging and showed me how computing grounded in science can be used to tackle important problems in aviation and beyond.
One of my biggest challenges was learning how to conduct research spanning different areas that I had never formally studied. I had to learn about atmospheric science and turbulence while also learning how to work with large datasets and develop machine learning models. I also had to deal with imperfect data and work through multiple initial ideas that did not succeed. These experiences taught me that research rarely follows a straight path and that failed experiments can be just as valuable as successful ones. My classes in physics, mathematics and computer science gave me a strong foundation, but much of the work required me to learn on my own. I completed the ForeCAT project independently and benefited from feedback on how to present the project clearly to a broad audience.
The aviation community could benefit from integrating ForeCAT with Air Traffic Control (ATC) systems to make air travel safer as global warming is expected to intensify jet streams and increase the frequency of CAT in the coming decades. Better predictions of CAT could give pilots and airlines more information to make routing decisions before an aircraft reaches a dangerous area, improving safety and comfort for tens of millions of people who fly daily. More broadly, this project showed me that technology can be a useful tool for addressing problems that directly affect people’s lives.
