京东影业影视传媒 Thaddaeus Kiker
Thaddaeus developed a machine-learning approach to predict the presence and properties of quasi-periodic oscillations (QPOs) in black holes. Then, he developed open-source software to allow other scientists to apply his methods to their work.
QPOML: Leveraging Machine Learning and Game Theory to Detect and Characterize Quasi-Periodic Oscillations in X-Ray Binaries
Thaddaeus Kiker, 18, of Fullerton, developed a machine learning approach to predict the presence and properties of quasi-periodic oscillations (QPOs) in black holes for his Regeneron Science Talent Search space science project. While scientists have long known about QPOs and proposed theories for their occurrence, they don鈥檛 know exactly why X-ray light from black holes flickers in these ways. Thaddaeus trained his models to make these predictions based on spectral properties like accretion disk temperature. Then he developed open-source software to allow other researchers to apply his methods to their own work. Thaddaeus hopes his work will help 鈥渢o unlock mysteries about QPOs and their black hole progenitors鈥� when extended to multiple systems simultaneously.
At Sunny Hills High School, Thaddaeus swims and heads the research laboratory, which he founded at his old high school and brought with him when he moved to California. The club鈥檚 first research project about young stars was published in a peer-reviewed journal, and they have since worked on genomics and exoplanet related projects as well, unexpectedly discovering a rare type of star along the way. Thaddaeus is the son of Anna and Jason Kiker.
Beyond the Project
As a data analyst volunteering for a Texas senate campaign, Thaddaeus optimized his group鈥檚 canvassing logistics by adapting the famous 鈥渢raveling salesman鈥� problem to minimize trip distances.
FUN FACTS: Thaddaeus co-leads his school鈥檚 coding club and uses game engines from past MIT Battlecode competitions so that club members can build their own 鈥渞obot army controllers鈥� during the off-season.
