Finding space objects

The headline is a little misleading. The story is that this high schooler did some summer work at cal tech. He saw a database full of information and wrote some fairly simple code to parse through it based on what we know. 

He used the notion that many objects will have a heat signature that would have been captured along the way and be in that database. 

The code picked out those objects and found literally millions of objects that would have been otherwise missed in that data.  

It's very, very cool. And yes there is an element of "machine learning" because the code adapted a bit as it found objects and information that would be valuable. 

https://dailygalaxy.com/2025/04/i-mapped-the-invisible-an-american-high-school-student-turns-astronomy-on-its-head-with-his-ai-that-reveals-1-5-million-forgotten-space-object/