If you’ve been looking for a fun problem to get into scientific machine learning, check out our new Helicpter SciML Challenge Problem:
This challenge problem gives a first principles model (along with its derivation) and data corresponding to measurements of the laboratory helicopter as it moves in response to changes in the electrical inputs. The simple physical model does not capture the full dynamics of the system, so the goal is to find the missing higher order physical equations (missing higher order frictions, etc.) to derive a better model. We’ll be using this in the scientific machine learning workshop on July 26th, 2020 (sign up for JuliaCon at https://juliacon.org/2020/), and hopefully the community can find this as a good model + dataset to learn from (pun intended).
P.S. it comes with a video!