Machine learning, data science and artificial intelligence applied to aircraft, spacecraft and air transport. This major brings together members passionate about algorithms and aerospace data.
To be the leading student hub for AI/ML innovation in aerospace engineering — where theoretical models meet real‑world flight data, and where members develop the skills to shape the future of intelligent aviation and space systems.
—”from blackboard to black box”
Empower members through hands-on machine learning projects using aerospace data; foster peer learning via biweekly technical sessions; collaborate on small group models and one final group project each semester — all while building a solid foundation in supervised learning, regression, and beyond.
biweekly · supervised learning track — theory + code.我们从 regression foundations to model evaluation. Every two weeks we meet to break down algorithms and apply them to aerospace scenarios.
Teams of 2‑3 members work on a defined ML task using real or simulated aerospace data — from predicting engine wear to classification of flight phases. Iterative, with peer reviews.
Culminating team project that integrates regression techniques on a larger aerospace dataset. past topics: predictive maintenance for turbofans, approach speed modelling.
Supervised Learning – Regression · from linear models to regularisation, applied to aerospace performance data.
All learning sessions and small group projects this semester revolve around regression techniques. From predicting aircraft fuel flow to estimating takeoff distance — we build, validate and interpret models.
AI & ML in Aerospace major – part of Aero Nova’s technical divisions. We work on data, models and algorithms that matter for the future of flight. Learning sessions are open to all members after joining the major.
The major operates on a semester rhythm. Each member participates in at least one small group project, with the option to propose a final project. This semester: regression, next semester: classification & deep learning fundamentals.