Prediction models are often based on first principles approaches, which can be very time-consuming or even impossible inpractice. Furthermore, if the underlying process or environmental conditions change, a once good model can degrade and thus
needs to be adapted. An alternative to first-principles approaches is to derive prediction models directly from measured data.
Maiworm M., D. Limon, and R. Findeisen (2020), Online learning-based Model Predictive Control with Gaussian Process Models and Stability Guarantees, International Journal of Robust and Nonlinear Control,2020;00:1–6.
