I've got a background in this field and I am very surprised to see this published in Nature. The model presented is purely statistical with no representation of the underlying physics. When we are dealing with a phenomenon that is driven by well-understood physical laws (e.g. geophysical fluid dynamics, radiation physics etc) then these physical models are the most reliable basis for prediction. When I say physical m…
Simpler models can yield better predictions than complex ones, even when the complex model is more "realistic". The many tunable parameters and complex feedback loops can increase uncertainty compared to a simple model.
See for example "To explain or to predict?" by Shmueli (2010, https://doi.org/10.1214/10-STS330)