Only if your structural theory is not-wrong enough.

Even if you KNOW that your model is not-wrong in the right direction and within acceptable orders of magnitude, how do you fit the parameters for that structural model? You need some kind of data, even if you're just using anecdata to pick magic constants.

All models are wrong, some are useful.

Fortunately models like these are often testable across many contexts, amenable to metastudies, available for calibration, etc.

That's my whole point. You just asserted that you can extrapolate outside a training set with a structural model. I am asserting that those "many contexts" and "metastudies" amount to a bigger, more representative training set.