Aurora air pollution model predicts NaNs / exhausts after around 13 days of autoregressive rollout

Hi,

I am running the Aurora air pollution model autoregressively and I am seeing that the model becomes unstable after about 13 days of forecasting. After that point, the predictions start to degrade badly and eventually produce NaN values.

What I observed
The rollout is stable initially.
Around day 13, the forecast starts to drift strongly.
After that, the model appears to exhaust / blow up and begins predicting NaNs.
In my tests, the surface variables degrade much faster, while some pressure-level variables remain relatively reasonable for longer.
My question

Is this expected behavior for the Aurora air pollution model during long autoregressive rollouts?

Since the model is mainly designed for shorter forecasts, I would like to understand:
Is there a known reason the model exhausts during longer rollouts?
What are the recommended ways to extend the forecast horizon more safely?

Specifically, I would appreciate guidance on:
Whether this is a limitation of the released checkpoint
Whether any normalization or preprocessing issues could cause this
Whether clamping is recommended
Best practices for extending inference beyond the standard forecast range

No files, tests, or entry points are named. Start by reproducing the reported autoregressive Aurora air-pollution rollout through the point where NaNs appear, then inspect the inference and normalization paths involved. Done means identifying whether the behavior is expected or a defect and documenting supported practices for longer forecasts.