ML-for-S2S

Subseasonal-to-Seasonal (S2S) prediction and predictability research using machine learning.

---

Related papers:

Molina, M. J., J. H. Richter, A. A. Glanville, K. Dagon, J. Berner, A. Hu, and G. A. Meehl (Submitted). Subseasonal Representation and Predictability of North American Weather Regimes using Machine Learning. Artificial Intelligence for the Earth Systems.

---

CESM Hindcast Variables

Variable	Description
pr	Total (convective and large-scale) precipitation rate (liq + ice) (kg/m2/s).
rlut	Upwelling longwave flux at top of model (W/m2).
tas2m	Reference height temperature (K).
ts	Surface temperature (radiative) (K).
ua_200	Zonal wind at 200 mbar pressure surface (m/s).
va_200	Meridional wind at 200 mbar pressure surface (m/s).
ua_850	Zonal wind at 850 mbar pressure surface (m/s).
va_850	Meridional wind at 850 mbar pressure surface (m/s).
u	Zonal wind at 300 mbar pressure surface (m/s).
v	Meridional wind at 300 mbar pressure surface (m/s).
zg_200	Geopotential Z at 200 mbar pressure surface (m).
zg_500	Geopotential Z at 500 mbar pressure surface (m).
sst	Sea surface temperature.
ps	Surface pressure.
div	Divergence (300-mb).
eta	Absolute vorticity.
rws	Rossby wave source.