search

monocongo / climate_learn

Deep learning for climate modeling.
BSD 3-Clause "New" or "Revised" License
38 stars 22 forks source link

Score models (train/test) for features: [PS, T, U, and V] and label: PTTEND #9

Open monocongo opened 6 years ago

monocongo commented 6 years ago

Determine which model works best for features: [PS, T, U, and V] and label: PTTEND

PTTEND (T total physics tendency) is the result of the CAM's processing of the PS (surface pressure), T (temperature), U (zonal wind), and V (meridional wind) input variables. This is a linear function.

We assume this process is suited to a simple linear regression model.

Score various linear models and corresponding parameters to determine which works best for these features/label.

monocongo commented 6 years ago

Running the script scripts/score_pttend.py using the following invocation:

$ python scripts/score_pttend.py --input_flows C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h0.2000-12-27-00000_lowres.nc C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h0.2001-01-11-00000_lowres.nc C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h0.2001-01-26-00000_lowres.nc C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h0.2001-02-10-00000_lowres.nc --input_tendencies C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h1.2000-12-27-00000_lowres.nc C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h1.2001-01-11-00000_lowres.nc C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h1.2001-01-26-00000_lowres.nc C:\home\cam_learn\examples\fv091x180L26_moist_HS.cam.h1.2001-02-10-00000_lowres.nc