search

openclimatefix / graph_weather

PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)
MIT License
186 stars 46 forks source link

Hydrostatic balance #18

Open byphilipp opened 2 years ago

byphilipp commented 2 years ago

Your forecasting system used 13 levels instead <=5 in others similar systems

The hydrostatic balance equation can greatly improve your system.

You could add to the loss function the hydrostatic balance discrepancy in each of the layers: ( (Tvi+Tv{i+1})/2 + g/R (H{i+1}-H{i}) / log(p_{i+1}/p_i) )^2 -> min where g = 9.8065 m/s^2 is the gravitational acceleration R = 287.04 is gas constant for air Tv [K] = T [K] (1+Q [kg/kg]/(Q + R/Rv)) is virtual temperature Rv = 461.51 is gas constant for vapor

jacobbieker commented 2 years ago

Thanks for the suggestion! Yeah, I can try adding that. I'm hoping to train these models on even more levels and variables than in the paper, and at a finer resolution.

peterdudfield commented 2 years ago

@all-contributors please add @byphilipp for ideas

allcontributors[bot] commented 2 years ago

@peterdudfield

I've put up a pull request to add @byphilipp! :tada: