Comments (3)
Some of the weighting is principled, like the area weighting correction by latitude to correct for the grid inputs/outputs over a sphere. Much of the rest is not especially optimized. The pressure level weights were chosen to bias towards ground level and worked well on 13 pressure levels, but weren't revisited when we switched to 37 levels. There are likely better weightings possible, as shown by us not doing especially well in the stratosphere relative to HRES. We started with equal weighting for surface/atmospheric variables, but found 0.1 for surface variables worked a bit better, other than t2m which was hurt by such a low weight. We didn't especially scan over many possible weightings, so there are almost certainly better weightings. What exactly is best also rather depends on your goal.
from graphcast.
Have you ever tried L1 loss? I have experimented with our own model, using both L1 and MSE losses without weighting for pressure levels and surface variables. The comparison was made with the models GraphCast and Pangu. Interestingly, L1 tends to favor the pressure levels over the surface variables, while MSE shows the opposite trend.
from graphcast.
I believe we tried L1 loss further back in this project and didn't see a clear benefit from it, I don't think we did a detailed breakdown by variable and level though so this is interesting and may be worth revisiting at some point. Anyway closing this issue as I think the main question is answered.
from graphcast.
Related Issues (20)
- Forecasting beyond 10 days HOT 8
- Cyclone tracking
- There are some questions about forecasting. HOT 1
- Fine-Tuning Strategy for the GraphCast Operational Model HOT 2
- About the atmospheric variable “Vertical velocity”
- about the autoregressive finetuning
- How to train a model by myself HOT 4
- How get the value from model dataset, such as norm_prediction?
- graphcast intro description needs ERA5 link fixing
- How was the Graphcast Small 1.0 degree Reanalysis made? HOT 1
- RESOURCE_EXHAUSTED HOT 1
- prediciton output time HOT 7
- Performance of GraphCast_small vs regular GraphCast vs GraphCast_operational HOT 1
- May I ask for a multiple batch example nc file?
- Training duration of pre-training model
- Issues with GraphCast Training – Request for Assistance
- Floating Point Error in 1-month forecast HOT 7
- Training: Learning Rate schedule based on iterations rather than epochs HOT 2
- Craphcast HOT 1
- UserWarning: no explicit representation of timezones available for np.datetime64
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from graphcast.