tobifinn/ensemble_transformer

Official PyTorch implementation of "Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Models".

27
/ 100
Experimental

This tool helps climate scientists and meteorologists process complex ensemble data from Earth system models, such as weather forecast outputs. It takes raw or pre-processed ensemble data (like ERA5 or IFS) and applies a novel neural network approach to generate improved, non-parametric forecasts or analyses. Earth system modelers can use this to enhance the accuracy and interpretation of their model predictions.

No commits in the last 6 months.

Use this if you need to analyze or post-process ensemble data from climate or weather models using advanced neural network techniques, moving beyond traditional parametric assumptions.

Not ideal if you prefer simpler, more interpretable statistical post-processing methods or if your primary focus is on models that don't involve ensemble data.

climate-modeling weather-forecasting ensemble-forecasting atmospheric-science geoscience-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tobifinn/ensemble_transformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.