blutjens/climate-emulator

Official repo for "The impact of internal variability on benchmarking deep learning climate emulators" in JAMES25 (public)

24
/ 100
Experimental

This project helps climate scientists and researchers evaluate the accuracy of different climate models in predicting future climate conditions. It takes climate data from global climate models and emission scenarios to produce scores and visualizations that compare how well simplified models (like pattern scaling or deep learning emulators) match more complex simulations. The main users are climate modelers and climate impact researchers who need to understand the reliability and limitations of various climate projection methods.

No commits in the last 6 months.

Use this if you are a climate scientist evaluating or developing simplified climate models and need to rigorously benchmark their performance against detailed ensemble climate simulations, especially concerning internal climate variability.

Not ideal if you are looking for a simple, out-of-the-box tool for general climate data analysis or generating quick, high-level climate projections without deep engagement in model benchmarking.

climate-modeling climate-projections earth-system-science model-evaluation climate-impact-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

21

Forks

Language

Jupyter Notebook

License

CC-BY-4.0

Last pushed

Sep 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/blutjens/climate-emulator"

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