ai2es/miles-guess

Machine learning models for estimating aleatoric and epistemic uncertainty with evidential and ensemble methods.

42
/ 100
Emerging

This project helps Earth system scientists develop machine learning models that not only make predictions about phenomena like latent heat or precipitation types, but also quantify the uncertainty in those predictions. It takes in observational or simulated Earth system datasets and outputs models that estimate both the inherent randomness (aleatoric) and the model's own lack of knowledge (epistemic) in its forecasts. Earth system scientists, atmospheric scientists, or climate modelers would use this to build more robust and interpretable predictive systems.

No commits in the last 6 months.

Use this if you need to understand the reliability and confidence of your machine learning model's predictions for Earth system phenomena, rather than just getting a single forecast.

Not ideal if you only need point predictions from your machine learning models and are not concerned with quantifying the uncertainty associated with them.

Earth-system-science atmospheric-modeling climate-science predictive-modeling uncertainty-quantification
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

30

Forks

10

Language

Jupyter Notebook

License

CC0-1.0

Last pushed

Jul 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ai2es/miles-guess"

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