ai2es/miles-guess
Machine learning models for estimating aleatoric and epistemic uncertainty with evidential and ensemble methods.
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.
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.
Higher-rated alternatives
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!