HPCForge/BubbleML

A multiphase multiphysics dataset and benchmarks for scientific machine learning

44
/ 100
Emerging

This project provides a comprehensive dataset of boiling simulations and a specialized AI model, Bubbleformer, to help thermal scientists understand and predict complex boiling processes. You provide simulation data detailing liquid-vapor interfaces, temperature distributions, and heat transfer. The outcome is a forecast of how these boiling dynamics will evolve over time, which is crucial for designing and optimizing systems like datacenter cooling or nuclear waste management.

Use this if you are a thermal scientist or engineer working with boiling phenomena and want to apply machine learning to predict dynamic behaviors without needing continuous simulation data during inference.

Not ideal if your primary need is to run new boiling simulations with highly customized, multi-parameter variations that go beyond the scope of the provided dataset parameters.

thermal-science fluid-dynamics heat-transfer datacenter-cooling nuclear-engineering
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

44

Forks

13

Language

Python

License

Last pushed

Feb 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HPCForge/BubbleML"

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