Welcome to miniWeatherML: A playground for learning and developing Machine Learning (ML) surrogate models and workflows. It is based on a simplified weather model simulating flows such as supercells that are realistic enough to be challenging and simple enough for rapid prototyping in:
- Data generation and curation
- Machine Learning model training
- ML model deployment and analysis
- End-to-end workflows
Documentation: https://github.com/mrnorman/miniWeatherML/wiki
Author: Matt Norman (Oak Ridge National Laboratory), https://mrnorman.github.io
Contributors so far:
- Matt Norman (Oak Ridge National Laboratory)
- Murali Gopalakrishnan Meena (Oak Ridge National Laboratory)
Written in portable C++, miniWeatherML runs out of the box on CPUs as well as Nvidia, AMD, and Intel GPUs.
The core infrastructure of miniWeatherML is less than 1K lines of code, and the minimal meaningful module set is comprised of less than 3K lines of code, very little of which needs to be understood in full detail in order to effectively use miniWeatherML for its intended purposes.