Resource Group – MLGEM

Overview

The Machine Learning Resource Group (ML RG) is a new component of the GEM workshop. Our mission is to advance system-of-systems science in Sun-Earth interaction from a data-driven perspective and develop an ML-based Geospace Environment Model (ML-GEM) by integrating community-wide ML efforts.

Leaders

Name	Affiliation
1. Hyunju Connor	NASA GSFC
2. Matthew Argall	UNH
3. Xiangning Chu	LASP, CU Boulder
4. Bashi Ferdousi	AFRL
5. Valluri Sai Gowtam	UAF

Machine Learning Models in Geospace

The GEM ML FG has compiled a comprehensive list of machine learning models that have been successfully applied to various aspects of geospace research. These models have been documented in numerous published papers, showcasing the diverse applications and advancements of ML techniques in heliophysics. Below are some highlighted ML models and their contributions.

A collection of ML models:

List of ML Models: A list of machine learning models.

Slide of ML models: A slide of machine learning models.

Machine Learning tutorials

Title	Author	Link
ML-GEM tutorial session 2024		ML-GEM tutorial session
Machine Learning in Space Physics	Jacob Bortnik	https://www.youtube.com/watch?v=t0eMDnPFBdc
Unraveling the mystery of plasmaspheric dynamics using a machine learning approach	Xiangning Chu	Cold plasma seminar page (Passcode: ?wZx7+Z0)
ML-GEM GEM Tutorial: Machine Learning based Geospace Environment Modeling	Hyunju Connor	https://www.youtube.com/watch?v=wGxw1iLw5gw

Computation resources:

Name	Link
Google Colab	https://colab.research.google.com/
NASA High-End Computing Program	https://hec.nasa.gov/
NSF Advanced Cyberinfrastructure Coordination Ecosystem: Services&Support	https://access-ci.org/
NCAR Advanced Research Computing	https://arc.ucar.edu/
Nvidia Data Center GPU Resource Center	https://resources.nvidia.com/l/en-us-gpu
Universities sponsored GPU computation nodes	Consult University IT

Visit the ML-RG Wiki page for more information. Contact xiangning.chu(at)lasp.colorado.edu for any changes.