Building connections to advance applications

Machine learning (ML), and other large-data analysis techniques, have become essential tools for analyzing the ever-increasing sizes of scientific data returned from planetary missions. In addition, ML methods have demonstrated potential to assist in mission planning and operations. Planetary space physics (or the study of plasmas around planets) has often been a field defined by sparse data concerns and extreme environments. These aspects provide a uniquely challenging, and rewarding field to apply ML methods.

This seminar series aims to bring together researchers in planetary science, space physics, machine learning, and other domain applications of ML methods to advance applications of large-data methods. We welcome presentations from a broad array of fields including: Earth based and planetary science applications, educational efforts, and basic ML research.

Upcoming Seminar

January 26 2021
9 AM Pacific / 12 PM Eastern / 5 PM Dublin

Special Theme: Model Metrics and Assessment

Michael Liemohn
University of Michigan

One is Not Enough
Thoughts on Choosing Data-Model Comparison Metrics

The magnetospheric physics research community uses a broad array of quantitative data-model comparison methods – metrics – when conducting their research investigations. It is often the case, though, that any particular study will only use one or two metrics. Because metrics are designed to test a specific aspect of the data-model relationship, limiting the comparison to only one or two metrics reduces the physical insights that can be gleaned from the analysis, restricting the possible findings from such studies. Additional physical insights can be obtained when many types of metrics are applied. A few best practices for choosing metrics for space physics studies are presented and discussed.

Sophie Murray
Dublin Institute of Advanced Studies

Finding the Right Metric
Solar Flare Forecast Evaluation [paper], [flare scoreboard]

One essential component of operational space weather forecasting is the prediction of solar flares. Early flare forecasting work focused on statistical methods based on historical flaring rates, and more complex machine learning based methods have been implemented in recent years. A multitude of flare forecasting methods are now available for operational use, and proper evaluation of these products is crucially important for model developers, forecasters, end-users, and stakeholders because it facilitates an understanding of the strengths and weaknesses of the forecasting process. This talk will outline current collaborative efforts in solar flare forecasting that are driving international standards based on terrestrial weather forecasting practices, such as defining evaluation metrics, climatological benchmarking, and ensemble requirements.

Full seminar series schedule with abstracts.


Abigail Azari

Post-Doctoral Scholar, Space Sciences Lab, University of California Berkeley

Caitriona Jackman

Honorary Professor, Dublin Institute for Advanced Studies


To receive invitations to our monthly series or to recommend speakers, please fill out our community form.