The Michigan Engineer News Center

Two Climate & Space PhD students honored at first-ever Machine Learning in Heliophysics conference

CLASP PhD students win early-career awards for presentations. | Short Read
EnlargeAbigail Azari presentation at MLH conference
IMAGE:  Abigail Azari presentation at MLH conference

This week, the first-ever Machine Learning in Heliophysics conference was held in Amsterdam, The Netherlands, and two Climate & Space students are walking away with awards for their presentations.

PhD Candidate Abigail Azari received the Early-Career Award for Best Oral Presentation for her talk, “Multivariate Supervised Classification for Instabilities at Saturn: A Comparison of Methods for Automated Event Detection in Magnetospheres.”

PhD Student Yeimy Rivera received the Early-Career Award for Best Poster Presentation for her work on “Investigating a prominence eruption using a non equilibrium ionization code constrained to heliospheric measurements of composition.”

EnlargeMachine Learning in Heliophysics conference 2019
IMAGE:  Machine Learning in Heliophysics conference 2019

The stated goal of this first Machine Learning in Heliophysics conference is “…to leverage the advancements happening in disciplines such as machine learning, deep learning, statistical analysis, system identification, and information theory, in order to address long-standing questions and enable a higher scientific return on the wealth of available heliospheric data.

“We aim at bringing together a cross-disciplinary research community: physicists in solar, heliospheric, magnetospheric, and aeronomy fields as well as computer and data scientists. ML- Helio will focus on the development of data science techniques needed to tackle fundamental problems in space weather forecasting, inverse estimation of physical parameters, automatic event identification, feature detection and tracking, times series analysis of dynamical systems, combination of physics-based models with machine learning techniques, surrogate models and uncertainty quantification.” 

Congratulations, Abigail and Yeimy! 

Abigail Azari presentation at MLH conference
Machine Learning in Heliophysics conference 2019
Portrait of EJ Olsen

Contact

EJ Olsen
Marketing Communications Specialist

Climate and Space Sciences and Engineering

(734) 548-3204

2239 SRB

The electrons absorb laser light and set up “momentum combs” (the hills) spanning the energy valleys within the material (the red line). When the electrons have an energy allowed by the quantum mechanical structure of the material—and also touch the edge of the valley—they emit light. This is why some teeth of the combs are bright and some are dark. By measuring the emitted light and precisely locating its source, the research mapped out the energy valleys in a 2D crystal of tungsten diselenide. Credit: Markus Borsch, Quantum Science Theory Lab, University of Michigan.

Mapping quantum structures with light to unlock their capabilities

Rather than installing new “2D” semiconductors in devices to see what they can do, this new method puts them through their paces with lasers and light detectors. | Medium Read