search

UMD     This Site





Associate Professor Akua Asa-Awuku holding a compact ozone monitor. Photo: John T. Consoli

Associate Professor Akua Asa-Awuku holding a compact ozone monitor. Photo: John T. Consoli

 

Look up at the sky. What do you see? Dynamic poems of color and shape attract the gaze of most.

But Akua Asa-Awuku, associate professor of chemical and biomolecular engineering, sees beyond beauty. She’s interested in the sky she can’t see with just a tip of her head.

Asa-Awuku strives to understand the molecular components of the atmosphere that exist at the ultrasmall nanoscale, where one nanometer is one-billionth of a meter. (For scale, a human hair is approximately 80,000–100,000 nanometers wide.)

In nature, atmospheric nanoparticles have a range of effects, from interacting with cloud droplets to form or inhibit rain to modulating greenhouse gas behavior. In humans, they can be inhaled and impact the respiratory system or be used as biological or chemical threats in conflicts.

“There are many exciting opportunities and important issues for society that rely on understanding the molecular composition of the atmosphere,” she explains.

To do this, her work centers on identifying chemicals’ structural “fingerprints,” called spectra.

Machine learning (ML) helps her go deeper. It expands the reach and utility of research by helping speed and improve the classification and categorization of air sample data.

One collaborative ML-based project Asa-Awuku’s team is working on involves the U.S. Army Research Laboratory (ARL). The collaboration gives her and UMD students access to ARL’s sophisticated Raman spectroscopy technology to make highly detailed molecular identifications.

It also eliminates tedium. “Studying spectra gets laborious. In order to do this, someone has to sit there and manually study it,” she says.

Thousands of different molecular compositions exist in the air, and with this ML-informed technology, Asa-Awuku and her colleagues are able to make continuous, real-time measurements as opposed to static “snapshot” measurements showing only a moment in time. Having a fluid series of images helps scientists monitor change over time—and can be applied to defending national security through threat detection.

“The Army Research Lab looks at threat detection, because we know that aerosols are constantly around us,” she says. While many of these aerosols are not dangerous at all, other harmful particles could be released in warfare—and Asa-Awuku’s collaboration with ARL could help innovate early threat detection and safe responses.

“If you were able to have a real-time measurement and subsequent analysis of atmospheric composition, that would give you really interesting and useful data to help protect against threats,” Asa-Awuku says.



Related Articles:
The Battery Revolution
Algorithms and Autonomous Discovery
Machine Learning's Translational Medicine
The Buddy System: Human-Computer Teams
New affiliate faculty Mark Fuge is expert in machine learning and artificial intelligence
Study validates face recognition experts, but shows humans perform best with an AI partner
Alumnus Amir Ali Ahmadi receives PECASE Award
Do Good Robotics Symposium to explore technologies that benefit society and the planet
Regli named interim executive director of ARLIS
Shoukry, Krishnaprasad receive NSF grant for resilient-by-cognition cyber-physical systems

April 4, 2019


«Previous Story  

 

 

Current Headlines

Chellappa Chairs National Academy Workshop on Machine Learning

Khaligh, Rudnick-Cohen win 2019 ISR awards

Special Delivery

Welcome, NAE Members

Lockheed Martin Awards $3M to Clark School

NSF Awards $1M Grant to UMD Researchers

Ghodssi Receives Senior Faculty Outstanding Research Award

ISR remembers Carlos Berenstein

NIH Awards $2M to UMD Entomologist Megan Fritz

University of Maryland Launches Quantum Technology Center

 
 
Back to top  
Home Clark School Home UMD Home