About Tech AI
Tech AI is Georgia Tech's hub for artificial intelligence research, education, and responsible deployment. With over $120 million in active AI research funding, including more than $60 million in NSF support for five AI Research Institutes, Tech AI drives innovation through cutting-edge research, industry partnerships, and real-world applications. With over 370 papers published at top AI conferences and workshops, Tech AI is a leader in advancing AI-driven engineering, mobility, and enterprise solutions. Through strategic collaborations, Tech AI bridges the gap between AI research and industry, optimizing supply chains, enhancing cybersecurity, advancing autonomous systems, and transforming healthcare and manufacturing. Committed to workforce development, Tech AI provides AI education across all levels, from K-12 outreach to undergraduate and graduate programs, as well as specialized certifications. These initiatives equip students with hands-on experience, industry exposure, and the technical expertise needed to lead in AI-driven industries. Bringing AI to the world through innovation, collaboration, and partnerships. Visit tech.ai.gatech.edu.

Peter Yunker boils down his advice for researchers wanting to commercialize their lab advances. 

“You can’t go it alone,” said Yunker, an associate professor of physics at Georgia Tech. 

In January, Yunker co-founded the biotechnology startup TopoDx LLC, with David Weiss, an Emory University School of Medicine researcher and director of the Emory Antibiotic Resistance Center, and Yogi Patel, a Georgia Tech alumnus with a background in business development and bioengineering. 

“Researchers often think that they have a good commercialization idea to help people, but that alone does not guarantee success,” said Yunker. “Look for partners with complementary skills who understand aspects of the commercialization process that you don’t. Find mentors with business and scientific backgrounds in the specific industry you want to enter.”

TopoDx has developed a microbial test to identify antibiotic resistance and susceptibility rapidly and accurately. Current tests produce a result in three to five days. TopoDx’s approach can gain a result within four hours. Every hour counts in treating serious infections. Delays in accurate treatment can increase antibiotic resistance, which is a global challenge, causing up to 1 million deaths a year. 

The company’s testing method was inspired by a fundamental biophysics project in Yunker’s lab. His team was interested in understanding how bacterial colonies behave. They tested white-light interferometry, a technology that can measure bacterial colonies down to the nanometer level. 

“White-light interferometry allowed us to identify changes in the topography of a colony that indicated larger changes in the volume of cells in the entire colony,” said Yunker. “We thought this might have practical applications.” 

The next step was giving research talks at meetings and looking for collaborators. “I wanted to find someone with expertise on the bacteriology side, and I was very fortunate to meet David Weiss,” Yunker said, noting his proficiency in heteroresistance, a phenomenon where a small subset of a bacterial colony resists an antibiotic. 

“If you have just one antibiotic-resistant cell in a hundred cells, it can cause treatments to fail,” said Yunker. 

The two collaborators hoped to commercialize their technology, identifying heteroresistance in microbial samples. However, they needed guidance in creating a business model. They consulted Harold Solomon, an entrepreneur with Georgia Tech VentureLab and a principal in the Quadrant-i program, a specialized program helping Georgia Tech faculty and students commercialize research.  

Solomon became a key mentor. He guided them away from an ill-advised partnership and instead introduced them to Yogi Patel, who became a co-founder and the company CEO. 

This new collaboration provided the team with an important lesson — one that Yunker passes along to other researchers looking to commercialize their discoveries. “Seek expertise outside your field, be humble about your knowledge limitations, and view collaboration as a strategic partnership,” he says.

When Patel came on board, he conducted extensive interviews with more than 15 clinical professionals.

“You need to interview end users or purchasers of whatever solution you want to build,” said Patel. “Ask them if the problem you think you may have solved is a problem with scale, with a market need.” 

Clinicians, Patel learned, did not see heteroresistance as a significant issue. Instead, the slow pace of antibiotic testing was identified as a major problem. Faster testing could allow clinicians to prescribe targeted drugs more quickly and accurately, reducing unnecessary antibiotic use and the risk of multi-resistant infections. 

With this survey information, Patel asked Yunker and Weiss to rethink how their technology could be commercialized. 

“A company must solve a real-world problem,” said Patel. “I recommended that we switch from heteroresistance to solving slow antibiotic testing. We could keep heteroresistance as something we can still do as a second or third priority.” 

TopoDx’s new technology can measure, with single-nanometer accuracy, how bacterial colonies are responding to antibiotics in real time. This method could revolutionize how antibiotics are tested and prescribed. Testing would be conducted on a countertop device about the size of a large microwave. The co-founders envision the device as eventually being used by urgent care facilities and hospitals. 

“We want to make microbial testing susceptibility accessible anywhere and everywhere,” said Patel.   

Adam Krueger, once a Ph.D. student in Yunker's lab, has continued to refine the technology. Now a post-doctoral researcher, Krueger joined TopoDx in a technical leadership role to expand the technology’s capabilities for microbiological diagnostics.

“We will keep pushing the envelope forward scientifically while we try to commercialize the accomplishments that we have already made,” Yunker said. “We hope that some fundamental studies we are doing now out of scientific curiosity could lead to further commercial applications.”

Georgia Tech faculty members and graduate students, join the Quadrant-i Startup Launch Program to commercialize your research this summer: Over 12 weeks, you'll receive comprehensive support including guidance from experienced mentors, a $10,000 commercialization grant, and $150,000 worth of in-kind services. Showcase your innovation at Demo Day, where you'll have the opportunity to present to over 1,500 attendees, including industry leaders and investors. Apply today! Applications close April 11.

Many communities rely on insights from computer-based models and simulations. This week, a nest of Georgia Tech experts are swarming an international conference to present their latest advancements in these tools, which offer solutions to pressing challenges in science and engineering.

Students and faculty from the School of Computational Science and Engineering (CSE) are leading the Georgia Tech contingent at the SIAM Conference on Computational Science and Engineering (CSE25). The Society of Industrial and Applied Mathematics (SIAM) organizes CSE25, occurring March 3-7 in Fort Worth, Texas.

At CSE25, the School of CSE researchers are presenting papers that apply computing approaches to varying fields, including:                   

• Experiment designs to accelerate the discovery of material properties
• Machine learning approaches to model and predict weather forecasting and coastal flooding
• Virtual models that replicate subsurface geological formations used to store captured carbon dioxide
• Optimizing systems for imaging and optical chemistry
• Plasma physics during nuclear fusion reactions

[Related: GT CSE at SIAM CSE25 Interactive Graphic] 

“In CSE, researchers from different disciplines work together to develop new computational methods that we could not have developed alone,” said School of CSE Professor Edmond Chow. 

“These methods enable new science and engineering to be performed using computation.” 

CSE is a discipline dedicated to advancing computational techniques to study and analyze scientific and engineering systems. CSE complements theory and experimentation as modes of scientific discovery. 

Held every other year, CSE25 is the primary conference for the SIAM Activity Group on Computational Science and Engineering (SIAG CSE). School of CSE faculty serve in key roles in leading the group and preparing for the conference.

In December, SIAG CSE members elected Chow to a two-year term as the group’s vice chair. This election comes after Chow completed a term as the SIAG CSE program director. 

School of CSE Associate Professor Elizabeth Cherry has co-chaired the CSE25 organizing committee since the last conference in 2023. Later that year, SIAM members reelected Cherry to a second, three-year term as a council member at large. 

At Georgia Tech, Chow serves as the associate chair of the School of CSE. Cherry, who recently became the associate dean for graduate education of the College of Computing, continues as the director of CSE programs. 

“With our strong emphasis on developing and applying computational tools and techniques to solve real-world problems, researchers in the School of CSE are well positioned to serve as leaders in computational science and engineering both within Georgia Tech and in the broader professional community,” Cherry said. 

Georgia Tech’s School of CSE was first organized as a division in 2005, becoming one of the world’s first academic departments devoted to the discipline. The division reorganized as a school in 2010 after establishing the flagship CSE Ph.D. and M.S. programs, hiring nine faculty members, and attaining substantial research funding.

Ten School of CSE faculty members are presenting research at CSE25, representing one-third of the School’s faculty body. Of the 23 accepted papers written by Georgia Tech researchers, 15 originate from School of CSE authors.

The list of School of CSE researchers, paper titles, and abstracts includes:
Bayesian Optimal Design Accelerates Discovery of Material Properties from Bubble Dynamics
Postdoctoral Fellow Tianyi Chu, Joseph Beckett, Bachir Abeid, and Jonathan Estrada (University of Michigan), Assistant Professor Spencer Bryngelson
[Abstract]

Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data
Ph.D. student Phillip Si, Assistant Professor Peng Chen
[Abstract]

A Goal-Oriented Quadratic Latent Dynamic Network Surrogate Model for Parameterized Systems
Yuhang Li, Stefan Henneking, Omar Ghattas (University of Texas at Austin), Assistant Professor Peng Chen
[Abstract]

Posterior Covariance Structures in Gaussian Processes
Yuanzhe Xi (Emory University), Difeng Cai (Southern Methodist University), Professor Edmond Chow
[Abstract]

Robust Digital Twin for Geological Carbon Storage
Professor Felix Herrmann, Ph.D. student Abhinav Gahlot, alumnus Rafael Orozco (Ph.D. CSE-CSE 2024), alumnus Ziyi (Francis) Yin (Ph.D. CSE-CSE 2024), and Ph.D. candidate Grant Bruer
[Abstract]

Industry-Scale Uncertainty-Aware Full Waveform Inference with Generative Models
Rafael Orozco, Ph.D. student Tuna Erdinc, alumnus Mathias Louboutin (Ph.D. CS-CSE 2020), and Professor Felix Herrmann
[Abstract]

Optimizing Coupled Systems: Insights from Co-Design Imaging and Optical Chemistry
Assistant Professor Raphaël Pestourie, Wenchao Ma and Steven Johnson (MIT), Lu Lu (Yale University), Zin Lin (Virginia Tech)
[Abstract]

Multifidelity Linear Regression for Scientific Machine Learning from Scarce Data
Assistant Professor Elizabeth Qian, Ph.D. student Dayoung Kang, Vignesh Sella, Anirban Chaudhuri and Anirban Chaudhuri (University of Texas at Austin)
[Abstract]

LyapInf: Data-Driven Estimation of Stability Guarantees for Nonlinear Dynamical Systems
Ph.D. candidate Tomoki Koike and Assistant Professor Elizabeth Qian
[Abstract]

The Information Geometric Regularization of the Euler Equation
Alumnus Ruijia Cao (B.S. CS 2024), Assistant Professor Florian Schäfer
[Abstract]

Maximum Likelihood Discretization of the Transport Equation
Ph.D. student Brook Eyob, Assistant Professor Florian Schäfer
[Abstract]

Intelligent Attractors for Singularly Perturbed Dynamical Systems
Daniel A. Serino (Los Alamos National Laboratory), Allen Alvarez Loya (University of Colorado Boulder), Joshua W. Burby, Ioannis G. Kevrekidis (Johns Hopkins University), Assistant Professor Qi Tang (Session Co-Organizer)
[Abstract]

Accurate Discretizations and Efficient AMG Solvers for Extremely Anisotropic Diffusion Via Hyperbolic Operators
Golo Wimmer, Ben Southworth, Xianzhu Tang (LANL), Assistant Professor Qi Tang 
[Abstract]

Randomized Linear Algebra for Problems in Graph Analytics
Professor Rich Vuduc
[Abstract]

Improving Spgemm Performance Through Reordering and Cluster-Wise Computation
Assistant Professor Helen Xu
[Abstract]

The Georgia Institute of Technology recently joined the National Semiconductor Technology Center (NSTC), a public-private consortium dedicated to supporting and extending U.S. leadership in semiconductor research, design, engineering, and advanced manufacturing. This collaboration aligns with Georgia Tech's commitment to fostering innovation and driving economic growth through cutting-edge research and development.

"Joining the NSTC is a significant milestone for Georgia Tech," said George White, senior director for strategic partnerships. "This partnership will enable us to collaborate with leading experts in the semiconductor field, drive groundbreaking research, and contribute to the advancement of semiconductor technology in the U.S."

The NSTC is operated by Natcast (National Center for the Advancement of Semiconductor Technology) and supported by the Department of Commerce through the CHIPS and Science Act. NSTC brings together key stakeholders from academia, industry, and government to create a robust semiconductor ecosystem. As a member, Georgia Tech will have access to a wide range of benefits, including research grant opportunities, participation in NSTC-led research projects, and access to state-of-the-art facilities and resources.

Georgia Tech's involvement in the NSTC will focus on several key areas, including workforce development, research and development initiatives, and fostering collaboration between academia and industry. By participating in the NSTC, Georgia Tech aims to enhance its research capabilities, support the growth of the semiconductor industry, and contribute to national economic and security goals.

Learn more about CHIPS initiatives at Georgia Tech:

$100M Investment Will Propel Absolics Inc., Georgia Tech’s Advanced Packaging Research

Georgia Tech Joins $840M DoD Project to Develop and Manufacture Next-gen Semiconductor Microsystems

Semiconductor Research Corp. and Georgia Tech Secure $285M SMART USA Institute

The 2025 Southeastern Energy Conference, Georgia Tech’s annual student-led energy and sustainability conference, took place from Feb. 28 to March 1, 2025. Organized by the Energy Club at Georgia Tech, the conference welcomed over 100 attendees, including industry leaders, policymakers, researchers, and students, fostering dynamic discussions on the future of energy. The theme for this year’s conference, "Going Global: Energy’s Place on the World Stage," highlighted the international nature of energy challenges and solutions, emphasizing collaboration across borders.

The event kicked off with a keynote address from Hon. John Tien, who provided thought-provoking insights into the evolving energy landscape. Following the keynote, the first panel of the day, "The Ukraine Energy War: Lessons in Energy Security," featured expert analysis from Anna Mikulsa of the IDA Science and Technology Policy Institute and Gabriel Collins of Rice University’s Baker Institute. The session was moderated by Georgia Tech student Grant Espy. This was followed by a discussion on the role of nuclear energy globally, where Seth Grae, president and CEO of Lightbridge Corporation, and CJ Fong, vice president of Regulatory Affairs at Blue Energy, shared their perspectives, moderated by Anna Schafer, a student at Georgia Tech.

Throughout the day, attendees had the opportunity to engage with representatives from 10 local and regional energy companies through the Industry Showcase. Companies such as GE Vernova, Georgia Power, Kimley-Horn, and the Georgia Cleantech Innovation Hub were present, providing valuable networking and career development opportunities for students and professionals alike. The day concluded with an engaging panel on "The Potential of Clean Hydrogen," featuring insights from industry leaders including Comas Haynes of Georgia Tech's Strategic Energy Institute, Hayley Ryan of ExxonMobil, Luis Alcoser of Chevron Technology Ventures, and Scott McWhorter of the Southeast Hydrogen Energy Alliance, moderated by Eli Acree, a student at Georgia Tech.

The second day of the conference opened with a keynote speech from Tim Lieuwen, executive vice president for Research at Georgia Tech, who laid out what a carbon-neutral future could truly look like in energy. The "Cybersecurity for Energy Systems" panel brought together Seymour E. Goodman of Georgia Tech, Jake Braun of the University of Chicago, Juan Villarreal of Villarreal Energy, and Forrest Shriver of Sentinel Devices to discuss the challenges and solutions in securing energy infrastructure. Following that, the "Applications of Solar Microgrids" panel moderated by John Blankenhorn, a Ph.D. candidate at Georgia Tech, featured expert perspectives from Letian Dou of Purdue University, Ben Ollis of Oak Ridge National Laboratory, and Raymond Hill of Emory University’s Goizueta Business School.

One of the standout moments of the conference was the Student Symposium, where seven student researchers had the opportunity to present their work, competing for $500 in prize money. Projects explored topics ranging from photocatalysts to heat-driven desalination to thermal batteries for buildings.

The final panel of the event, "Scaled Sustainable Development," moderated by Conference Chair Sam Woolsey, a student at Georgia Tech, featured Jonathan Elkind of Columbia University’s Center on Global Energy Policy, Miguel Granier of the Cox Cleantech Accelerator, and Hon. Jobeth Lillian Coleby-Davis, Minister of Energy & Transport for the Government of the Bahamas.

Faculty Advisor Dan Molzahn also praised the conference, stating, "I've been incredibly impressed by the student organizers in pulling together such a remarkable and well-executed event. Given all the change occurring in the world today around energy, the students' foresight to focus on this topic by bringing in a broad range of experts was a huge benefit to the Georgia Tech community."

Reflecting on the success of the event, Sam Woolsey shared, "I was honored to serve as Energy Club's 2025 Conference Chair and to see the conference so positively received. It was a pleasure to see the ways this year's conference encouraged Georgia Tech engineers to get out of their comfort zone and discuss the policy and international affairs of energy."

The 11th annual Southeastern Energy Conference set a high standard for future student-led initiatives in energy and sustainability at Georgia Tech, fostering meaningful discussions and connections that will continue shaping the field. With a diverse lineup of experts, engaging panels, and invaluable networking opportunities, this event demonstrated Georgia Tech’s leadership in fostering innovative discussions on global energy challenges. The Energy Club extends its heartfelt thanks to all speakers, panelists, industry representatives, and attendees for making this conference a success. Stay tuned for future events and continued conversations on the evolving energy landscape!

Written by: Energy Conference Committee Members:  Braden Queen, Eli Acree, Sam Woolsey, Anna Schafer, Grant Espy, John Blankenhorn

Successful test results of a new machine learning (ML) technique developed at Georgia Tech could help communities prepare for extreme weather and coastal flooding. The approach could also be applied to other models that predict how natural systems impact society. 

Ph.D. student Phillip Si and Assistant Professor Peng Chen developed Latent-EnSF, a technique that improves how ML models assimilate data to make predictions.

In experiments predicting medium-range weather forecasting and shallow water wave propagation, Latent-EnSF demonstrated higher accuracy, faster convergence, and greater efficiency than existing methods for sparse data assimilation.

“We are currently involved in an NSF-funded project aimed at providing real-time information on extreme flooding events in Pinellas County, Florida,” said Si, who studies computational science and engineering (CSE). 

“We're actively working on integrating Latent-EnSF into the system, which will facilitate accurate and synchronized modeling of natural disasters. This initiative aims to enhance community preparedness and safety measures in response to flooding risks.” 

Latent-EnSF outperformed three comparable models in assimilation speed, accuracy, and efficiency in shallow water wave propagation experiments. These tests show models can make better and faster predictions of coastal flood waves, tides, and tsunamis. 

In experiments on medium-range weather forecasting, Latent-EnSF surpassed the same three control models in accuracy, convergence, and time. Additionally, this test demonstrated Latent-EnSF's scalability compared to other methods.

These promising results support using ML models to simulate climate, weather, and other complex systems.

Traditionally, such studies require employment of large, energy-intensive supercomputers. However, advances like Latent-EnSF are making smaller, more efficient ML models feasible for these purposes.

The Georgia Tech team mentioned this comparison in its paper. It takes hours for the European Center for Medium-Range Weather Forecasts computer to run its simulations. Conversely, the ML model FourCastNet calculated the same forecast in seconds.

“Resolution, complexity, and data-diversity will continue to increase into the future,” said Chen, an assistant professor in the School of CSE. 

“To keep pace with this trend, we believe that ML models and ML-based data assimilation methods will become indispensable for studying large-scale complex systems.”

Data assimilation is the process by which models continuously ingest new, real-world data to update predictions. This data is often sparse, meaning it is limited, incomplete, or unevenly distributed over time. 

Latent-EnSF builds on the Ensemble Filter Scores (EnSF) model developed by Florida State University and Oak Ridge National Laboratory researchers. 

EnSF’s strength is that it assimilates data with many features and unpredictable relationships between data points. However, integrating sparse data leads to lost information and knowledge gaps in the model. Also, such large models may stop learning entirely from small amounts of sparse data.

The Georgia Tech researchers employ two variational autoencoders (VAEs) in Latent-EnSF to help ML models integrate and use real-world data. The VAEs encode sparse data and predictive models together in the same space to assimilate data more accurately and efficiently.

Integrating models with new methods, like Latent-EnSF, accelerates data assimilation. Producing accurate predictions more quickly during real-world crises could save lives and property for communities.

[Related: University of South Florida Researchers Track Flooding in Coastal Communities During Hurricanes Helene and Milton]

To share Latent-EnSF to the broader research community, Chen and Si presented their paper at the SIAM Conference on Computational Science and Engineering (CSE25). The Society of Industrial and Applied Mathematics (SIAM) organized CSE25, held March 3-7 in Fort Worth, Texas.

Chen was one of ten School of CSE faculty members who presented research at CSE25, representing one-third of the School’s faculty body. Latent-EnSF was one of 15 papers by School of CSE authors and one of 23 Georgia Tech papers presented at the conference.

The pair will also present Latent-EnSF at the upcoming International Conference on Learning Representations (ICLR 2025). Occurring April 24-28 in Singapore, ICLR is one of the world’s most prestigious conferences dedicated to artificial intelligence research.

“We hope to bring attention to experts and domain scientists the exciting area of ML-based data assimilation by presenting our paper,” Chen said. “Our work offers a new solution to address some of the key shortcomings in the area for broader applications.”

Devesh Ranjan, the Eugene C. Gwaltney, Jr. School Chair of the George W. Woodruff School of Mechanical Engineering, has been named dean of the College of Engineering at the University of Wisconsin-Madison (UW).

Ranjan graduated from UW and has been at Georgia Tech since 2014. He was selected as dean by UW Provost Charles Isbell, a Georgia Tech graduate and former dean of the College of Computing.

Ranjan will lead the Woodruff School through the spring semester. He will join UW in June.

“Devesh is a visionary leader who has created numerous programs to strengthen the Woodruff School community,” said Raheem Beyah, dean of the College of Engineering and Southern Company Chair. “Georgia Tech is my alma mater, and I know there’s nothing like going home. Devesh’s deep commitment and determination will undoubtedly lead to his continued success as he returns to UW to innovate and lead the university’s college of engineering. I’m grateful for his commitment to Tech and the Woodruff School, as well as his valuable guidance and partnership.”

Read more on the COE Website

Many communities rely on insights from computer-based models and simulations. This week, a nest of Georgia Tech experts are swarming an international conference to present their latest advancements in these tools, which offer solutions to pressing challenges in science and engineering.

Students and faculty from the School of Computational Science and Engineering (CSE) are leading the Georgia Tech contingent at the SIAM Conference on Computational Science and Engineering (CSE25). The Society of Industrial and Applied Mathematics (SIAM) organizes CSE25, occurring March 3-7 in Fort Worth, Texas.

At CSE25, the School of CSE researchers are presenting papers that apply computing approaches to varying fields, including:                   

• Experiment designs to accelerate the discovery of material properties
• Machine learning approaches to model and predict weather forecasting and coastal flooding
• Virtual models that replicate subsurface geological formations used to store captured carbon dioxide
• Optimizing systems for imaging and optical chemistry
• Plasma physics during nuclear fusion reactions

[Related: GT CSE at SIAM CSE25 Interactive Graphic] 

“In CSE, researchers from different disciplines work together to develop new computational methods that we could not have developed alone,” said School of CSE Professor Edmond Chow. 

“These methods enable new science and engineering to be performed using computation.” 

CSE is a discipline dedicated to advancing computational techniques to study and analyze scientific and engineering systems. CSE complements theory and experimentation as modes of scientific discovery. 

Held every other year, CSE25 is the primary conference for the SIAM Activity Group on Computational Science and Engineering (SIAG CSE). School of CSE faculty serve in key roles in leading the group and preparing for the conference.

In December, SIAG CSE members elected Chow to a two-year term as the group’s vice chair. This election comes after Chow completed a term as the SIAG CSE program director. 

School of CSE Associate Professor Elizabeth Cherry has co-chaired the CSE25 organizing committee since the last conference in 2023. Later that year, SIAM members reelected Cherry to a second, three-year term as a council member at large. 

At Georgia Tech, Chow serves as the associate chair of the School of CSE. Cherry, who recently became the associate dean for graduate education of the College of Computing, continues as the director of CSE programs. 

“With our strong emphasis on developing and applying computational tools and techniques to solve real-world problems, researchers in the School of CSE are well positioned to serve as leaders in computational science and engineering both within Georgia Tech and in the broader professional community,” Cherry said. 

Georgia Tech’s School of CSE was first organized as a division in 2005, becoming one of the world’s first academic departments devoted to the discipline. The division reorganized as a school in 2010 after establishing the flagship CSE Ph.D. and M.S. programs, hiring nine faculty members, and attaining substantial research funding.

Ten School of CSE faculty members are presenting research at CSE25, representing one-third of the School’s faculty body. Of the 23 accepted papers written by Georgia Tech researchers, 15 originate from School of CSE authors.

The list of School of CSE researchers, paper titles, and abstracts includes:
Bayesian Optimal Design Accelerates Discovery of Material Properties from Bubble Dynamics
Postdoctoral Fellow Tianyi Chu, Joseph Beckett, Bachir Abeid, and Jonathan Estrada (University of Michigan), Assistant Professor Spencer Bryngelson
[Abstract]

Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data
Ph.D. student Phillip Si, Assistant Professor Peng Chen
[Abstract]

A Goal-Oriented Quadratic Latent Dynamic Network Surrogate Model for Parameterized Systems
Yuhang Li, Stefan Henneking, Omar Ghattas (University of Texas at Austin), Assistant Professor Peng Chen
[Abstract]

Posterior Covariance Structures in Gaussian Processes
Yuanzhe Xi (Emory University), Difeng Cai (Southern Methodist University), Professor Edmond Chow
[Abstract]

Robust Digital Twin for Geological Carbon Storage
Professor Felix Herrmann, Ph.D. student Abhinav Gahlot, alumnus Rafael Orozco (Ph.D. CSE-CSE 2024), alumnus Ziyi (Francis) Yin (Ph.D. CSE-CSE 2024), and Ph.D. candidate Grant Bruer
[Abstract]

Industry-Scale Uncertainty-Aware Full Waveform Inference with Generative Models
Rafael Orozco, Ph.D. student Tuna Erdinc, alumnus Mathias Louboutin (Ph.D. CS-CSE 2020), and Professor Felix Herrmann
[Abstract]

Optimizing Coupled Systems: Insights from Co-Design Imaging and Optical Chemistry
Assistant Professor Raphaël Pestourie, Wenchao Ma and Steven Johnson (MIT), Lu Lu (Yale University), Zin Lin (Virginia Tech)
[Abstract]

Multifidelity Linear Regression for Scientific Machine Learning from Scarce Data
Assistant Professor Elizabeth Qian, Ph.D. student Dayoung Kang, Vignesh Sella, Anirban Chaudhuri and Anirban Chaudhuri (University of Texas at Austin)
[Abstract]

LyapInf: Data-Driven Estimation of Stability Guarantees for Nonlinear Dynamical Systems
Ph.D. candidate Tomoki Koike and Assistant Professor Elizabeth Qian
[Abstract]

The Information Geometric Regularization of the Euler Equation
Alumnus Ruijia Cao (B.S. CS 2024), Assistant Professor Florian Schäfer
[Abstract]

Maximum Likelihood Discretization of the Transport Equation
Ph.D. student Brook Eyob, Assistant Professor Florian Schäfer
[Abstract]

Intelligent Attractors for Singularly Perturbed Dynamical Systems
Daniel A. Serino (Los Alamos National Laboratory), Allen Alvarez Loya (University of Colorado Boulder), Joshua W. Burby, Ioannis G. Kevrekidis (Johns Hopkins University), Assistant Professor Qi Tang (Session Co-Organizer)
[Abstract]

Accurate Discretizations and Efficient AMG Solvers for Extremely Anisotropic Diffusion Via Hyperbolic Operators
Golo Wimmer, Ben Southworth, Xianzhu Tang (LANL), Assistant Professor Qi Tang 
[Abstract]

Randomized Linear Algebra for Problems in Graph Analytics
Professor Rich Vuduc
[Abstract]

Improving Spgemm Performance Through Reordering and Cluster-Wise Computation
Assistant Professor Helen Xu
[Abstract]

Georgia Tech researchers have developed a pacifier that can constantly monitor a baby’s electrolyte levels in real time, eliminating the need for repeated invasive blood draws.

Read more »

It’s a fairly niche product now, but a new study from Georgia Tech engineers suggests insulation made from hemp fibers could be a viable industry in the U.S., creating jobs, a manufacturing base, and greener homes and buildings at the same time.

Making the switch could slash the impact of one of the biggest sources of greenhouse gas emissions: Buildings account for roughly 1/5 of emissions globally. By some estimates, using hemp-based products would reduce the environmental impact of insulation by 90% or more. 

The Georgia Tech researchers’ work, reported this month in the Journal of Cleaner Production, is one of the first studies to evaluate the potential for scaling up U.S. production and availability of hemp-based insulation products.

Read about their findings on the College of Engineering website.