The National Institute of Health (NIH) has awarded Yunan Luo a grant for more than $1.8 million to use artificial intelligence (AI) to advance protein research.

New AI models produced through the grant will lead to new methods for the design and discovery of functional proteins. This could yield novel drugs and vaccines, personalized treatments against diseases, and other advances in biomedicine.

“This project provides a new paradigm to analyze proteins’ sequence-structure-function relationships using machine learning approaches,” said Luo, an assistant professor in Georgia Tech’s School of Computational Science and Engineering (CSE).

“We will develop new, ready-to-use computational models for domain scientists, like biologists and chemists. They can use our machine learning tools to guide scientific discovery in their research.” 

Luo’s proposal improves on datasets spearheaded by AlphaFold and other recent breakthroughs. His AI algorithms would integrate these datasets and craft new models for practical application.

One of Luo’s goals is to develop machine learning methods that learn statistical representations from the data. This reveals relationships between proteins’ sequence, structure, and function. Scientists then could characterize how sequence and structure determine the function of a protein.

Next, Luo wants to make accurate and interpretable predictions about protein functions. His plan is to create biology-informed deep learning frameworks. These frameworks could make predictions about a protein’s function from knowledge of its sequence and structure. It can also account for variables like mutations.

In the end, Luo would have the data and tools to assist in the discovery of functional proteins. He will use these to build a computational platform of AI models, algorithms, and frameworks that ‘invent’ proteins. The platform figures the sequence and structure necessary to achieve a designed proteins desired functions and characteristics.

“My students play a very important part in this research because they are the driving force behind various aspects of this project at the intersection of computational science and protein biology,” Luo said.

“I think this project provides a unique opportunity to train our students in CSE to learn the real-world challenges facing scientific and engineering problems, and how to integrate computational methods to solve those problems.”

The $1.8 million grant is funded through the Maximizing Investigators’ Research Award (MIRA). The National Institute of General Medical Sciences (NIGMS) manages the MIRA program. NIGMS is one of 27 institutes and centers under NIH.

MIRA is oriented toward launching the research endeavors of young career faculty. The grant provides researchers with more stability and flexibility through five years of funding. This enhances scientific productivity and improves the chances for important breakthroughs.

Luo becomes the second School of CSE faculty to receive the MIRA grant. NIH awarded the grant to Xiuwei Zhang in 2021. Zhang is the J.Z. Liang Early-Career Assistant Professor in the School of CSE.

[Related: Award-winning Computer Models Propel Research in Cellular Differentiation]

“After NIH, of course, I first thanked my students because they laid the groundwork for what we seek to achieve in our grant proposal,” said Luo.

“I would like to thank my colleague, Xiuwei Zhang, for her mentorship in preparing the proposal. I also thank our school chair, Haesun Park, for her help and support while starting my career.”

Georgia Tech researchers have created a machine learning (ML) visualization tool that must be seen to believe.

Ph.D. student Alec Helbling is the creator of ManimML, a tool that renders common ML concepts into animation. This development will enable new ML technologies by allowing designers to see and share their work in action. 

Helbling presented ManimML at IEEE VIS, the world’s highest-rated conference for visualization research and second-highest rated for computer graphics. It received so much praise at the conference that it won the venue’s prize for best poster. 

“I was quite surprised and honored to have received this award,” said Helbling, who is advised by School of Computational Science and Engineering Associate Professor Polo Chau.

“I didn't start ManimML with the intention of it becoming a research project, but because I felt like a tool for communicating ML architectures through animation needed to exist.”

[RELATED: Polo Chau is One of Three College of Computing Faculty to Receive 2023 Google Award for Inclusion Research]

ManimML uses animation to show ML developers how their algorithms work. Not only does the tool allow designers to watch their projects come to life, but they can also explain existing and new ML techniques to broad audiences, including non-experts.

ManimML is an extension of the Manim Community library, a Python tool for animating mathematical concepts. ManimML connects to the library to offer a new capability that animates ML algorithms and architectures.

Helbling chose familiar platforms like Python and Manim to make the tool accessible to large swaths of users varying in skill and experience. Enthusiasts and experts alike can find practical use in ManimML considering today’s widespread interest and application of ML.

“We know that animation is an effective means of instruction and learning,” Helbling said. “ManimML offers that ability for ML practitioners to easily communicate how their systems work, improving public trust and awareness of machine learning.”

ManimML overcomes what has been an elusive approach to visualizing ML algorithms. Current techniques require developers to create custom animations for every specific algorithm, often needing specialized software and experience.

ManimML streamlines this by producing animations of common ML architectures coded in Python, like neural networks.

A user only needs to specify a sequence of neural network layers and their respective hyperparameters. ManimML then constructs an animation of the entire network.

“To use ManimML, you simply need to specify an ML architecture in code, using a syntax familiar to most ML professionals,” Helbling said. “Then it will automatically generate an animation that communicates how the system works.”

ManimML ranked as the best poster from a field of 49 total presentations. IEEE VIS 2023 occurred Oct. 22-27 in Melbourne, Australia. This event marks the first time IEEE held the conference in the Southern Hemisphere.

ManimML has more than 23,000 downloads and a demonstration on social media has hundreds of thousands of views.

ManimML is open source and available at: https://github.com/helblazer811/ManimML

AI solutions have the power to become our silent partners in ways that could drastically improve our daily lives — and are already doing it. Yet, in a world where algorithms can sift through data with a precision no human can match, uneasiness stirs. 

Georgia Tech researchers are confronting the paradoxes, pitfalls, and potential of artificial intelligence. Here, some of them shed light on the emerging role of AI in our lives — and answer questions about how humans and machines will coexist in the future.  

We asked Georgia Tech AI experts key questions about the technology, its use and misuse, and how it might shape our shared future. Here’s what they had to say.

Click here to read the story. 

A new kind of polymer membrane created by researchers at Georgia Tech could reshape how refineries process crude oil, dramatically reducing the energy and water required while extracting even more useful materials.

The so-called DUCKY polymers — more on the unusual name in a minute — are reported Oct. 16 in Nature Materials. And they’re just the beginning for the team of Georgia Tech chemists, chemical engineers, and materials scientists. They also have created artificial intelligence tools to predict the performance of these kinds of polymer membranes, which could accelerate development of new ones.

The implications are stark: the initial separation of crude oil components is responsible for roughly 1% of energy used across the globe. What’s more, the membrane separation technology the researchers are developing could have several uses, from biofuels and biodegradable plastics to pulp and paper products.

“We're establishing concepts here that we can then use with different molecules or polymers, but we apply them to crude oil because that's the most challenging target right now,” said M.G. Finn, professor and James A. Carlos Family Chair in the School of Chemistry and Biochemistry.

Read the full story on the College of Engineering website.

Sean Castillo is in the win-win business. As an industrial hygienist in the Georgia Tech Enterprise Innovation Institute (EI2), his job is to ensure that employees are safe in their workspaces, and when he does that, he simultaneously improves a company’s performance.

That’s been a theme for Castillo and his colleagues in the Safety, Health, Environmental Services (SHES) program and their partners in the Georgia Manufacturing Extension Partnership (GaMEP), part of EI2’s suite of programs aimed at helping Georgia businesses thrive.

“A healthier workforce is healthy for business,” said Castillo, part of the SHES team of consultants who often work closely with their GaMEP counterparts to improve safety while also maximizing productivity.

This team of experts from EI2 assist companies trying to reach that critical intersection of both, combining smart ergonomics and safety enhancements with lean manufacturing practices. This can solve human performance gaps due to fatigue, heat, or some other environmental stressor, while helping businesses continue to improve their production processes and, ultimately, their bottom line.

These stressors cost U.S. industry billions of dollars each year — fatigue, for example, is responsible for about $136 billion in lost productivity.

“Protecting your employee — investing in safety now — saves a lot of money later,” Castillo said. “It equates to less money spent on workers compensation and less employee turnover, which means less time training new employees, and that ideally leads to a more efficient process in the workplace.”

It takes careful and intentional collaboration to bring those moving pieces together, and inextricably linked programs like SHES and GaMEP can help orchestrate all of that.

Ensuring Safe Workspaces

SHES is staffed by safety consultants, like Castillo, who provide a free and essential service to Georgia businesses. They help companies ensure that they meet or exceed the standards set by the federal Occupational Health and Safety Administration (OSHA), mainly through SHES’ flagship OSHA 21(d) Consultation Program.

“Our job is to ensure that workspaces and processes are designed so that anybody can perform the work safely,” said Trey Sawyers, a safety, health, and ergonomics consultant on the SHES team, aiding small and mid-sized businesses in Georgia. When a company reaches out to SHES to apply for the free, confidential OSHA consultation program, a consultant like Sawyers gets assigned to the task, “based on our area of expertise,” said Sawyers, an expert in ergonomics, which is the science of designing and adapting a workspace to efficiently suit the physical and mental needs and limitations of workers.

“If a company is having ergonomic issues — maybe they’re experiencing a lot of strains and sprains — then I might get the call because of my knowledge and understanding of anthropometry, and then I’ll go take a close look at the facility,” Sawyers said. Anthropometry is the scientific study of a human’s size, form, and functional capacity.

SHES consultants can identify potential workplace hazards, provide guidance on how to comply with OSHA standards, and establish or improve safety and health programs in the company.

“The caveat is the company has to correct any serious hazards that we find,” said Castillo, who visits a wide range of workspaces in his role. For instance, his job will take him to construction and manufacturing sites, gun ranges, even office settings. “We do noise and air monitoring at all different types of workplaces. I was at a primary care clinic the other day. And over the past few years, we’ve had a significant emphasis on stone fabricators, looking for overexposures to respirable crystalline silica.”

Silica, which is dust residue from the process of creating marble and quartz slabs, can lead to a lung disease called silicosis. OSHA established new limits that cut the permissible exposure limits in half, and that has kept the SHES consultants busy as Georgia manufacturers try to achieve and maintain compliance.

Keeping Companies Cool

Another area of growing emphasis for Georgia Tech’s consultants is heat-related stress in the workplace.

“Currently, there are no standards to address this,” Castillo said. “For example, there are no rules that say a construction site worker should drink this much water. There are suggested guidelines and emphasis programs for inspections for targeted industries where heat stress may be prevalent — but no standards, though that is coming.”

The SHES team is trying to stay ahead of what will likely be new federal rules for heat mitigation. To help develop safe standards and better understand the effects of heat on workers, consultants like Castillo are going to construction sites, plant nurseries, and warehouses, and enlisting volunteers in field studies. Using heat stress monitor armbands, they’re monitoring data on workers’ core body temperatures and heart rates.

“These tools are great because we’re not only gathering some good data, but we can use them proactively to prevent heat events such as heat exhaustion and heatstroke, which can be fatal if left untreated,” Castillo said.

To further help educate Georgia companies about the risks of heat-related problems, SHES applied for and recently won a Susan Harwood Training Grant from the U.S. Department of Labor. The $160,000 award will support SHES consultants’ efforts to further their work in heat stress education so that “companies and workers will understand the warning signs and the potential effects of heat stress, and how they can stay safe,” Castillo said. “We’re sure this will all become part of OSHA standards eventually, and we’d like to help our clients stay ahead of the curve to protect their employees.”

OSHA standards are the law, and while larger corporations routinely hire consulting firms to keep them on the straight and narrow, SHES is providing the same level of expertise for its smaller business clients for free. Most of those clients apply for help through SHES’ online request form. And others find the help they need through the guidance of process improvement specialist Katie Hines and her colleagues in GaMEP.

Lean and Safe

Hines came to her appreciation of ergonomics naturally. After graduating from Auburn University, she entered the workforce as a manufacturing engineer for a building materials company, where “it was just part of our day-to-day work life in that manufacturing environment, on the production floor,” she said.

It took grad school and a deeper focus on lean and continuous improvement processes to formalize that appreciation.

While working toward her master’s degree in chemical engineering at Auburn, Hines earned a certificate in occupational safety and ergonomics (like Sawyers, her SHES colleague). At the same time, Hines was helping to guide her company’s lean and continuous improvement program. And when she joined Proctor and Gamble after completing her degree, “The lean concept and safety best practices were fully ingrained, part of the daily discussion there,” she said.

All those hands-on manufacturing production floor experiences managing people and systems prepared Hines well for her current role as a project manager on GaMEP’s Operational Excellence team, where her focus is entirely on lean and continuous improvement work — that is, helping companies reduce waste and improve production while also enhancing safety and ergonomics.

Hines uses her expertise in knowing how manufacturing processes and people should look when everyone is safe and also productive. She can walk into a GaMEP client’s facility and drive the process improvements and solutions that will help them achieve a leaner, more efficient form of production. And then, when she sees the need, Hines will recommend the client contact SHES, “the people who have their fingers on the data and the expertise to improve safety.”

These were concepts that, for a long time, seemed to be working against each other — the very idea of maximizing production and improving profits while also emphasizing worker safety and comfort.

“But you can have both,” Castillo said. “You should have both.”

The start of the fall semester can be busy for most Georgia Tech students, but this is especially true for Rafael Orozco. The Ph.D. student in Computational Science and Engineering (CSE) is part of a research group that presented at a major conference in August and is now preparing to host a research meeting in November.

We used the lull between events, research, and classes to meet with Orozco and learn more about his background and interests in this Meet CSE profile.

Student: Rafael Orozco  

Research Interests: Medical Imaging; Seismic Imaging; Generative Models; Inverse Problems; Bayesian Inference; Uncertainty Quantification 

Hometown: Sonora, Mexico 

Tell us briefly about your educational background and how you came to Georgia Tech. 
I studied in Mexico through high school. Then, I did my first two years of undergrad at the University of Arizona and transferred to Bucknell University. I was attracted to Georgia Tech’s CSE program because it is a unique combination of domain science and computer science. It feels like I am both a programmer and a scientist.  

How did you first become interested in computer science and machine learning? 

In high school, I saw a video demonstration of a genetic algorithm on the internet and became interested in the technology. My high school in Mexico did not have a computer science class, but a teacher mentored me and helped me compete at the Mexican Informatics Olympiad. When I started at Arizona, I researched the behavior of clouds from a Bayesian perspective. Since then, my research interests have always involved using Bayesian techniques to infer unknowns.  

You mentioned your background a few times. Since it is National Hispanic Heritage Month, what does this observance mean to you? 

I am quite proud to be a part of this group. In Mexico and the U.S., fellow Hispanics have supported me and my pursuits, so I know firsthand of their kindness and resourcefulness. I think that Hispanic people welcome others, celebrating the joy our culture brings, and they appreciate that our country uses the opportunity to reflect on Hispanic history. 

You study in Professor Felix Herrmann’s Seismic Laboratory for Imaging and Modeling (SLIM) group. In your own words, what does this research group do? 

We develop techniques and software for imaging Earth’s subsurface structures. These range from highly performant partial differential equation solvers to randomized numerical algebra to generative artificial intelligence (AI) models.  

One of the driving goals of each software package we develop is that it needs to be scalable to real world applications. This entails imaging seismic areas that can be kilometers cubed in volume, represented typically by more than 100,000,000 simulation grid cells. In my medical applications, high-resolution images of human brains that can be resolved to less than half a millimeter.  

The International Meeting for Applied Geoscience and Energy (IMAGE) is a recent conference where SLIM gave nine presentations. What research did you present here? 
The challenge of applying machine learning to seismic imaging is that there are no examples of what the earth looks like. While making high quality reference images of human tissues for supervised machine learning is possible, no one can “cut open” the earth to understand exactly what it looks like.  

To address this challenge, I presented an algorithm that combines generative AI with an unsupervised training objective. We essentially trick the generative model into outputting full earth models by making it blind to which part of the Earth we are asking for. This is like when you take an exam where only a few questions will be graded, but you don’t know which ones, so you answer all the questions just in case.  

While seismic imaging is the basis of SLIM research, there are other applications for the group’s work. Can you discuss more about this? 

The imaging techniques that the energy industry has been using for decades toward imaging Earth’s subsurface can be applied almost seamlessly to create medical images of human sub tissue.  

Lately, we have been tackling the particularly difficult modality of using high frequency ultrasound to image through the human skull. In our recent paper, we are exploring a powerful combination between machine learning and physics-based methods that allows us to speed up imaging while adding uncertainty quantification.  
 
We presented the work at this year’s MIDL conference (Medical Imaging with Deep Learning) in July. The medical community was excited with our preliminary results and gave me valuable feedback on how we can help bring this technique closer to clinical viability. 

A scientific machine learning (ML) expert at Georgia Tech is lending a hand in developing an app to identify and help Florida communities most at risk of flooding.

School of Computational Science and Engineering (CSE) Assistant Professor Peng Chen is co-principal investigator of a $1.5 million National Science Foundation grant to develop the CRIS-HAZARD system.

CRIS-HAZARD‘s strength derives from integrating geographic information and data mined from community input, like traffic camera videos and social media posts.  

This ability helps policymakers identify areas most vulnerable to flooding and address community needs. The app also predicts and assesses flooding in real time to connect victims with first responders and emergency managers.

“Successfully deploying CRIS-HAZARD will harness community knowledge through direct and indirect engagement efforts to inform decision-making,” Chen said. “It will connect individuals to policymakers and serve as a roadmap at helping the most vulnerable communities.”

Chen’s role in CRIS-HAZARD will be to develop new ML models for the app’s prediction capability. These assimilation models integrate the mined data with predictions from current hydrodynamic models.

Along with making an immediate impact in flood-prone coastal communities, Chen said these models could have broader applications in the future. These include models for improved hurricane prediction and management of water resources.

The models Chen will build for CRIS-HAZARD derive from past applications aimed at helping communities.

Chen has crafted similar models for monitoring and mitigating disease spread, including Covid-19. He has also worked on materials science projects to accelerate the design of metamaterials and self-assembly materials.

“Scientific machine learning is very broad concept and can be applied to many different fields,” Chen said. “Our group looks at how to accelerate optimization, account for risk, and quantify uncertainty in these applications.”

Uncertainty in CRIS-HAZARD is what brings Chen to the project, headed by University of South Florida researchers. While the app’s novelty lies in its use of heterogenous data, inferring predictions can be challenging since the data comes from different sources in varying formats. 

To overcome this, Chen intends to build new data assimilation models from scratch powered by deep neural networks (DNNs).

Along with their ability to find connections between heterogeneous data, DNNs are scalable and inexpensive. This beats the alternative of using supercomputers to make the same calculations.

DNNs are also fast and can significantly reduce computational time. According to Chen, the efficiency of DNNs can achieve acceleration hundreds of thousands of times greater than classical models.

Low cost and time make it possible to run DNN-based simulations multiple times. This improves reliability in prediction results in real-time once the DNNs are properly trained.

“The data may not be consistent or compatible since there are different models we’re trying to integrate, making prediction uncertain,” Chen said. “We can run these ML models many times to quantify the uncertainty and give a probability distribution or a range of predictions.”

CRIS-HAZARD also exemplifies the power of collaboration across disciplines and universities. In this case, machine learning techniques reach across state boundaries to help people that are vulnerable to flooding or other natural disasters.

USF Professor Barnali Dixon leads the project with Associate Professor Yi Qiang— both geocomputation researchers in the School of Geosciences, incorporating data science and artificial intelligence.

Subhro Guhathakurta collaborates with Chen from Georgia Tech. Along with being a professor in the School of City & Regional Planning, Guhathkurta is director of Tech’s Master of Science in Urban Analytics program and the Center for Spatial Planning and Analytics and Visualization.

Centipedes are known for their wiggly walk. With tens to hundreds of legs, they can traverse any terrain without stopping.

“When you see a scurrying centipede, you're basically seeing an animal that inhabits a world that is very different than our world of movement,” said Daniel Goldman, the Dunn Family Professor in the School of Physics. “Our movement is largely dominated by inertia. If I swing my leg, I land on my foot and I move forward. But in the world of centipedes, if they stop wiggling their body parts and limbs, they basically stop moving instantly.”

Intrigued to see if the many limbs could be helpful for locomotion in this world, a team of physicists, engineers, and mathematicians at the Georgia Institute of Technology are using this style of movement to their advantage. They developed a new theory of multilegged locomotion and created many-legged robotic models, discovering the robot with redundant legs could move across uneven surfaces without any additional sensing or control technology as the theory predicted.

These robots can move over complex, bumpy terrain — and there is potential to use them for agriculture, space exploration, and even search and rescue.

The researchers presented their work in the papers, “Multilegged Matter Transport: A Framework for Locomotion on Noisy Landscapes,” in Science in May and “Self-Propulsion via Slipping: Frictional Swimming in Multilegged Locomotors,” in Proceedings of the National Academy of Sciences in March.

A Leg Up

For the Science paper, the researchers were motivated by mathematician Claude Shannon’s communication theory, which demonstrates how to reliably transmit signals over distance, to understand why a multilegged robot was so successful at locomotion. The theory of communication suggests that one way to ensure a message gets from point A to point B on a noisy line isn’t to send it as an analog signal, but to break it into discrete digital units and repeat these units with an appropriate code.

“We were inspired by this theory, and we tried to see if redundancy could be helpful in matter transportation,” said Baxi Chong, a physics postdoctoral researcher. “So, we started this project to see what would happen if we had more legs on the robot: four, six, eight legs, and even 16 legs.”

A team led by Chong, including School of Mathematics postdoctoral fellow Daniel Irvine and Professor Greg Blekherman, developed a theory that proposes that adding leg pairs to the robot increases its ability to move robustly over challenging surfaces — a concept they call spatial redundancy. This redundancy makes the robot’s legs successful on their own without the need for sensors to interpret the environment. If one leg falters, the abundance of legs keeps it moving regardless. In effect, the robot becomes a reliable system to transport itself and even a load from A to B on difficult or “noisy” landscapes. The concept is comparable to how punctuality can be guaranteed on wheeled transport if the track or rail is smooth enough but without having to engineer the environment to create this punctuality.

“With an advanced bipedal robot, many sensors are typically required to control it in real time,” Chong said. “But in applications such as search and rescue, exploring Mars, or even micro robots, there is a need to drive a robot with limited sensing. There are many reasons for such sensor-free initiative. The sensors can be expensive and fragile, or the environments can change so fast that it doesn’t allow enough sensor-controller response time.”

To test this, Juntao He, a Ph.D. student in robotics, conducted a series of experiments where he and Daniel Soto, a master’s graduate in the George W. Woodruff School of Mechanical Engineering, built terrains to mimic an inconsistent natural environment. He then tested the robot by increasing its number of legs by two each time, starting with six and eventually expanding to 16. As the leg count increased, the robot could more agilely move across the terrain, even without sensors, as the theory predicted. Eventually, they tested the robot outdoors on real terrain, where it was able to traverse in a variety of environments.

“It's truly impressive to witness the multilegged robot's proficiency in navigating both lab-based terrains and outdoor environments,” Juntao said. “While bipedal and quadrupedal robots heavily rely on sensors to traverse complex terrain, our multilegged robot utilizes leg redundancy and can accomplish similar tasks with open-loop control.”

Next Steps

The researchers are already applying their discoveries to farming. Goldman has co-founded a company that aspires to use these robots to weed farmland where weedkillers are ineffective.

“They’re kind of like a Roomba but outside for complex ground,” Goldman said. “A Roomba works because it has wheels that function well on flat ground. Until the development of our framework, we couldn’t confidently predict locomotor reliability on bumpy, rocky, debris-ridden terrain. We now have the beginnings of such a scheme, which could be used to ensure that our robots traverse a crop field in a certain amount of time.”

The researchers also want to refine the robot. They know why the centipede robot framework is functional, but now they’re determining the optimal number of legs to achieve motion without sensing in a way that is cost-effective yet still retains the benefits.

“In this paper, we asked, ‘How do you predict the minimum number of legs to achieve such tasks?’” Chong said. “Currently we only prove that the minimum number exists, but we don't know that exact number of legs needed. Further, we need to better understand the tradeoff between energy, speed, power, and robustness in such a complex system.”

CITATION:

Baxi Chong et al., Multilegged matter transport: A framework for locomotion on noisy landscapes.Science380,509-515(2023).DOI:10.1126/science.ade4985

Lisa Marks is launching the ancient craft of fishing villages into space vehicle design. Her work adapting traditional textile handcraft to modern problems created a unique opportunity for collaboration cleaning up space debris.

According to NASA's Orbital Debris Program Office (OPDO), this debris jeopardizes future space projects. Large objects like rocket bodies and non-functional satellites are the source of fragmentation debris.

The OPDO website says removal of even five of the highest-risk objects per year could stabilize the low Earth orbit debris environment.

A research team with members from the Georgia Tech Research Institute, the Aerospace Systems Design Laboratory, and the Space Systems Design Laboratory has developed a concept using a net to capture and de-orbit large debris.

A mutual connection at Tech's GVU recommended that the team speak to Lisa Marks, assistant professor in the School of Industrial Design, based on her work combining traditional textile with new materials and methods.

Putting Textiles in Space Requires Creative Expertise

“There’s a lot of different projects on space debris happening all around the world,” Marks said, “and there’ve been a few concept papers talking about using a net.”

“But all the drawings of the net are basic concepts, just a square with a few hatches through it. No one has figured out what that net might be.”

Marks researches ways to combine traditional textile handcraft with algorithmic modeling. “I specialize in analyzing the shape of every stitch and how we can use that stitch differently. Can we create new patterns through coding, or make it larger and out of wood?”

“It allows me to think really creatively about how we can use different textiles.”

This innovative, exploratory approach is a natural fit to create a net for a job no has ever done. “There's a lot of technical considerations with this,” Marks said. 

“It must pack incredibly small, weigh very little, and still be strong enough to capture and drag a rocket fuselage. There are considerations just for a material to exist in space. It needs to have low UV reactivity, low off gassing.”

“We need to understand every single little aspect of each of these techniques in order to do this.”

Static Nets Catch Fish; Slippery Nets Catch Rockets

Marks is working with Teflon, using the same knots used for fishing nets, but the non-traditional material means the nets work differently than fishing nets, she said. “These knots are made to be static, because you don’t want fish to get through the nets. But because Teflon is so slippery, the knots move around.”

“I think it will help the net’s strength, because the net will deform around irregular shapes before it breaks. What makes it unsuitable for fishing and annoying to work with becomes a huge benefit for what we need it to do.”

Some traditional handcraft techniques are dying out, and Marks sees projects like this as a reason preserving these techniques is important. “We don’t know what problems we’re going to have to solve in the future, and these crafts can be used in really surprising ways.”

“I would not have thought, ‘Netted filet lace, that’s how we’re going to solve a space problem!’ But if we lose this type of lace, we can’t solve space problems with it.”

Semiconductors, or microchips, are vital to life in the modern world. They’re used in the microwave you heated your breakfast in this morning, the car you drove to work, the mobile phone you shouldn’t use while driving, the bank ATM you visited, and the screened device you’re reading this story on.

They’re in our TVs, refrigerators, and washing machines, helping us live comfortable lives. They also help us stay alive as part of the medical network, used in pacemakers, blood pressure monitors, and MRI machines, among other things. Also, our national economic and defense systems rely on them. Basically, semiconductors control and manage the flow of information in the machinery that keeps the world going.

And right now, at Georgia Tech, researchers are working to innovate chip technology to ensure that U.S. semiconductor development is globally competitive, reliable, sustainable, and resilient, today and in the future.

“If you look at semiconductors, or the whole area of computing, it spans across Georgia Tech — across many different schools and disciplines,” said Arijit Raychudhury, professor and Steve W. Chaddick Chair in the School of Electrical and Computer Engineering (ECE). “Starting with physics and chemistry, where we essentially learn how different types of materials will react, to materials science and engineering, to electrical engineering and computer engineering, to computer science.”

It's a diverse, multidisciplinary enterprise from bottom to top, Raychudhury noted. And there is still plenty of room at the bottom, as theoretical physicist Richard P. Feynman famously said more than 60 years ago, predicting that one day we’d be making things at the atomic level. We are. It’s a familiar realm to Victor Fung and his lab, where they are designing new materials for semiconductors from the ground up, atom by atom.

“We are interested in exploring how to translate the latest advances in AI and machine learning to aid in accelerating computational materials simulations and materials discovery,” said Fung, assistant professor in the School of Computational Science. “We’ve been developing methods which can accurately predict a wide range of materials’ properties, to greatly facilitate high-throughput materials screening.”

Fung’s lab is using AI to discover previously unstudied materials with the electronic properties to build into chips. This approach to creating “designer” semiconductors would be significantly faster and cover more of the materials space than current methods.

Improving the Landscape

Smaller, more efficient, and more powerful are all part of the constantly evolving landscape in semiconductor research and development. It’s a very expensive landscape. While many chips are about the size of a fingernail, they are among the most complex human-made objects on Earth. Just building a semiconductor fabrication factory costs billions of dollars.

For a chemical engineer like Michael Filler, that sounds like opportunity.

“Chemical engineers think about how we produce products on a massive scale,” said Filler, associate professor in the School of Chemical and Biomolecular Engineering and associate director of the Institute for Electronics and Nanotechnology (IEN).

Filler, whose research involves the growing of semiconductor components, like transistors, from seed particles, is aiming to help democratize the process of chip development, bringing down the cost substantially while maintaining performance. In a not too distant future, that could mean an individual at home printing a chip on a machine similar to a 3D printer.

“Imagine a laser printer that can literally spit out custom electronics in a matter of minutes,” Filler said. “We’re big believers in the individual’s ability to be creative and know what they want to build for their applications. Ultimately, we’re interested in giving makers and prototypers opportunities to customize electronics.”

He’s in the right place for the far-reaching research he has in mind, adding, “We are so blessed with great facilities at Georgia Tech. It would be hard to imagine working somewhere else, because very few places have the diversity and quality of tooling we have here.”

IEN, which facilitates much of the semiconductor research at Georgia Tech, is based in the Marcus Nanotechnology Building, with its state-of-the-art micro/nano fabrication facilities such as the shared cleanroom space and a laser machine lab for micromachining.

But it is the range of expertise and creativity among faculty and students who are making IEN and Georgia Tech a thought leader in semiconductor research. This is evidenced by Tech’s recent grant of $65.7 million from the Semiconductor Research Corporation and the Defense Research Projects Agency to launch two new interdisciplinary research centers.

Events like Georgia Tech Chip Day (May 2) and Nanowire Week, an international gathering happening in Atlanta in October, also speak to Tech’s growing influence in this area.

Answering the Call

The Covid-19 pandemic clarified just how difficult it can be to make more chips. A shortage of semiconductors affected the supply of phones, computers, and other commonly used items during the global shutdown. Increased demand, depleted reserves, and too few manufacturing plants and workers significantly crippled the supply chain.

“The high degree of geographic concentration in certain parts of the semiconductor supply chain has recently created a heightened risk of supply interruptions,” said Chip White, Schneider National Chair in Transportation and Logistics and professor in the H. Milton Stewart School of Industrial and Systems Engineering (ISyE). “Such interruptions and resulting wild fluctuations in semiconductor demand can threaten the nation’s public health, defense, and economic security.”

With that in mind, translational supply chain research is going on in several places on campus, White said, including the Supply Chain and Logistics Institute and the NSF AI Research Institute for Advances in Optimization. White and his colleagues are developing software platforms for stress testing manufacturing supply chains. The goal is to identify vulnerabilities and risk mitigation procedures to design and operate next generation supply chains for critical industries such as the semiconductor industry, to improve global competitiveness and strike a balance between market forces and national security.

In an effort to address and feed the next generation demand for chips, the Biden administration recently launched a massive effort to outcompete China in semiconductor manufacturing, offering $39 billion in funding incentives for companies seeking to build plants in the U.S.

Another related area of importance in the ongoing development of semiconductors is growing the workforce of the future, and that includes a new wave of researchers. This is a role that Jennifer Hasler takes seriously.

“I have a strong interest and belief in mentoring,” said Hasler, ECE professor and founder of the Integrated Computational Electronics lab at Georgia Tech. She’s proven, theoretically at least, that the technology already exists to build a silicon-based version of the human cerebral cortex (which would cost billions of dollars to design and build), but one of her favorite roles is working with new, young faculty.

“It’s a personal thing for me, but it’s one of the coolest things I’m involved in,” she said. “When they come to Georgia Tech, they see how big this place is, bigger than a company. I like to say to them, ‘Let’s calm down, take a breath, you’re good, so let’s go make some cool stuff. Let’s get some momentum going.’”

For Raychowdhury, director of the new Center for the Co-Design of Cognitive Systems (part of the JUMP 2.0 program), developing the skilled workforce of the future means answering the call of the nation.

“This is one of the largest ECE departments in the country, with many, many talented students,” he said. “And given the need and shortage of skilled professionals in this particular area, I think it’s critical for us to create that kind of pipeline.” Last year, ECE undergraduate students started taking a new, two-semester course, sponsored by Apple, in which they actually build microprocessors from scratch.

“This is completely new,” Raychowdhury said. “It’s expensive to offer this course, but we plan to keep doing it and we’re in conversations with other companies that want to invest in workforce development. So, in addition to doing fantastic research, we want to be sensitive to the needs of the country and a new generation.”