For the 10th Demo Day, the Tech community came out in droves to support 75 Georgia Tech startups created by students, alumni, and faculty. In booths spread out in Exhibition Hall, they displayed their products, which ranged from AI and robotic training gear to fungi fashion, and more. Over four hours, more than 1,500 people filed in and out of the hall. Founders pitched their innovations to business and community leaders, as well as students and the public, eager to witness groundbreaking innovations across various industries.
Kiandra Peart, co-founder of Reinvend, said the amount of people surprised her.
“After the first VIP session was over, hundreds of people were just flooding through the door at all times,” she said. “We had to give the pitch a million times to explain it to a lot of different people, but they seemed really, really engaged, and we were also able to get a few interactions.”
Reinvend is working through a potential deal with Tech Dining on using their vending machines, which would expand food options for students after dining halls close.
Demo Day is the culmination of the 12-week summer accelerator, Startup Launch, where founders learn about entrepreneurship and build out their businesses with the support of mentors. Along with guidance from experts in business, teams receive $5,000 in optional funding and $30,000 of in-kind services. This year, the program had over 100 startups and 250 founders, continuing the growth trend for CREATE-X. The program aims to eventually support the launch of 300 startups per year.
Peart said the experience taught the team how to better pitch to potential clients and formulate a call to action after a successful interaction.
Since its inception in 2014, CREATE-X has had more than 5,000 participate in their programming, which is segmented in three areas: Learn, Make, and Launch. Besides providing resources, the program also helps founders through its rich entrepreneurial ecosystem.
“We want to increase access to entrepreneurship. That’s the heart of the program, and it’s the goal to have everyone in the Tech community to have entrepreneurial confidence. The energy and passion of our founders to solve real-world problems — it’s palpable at Demo Day. I’d say it’s the best place to see what we’re about and understand what this program offers,” said Rahul Saxena, director of CREATE-X, who also reminded founders that the connections they make here would last for years.
At its core, CREATE-X is a community geared toward innovation. Participants were at the forefront of integrating OpenAI's GPT-3 when it was not yet widely adopted. They share their insights with each other, and the program has mentors coming back from even the very first cohort. Starting with eight teams, CREATE-X has now launched more than 400 startup teams, with founders representing 38 academic majors. Its total startup portfolio valuation is above $1.9 billion.
Peart compared CREATE-X to an energy drink.
“After going through the program, I was really able to refine my ideas, talk with other people, and now that the program is over, I feel energized,” she said. “I think that having an accelerator right at home allows students who may have never considered starting a company, or didn't have access to an accelerator, to actually utilize their resources from their school and their own community to get their companies started.”
Although Demo Day just ended, CREATE-X is already gearing up for the next cohort. Applications for Startup Launch opened Aug. 31, the same day as Demo Day.
“Consider interning for yourself next summer,” said Saxena. “We know you have ideas about solutions to address global challenges. You’re at Tech; you have the talent. Let us help you with the resources and support system.”
Georgia Tech students, alumni, and faculty can apply to GT Startup Launch now. The priority deadline is Nov. 6. To learn more about CREATE-X, find CREATE-X events to build a startup team, or learn more about entrepreneurship, visit th CREATE-X website
News Contact
Breanna Durham
Marketing Strategist
The water coming out of your faucet is safe to drink, but that doesn’t mean it’s completely clean. Chlorine has long been the standard for water treatment, but it often contains trace levels of disinfection byproducts and unknown contaminants. Georgia Institute of Technology researchers developed the minus approach to handle these harmful byproducts.
Instead of relying on traditional chemical addition (known as the plus approach), the minus approach avoids disinfectants, chemical coagulants, and advanced oxidation processes typical to water treatment processes. It uses a unique mix of filtration methods to remove byproducts and pathogens, enabling water treatment centers to use ultraviolet light and much smaller doses of chemical disinfectants to minimize future bacterial growth down the distribution system.
“The minus approach is a groundbreaking philosophical concept in water treatment,” said Yongsheng Chen, the Bonnie W. and Charles W. Moorman IV Professor in the School of Civil and Environmental Engineering. “Its primary objective is to achieve these outcomes while minimizing the reliance on chemical treatments, which can give rise to various issues in the main water treatment stream.”
Chen and his student Elliot Reid, the primary author, presented the minus approach in the paper, “The Minus Approach Can Redefine the Standard of Practice of Drinking Water Treatment,” in The American Chemical Society.
The minus approach physically separates emerging contaminants and disinfection byproducts from the main water treatment process using these already proven processes:
- Bank filtration withdraws water from naturally occurring or constructed banks like rivers or lakes. As the water travels through the layers of soil and gravel, it naturally filters out impurities, suspended particles, and certain microorganisms.
- Biofiltration uses biological processes to treat water by passing it through filter beds made of sand, gravel, or activated carbon that can support the growth of beneficial microorganisms, which in turn can remove contaminants.
- Adsorption occurs when an adsorbent material like activated carbon is used to trap contaminants.
- Membrane filtration uses a semi-permeable membrane to separate particles and impurities from the main treatment process.
The minus approach is intended to engage the water community in designing safer, more sustainable, and more intelligent systems. Because its technologies are already available and proven, the minus approach can be implemented immediately.
It can also integrate with artificial intelligence (AI) to improve filtration’s effectiveness. AI can aid process optimization, predictive maintenance, faulty detection and diagnosis, energy optimization, and decision-support systems. AI models have also been able to reliably predict the origin of different types of pollution in source water, and models have also successfully detected pipeline damage and microbial contamination, allowing for quick and efficient maintenance.
“This innovative philosophy seeks to revolutionize traditional water treatment practices by providing a more sustainable and environmentally friendly solution,” Chen said. “By reducing the reliance on chemical treatments, the minus approach mitigates the potential risks associated with the use of such chemicals, promoting a safer water supply for both human consumption and environmental protection.”
CITATION: Elliot Reid, Thomas Igou, Yangying Zhao, John Crittenden, Ching-Hua Huang, Paul Westerhoff, Bruce Rittmann, Jörg E. Drewes, and Yongsheng Chen
Environmental Science & Technology 2023 57 (18), 7150-7161
DOI: 10.1021/acs.est.2c09389
News Contact
Tess Malone, Senior Research Writer/Editor
tess.malone@gatech.edu
Large-bodied mammals play crucial roles in ecosystems. They create habitats, serve as prey, help plants thrive, and even influence how wildfires burn. But now, fewer than half of the large mammal species that were alive 50,000 years ago exist today, and those that remain are threatened with extinction from intensifying climate change and human activities.
While mammal extinctions are well-documented, very little research has explored the impact those losses had on the nuanced ways in which mammal communities interact with their environments. Researchers at the Georgia Institute of Technology are using a novel methodology to investigate how mammals’ ability to function in their environments has been threatened in the past, and what challenges they can expect to face in the future.
Jenny McGuire, associate professor in the School of Biological Sciences and leader of the Spatial Ecology and Paleontology Lab, and Daniel Lauer, a graduate student, looked millions of years into the past, observing how and why eastern African herbivores’ relationships with their environments changed across space and time in the face of biodiversity loss. They used a novel approach to build models that show how specific mammal traits — like body mass and tooth shape — evolved with their changing environments over time, revealing the factors that caused the biodiversity losses and how the losses affected the functioning of mammal communities. Their method offers a new strategy for investigating the implications of changing ecologies and prioritizing conservation efforts toward helping mammal communities flourish in the future.
Their research paper was published in the journal Nature Communications.
Combing the Data
The researchers began by diving into a collection of data from 186 sites across eastern Africa. The data contained records of over 200 extinct and 48 modern herbivore species (including the African elephant, giraffe, and hippopotamus), showing where and when each species lived at a given point in time over the past 7.4 million years. The data showed that mammal biodiversity in eastern Africa began to decline around 5 million years ago. It also revealed that aspects of biodiversity decline happened at multiple points, and that extinctions coincided with environmental changes and the emergence of early humans. But McGuire and Lauer wanted to know more.
“We wondered what we would find if we investigated how the mammals’ physical traits changed as their environments changed over time, rather than just looking at patterns in their biodiversity,” Lauer said. “This is important because if a mammal species possesses traits that are well-suited to its environment, it’s better able to contribute to the functioning of that environment. But if that is not the case, environments may not function as well as they could.”
To paint a fuller picture, they needed to examine biodiversity from a different perspective. This required a fresh approach, which led them to adapting a methodology known as ecometrics.
Ecometrics is an approach that looks at the relationships between the environmental conditions where animal communities are found — such as weather and vegetation — and the animal’s functional traits, which are traits that affect its biological performance. The team chose to focus on three traits: body mass, tooth height, and loph count (the number of ridges on molars).
Each of these traits exhibits a relationship based on the degree to which an environment is dominated by grasses versus woody plants. For example, if a species has a taller tooth, it can more durably consume the abrasive grassy vegetation of grasslands. With a shorter tooth, a species is instead suited to consume softer, woody vegetation, like shrubs.
For each of the three traits, they built a model of trait-environment relationships. They used trait data to estimate what the surrounding vegetation was like in each mammal community over time, specifically the percentage of trees and shrubs versus grassland.
“Using our models, we were able to use information about the traits occurring within mammal communities to estimate how the surrounding vegetation looked,” Lauer said. “Because these communities existed at different points in time, this enabled us to observe how consistent the mammals’ relationships with their environments remained through time.”
Analyzing Disruptions
Using their ecometric framework, the researchers uncovered a key difference between the mammal biodiversity declines that occurred before approximately 1.7 million years ago and those that occurred after. While biodiversity began declining around 5 million years ago, trait-environment relationships remained consistent despite that loss.
Their analysis demonstrated that earlier biodiversity losses were a result of species adapting to grassland environments or tracking their preferred environments across geographies. In short, those biodiversity losses didn't necessarily have any sort of negative impact on the ability of mammal communities to function properly in their environments.
But later, around 1.7 million years ago, when climates became more arid and variable and tree cover declined to below 35%, a major shift occurred. Rapid losses in the number and variety of species occurred, along with a significant disruption in trait-environment relationships. The researchers’ findings suggest that, unlike prior biodiversity losses, those occurring over the past 1.7 million years likely threatened the ability for many mammal species to function well in local environmental conditions.
“Our findings fascinated us, because we were able to differentiate between the different biodiversity losses that were happening and their implications,” Lauer said. “This work reinforces the idea that not all biodiversity losses are the same.”
Protecting the Vulnerable
Their findings have important implications for the types of environmental and climatic changes that could affect mammals going forward. In the past, when changes were gradual and wildlife were able to move freely on the landscape, they could readily adapt to these environmental conditions.
Now, fragmentation of wildlife habitats by fences, roadways, and cities has the potential to limit the ability of wildlife to adapt to the rapid environmental changes occurring today. That is exacerbated by both the fast pace and increasing variability of today’s climate, which puts animals at risk of losing their ability to function properly in their local environments.
Moving forward, the team’s analysis can shed light on which mammal communities should be prioritized for future conservation efforts. The study demonstrates that among all the communities that are experiencing biodiversity losses, priority should be given to those most at-risk — the communities for whom future biodiversity losses will profoundly affect their ability to function properly.
“By examining the past, we can get a remarkably clear understanding of how animals have responded to prior environmental changes,” McGuire said. “We plan to work with conservation practitioners to use our findings to develop well-informed strategies for conserving the most at-risk mammal communities.”
***
Co-authors include A. Michelle Lawing (Texas A&M University), Rachel A. Short (South Dakota State University), Fredrick K. Manthi (National Museums of Kenya), Johannes Müller (Leibniz Institute for Evolution and Biodiversity Science), and Jason J. Head (University of Cambridge).
Citation: Lauer, D.A., Lawing, A.M., Short, R.A. et al. Disruption of trait-environment relationships in African megafauna occurred in the middle Pleistocene. Nat Commun 14, 4016 (2023).
DOI: https://doi.org/10.1038/s41467-023-39480-8
Funding: This work was completed as part of a collaborative initiative from NSFDEB-NERC, with funding from NSF 2124836 to A.M.L., F.K.M., and J.M.; NSF 2124770 to J.L.M.; and NERC NE/W007576/1 to J.J.H. R.A.S. was supported by the NSF Postdoctoral Research Fellowships in Biology Program under grant DBI 2010680 and the USDA NIFA Hatch project SD00H787-23 (7004129 and 7004187). J.L.M. was also funded through NSF-CAREER and NSF 1945013.
News Contact
Catherine Barzler, Senior Research Writer/Editor
Institute Communications
Researchers from Georgia Tech's School of Civil and Environmental Engineering received a $2.1 million grant from the U.S. Environmental Protection Agency (EPA) to investigate contaminants in drinking water.
The EPA is funding the research on the occurrence and concentration of pathogens and disinfection by-products and the environmental conditions favorable to their growth in drinking water distribution systems.
Carlton S. Wilder Associate Professor Ameet Pinto, the project's principal investigator, said disinfection is used to kill microorganisms to make drinking water safe for consumption. Yet, disinfecting to kill microorganisms can also result in formation of harmful disinfection by-products.
“Our key project goal is to shine a light on when, where, and why pathogens and disinfection by-products occur and co-occur in drinking water systems across the country,” Pinto said. “This will help water utilities better navigate the tradeoff of managing microbiological and chemical risks in drinking water and thus enhance the reliability of safe drinking water supply to their consumers.”
According to the EPA, opportunistic pathogens such as Legionella pneumophila, nontuberculous mycobacteria, and Pseudomonas aeruginosa can grow in drinking water systems and pose potential risks to public health. The occurrence of these and other microbial pathogens is also associated with contaminated storage facilities and other problems in water distribution systems such as backflow and low-pressure incidents.
If left untreated, these contamination events can lead to outbreaks of gastrointestinal, respiratory, and other waterborne illnesses. The disinfectants used to control these pathogens can cause additional problems by reacting with natural organic matter, bromide, and other contaminants to form disinfectant by-products, which also have the potential to be harmful to human health.
Georgia Tech is one of four institutions selected by the EPA to receive nearly $8.5 million in grant funding, along with the University of Minnesota, Michigan State University, and the University of Texas. The Georgia Tech team includes Turnipseed Family Chair & Professor Ching-Hua Huang and Assistant Professor Katy Graham.
News Contact
Melissa Fralick | melissa.fralick@ce.gatech.edu
Artificial intelligence (AI) research by two Georgia Institute of Technology students has caught the attention of one of the world's leading financial services companies.
Gaurav Verma and Yuxi Wu are recipients of 2023 J.P. Morgan AI Research Ph.D. Fellowship Awards. They are among 13 scholars being honored this year by J.P. Morgan Chase & Co. for AI research projects taking on real-world challenges.
"Our goal is to recognize and enable the next generation of leading AI researchers. We want to create an environment where researchers can inspire change and make a lasting impact in our communities and across our industry," said Manuela Veloso, Ph.D., head of AI Research, J.P. Morgan Chase & Co.
Verma is pursuing his Ph.D. in the School of Computational Science and Engineering. Working with his advisor, Assistant Professor Srijan Kumar, Verma expects to ensure safety, equity, and well-being by creating multimodal learning and natural language processing approaches to achieve better human-AI interactions.
Wu is a Ph.D. candidate in the School of Interactive Computing. Empowering people regarding their privacy concerns is at the core of her research. Wu examines how cross-sector, collective action systems could better support end-user privacy. Professor Keith Edwards and Adjunct Assistant Professor Sauvik Das advise Wu.
"It's inspiring to see our students and their work being honored with these prestigious fellowships," said Irfan Essa, computer science professor and director of the Machine Learning Center at Georgia Tech.
"Georgia Tech continues to lead in AI education and research. These fellowships for Gaurav and Yuxi are evidence that we're continuing to move in the right direction."
Verma and Wu are part of a spectrum of AI research spanning Georgia Tech. To unite this broad community and ensure it continues moving in the right direction, the Institute recently established AI Hub at Georgia Tech.
"AI has a deep history at Georgia Tech, and we continue to serve as leaders in many areas of AI research and education," said Essa, interim co-director of AI Hub at Georgia Tech.
"Bringing all areas of AI under one umbrella, AI Hub at Georgia Tech will provide structure and governance as the Institute continues to lead and innovate in the burgeoning discipline of AI."
News Contact
Ben Snedeker, Communications Manager II
Georgia Tech College of Computing
This feature supports Georgia Tech's presence at the International Conference on Machine Learning, July 23-29 in Honolulu.
Honolulu Highlights | ICML 2023
Students and faculty have been focused and energized in their efforts this week engaging with the international machine learning community at ICML. See some of those efforts, hear from students themselves in our video series, and read about their latest contributions in #AI.
Georgia Tech’s experts and larger research community are invested in a future where artificial intelligence (AI) solutions can benefit individuals and communities across our planet. Meet the machine learning maestros among Georgia Tech’s faculty at the International Conference on Machine Learning — July 23-29, 2023, in Honolulu — and learn about their work. The faculty in the main program are working with partners across many domains and industries to help invent powerful new ways for technology to benefit all our futures.
One of the experts in Honolulu is Wenjing Liao, an assistant professor in the School of Mathematics. In addition to machine learning, Liao's research interests include imaging, signal processing, and high dimensional data analysis.
Learn more about the Georgia Tech contingent at the ICML here. Read more about machine learning research at Georgia Tech here.
News Contact
Renay San Miguel
Communications Officer II/Science Writer
College of Sciences
404-894-5209
In February, a major earthquake event devastated the south-central region of the Republic of Türkiye (Turkey) and northwestern Syria. Two earthquakes, one magnitude 7.8 and one magnitude 7.5, occurred nine hours apart, centered near the heavily populated city of Gaziantep. The total rupture lengths of both events were up to 250 miles. The president of Turkey has called it the “disaster of the century,” and the threat is still not over — aftershocks could still affect the region.
Now, Zhigang Peng, a professor in the School of Earth and Atmospheric Sciences at Georgia Tech and graduate students Phuc Mach and Chang Ding, alongside researchers at the Scientific and Technological Research Institution of Türkiye (TÜBİTAK) and researchers at the University of Missouri, are using small seismic sensors to better understand just how, why, and when these earthquakes are occurring.
Funded by an NSF RAPID grant, the project is unique in that it aims to actively respond to the crisis while it’s still happening. National Science Foundation (NSF) Rapid Response Research (RAPID) grants are used when there is a severe urgency with regard to availability of or access to data, facilities or specialized equipment, including quick-response research on natural or anthropogenic disasters and other similar unanticipated events.
In an effort to better map the aftershocks of the earthquake event — which can occur weeks or months after the main event — the team placed approximately 120 small sensors, called nodes, in the East Anatolian fault region this past May. Their deployment continues through the summer.
It’s the first time sensors like this have been deployed in Turkey, says Peng.
“These sensors are unique in that they can be placed easily and efficiently," he explains. "With internal batteries that can work up to one month when fully charged, they’re buried in the ground and can be deployed within minutes, while most other seismic sensors need solar panels or other power sources and take much longer time and space to deploy.” Each node is about the size of a 2-liter soda bottle, and can measure ground movement in three directions.
“The primary reason we’re deploying these sensors quickly following the two mainshocks is to study the physical mechanisms of how earthquakes trigger each,” Peng adds. Mainshocks are the largest earthquake in a sequence. “We’ll use advanced techniques such as machine learning to detect and locate thousands of small aftershocks recorded by this network. These newly identified events can provide new important clues on how aftershocks evolve in space and time, and what drives foreshocks that occur before large events.”
Unearthing fault mechanisms
The team will also use the detected aftershocks to illuminate active faults where three tectonic plates come together — a region known as the Maraş Triple Junction. “We plan to use the aftershock locations and the seismic waves from recorded events to image subsurface structures where large damaging earthquakes occur,” says Mach, the Georgia Tech graduate researcher. This will help scientists better understand why sometimes faults ‘creep’ without any large events, while in other cases faults lock and then violently release elastic energy, creating powerful earthquakes.
Getting high-resolution data of the fault structures is another priority. “The fault line ruptured in the first magnitude 7.8 event has a bend in it, where earthquake activity typically terminates, but the earthquake rupture moved through this bend, which is highly unusual,” Peng says. By deploying additional ultra-dense arrays of sensors in their upcoming trip this summer, the team hopes to help researchers ‘see’ the bend under the Earth’s surface, allowing them to better understand how fault properties control earthquake rupture propagation.
The team also aims to learn more about the relationship between the two main shocks that recently rocked Turkey, sometimes called doublet events. Doublet events can happen when the initial earthquake triggers a secondary earthquake by adding extra stress loading. While in this instance, the doublet may have taken place only 9 hours after the initial event, these secondary earthquakes have been known to take place days, months, or even years after the initial one — a famous example being the sequence of earthquakes that spanned 60 years in the North Anatolian fault region in Northern Turkey.
“Clearly the two main shocks in 2023 are related, but it is still not clear how to explain the time delays,” says Peng. The team plans to work with their collaborators at TÜBİTAK to re-analyze seismic and other types of geophysical data right before and after those two main shocks in order to better understand the triggering mechanisms.
“In our most recent trip in southern Türkiye, we saw numerous buildings that were partially damaged during the mainshock, and many people will have to live in temporary shelters for years during the rebuilding process,” Peng adds. “While we cannot stop earthquakes from happening in tectonically active regions, we hope that our seismic deployment and subsequent research on earthquake triggering and fault imaging can improve our ability to predict what will happen next — before and after a big one — and could save countless lives.”
News Contact
Written By:
Selena Langner
Media Contact:
Jess Hunt-Ralston
Findings from two published studies could lead to enhancements in artificial intelligence (AI) models by focusing on their flaws.
One paper found that adding visual attributes to text in multimodal models could boost performance and usefulness for humans.
Another study determined that few-shot learning (FSL) models lack robustness against adversarial treatments and need improvements.
Georgia Tech Assistant Professor Srijan Kumar and Ph.D. student Gaurav Verma lead the research being presented at the upcoming 61st Annual meeting of the Association for Computational Linguistics (ACL 2023).
Co-authors from Georgia Tech joining Kumar and Verma include Shivaen Ramshetty and Venkata Prabhakara Sarath Nookala, as well as Subhabrata Mukherjee, a principal researcher at Microsoft Research.
ACL 2023 brings together experts from around the world to discuss topics in natural language processing (NLP) and AI research. Kumar’s group offers to those discussions their work that focuses on robustness in AI models.
“Security of AI models is paramount. Development of reliable and responsible AI models are important discussion topics at the national and international levels,” Kumar said. “As Large Language Models become part of the backbone of many products and tools with which users will interact, it is important to understand when, how, and why these AI models will fail.”
[MICROSITE: Georgia Tech at ACL 2023]
Robustness refers to the degree to which an AI model’s performance changes when using new data versus training data. To ensure that a model performs reliably, it is critical to understand its robustness.
Trust is of essential value within robustness, both for researchers that work in AI and consumers that use it.
People lose trust in AI technology when models perform unpredictably. This issue is relevant in the ongoing societal discussion about AI security. Investigating robustness can prevent, or at least highlight, performance issues arising from unmodeled behavior and malicious attacks.
Deep Learning for Every Kind of Media
One aspect of AI robustness Kumar’s group will present at ACL 2023 delves into multimodal deep learning. Using this method, AI models receive and apply data through modes ranging from text, images, video, and audio.
The group’s paper presents a way to evaluate multimodal learning robustness called Cross-Modal Attribute Insertions (XMAI).
XMAI found that multimodal models perform poorly in text-to-image retrieval tasks. For example, adding more descriptive wording in search text for an image, like from “girl on a chair” to “little girl on a wooden chair,” caused the correct image to be retrieved at a lower rank.
Kumar’s group determined this when XMAI outperformed five other benchmarks in two different task retrieval tests.
“By conducting experiments in a sandbox setting to identify the plausible realistic inputs that make multimodal models fail, we can estimate various dimensions of a model’s robustness,” said Kumar. “Once these shortcomings are identified, these models can be updated and made more robust.”
Labels Matter When It Comes to Adversarial Robustness
Prompt-based few-shot learning (FSL) is another class of AI models that, like multimodal learning, uses text as input.
While FSL is a useful framework for AI to improve task performance when labeled data is limited, Kumar’s group points out in their ACL findings paper that there is limited understanding of the methods’ adversarial robustness.
“Our findings shine a light on a significant vulnerability in FSL models – a marked lack of adversarial robustness,” Verma explained. “This indicates a non-trivial balancing act between accuracy and adversarial robustness of prompt-based few-shot learning for NLP.”
Kumar’s team ran tests on six GLUE benchmark tasks, comparing FSL models with fully fine-tuned models. Here, they found a notable, greater drop in task performance of FSL models treated with adversarial perturbations than that of fully fine-tuned models.
In the same study, Kumar’s group found and proposed a few ways to improve FSL robustness.
These include using unlabeled data for prompt-based FSLs and expanding to an ensemble of models trained with different prompts. The group also demonstrated that increasing the number of few-shot examples and model size led to increased adversarial robustness of FSL methods.
“Improved adversarial robustness of few-shot learning models is essential for their broader application and adoption,” Verma said. “By securing a balance between robustness and accuracy, all from a handful of labeled instances, we can potentially implement these models in safety-critical domains.”
News Contact
Bryant Wine, Comms. Officer I
School of Computational Science & Engineering
Bryant.wine@cc.gatech.edu
Georgia Institute of Technology Physics Professor and Center for Relativistic Astrophysics member Ignacio Taboada serves as spokesperson for IceCube Collaboration.
Our Milky Way galaxy is an awe-inspiring feature of the night sky, viewable with the naked eye as a horizon-to-horizon hazy band of stars. Now, for the first time, the IceCube Neutrino Observatory has produced an image of the Milky Way using neutrinos — tiny, ghostlike astronomical messengers.
In an article to be published June 30, 2023, in the journal Science, the IceCube Collaboration, an international group of over 350 scientists, presents evidence of high-energy neutrino emission from the Milky Way.
The detected high-energy neutrinos hold energies millions to billions of times higher than those produced by the fusion reactions that power stars.
IceCube was built and is operated with National Science Foundation (NSF) funding and additional support from the fourteen countries that host institutional members of the IceCube Collaboration. IceCube Observatory searches for signs of high-energy neutrinos originating from our galaxy and beyond, out to the farthest reaches of the universe.
A cubic-kilometer neutrino detector operating at Amundsen-Scott South Pole Station observes these high-energy neutrinos, explains Ignacio Taboada, spokesperson for IceCube and a physics professor at Georgia Institute of Technology. “IceCube is truly unique,” Taboada says. “Built deep in Antarctic ice, its over 5,000 light sensors search for the flashes of blue light — Cherenkov radiation produced by neutrinos in the upper atmosphere, the Milky Way, and deep into the cosmos.”
Searching the southern sky
“What's intriguing is that, unlike the case for light of any wavelength, in neutrinos, the universe outshines the nearby sources in our own galaxy," says Francis Halzen, a professor of physics at the University of Wisconsin–Madison and principal investigator of IceCube.
"As is so often the case, significant breakthroughs in science are enabled by advances in technology," says Denise Caldwell, director of NSF's Physics Division. "The capabilities provided by the highly sensitive IceCube detector, coupled with new data analysis tools, have given us an entirely new view of our galaxy — one that had only been hinted at before. As these capabilities continue to be refined, we can look forward to watching this picture emerge with ever-increasing resolution, potentially revealing hidden features of our galaxy never before seen by humanity."
Interactions between cosmic rays — high-energy protons and heavier nuclei, also produced in our galaxy, and galactic gas and dust inevitably produce both gamma rays and neutrinos. Given the observation of gamma rays from the galactic plane, the Milky Way was expected to be a source of high-energy neutrinos.
“A neutrino counterpart has now been measured, thus confirming what we know about our galaxy and cosmic ray sources,” says Steve Sclafani, a physics Ph.D. student at Drexel University, IceCube member, and co-lead analyzer.
The search focused on the southern sky, where the bulk of neutrino emission from the galactic plane is expected near the center of our galaxy. However, until now, the background of muons and neutrinos produced by cosmic-ray interactions with the Earth’s atmosphere posed significant challenges.
To overcome them, IceCube collaborators at Drexel University developed analyses that select for "cascade" events, or neutrino interactions in the ice that result in roughly spherical showers of light. Because the deposited energy from cascade events starts within the instrumented volume, contamination of atmospheric muons and neutrinos is reduced. Ultimately, the higher purity of the cascade events gave a better sensitivity to astrophysical neutrinos from the southern sky.
Machine learning in the Milky Way
However, the final breakthrough came from the implementation of machine learning methods, developed by IceCube collaborators at TU Dortmund University, that improve the identification of cascades produced by neutrinos as well as their direction and energy reconstruction. The observation of neutrinos from the Milky Way is a hallmark of the emerging critical value that machine learning provides in data analysis and event reconstruction in IceCube.
“The improved methods allowed us to retain over an order of magnitude more neutrino events with better angular reconstruction, resulting in an analysis that is three times more sensitive than the previous search,” says IceCube member, TU Dortmund physics Ph.D. student, and co-lead analyzer Mirco Hünnefeld.
The dataset used in the study included 60,000 neutrinos spanning 10 years of IceCube data, 30 times as many events as the selection used in a previous analysis of the galactic plane using cascade events. These neutrinos were compared to previously published prediction maps of locations in the sky where the galaxy was expected to shine in neutrinos.
The maps included one made from extrapolating Fermi Large Area Telescope gamma-ray observations of the Milky Way and two alternative maps identified as KRA-gamma by the group of theorists who produced them.
“This long-awaited detection of cosmic ray-interactions in the galaxy is also a wonderful example of what can be achieved when modern methods of knowledge discovery in machine learning are consistently applied.” says Wolfgang Rhode, professor of physics at TU Dortmund University, IceCube member, and Hünnefeld’s advisor.
The power of machine learning offers great future potential, bringing other observations closer within reach.
“The strong evidence for the Milky Way as a source of high-energy neutrinos has survived rigorous tests by the collaboration,” says Taboada, the IceCube spokesperson. “Now, the next step is to identify specific sources within the galaxy.”
These and other questions will be addressed in planned follow-up analyses by IceCube.
“Observing our own galaxy for the first time using particles instead of light is a huge step,” says Naoko Kurahashi Neilson, professor of physics at Drexel University, IceCube member, and Sclafani’s advisor. “As neutrino astronomy evolves, we will get a new lens with which to observe the universe.”
About IceCube Neutrino Observatory
The IceCube Neutrino Observatory is funded and operated primarily through an award from the National Science Foundation to the University of Wisconsin–Madison. The IceCube Collaboration, with over 350 scientists in 58 institutions from around the world, runs an extensive scientific program that has established the foundations of neutrino astronomy. IceCube’s research efforts, including critical contributions to the detector operation, are funded by agencies in Australia, Belgium, Canada, Denmark, Germany, Italy, Japan, New Zealand, Republic of Korea, Sweden, Switzerland, Taiwan, the United Kingdom, and the United States, including NSF. IceCube construction was also funded with significant contributions from the National Fund for Scientific Research (FNRS & FWO) in Belgium; the Federal Ministry of Education and Research (BMBF) and the German Research Foundation (DFG) in Germany; the Knut and Alice Wallenberg Foundation, the Swedish Polar Research Secretariat, and the Swedish Research Council in Sweden; and the Wisconsin Alumni Research Fund.
About Georgia Institute of Technology
The Georgia Institute of Technology, or Georgia Tech, is one of the top public research universities in the U.S., developing leaders who advance technology and improve the human condition. The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees. Its more than 45,000 undergraduate and graduate students, representing 50 states and more than 148 countries, study at the main campus in Atlanta, at campuses in France and China, and through distance and online learning. As a leading technological university, Georgia Tech is an engine of economic development for Georgia, the Southeast, and the nation, conducting more than $1 billion in research annually for government, industry, and society.
News Contact
Science Contacts:
Francis Halzen, IceCube Principal Investigator
Vilas Research Professor and Gregory Breit Distinguished Professor of Physics
Wisconsin IceCube Particle Astrophysics Center, University of Wisconsin–Madison
Ignacio Taboada, IceCube Spokesperson
Professor of Physics, Georgia Institute of Technology
Press Contacts:
Georgia Institute of Technology
Jess Hunt-Ralston
Director of Communications, College of Sciences
IceCube Press
press@icecube.wisc.edu
NSF Media Affairs
media@nsf.gov
Alex Robel is improving how computer models of melting ice sheets incorporate data from field expeditions and satellites by creating a new open-access software package — complete with state-of-the-art tools and paired with ice sheet models that anyone can use, even on a laptop or home computer.
Improving these models is critical: while melting ice sheets and glaciers are top contributors to sea level rise, there are still large uncertainties in sea level projections at 2100 and beyond.
“Part of the problem is that the way that many models have been coded in the past has not been conducive to using these kinds of tools,” Robel, an assistant professor in the School of Earth and Atmospheric Sciences, explains. “It's just very labor-intensive to set up these data assimilation tools — it usually involves someone refactoring the code over several years.”
“Our goal is to provide a tool that anyone in the field can use very easily without a lot of labor at the front end,” Robel says. “This project is really focused around developing the computational tools to make it easier for people who use ice sheet models to incorporate or inform them with the widest possible range of measurements from the ground, aircraft and satellites.”
Now, a $780,000 NSF CAREER grant will help him to do so.
The National Science Foundation Faculty Early Career Development Award is a five-year funding mechanism designed to help promising researchers establish a personal foundation for a lifetime of leadership in their field. Known as CAREER awards, the grants are NSF’s most prestigious funding for untenured assistant professors.
“Ultimately,” Robel says, “this project will empower more people in the community to use these models and to use these models together with the observations that they're taking.”
Ice sheets remember
“Largely, what models do right now is they look at one point in time, and they try their best — at that one point in time — to get the model to match some types of observations as closely as possible,” Robel explains. “From there, they let the computer model simulate what it thinks that ice sheet will do in the future.”
In doing so, the models often assume that the ice sheet starts in a state of balance, and that it is neither gaining nor losing ice at the start of the simulation. The problem with this approach is that ice sheets dynamically change, responding to past events — even ones that have happened centuries ago. “We know from models and from decades of theory that the natural response time scale of thick ice sheets is hundreds to thousands of years,” Robel adds.
By informing models with historical records, observations, and measurements, Robel hopes to improve their accuracy. “We have observations being made by satellites, aircraft, and field expeditions,” says Robel. “We also have historical accounts, and can go even further back in time by looking at geological observations or ice cores. These can tell us about the long history of ice sheets and how they've changed over hundreds or thousands of years.”
Robel’s team plans to use a set of techniques called data assimilation to adjust, or ‘nudge’, models. “These data assimilation techniques have been around for a really long time,” Robel explains. “For example, they’re critical to weather forecasting: every weather forecast that you see on your phone was ultimately the product of a weather model that used data assimilation to take many observations and apply them to a model simulation.”
“The next part of the project is going to be incorporating this data assimilation capability into a cloud-based computational ice sheet model,” Robel says. “We are planning to build an open source software package in Python that can use this sort of data assimilation method with any kind of ice sheet model.”
Robel hopes it will expand accessibility. “Currently, it's very labor-intensive to set up these data assimilation tools, and while groups have done it, it usually involves someone re-coding and refactoring the code over several years.”
Building software for accessibility
Robel’s team will then apply their software package to a widely used model, which now has an online, browser-based version. “The reason why that is particularly useful is because the place where this model is running is also one of the largest community repositories for data in our field,” Robel says.
Called Ghub, this relatively new repository is designed to be a community-wide place for sharing data on glaciers and ice sheets. “Since this is also a place where the model is living, by adding this capability to this cloud-based model, we'll be able to directly use the data that's already living in the same place that the model is,” Robel explains.
Users won’t need to download data, or have a high-speed computer to access and use the data or model. Researchers collecting data will be able to upload their data to the repository, and immediately see the impact of their observations on future ice sheet melt simulations. Field researchers could use the model to optimize their long-term research plans by seeing where collecting new data might be most critical for refining predictions.
“We really think that it is critical for everyone who's doing modeling of ice sheets to be doing this transient data simulation to make sure that our simulations across the field are all doing the best possible job to reproduce and match observations,” Robel says. While in the past, the time and labor involved in setting up the tools has been a barrier, “developing this particular tool will allow us to bring transient data assimilation to essentially the whole field.”
Bringing Real Data to Georgia’s K-12 Classrooms
The broad applications and user-base expands beyond the scientific community, and Robel is already developing a K-12 curriculum on sea level rise, in partnership with Georgia Tech CEISMC Researcher Jayma Koval. “The students analyze data from real tide gauges and use them to learn about statistics, while also learning about sea level rise using real data,” he explains.
Because the curriculum matches with state standards, teachers can download the curriculum, which is available for free online in partnership with the Southeast Coastal Ocean Observing Regional Association (SECOORA), and incorporate it into their preexisting lesson plans. “We worked with SECOORA to pilot a middle school curriculum in Atlanta and Savannah, and one of the things that we saw was that there are a lot of teachers outside of middle school who are requesting and downloading the curriculum because they want to teach their students about sea level rise, in particular in coastal areas,” Robel adds.
In Georgia, there is a data science class that exists in many high schools that is part of the computer science standards for the state. “Now, we are partnering with a high school teacher to develop a second standards-aligned curriculum that is meant to be taught ideally in a data science class, computer class or statistics class,” Robel says. “It can be taught as a module within that class and it will be the more advanced version of the middle school sea level curriculum.”
The curriculum will guide students through using data analysis tools and coding in order to analyze real sea level data sets, while learning the science behind what causes variations and sea level, what causes sea level rise, and how to predict sea level changes.
“That gets students to think about computational modeling and how computational modeling is an important part of their lives, whether it's to get a weather forecast or play a computer game,” Robel adds. “Our goal is to get students to imagine how all these things are combined, while thinking about the way that we project future sea level rise.”
News Contact
Written by Selena Langner
Contact: Jess Hunt-Ralston
Pagination
- Previous page
- Page 72
- Next page