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

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. 

Dipayan Banerjee and Sushil Varma, Ph.D. students in Operations Research at the H. Milton Stewart School of Industrial and Systems Engineering (ISyE), were recently selected as finalists for the INFORMS Transportation Science and Logistics (TSL) student paper competition. The winner will receive the TSL Best Student Paper Award, given to an outstanding paper primarily authored by a student(s) and whose topic is of interest to the broad TSL community.

Out of a total of 40 submissions, four were designated as finalists. The winner will be chosen at the October 15-18, 2023 INFORMS Annual Meeting taking place in Phoenix Arizona, during which the finalists will showcase their work in a dedicated session. All finalists receive a commemorative plaque, and the winning entrant(s) receives a $500 honorarium. In addition, the winning paper, if not published or under review elsewhere, will be invited for a fast-track review at Transportation Science.

Dipayan Banerjee
Fleet Sizing and Service Region Partitioning for Same-Day Delivery Systems

Many existing Same-Day Delivery (SDD) studies focus primarily on operational dispatch problems and do not consider system design questions. Furthermore, prior work on SDD system design does not consider the fleet sizing decision when a service region may be partitioned into zones dedicated to individual vehicles (such designs have been shown to improve system efficiency in related vehicle routing settings). Banerjee's research utilizes a novel approach to addressing two key tactical design challenges when planning an SDD system: figuring out how many delivery vehicles you need and dividing the delivery area into manageable zones.

Using continuous approximations to capture average-case operational behavior, the problem of independently maximizing the area of a single-vehicle delivery zone is considered first. The approach then characterizes area-maximizing dispatching policies and leverages the results to develop a procedure for calculating optimal areas as a function of a zone's distance from the depot, given a maximum number of daily dispatches per vehicle. Using minimal computation, the approach specifies fleet sizes and builds vehicle delivery zones that meet operational requirements, verified by simulation results.

Sushil Varma
Electric Vehicle Fleet and Charging Infrastructure Planning

Varma's research focuses on finding the best way to dispatch electric vehicles to pick up customers while making sure they charge periodically. As customer requests arrive, system operators must determine the minimum number of vehicles and chargers for a given service level, along with a matching and charging policy that maximizes that service level. Varma's approach provides a sharp characterization of the fleet size and the charging infrastructure requirements as demand grows. The research highlights the fundamental differences between planning for an electric vehicle system and a gas-powered system. To understand the difference, note that serving a customer comprises two steps -  pickup and trip, each contributing to the fleet size requirement of the system. As EVs require charging time, they need more vehicles to compensate for the trip part of the service. In turn, the optimal dispatching policy can reduce the EV requirement induced by the pick up part of the service by lowering the pickup times, owing to the extra EVs due to the trip phase. The reduction in the EV requirement depends on the number of charging stations and the size of the EV battery packs. 

The research proposes the "Power-of-d" dispatching policy, which achieves this performance by selecting the d closest vehicles to a trip request and choosing the one with the highest battery level. Varma also conducted detailed simulations that verified the scaling results. The paper discusses how the results extend to accommodate demand that increases/decreases repetitively or cyclically over time.

About Dipayan

Dipayan Banerjee is a fifth-year ISyE Ph.D. candidate advised by Professors Alan Erera and Alejandro Toriello. He is broadly interested in optimization for logistics and supply chain management with a focus on modern e-commerce systems. His doctoral research, supported by the NSF Graduate Research Fellowship and the Eisenhower Transportation Research Fellowship, studies demand management and delivery optimization for e-retail fulfillment. Dipayan was jointly awarded ISyE's Atlanta Air Cargo Association Fellowship for Ph.D. Research Excellence in Supply Chain Engineering in 2022. In addition to being named a finalist for the 2023 INFORMS TSL Society Best Student Paper Award, he also was a finalist for the 2019 INFORMS Undergraduate Operations Research Prize.

About Sushil

Sushil Varma, also a 5th-year ISyE Ph.D. student, is advised by Professor Siva Theja Maguluri. His research interests include queueing theory, game theory, and revenue management with applications in electric vehicles, online marketplaces like ride-hailing, load balancing, and stochastic processing/matching networks. Sushil was awarded the Stephen. S. Lavenberg Best Student Paper Award in IFIP Performance 2021 and the Alice and John Jarvis Best Student Paper Award in 2022.

We extend our wishes for success to both of these remarkable students. Their dedication, hard work, and commitment to their research have already set them on a remarkable path. Regardless of the outcome, their recognition is a testament to academic excellence.

The discovery of nucleic acids is a recent event in the history of scientific phenomenon, and there is still much learn from the enigma that is genetic code.

Advances in computing techniques though have ushered in a new age of understanding the macromolecules that form life as we know it. Now, one Georgia Tech research group is receiving well-deserved accolades for their applications in data science and machine learning toward single-cell omics research. 

Students studying under Xiuwei Zhang, an assistant professor in the School of Computational Science and Engineering (CSE), received awards in April at the Atlanta Workshop on Single-cell Omics (AWSOM 2023).

School of CSE Ph.D. student Ziqi Zhang received the best oral presentation award, while Mihir Birfna, an undergraduate student majoring in computer science, took the best poster prize.

Along with providing computational tools for biological researchers, the group’s papers presented at AWSOM 2023 could benefit populations of people as the research could lead to improved disease detection and prevention. They can also provide a better understanding of causes and treatments of cancer and new ability to accurately simulate cellular processes.

“I am extremely proud of the entire research group and very thankful of their work and our teamwork within our lab,” said Xiuwei Zhang. “These awards are encouraging because it means we are on the right track of developing something that will contribute both to the biology community and the computational community.”

Ziqi Zhang presented the group’s findings of their deep learning framework called scDisInFact, which can carry out multiple key single cell RNA-sequencing (scRNA-seq) tasks all at once and outperform current models that focus on the same tasks individually.

The group successfully tested scDisInFact on simulated and real Covid-19 datasets, demonstrating applicability in future studies of other diseases.

Bafna’s poster introduced CLARIFY, a tool that connects biochemical signals occurring within a cell and intercellular communication molecules. Previously, the inter- and intra-cell signaling were often studied separately due to the complexity of each problem.

Oncology is one field that stands to benefit from CLARIFY. CLARIFY helps to understand the interactions between tumor cells and immune cells in cancer microenvironments, which is crucial for enabling success of cancer immunotherapy.

At AWSOM 2023, the group presented a third paper on scMultiSim. This simulator generates data found in multi-modal single-cell experiments through modeling various biological factors underlying the generated data. It enables quantitative evaluations of a wide range of computational methods in single-cell genomics. That has been a challenging problem due to lack of ground truth information in biology, Xiuwei Zhang said. 

“We want to answer certain basic questions in biology, like how did we get these different cell types like skin cells, bone cells, and blood cells,” she said. “If we understand how things work in normal and healthy cells, and compare that to the data of diseased cells, then we can find the key differences of those two and locate the genes, proteins, and other molecules that cause problems.”

Xiuwei Zhang’s group specializes in applying machine learning and optimization skills in analysis of single-cell omics data and scRNA-seq methods. Their main interest area is studying mechanisms of cellular differentiation— the process when young, immature cells mature and take on functional characteristics.

A growing, yet effective approach to research in molecular biology, scRNA-seq gives insight of existence and behavior of different types of cells. This helps researchers better understand genetic disorders, detect mechanisms that cause tumors and cancer, and develop new treatments, cures, and drugs. 

If microenvironments filled with various macromolecules and genetic material are considered datasets, the need for researchers like Xiuwei Zhang and her group is obvious. These massive, complex datasets present both challenges and opportunities for the group experienced in computational and biological research.

Collaborating authors include School of CSE Ph.D. students Hechen Li and Michael Squires, School of Electrical and Computer Engineering Ph.D. student Xinye Zhao, Wallace H. Coulter Department of Biomedical Engineering Associate Professor Peng Qiu, and Xi Chen, an assistant professor at Southern University of Science and Technology in Shenzhen, China.

The group’s presentations at AWSOM 2023 exhibited how their work makes progress in biomedical research, as well as advancing scientific computing methods in data science, machine learning, and simulation.

scDisInFact is an optimization tool that can perform batch effect removal, condition-associated key gene detection, and perturbation, which is made possible by considering major variation factors in the data. Without considering all these factors, current models can only do these tasks individually, but scDisInFact can do each task better and all at the same time.

CLARIFY delves into how cells employ genetic material to communicate internally, using gene regulatory networks (GRNs) and externally, called cell-cell interactions (CCIs). Many computational methods can infer GRNs and inference methods have been proposed for CCIs, but until CLARIFY, no method existed to infer GRNs and CCIs in the same model.

scMultiSim simulations perform closer to real-world conditions than current simulators that model only one or two biological factors. This helps researchers more realistically test their computational methods, which can guide directions for future method development.

Whether they be computer scientists, biologists, or non-academics alike, the advantage of interdisciplinary and collaborative research, like Xiuwei Zhang’s group, is its wide-reaching impact that advances technology to improve the human condition.

“We’re exploring the possibilities that can be realized by advanced computational methods combined with cutting edge biotechnology,” said Xiuwei Zhang. “Since biotechnology keeps evolving very fast and we want to help push this even further by developing computational methods, together we will propel science forward.”

James X. Zhong Manis, who is pursuing his Ph.D. in Physical Chemistry at Georgia Tech, will get a chance to conduct his thesis research at a Department of Energy national laboratory at Stanford University, thanks to his selection to the DOE Office of Science Graduate Student Research (SCGSR) program.

The goal of the SCGSR program is to prepare graduate students for science, technology, engineering, or mathematics (STEM) careers critically important to the DOE Office of Science mission. The agency provides graduate thesis research opportunities through extended residency at DOE national laboratories.

“I am so excited and feel extremely lucky to have this opportunity to continue my research with DOE help,” Manis said. “I am thankful for everyone’s help to get me where I am, especially my principal investigator Thomas Orlando, our lab senior research scientist Brant Jones, my collaborating DOE scientist Thorsten Weber, and also everyone else in my research group. I am so thrilled to be working with world class scientists on cutting edge equipment.”

Manis is one of 87 awardees from 58 different universities who will conduct research at 16 DOE national laboratories. The research projects proposed by the new awardees are aligned with the priority mission areas of the DOE Office of Science that have a high need for workforce development. 

“The SCGSR program provides a way for graduate students to enrich their scientific research by engaging with researchers at DOE National Labs, learning from world class scientists, and using state-of-the-art equipment and facilities,” notes Asmeret Asefaw Berhe, Director of the DOE Office of Science. “In addition, they get valuable opportunities to network and observe firsthand what it’s like to have a scientific career. I can’t wait to see what these young researchers do in the future. I know they will meet upcoming scientific challenges in new and innovative ways.”  

Manis, who also earned a Bachelor of Science degree from the Wallace H. Coulter Department of Biomedical Engineering in 2018, will join the DOE’s Gas Phase Chemical Physics program at the Stanford Linear Accelerator Center (SLAC) at Stanford University. The Center supports research on fundamental gas-phase chemical processes important in energy applications.

SCGSR awardees work on research projects of significant importance to the Office of Science mission that address critical energy, environmental, and nuclear challenges at national and international scales. Projects in this new cohort span eight different  DOE Office of Science research programs. 

Manis’ project falls into the Basic Energy Sciences category. “I am interested in understanding the low energy electron interaction with biomolecules, which is a potential way of causing DNA damage,” he said. “The research I will conduct at the SLAC National Accelerator Laboratory is to first help in commissioning the DREAM (Dynamic REAction Microscope) end station in the TMO (time-resolved atomic, molecular and optical science) instrument hub.

“I have never visited SLAC before, but I am extremely excited to work there,” Manis added. “It’s going to be a change of pace collaborating with another group of scientists, and I can’t wait to start.”

The 2022-23 Micro-Grants Community-Based Research awardees presented their findings at the second annual symposium, held on April 18, 2023, in the auditorium of the Kendeda Building for Innovative Sustainable Design, which is the region’s first Living Building. Ten teams presented to faculty, staff, students, and student family members. The topics were wide ranging, and dealt with both practical and theoretical issues. The work surpassed all expectations for quality and quantity.

Devised by the Kendeda Building Advisory Board and sponsored by the Brook Byers Institute for Sustainable Systems and the Kendeda Building, the Micro-Grants Research Program solicits proposals for very small scale ($50 to $500), short term, sustainability related, research studies to be conducted by members of the Georgia Tech community. Community investigators are encouraged to explore ways in which the Georgia Tech campus can continue to innovate, demonstrate, prove, and promote the adoption of best and next practices in regenerative design and operations. Researchers were also encouraged to use the United Nations Sustainable Development Goals as a framework for research design. All members of the Georgia Tech community were encouraged to apply. The program especially sought proposals from students and staff that had little or no prior research experience.

The program has four objectives:

1. to expand scientific thinking and the understanding of the research process amongst those not (yet) directly involved in scientific research;
2. to bolster the use of the campus as a living laboratory;
3. to give voice to people and communities outside of research that have culturally novel perspectives on problems and their possible solutions, and to create new pathways for partnering with them; and
4. to seed novel ideas and nurture nascent investigators.

The 2022-23 awardees and the titles of their projects are:

• Alex Lomis, Devi Patel, and Dr. Jung-Ho Lewe, "Design and Development of a Low-Cost and Highly-Scaleable Occupancy Counter to Optimize the Utilization of HVAC Resources"
• Kaitlyn Tran, Shivani Potdar, and Amanda Janusz, "Bird Safe Campus"
• Ricardo Martinez, "Chiropterans at Georgia Tech"
• Elizabeth Umanah, "Reimagining Eco-Friendly Parking Lot Design Through Simulations"
• Lujain Diab, Ally Kimpling, Jenna Sitta, Marcus Morris, Skylar Ryan, Dr. Jennifer Leavey, and Steve Place, "A Greener Grey: “Ironing” Out Issues in Greywater Systems"
• Jun Wang and Yilun Zha, "Kendeda’s Educational Role in Waste Management and Recycling"
• Siddharth Sivakumarun, "Investigating Capacity for Regenerative Energy through Foot Traffic"
• Alexandra Rodriguez Dalmau and John Fortner, "Recognition of Insect Species in the Georgia Tech campus with Machine Learning"
• Gray Simmons, Kevin Leach, and Dr. Jung-Ho Lewe, "IOT Climate Sensor Development for HVAC Efficiency Analysis"
• Kaylin Cross, Pranav Jothi, Maanas Kumar, Brian Wu, Savannah Howard, and Sheng Dai, "Prototyping Bio-inspired Geothermal Energy Recovery for Space Heating and Cooling"

More details and links to all the presentations are available at this web page.

Beginning Summer 2023, prospective and current Georgia Tech students will have three new Bachelor of Science degrees to choose from in the School of Earth and Atmospheric Sciences. The expanded undergraduate offerings target a wider range of job and research opportunities — from academia to analytics, NASA to NOAA, meteorology to marine science, climate and earth science, to policy, law, consulting, sustainability, and beyond.

The Board of Regents of the University System of Georgia has approved two new specific degrees within the School: Atmospheric and Oceanic Sciences (AOS) and Solid Earth and Planetary Sciences (SEP). Regents also approved Environmental Science (ENVS) as an interdisciplinary College of Sciences degree between the School of Earth and Atmospheric Sciences and the School of Biological Sciences. The existing Earth and Atmospheric Sciences B.S. degree will sunset in two years for new students.

“We are really excited to be able to offer this new interdisciplinary undergraduate degree program in Environmental Science,” said Jean Lynch-Stieglitz, ADVANCE Professor in Earth and Atmospheric Sciences (EAS). “While it was developed jointly between the Schools of Earth and Atmospheric Sciences and Biological Sciences, it brings together Georgia Tech’s broad expertise and course offerings related to the Earth’s environment from across the Institute.”

“We are excited to see these new programs develop,” added Andrew Newman, professor and the School’s undergraduate coordinator, “as these degrees highlight the quantitative and computational skills of Georgia Tech students, and align better with their interests in global understanding of problems related to environmental impact and sustainability, natural hazards and landscape development, as well as planetary evolution, habitability, and exploration.”

“Students looking for specific types of programs will also be more understanding of what their program offers,” Newman said. “Under our current degree, a student interested in ocean science, planetary science, and environmental chemistry all would be looking at the same degree that doesn’t define their interests. Now, having programs with those interests in their name, and described well on the upcoming webpage, will greatly increase their interest in our program.”

The Evolution of EAS at Georgia Tech 

Newman also shared that, in Fall 2021, the School surveyed current EAS undergraduate students and recent alumni for feedback and thoughts on the potential degrees. Responses from the community highlighted that the plan for transitioning the existing major could not only help new students hone their academic and career plans, but also help them communicate beyond EAS about their chosen major. 

“These degrees make it more clear what the student is studying,” shared one student. “Before, people would ask what my major ‘even is’ and what kinds of jobs I could get with it. I think the new majors make it more clear.” 

“Finally, Planetary Science!” said another student. “This degree would go well with a Physics or AE (Aerospace Engineering) certificate or dual degree.”

All about the new Georgia Tech EAS degrees

The expanded undergraduate degree offerings are designed to continue Georgia Tech’s reputation for academic rigor — and also reflect trends in student interests, as well as current and forecasted needs in the job marketplace. 

“A key aspect of the new Environmental Science degree program will be its flexibility,” said Lynch-Stieglitz. “Students will be able to focus their study to support their interests and career goals whether those be in conservation, climate change, or environmental health. We’ve also left space in their program to encourage participation in especially impactful experiences such as study abroad and research projects. Georgia Tech students are fantastic — well prepared, diverse, smart, hard-working, and passionate. This flexible approach will allow them to become the broadly educated leaders who will envision the solutions to environmental problems that are so urgently needed.”

More on the new undergraduate degrees and what they will require:

B.S. Atmospheric and Oceanic Sciences (AOS) Degree

AOS uses the current Meteorology track as its foundation and will include aspects of Atmospheric Sciences, Oceanography and Climate Sciences.

• EAS will continue to offer courses needed for American Meteorological Society (AMS) certifications as well as those required for eligibility for National Weather Service meteorology jobs.

• Some courses will be reduced and others added (e.g. the existing course Physics of Weather will now be formally required instead of Earth Processes; the National Weather Service Practical Internship course in partnership with NWS Peachtree City will continue).

The AOS degree is designed to take advantage of Atlanta as a “hotspot” for major meteorological organizations including The Weather Channel, CNN, local stations in a top 10 TV market, and the National Weather Service (NWS) Peachtree City, Georgia office. The degree also builds on Georgia Tech’s existing expertise in Atmospheric Chemistry, Oceanography, Climate Dynamics, Paleoclimatology and Paleoceanography, and meteorological research.

AOS degree recipients looking for jobs or graduate research can target the energy sector, insurance risk modeling, broadcast meteorology, consulting, data analytics, aviation, military, and K-12 education, among other positions.

B.S. Environmental Science (ENVS) Degree

ENVS was developed by a joint committee involving EAS and the School of Biological Sciences.

• ENVS requires core content in mathematics, physics, chemistry, biology, Earth sciences, and public policy.

• Upper level coursework allows students to customize their program of study based on interest.

• Students will complete a capstone research project that integrates the knowledge they have gained through the program.

This degree takes advantage of Georgia Tech’s expertise in Environmental Chemistry, climate science, marine science, Aquatic Chemical Ecology, microbial dynamics, and Environmental Policy. Newman added that there is a critical emerging market need for scientists with expertise in the Earth’s environmental systems.

The ENVS degree will provide a strong base for students pursuing graduate programs and careers in environmental policy, environmental law, medicine, and other master’s and Ph.D. programs in environmentally related disciplines.

B.S. Solid Earth and Planetary Sciences (SEP) Degree

SEP builds on the existing Earth Science track to include Planetary Sciences. 

• There is an opportunity to reduce some courses.

• Some courses will now be required (e.g. Physics II, Physics of Planets, Introduction to Geophysics).

According to an SEP prospectus, “the degree will support Georgia Tech’s mission to develop leaders who advance technology and improve the human condition, through developing holistically minded students that can put human development in context of the environment for which we live, including resource availability, hazards that affect sustainability, and our exploratory nature to understand our place on the planet and solar system.” 

Career and graduate opportunities include energy sector positions, NASA, NOAA, U.S. Geological Survey, environmental remediation, hazard assessment and data analytics.

Learn more, contact EAS Undergraduate Advising, and apply: 

• eas.gatech.edu/undergraduate 

• eas.gatech.edu/aos

• eas.gatech.edu/envs

• eas.gatech.edu/sep

A small spacecraft assembled and tested at the Georgia Institute of Technology is on its way to the moon, where it will use lasers to search for surface water ice in lunar craters that are never warmed by light from the sun.

The briefcase-sized Lunar Flashlight will be monitored and controlled over the next several months by a team of graduate and undergraduate students in Georgia Tech’s School of Aerospace Engineering. The team will keep the spacecraft on track and capture the data it gathers to be studied by the Lunar Flashlight Science team.

Watch a video on the Lunar Flashlight mission on YouTube

The spacecraft launched at 2:38 a.m. December 11 on a SpaceX Falcon 9 rocket that also carried a Japanese-built lunar lander and a United Arab Emirates rover. Shortly after launch, Lunar Flashlight separated from the Falcon 9 to begin an approximately three-month journey that will carry it into a fuel-conserving orbital trajectory 42,000 miles beyond the moon. Gravity from the moon, Earth, and Sun will ultimately bring it into a path that will come within nine miles of the lunar surface.

Once in its science orbit around the moon, Lunar Flashlight will shine four lasers into perpetually-dark craters near the lunar South Pole. Each laser operates at a slightly different frequency, and the reflected light acts like a spectral fingerprint that identifies the material that it illuminated. If ice is there, the near-infrared light from the lasers will be absorbed by the water. If the light reflects back to the Lunar Flashlight, that will indicate the absence of ice. Data from the spacecraft will be radioed to NASA’s Deep Space Network and received by student controllers on the Georgia Tech campus, who will then share it with the Lunar Flashlight Science Team.

Surface water ice may be a treasure trove of water from different sources such as volcanic outgassing and meteorite impact, so knowing where it resides will help point future assets to examine it at the surface. If sufficient amounts exist, the precious liquid may be used to help meet the drinking water needs of future lunar colonies. Water molecules from potential ice reservoirs in the South Pole craters could also be split to provide a source of oxygen for breathing and hydrogen for rocket fuel.

Big Capabilities in a Small Spacecraft

Despite its small size, Lunar Flashlight – which was designed by NASA’s Jet Propulsion Laboratory – has big capabilities. Lunar Flashlight carries a propulsion system that will be used to make mid-course corrections and allow the spacecraft to get into lunar orbit and accomplish its mission. Built at Georgia Tech’s School of Aerospace Engineering, the propulsion system uses a new monopropellant developed at the Air Force Research Laboratory to be more environmentally safe than earlier propellants.

“It’s a very capable spacecraft for sure,” said Jud Ready, a Georgia Tech Research Institute (GTRI) principal research engineer who served as principal investigator for the final assembly and testing of Lunar Flashlight at Georgia Tech. “Achieving lunar orbit insertion can be challenging for a conventional spacecraft, let alone a vehicle the size of a desktop computer.”

The solar-powered Lunar Flashlight is part of a new generation of small spacecraft with capabilities formerly seen only on larger vehicles. First used in low earth orbit, the smaller vehicles are now traveling to the moon, and potentially to other planets in the solar system.

“Space exploration was formerly the realm of major governments – the United States, Russia, China, Japan, and a few others,” said Ready. “Using smaller spacecraft like Lunar Flashlight means a lot more opportunity for this. There will likely be thousands of other small spacecraft launching behind us.”

A Learning Experience for GTRI and Georgia Tech

Final assembly of the Lunar Flashlight took place in a cleanroom in a GTRI building on the main Atlanta campus, where the laser system also was tested. Specialized equipment at GTRI’s Cobb County Research Facility tested the spacecraft’s radio equipment and simulated the stresses of launch. Thermal, vacuum, and other testing took place in Georgia Tech’s School of Aerospace Engineering.

For the faculty, staff, and students involved, Lunar Flashlight has provided a great learning experience.

“We learned how to apply NASA’s rigorous protocols to everything we did, protect the spacecraft from electrostatic discharge, schedule complex testing tasks, and utilize our student researchers who must also maintain their schoolwork and take exams,” Ready said. “There have been some real sacrifices by a lot of folks who worked long and odd hours.”

After completion of the final assembly and testing at Georgia Tech, Lunar Flashlight traveled to the Marshall Space Flight Center in Huntsville, Alabama, for fueling and additional testing. Finally, it made the trip to the Cape Canaveral Space Force Station in Florida for integration onto the SpaceX rocket.

Ready is hopeful that if Lunar Flashlight finds evidence of significant ice deposits on the moon’s South Pole, the precious water will help set the stage for creating a permanent human presence there.

“It’s really disappointing that we went to the moon in the 1970s, but didn’t stay there,” he said. “However, when you look at the big scheme of things, exploration is often measured in hundreds or even thousands of years. So, it’s not surprising that colonization of the moon would take longer than a few decades.”

Writer: John Toon (john.toon@gtri.gatech.edu).

GTRI Communications

Georgia Tech Research Institute

Atlanta, Georgia USA

About GTRI: The Georgia Tech Research Institute (GTRI) is the nonprofit, applied research division of the Georgia Institute of Technology (Georgia Tech). Founded in 1934 as the Engineering Experiment Station, GTRI has grown to more than 2,800 employees, supporting eight laboratories in over 20 locations around the country and performing more than $700 million of problem-solving research annually for government and industry. GTRI's renowned researchers combine science, engineering, economics, policy, and technical expertise to solve complex problems for the U.S. federal government, the state, and industry. For more information, please visit www.gtri.gatech.edu.

Though it is a cornerstone of virtually every process that occurs in living organisms, the proper folding and transport of biological proteins is a notoriously difficult and time-consuming process to experimentally study.

In a new paper published in eLife, researchers in the School of Biological Sciences and the School of Computer Science have shown that AF2Complex may be able to lend a hand.

Building on the models of DeepMind’s AlphaFold 2, a machine learning tool able to predict the detailed three-dimensional structures of individual proteins, AF2Complex — short for AlphaFold 2 Complex — is a deep learning tool designed to predict the physical interactions of multiple proteins. With these predictions, AF2Complex is able to calculate which proteins are likely to interact with each other to form functional complexes in unprecedented detail.

“We essentially conduct computational experiments that try to figure out the atomic details of supercomplexes (large interacting groups of proteins) important to biological functions,” explained Jeffrey Skolnick, Regents’ Professor and Mary and Maisie Gibson Chair in the School of Biological Sciences, and one of the corresponding authors of the study. With AF2Complex, which was developed last year by the same research team, it’s “like using a computational microscope powered by deep learning and supercomputing.”

In their latest study, the researchers used this ‘computational microscope’ to examine a complicated protein synthesis and transport pathway, hoping to clarify how proteins in the pathway interact to ultimately transport a newly synthesized protein from the interior to the outer membrane of the bacteria — and identify players that experiments might have missed. Insights into this pathway may identify new targets for antibiotic and therapeutic design while providing a foundation for using AF2Complex to computationally expedite this type of biology research as a whole.

Computing complexes

Created by London-based artificial intelligence lab DeepMind, AlphaFold 2 is a deep learning tool able to generate accurate predictions about the three-dimensional structure of single proteins using just their building blocks, amino acids. Taking things a step further, AF2Complex uses these structures to predict the likelihood that proteins are able to interact to form a functional complex, what aspects of each structure are the likely interaction sites, and even what protein complexes are likely to pair up to create even larger functional groups called supercomplexes.

“The successful development of AF2Complex earlier this year makes us believe that this approach has tremendous potential in identifying and characterizing the set of protein-protein interactions important to life,” shared Mu Gao, a senior research scientist at Georgia Tech. “To further convince the broad molecular biology community, we [had to] demonstrate it with a more convincing, high impact application.”

The researchers chose to apply AF2Complex to a pathway in Escherichia coli (E. coli), a model organism in life sciences research commonly used for experimental DNA manipulation and protein production due to its relative simplicity and fast growth. 

To demonstrate the tool’s power, the team examined the synthesis and transport of proteins that are essential for exchanging nutrients and responding to environmental stressors: outer membrane proteins, or OMPs for short. These proteins reside on the outermost membrane of gram-negative bacteria, a large family of bacteria characterized by the presence of inner and outer membranes, like E. coli. However, the proteins are created inside the cell and must be transported to their final destinations. 

“After more than two decades of experimental studies, researchers have identified some of the protein complexes of key players, but certainly not all of them,” Gao explained. AF2Complex “could enable us to discover some novel and interesting features of the OMP biogenesis pathway that were missed in previous experimental studies.”

New insights

Using the Summit supercomputer at the Oak Ridge National Laboratory, the team, which included computer science undergraduate Davi Nakajima An, put AF2Complex to the test. They compared a few proteins known to be important in the synthesis and transport of OMPs to roughly 1,500 other proteins — all of the known proteins in E. coli’s cell envelope — to see which pairs the tool computed as most likely to interact, and which of those pairs were likely to form supercomplexes. 

To determine if AF2Complex’s predictions were correct, the researchers compared the tool’s predictions to known experimental data. “Encouragingly,” said Skolnick, “among the top hits from computational screening, we found previously known interacting partners.” Even within those protein pairs known to interact, AF2Complex was able to highlight structural details of those interactions that explain data from previous experiments, lending additional confidence to the tool’s accuracy.

In addition to known interactions, AF2Complex predicted several unknown pairs. Digging further into these unexpected partners revealed details on what aspects of the pairs might interact to form larger groups of functional proteins, likely active configurations of complexes that have previously eluded experimentalists, and new potential mechanisms for how OMPs are synthesized and transported. 

“Since the outer membrane pathway is both vital and unique to gram-negative bacteria, the key proteins involved in this pathway could be novel targets for new antibiotics,” said Skolnick. “As such, our work that provides molecular insights about these new drug targets might be valuable to new therapeutic design.”

Beyond this pathway, the researchers are hopeful that AF2Complex could mean big things for biology research. 

“Unlike predicting structures of a single protein sequence, predicting the structural model of a supercomplex can be very complicated, especially when the components or stoichiometry of the complex is unknown,” Gao noted. “In this regard, AF2Complex could be a new computational tool for biologists to conduct trial experiments of different combinations of proteins,” potentially expediting and increasing the efficiency of this type of biology research as a whole.

AF2Complex is an open-source tool available to the public and can be downloaded here.

This work was supported in part by the DOE Office of Science, Office of Biological and Environmental Research (DOE DE-SC0021303) and the Division of General Medical Sciences of the National Institute Health (NIH R35GM118039). DOI: https://doi.org/10.7554