SURE: Summer Undergraduate Research Experience

Spend the summer with a computer science or applied mathematics research team in a College of Computing Summer Undergraduate Research Experience (SURE) program.

College of Computing
Research
Student Research
SURE: Summer Undergraduate Research Experience

91��Ƭ�� Tech will host the Summer Undergraduate Research Experience (SURE) 2025 from June 2 to August 8, 2025. This program offers immersive, hands-on research opportunities that allow participants to explore exciting data science and computational mathematics topics.

About SURE 2025

At SURE, we bring the classroom to life by offerings. Dive into real-world research experience that address today’s most pressing data science and computational mathematics challenges. Guided by 91��Ƭ�� Tech’s distinguished faculty and graduate mentors, SURE students will build technical skills and learn to think critically, gaining first-hand insight into academic research.

Program Benefits

Stipend and Free Housing: SURE candidates receive a weekly stipend of $550 for ten weeks, plus free housing on campus. This financial support allows them to focus on research and fully engage in the SURE experience without worrying about additional expenses.

Cutting-Edge Research Projects: Work on impactful projects in machine learning, data analytics, computational modeling, and more. Each project is designed to challenge and equip with highly valued skills in today’s job market.
Collaboration and Teamwork: Join a dynamic community of peers, graduate students, and faculty, working as part of a research team emphasizing cooperation and mutual growth. This experience fosters teamwork and communication skills essential for success in any career.
Professional Development: From technical workshops to mentorship sessions, SURE provides a well-rounded experience, helping students navigate the complexities of research, understand research ethics, and gain exposure to potential career paths in STEM.

Eligibility and Requirements

SURE 2025 is designed for undergraduate students with a foundational background in mathematics, including calculus, differential equations, linear algebra, and some programming skills. Currently, we can only accept applications from U.S. citizens and permanent residents.

How to Apply

Are you ready to embark on a summer of discovery, innovation, and growth? Visit our to learn more about eligibility requirements and deadlines. You must submit your academic transcripts, essays regarding the program, and a letter of recommendation to apply. The reference letter should address your potential for conducting research and highlight your strengths and areas for growth. All applications received by January 31, 2025, will be fully considered. Applications will be accepted until the positions are filled.

Project Information

More detailed project information will be released soon, offering prospective students insight into the exciting research areas they’ll explore over the summer.

Supporting Diversity in STEM

SURE 2025 is committed to creating a welcoming, inclusive environment by actively recruiting students from underrepresented groups. Diverse perspectives drive innovation and aim to empower students from all backgrounds to make meaningful contributions to their fields and communities.

Join us at 91��Ƭ�� Tech’s SURE 2025 and discover what it takes to be a researcher, problem-solver, and collaborator. Whether aspiring to a research career or simply wanting to expand your understanding of data science and computational mathematics, SURE offers an unparalleled experience.

If you have any questions regarding the program, please contact us at yding2@iit.edu.

We welcome you to 91��Ƭ�� Tech’s vibrant research community this summer!

Program Funding

The SURE program gratefully acknowledges the funding provided by the National Science Foundation, whose support makes this opportunity possible for students to pursue cutting-edge research and development.

Summer Undergraduate Research Experience (SURE) Summer 2025

SURE offers insight and learning into some of the hottest topics in data science and computational mathematics through hands-on research experience. Learn to work as a team member by interacting with graduate students and faculty and gain an understanding of what it takes to conduct real-world research.

A 10-week SURE program will be hosted at 91��Ƭ�� Tech from June 2 to August 8, 2025. The program candidates will receive a stipend of $550 per week. The applicants are required to have a foundational background in mathematics (calculus, differential equations, and linear algebra) and some programming skills.

Topic: Speedier Simulations

Advisers: Fred Hickernell and Nathan Kirk

Adding state-of-the-art LD generation procedures, using tools from machine learning methods (graph neural networks), to QMCPy,
Exploring novel and exciting applications of QMC (e.g., in graph networks, or robotic simulations),
Explore new randomization techniques for machine learning generated LD points, and
Exploring the performance of new LD sets.

By joining the speedy simulations research group, students will experience teamwork, learn to identify and solve research problems, follow good practices in technical software development, and hone their communication skills. A background in statistics and Python and C++ programming is highly desired.

Topic: Enhancing Construction Worker Safety through AI

Advisers: Sou-Cheng Choi and Yuhan Ding

Description: The construction industry experiences high accident rates. Traditional safety protocols frequently neglect the specific physiological and mental states of individual workers, as well as dynamic environmental factors contributing to hazards. Advancements in wearable technology and artificial intelligence (AI) present new opportunities for predicting and mitigating risk before incidents occur. We invite undergraduate students in computational mathematics to explore the application of AI in enhancing safety within the construction industry. Participants will develop and assess AI models to predict risky worker mental states by processing and analyzing time series of physiological data and external factors, including weather conditions and site-specific hazards. A background in statistics and Python programming will be beneficial.

Topic: Machine Learning for Spatial-Temporal Data Modeling

Advisers: Huiling Liao

Spatial-temporal modeling involves analyzing data, such as air pollution levels, disease incidence, or weather patterns, that vary across both space and time to uncover patterns, make predictions, and understand dynamic processes. Emphasis will be placed on developing interpretable models that account for possibly nonlinear evolution of spatio-temporal patterns, and possibly uncertainty quantification. In this project, students will work with real-world datasets—such as environmental measurements or public health records—and apply statistical and computational methods to explore how changes unfold over time and across regions.

Machine Learning for Traffic Accident Prediction Team

Previous SURE Projects

Summer 2024 projects

Topic: Speedier Simulations

Advisers: Fred Hickernell

Description: Monte Carlo methods are used to solve problems involving uncertainty, such as financial risk and geophysical problems whose parameters are not known precisely. The speedy simulations research group develops and implements algorithms in an open source Python package, called QMCPy that speeds up Monte Carlo simulations. Students will contribute to QMCPy by exploring new use cases, by implementing new algorithms, and/or by improving performance through parallel processing. By joining the speedy simulations research group, students will experience teamwork, learn to identify and solve research problems, follow good practices in technical software development, and hone their communication skills. A background in statistics and Python (or other language) programming will be an advantage.

Topic: Baseball Game Simulation

This is a collaborative project with the Chicago White Sox.

Advisers: and Yuhan Ding

Descriptions: Take in two rosters, starting lineups, statistical data, and the rules of a baseball game to create a game simulator to predict the final score and statistics of a game. This simulator will simulate each at bat of a game using the present situation, players, and rules to predict the outcome. This tool could be used to test out the performance of different lineups, predict a season, or to predict a certain outcome.

Topic: Machine Learning for Traffic Accident Prediction

Advisers:

Descriptions: Controlling traffic accidents is an important public safety challenge, therefore, accident prediction has been a topic of much research. With a large-scale but sparse publicly available dataset including a variety of data attributes such as traffic events and weather data, we try to tackle the traffic accident prediction through modeling the nonlinear evolution of spatio-temporal patterns. In this study, students will work together, starting from identifying research problems to coming up with a solution, to explore different spatio-temporal models and also learn to model the patterns and predict the occurrence and severity of accidents with the proper machine learning tools.

91��Ƭ��