Research Projects
Impacts of Multiple Climate Stressors and Extreme Events on Biodiversity in Climate Change and Climate Intervention Scenarios: A Big Data Approach
Mentor: Dr Phoebe Zarnetske
Description: Climate change is increasing the frequency and intensity of extreme events, such as heatwaves, droughts, floods, and storms, resulting in cascading impacts on organisms and biodiversity. This project aims to develop a computational framework to identify and analyze the spatio-temporal impacts of multiple climate stressors and extreme events under both climate change and climate intervention (e.g., Stratospheric Aerosol Injection) scenarios. By leveraging large-scale climate datasets and advanced computational tools, including machine learning, spatial statistics, and time-series analysis, students will process and analyze extensive climate data to map where and when multiple stressors co-occur during extreme events. This approach will identify spatiotemporal "hot spots" of ecological vulnerability and provide critical insights into how climate interventions might change the frequency, intensity, and interactions of extreme events. The findings will be instrumental in guiding conservation efforts and informing strategic decisions to address the impact of climate change.
Generating Drug Molecules Inside a Protein Binding Pocket
Mentor: Dr Alex Dickson
Description: Diffusion models are generative machine learning models that have shown much recent success in creating data such as text (LLMs), images (DALL-E), audio, video and more. Diffusion models have also been applied to generate conformations of atoms representing proteins and drug molecules, however there are concerns about generalizability to new chemical structures and interactions that aren’t observed in the training set. In this project the student researcher will apply a recently developed method to integrate diffusion models into physics-based molecular dynamics simulations and assess its performance on a number of targets. This project integrates computation with aspects of physics, chemistry, molecular biology and pharmacology. Students from all of these backgrounds (and more) are encouraged to apply!
SEE-Insight Lab – Advancing Scientific Discovery with AI
Mentor: Dr Dirk Colbry
Description: The SEE-Insight Lab focuses on advancing scientific data understanding through intelligent, high-performance tools. Our research develops systems that streamline data annotation and exploration workflows, enabling scientists to speed up their analysis. We integrate cutting-edge techniques such as machine learning, genetic search, and generative models (including large language models) to create adaptive and transparent workflows that support reproducible science. By leveraging high-performance computing (HPC) resources, we enable scalable experimentation and discovery across diverse science and engineering domains. Our work emphasizes transparent, reproducible methodologies, ensuring that computational experiments can be validated and extended by the broader research community. Students participating in this REU project will: contribute to the development of intelligent tools for scientific data analysis, explore integration of AI-driven methods with HPC systems, gain experience in designing workflows that combine researcher insight with computational tools, and apply these methods to real-world scientific and engineering challenges.
User-Focused Platforms for Nuclear Physics
Mentor: Dr. Kyle Godbey
Description: User-focused platforms for exploring data coming from nuclear theory and experiment have many applications, including nuclear astrophysics. Development of these platforms where the science cases is nuclear astrophysics is well aligned with the NSF's "Harnessing the Data Revolution" and the "Windows on the Universe" big ideas. This project will involve the development and deployment of efficient machine learning surrogates to enable on-the-fly computations in a cloud environment. While a background in cloud, data science, or frontend development would be nice to have, we have a number of resources to quickly upskill new students in both the domain science and technical areas. The only requirements are basic programming skills and an interest in the topic.
Classical Simulation of Noisy, Large-Scale Quantum Circuits
Mentor: Dr Ryan LaRose
Description: Classically simulating quantum circuits is important theoretically to understand the power of quantum computers and practically to benchmark algorithms and error correction. New classical simulation techniques can even challenge or refute claims of quantum advantage [https://arxiv.org/abs/2412.14703]. In this project we seek to emulate Google and IBM quantum computers by incorporating the noise models of these devices into methods for noisy simulation. Our methods build on the BGLS simulation algorithm [https://dl.acm.org/doi/10.1145/3624062.3624215] and a technique to exploit noisy channels to reduce simulation complexity. The goal of the project is to implement and optimize these methods on HPC resources to classically simulate noisy quantum circuits on the order of 100s of qubits and 1000s of quantum operations.
Predictive Pipelines for Protein Function
Mentor: Dr Josh Vermaas
Description: As part of a larger research effort, we are developing a computational pipeline to make accurate predictions for protein function and structural ensembles through AI/ML approaches complemented by simulation. We anticipate opportunities for the student to test all or parts of this pipeline, evaluate its predictive power, and refine this workflow. Concretely, the input for the data pipeline will be an amino acid sequence, and all remaining outputs (like protein function annotations, binding affinity predictions, or thermodynamic weights) are downstream of this input, so there are many opportunities to contribute. No specific skills are required, outside of some prior programming experience in any language, though we mostly use python glued together with some bash.
Understanding Reaction Mechanisms using Ab-Initio Molecular Dynamics
Mentor: Dr Samik Bose
Description: The mechanism of chemical reactions is characterized via a combination of experimental techniques such as spectroscopy, isotope labeling, kinetic assays, which are both time and cost intensive. One can also computationally model a chemical reaction using the laws of quantum mechanics to view the reaction mechanism and provide information about activation energies and transition states. Computational modeling of reactions is tremendously helpful in the context of catalysis in chemistry and biology as it can explore the avenues to increase catalytic activity, without explicitly carrying out the reactions in an experimental laboratory setting. Ab-initio molecular dynamics simulation is the tool that allows one to carry out chemical reactions in computers. In this project, the student will learn the basic concepts of ab-initio MD and help implement an enhanced sampling ab-initio MD simulation method to study well known catalytic reactions and their mechanisms. Students applying for this project should have experience in python programming.
Developing Data Sets for Training AI on Stellar Flares
Mentor: Dr Adina Feinstein
Description: All-sky photometric time-series missions, like NASA's Transiting Exoplanet Survey Satellite (TESS) have allowed for the monitoring of millions of stars simultaneously. This allows us to study how different forms of stellar activity (e.g., flares) change as a function of stellar spectral type and age. The detection and characterization of stellar flares is non-trivial, as their temporal signatures can be confused with other astrophysical sources. Machine learning techniques, including the use of neural networks, have been used to more accurately and efficiently detect these events. However, as TESS has continued to collect data these neural networks have become outdated and less efficient. As part of this project, the student will develop a new training, test, and validation data set that could be used to retrain the publicly available neural network architecture stella (https://github.com/afeinstein20/stella). To create the new dataset, the student will use standard techniques in flare outlier identification (e.g., https://altaipony.readthedocs.io/en/latest/) and vet the flares that have been marked as true events. Required skills include a familiarity with python, data visualization, and some experience with time-series data analysis.
GPU-Based Routines for Molecular Simulations
Mentor: Dr Dylan Anstine
Description: Frontier efforts in molecular simulations are focused on machine learned models of particle interactions. In this summer research project, the student will receive hands-on training on how to develop and optimize GPU-based routines that ultimately support the development of an accelerated version of the Chebyshev Interaction Model for Efficient Simulation (ChIMES) potential. Model development will be validated on molecular dynamics simulations of solid state electrolytes. An ideal prospective student should have experience with python programming and a willingness to learn. The student will gain experience with Triton (https://triton-lang.org) for GPU programming.
Simulating Interstellar Impactors
Mentor: Dr Darryl Seligman
Description: The discovery of `Oumuamua, Borisov, and most recently and excitingly ATLAS (with strong MSU contributions) demonstrated that large scale interstellar objects traverse the Solar System routinely. The very real prospect of interstellar meteoritics from this newly discovered population would open a new window into the formation of extrasolar planets and stars throughout the galaxy and represents the newest frontier in planetary science. In this project the student would work to identify the optimal location within the solar system to search for interstellar impactors. Specifically, the student will adopt cutting-edge methodology from Seligman, Marčeta, & Peña-Asensio, (2025) (https://arxiv.org/abs/2511.03374) to simulate interstellar impactors from an analogous synthetic population on Mars and Neptune. This will enable us to identify the easiest place to (i) get the largest flux of interstellar impactors and (ii) be able to distinguish between interstellar impactors and regular solar system impactors. The student should have some experience with python scripting and data visualization using matplotlib. A strong interest in Astronomy is helpful.