Graduate Students
Fall 2026 SAI Graduate Fellows
Esteban Amaya (CE)
Esteban Amaya is a Ph.D. student in civil engineering whose research combines earthquake engineering, scientific machine learning, uncertainty quantification, and infrastructure risk assessment. He earned a master's degree in earthquake engineering from Pontificia Universidad Católica de Chile, where he ranked first in his program, and has published research on seismic bridge performance and resilience. His SAI project will pair stochastic emulation with active learning to reduce the simulations needed for regional seismic risk assessment of a bridge network in Santiago, Chile. His Ph.D. advisors are Alexandros Taflanidis and Hernán Santa María, and his SAI project mentor is Keshav Rangan.
Bingxue An (ACMS)
Bingxue An is a Ph.D. student in applied and computational mathematics and statistics whose research centers on interpretable statistical learning and consensus dimension reduction. She developed the accompanying coMDS R package for her first-author work on multi-view larning and has taught courses in statistics, data analysis, and scientific computing. Her SAI project will develop Consensus Tree, a framework that distills a tree ensemble into one or a small set of representative trees while preserving predictive performance and structural information. Her Ph.D. advisor is Tiffany Tang, and her SAI project mentor is Chris Sweet.
Caroline Anscombe (BioS)
Caroline Anscombe is a Ph.D. student in biological sciences who studies how urbanization, agriculture, and climate change affect stream and river biogeochemistry. She earned a master's degree in crop, soil, and environmental science from the University of Arkansas, where her work examined nutrient export and decomposition in urbanizing watersheds. Her SAI project will train a deep-learning model to identify storm events in a 20-year watershed record and test its transferability across 25 U.S. Geological Survey gauges in the St. Joseph River Basin. Her Ph.D. advisor is Jennifer Tank, and her SAI project mentor is Sam Rund.
Olivia Bi (ACMS)
Olivia Bi is a Ph.D. student in applied and computational mathematics and statistics whose research interests include AI for science and environmental statistics. Before beginning doctoral study, she earned a bachelor's degree in economics with a second major in actuarial science from Singapore Management University and worked as a rates options trader. Her SAI project, LakeFlow, will combine sparse observations, lake characteristics, and meteorological data to reconstruct and forecast full-depth lake temperature profiles with physical constraints and calibrated uncertainty. Her Ph.D. advisor is Stefano Castruccio, and her SAI project mentor is Donald Brower.
Dominique (Nikki) Gramm (CBE)
Dominique Gramm is a Ph.D. student in Bioengineering and an NSF Graduate Research Fellow. Her research focuses on the intersection of biomaterials, mechanobiology, and cerebral organoid models, with an emphasis on understanding how the mechanical properties of the cellular microenvironment influence organoid growth and maturation. Her work involves engineering hydrogel-based microenvironments and using molecular and imaging approaches to characterize cerebral organoid development. She also contributed to a 2025 review on biomaterial strategies in regenerative medicine.Through the Scientific Artificial Intelligence (SAI) Fellowship, Dominique will develop a reproducible computational image-analysis and classification pipeline to investigate how cerebral organoid morphology and structure vary across hydrogel stiffness conditions. Her Ph.D. advisor is Donny Hanjaya-Putra, and her SAI project mentor is Sam Rund."
Adedayo Jigida (AME)
Adedayo Jigida is a Ph.D. candidate in aerospace and mechanical engineering whose work combines robotics, biomechanics, locomotion, sensor-based pressure mapping, assistive technologies, and data analytics. He holds a master's degree from the University of Notre Dame and a bachelor's degree from the University of Lagos. His SAI project will develop a physics-informed temporal model to predict patient-specific pressure trajectories inside lower-limb prosthetic sockets across devices and activities, using a dataset he collected from six transtibial prosthesis users. His doctoral research is advised by Dr. James P. Schmiedeler, and his SAI project mentor is Dr. Edgar Bolívar-Nieto.
Kaheon Kim (ACMS)
Kaheon Kim is a Ph.D. student in Applied and Computational Mathematics and Statistics whose research focuses on optimal transport, Wasserstein barycenters, distributional data analysis, and optimization. He is the first author of optimal-transport methods published at ICML 2025 and ICLR 2026. His SAI project will develop a scalable and interpretable vector-to-distribution regression framework based on flow matching, with the goal of modeling the relationship between individual-level covariates and high-dimensional distributions, beginning with publicly available single-cell RNA-sequencing data. His Ph.D. advisor is Changbo Zhu, and his SAI project mentor is Donald Brower.
Andrew Marquardt (CBE)
Andrew Marquardt is a Ph.D. candidate in chemical and biomolecular engineering who develops automated tools for polymer degradation research and laboratory data collection. His publication record includes a first-author paper in the Journal of Chemical Theory and Computation and collaborative work in Nature Chemistry, the Journal of the American Chemical Society, Science Advances, and Macromolecules. His SAI project will build a vision-language and image-analysis system that continuously captures, organizes, and evaluates experimental records in a membrane fabrication laboratory. His Ph.D. advisor is Brett Savoie, and his SAI project mentor is Charles Vardeman.
Xuezhong (Joe) Niu (EE)
Xuezhong (Joe) Niu is a Ph.D. student in electrical engineering whose research focuses on ferroelectric memory, oxide transistors, device physics, TCAD simulation, and compact modeling. His publication record includes first-author work presented at IEDM and published in IEEE Transactions on Electron Devices, as well as contributions selected for a Nano Letters cover and an Applied Physics Reviews feature. His SAI project will develop a physics-aware graph neural network surrogate for FeFET NAND variability, with transfer learning from experimental data and deployment through a compact SPICE model. His Ph.D. advisor is Kai Ni, and his SAI project mentor is Andrey Kuehlkamp.
Isabel Thompson (CHEM)
Isabel Thompson is a Ph.D. candidate in physical chemistry and an Arthur J. Schmitt Presidential Leadership Fellow. Her research focuses on developing methods for extracting thermodynamic and kinetic information from unconverged weighted-ensemble biomolecular simulations. Her SAI project recovers transfer-operator eigenfunctions directly from the time evolution of these simulations and uses the recovered slow modes to build a dynamically informed kernel for Gaussian-process free-energy surfaces. Her earlier training spans cell and molecular biology, bioinformatics, protein structural biology, and RNA folding simulation. Her Ph.D. advisor is Steven A. Corcelli, and her SAI project mentor is Charlie Maier.
Haoyu Wu (CBE)
Haoyu Wu is a Ph.D. student in chemical and biomolecular engineering whose research connects molecular simulation, polymer physics, and electrochemical soft materials. He has authored or co-authored 11 publications on polymer nanocomposites, molecular dynamics, and related materials, and received China's National Scholarship for Graduate Students in 2021 and 2022. His SAI project will use uncertainty-guided learning to select molecular observables and construct physically constrained closure relations that connect simulations of organic mixed ionic-electronic conductors to device-scale models. His Ph.D. advisors are Jonathan K. Whitmer and Bryan D. Paulsen, and his SAI project mentor is Charles Vardeman.
Guoyue Xu (AME)
Guoyue Xu is a Ph.D. student in mechanical engineering who develops autonomous systems, end-to-end machine-learning pipelines, and self-driving laboratory tools. His work includes a production polymer-discovery platform, a hardware-in-the-loop laboratory system, and a first-author study of autonomous optimization for thermoresponsive polymers. His SAI project will create a vision-language-action robotic layer that translates laboratory instructions into physical actions, beginning with a Kinova robotic arm performing aqueous-solution preparation under explicit safety controls. His Ph.D. advisor is Tengfei Luo, and his SAI project mentor is Brett Savoie.
Yihan Zhu (CSE)
Yihan Zhu is a Ph.D. student in computer science and engineering whose research spans AI for science, foundation models, and generative AI. Her work has been published at NeurIPS and ICLR, and she is also the developer of torch-molecule, an open-source toolkit for molecular discovery. Her SAI project will combine large-scale pretraining and post-training to develop a molecular foundation model for controllable, goal-directed generation, with promising candidates further evaluated through molecular dynamics simulations. Her Ph.D. advisor is Meng Jiang, and her SAI project mentor is Chris Sweet.
Spring 2026 SAI Graduate Fellows
Reza Farzad (CE/ACMS)
Reza Farzad is a Ph.D. student in Civil and Environmental Engineering at Notre Dame conducting research on mechanics-informed machine learning for structural systems under advisor Dr. Patrick Brewick. His SAI fellowship project, “Physics-Informed Multi-Fidelity Deep Generative Models for Interpretable Surrogates of Nonlinear Hysteretic Systems,” combines low-fidelity simulations with limited high-fidelity shake-table data to build interpretable variational models for seismic response prediction in base-isolated structures.
Yikang Gong (CBE)
Yikang Gong is a Bioengineering Ph.D. student at Notre Dame advised by Dr. Jeremiah J. Zartman, with prior training at the University of Pennsylvania and research experience spanning high-resolution imaging, quantitative biology, and machine learning. His SAI fellowship project, “An Explainable Multi-Agent System Powered Research Assistant for Calcium Imaging Analysis,” develops an LLM-based multi-agent platform that automates calcium-imaging workflows while making method choices transparent through literature-grounded reasoning, with the goal of improving reproducibility and usability across diverse cell-model datasets.
Luca Menicali (ACMS)
Luca Menicali is a Ph.D. student in Applied and Computational Mathematics and Statistics at Notre Dame advised by Stefano Castruccio whose research centers on physics-informed and probabilistic machine learning for environmental systems. His SAI fellowship project, “CAE-ViT: Efficient Climate Data Compression with Convolutional Autoencoders and Vision Transformers,” develops a physics-informed compression pipeline for large climate simulation outputs, aiming to preserve critical spatiotemporal structure while reducing storage and compute requirements for forecasting, anomaly detection, and broader climate-modeling workflows.
Miriam Mike (CHEM)
Miriam A. Mike is a biochemistry doctoral candidate at Notre Dame advised by Dr. Marya Lieberman, with prior research training at the University of Ibadan and the Federal University of Technology, Owerri. Her SAI fellowship project, “AI-Enhanced Algorithm for Detecting Substandard Parkinson Medications,” combines Paper Analytical Device (PAD) fingerprints and near-infrared spectra with multimodal machine-learning fusion to improve detection of falsified or degraded Parkinson’s medicines and validate predictions against reference HPLC assays.
Philip Root (AME)
Philip Root is a Ph.D. student in Aerospace and Mechanical Engineering at Notre Dame focused on biomedical additive manufacturing under advisor Dr. Yanliang Zhang. His SAI fellowship project, “RAPID: Robotic Autonomous Printing of Implantable Devices,” advances AI-driven machine vision and process control for printing bioelectronic tissue patches onto dynamically deforming surfaces such as beating hearts by improving point-cloud correspondence, deformation modeling, and spatiotemporal forecasting within the RAPID robotic platform.
Benjamin Sporrer (CSE)
Benjamin Sporrer is a Ph.D. candidate in Computer Science and Engineering at the University of Notre Dame, where he works in the Computer Vision Research Lab advised by Dr. Patrick Flynn and focuses on remote photoplethysmography (rPPG), biometrics, and machine learning for physiological signal analysis. For his Spring 2026 SAI fellowship project, “AI-Assisted Vital-Signal Extraction from Neonatal Hospital Video,” he is evaluating whether de-identified neonatal hospital videos from the 5000 Babies Project can support reliable non-contact heart-rate monitoring by combining classical and deep-learning rPPG methods across varied motion, lighting, and occlusion conditions.
Matt Toole (PHYS)
Matt Toole is a Ph.D. student in condensed matter physics at Notre Dame and a researcher in the Liu Lab of Quantum Matter, where he studies scanning tunneling microscopy (STM), unconventional superconductivity, and advanced data analysis for quantum materials. In his SAI fellowship project, “Disentangling Quantum Interference via Artificial Intelligence for Atomic-scale Quantum Materials Research,” he is building an AI framework to recover intrinsic single-defect quasiparticle-interference signals from overlapping STM data, using simulated training data and benchmarking on known materials before extending the method to challenging systems such as UTe2.
Renzheng Zhang (AME)
Renzheng Zhang is a Ph.D. student in Aerospace and Mechanical Engineering at Notre Dame working at the intersection of generative AI, molecular simulation, and high-performance computing, advised by Prof. Tengfei Luo. His SAI fellowship project, “Physics-Guided Reinforcement Learning for Controllable Graph Diffusion Molecular Generation,” integrates reinforcement learning into a graph diffusion transformer pipeline with density-functional-theory-based free-energy rewards to generate molecular candidates that are not only valid but thermodynamically stable and practically useful.
Fall 2025 SAI Graduate Fellows
Rachel Berg (Ecology, Evolution, and the Environment)
Rachel Berg is a doctoral student in Ecology, Evolution, and the Environment at Notre Dame, where she works with faculty mentor Julián Torres-Dowdall on genomic signatures of adaptation. Her SAI fellowship project, “Leveraging Machine Learning to Filter Structural Variants in Nanopore Data and Detect Signatures of Selection”, uses machine-learning filters to reduce false structural-variant calls in long-read data and builds a companion model for identifying genomic regions under selection.
Hao Chen (Electrical Engineering)
Hao Chen is a Ph.D. student in Electrical Engineering at Notre Dame advised by Dr. Scott Howard with research experience in photonics, signal processing, and fluorescence lifetime imaging microscopy (FLIM). His SAI fellowship project, “Correlated Signal Optimization for Multi-Modal Imaging Systems with Statistical Priors”, builds a physics-informed AI framework that models correlated noise across channels to improve inverse imaging tasks such as denoising and deconvolution in multimodal microscopy.
Stephen Cini (Chemical and Biomolecular Engineering)
Stephen S. Cini is a Ph.D. student in Chemical and Biomolecular Engineering at Notre Dame advised by Prof. Alexander W. Dowling, working on multiscale digital twins and design-of-experiments methods in collaboration with biological systems researchers. His SAI project, “Predicting the Spark: Classifying and Controlling Calcium Wave Initiators in Fruit Fly Larvae”, applies graph neural network classification to calcium imaging data to predict initiator-cell locations and support mechanistic modeling of calcium-wave dynamics.
Brenda Cruz Nogueira (Computer Science and Engineering)
Brenda Cruz Nogueira is a Ph.D. student in Computer Science and Engineering at Notre Dame and a graduate researcher in the NSF Center for Computer-Assisted Synthesis, where she works on graph learning and imbalanced-data problems with advisors Prof. Nitesh V. Chawla and Prof. Nuno Moniz. Her SAI project, “Graph Imbalance Regression for Drug–Target and Protein–Ligand Binding Affinity Prediction”, applies imbalance-aware graph neural models to better identify rare, high-value molecular interactions in drug discovery tasks.
Joseph (Joey) Farmer (Ph.D. Student, University of Notre Dame)
Joseph A. Farmer is a Notre Dame Ph.D. student in the group of Prof. Ryan McClarren with a background in mechanical engineering from Marquette University and current research spanning radiative transfer, Monte Carlo methods, and high-performance scientific computing. His SAI project, “Neutron Transport Simulations with Conditional Flow Matching”, develops a generative AI surrogate that learns particle-exit distributions to accelerate neutron and particle transport simulations while preserving fidelity for fixed-source and criticality-style benchmarks.
Veronica Freund (Physical Chemistry)
Veronica Freund is a Physical Chemistry Ph.D. student at Notre Dame in the Gezelter Lab researching molecular dynamics and neural-network potentials for metal-oxide systems. Her SAI project, “Machine Learned Force Fields for Platinum Oxide Formation using Neuroevolution Potentials”, trains and validates NEP-based force fields for platinum-oxygen systems and integrates the resulting models into OpenMD to support lower-cost simulation of oxide formation pathways.
Nell Karpinski (Chemistry)
Nell E. Karpinski is a Ph.D. student in Chemistry at Notre Dame advised by Prof. Steven A. Corcelli, with research centered on weighted-ensemble molecular dynamics for biomolecular binding mechanisms. Her SAI project, “Integrating a Deep Q-Network in a Markov Decision Process”, combines reinforcement learning with weighted-ensemble trajectory analysis to identify kinetic bottlenecks and mechanistic drivers in DNA minor-groove binder interactions while compressing otherwise massive simulation datasets.
Orlando Mendible Barreto (Chemical Engineering)
Orlando A. Mendible Barreto is a Ph.D. student in Chemical Engineering at Notre Dame working on machine-learning force fields for metal-organic framework (MOF) self-assembly under advisor Yamil J. Colón. His SAI fellowship project, “Artificial Intelligence to Study the Self-Assembly of Metal-Organic Frameworks and the Automation of Research Workflows”, trains ML force fields to capture ab initio-quality interactions at lower cost and couples that workflow with multi-agent LLM automation for faster, reusable research pipelines.
Shashank Ramesh (Aerospace and Mechanical Engineering / Robotics)
Shashank Ramesh is a Ph.D. student in Robotics and Control within Aerospace and Mechanical Engineering at Notre Dame, where he studies mechanism design and optimization for manipulators and grippers in the group of Prof. Mark Plecnik. His SAI project, “Generative AI Framework for Robot Mechanism Design via Ellipse Synthesis”, develops transformer and physics-based generative models to produce multiple feasible mechanism designs that match desired transmission properties and scale mechanism synthesis across architectures.
Andrew Schofield (Chemical Engineering)
Andrew B. Schofield is a Ph.D. student in Chemical Engineering at the University of Notre Dame advised by Dr. Brett Savoie, with prior graduate work at Purdue and undergraduate training in chemical engineering and mathematics at the University of Kentucky. His SAI fellowship project, “Expanded Chemical Property Prediction for Scarce and Corrupted Data Through Masking”, develops masking-based machine learning methods inspired by language modeling to improve prediction for data-scarce chemical properties and to correct inconsistent or noisy property datasets.
Thomas Summe (Computer Science and Engineering)
Thomas Manuel Summe is a Ph.D. student in Computer Science and Engineering at Notre Dame advised by Prof. Siddharth Joshi, with a research focus on neuromorphic computing and online learning in spiking neural networks. His SAI fellowship project, “Developing a Scalable Digital Twin for Resistive RAM-Based Machine Learning Accelerators”, builds surrogate deep-learning models to emulate memristor-based analog circuits at scale and enable faster training/evaluation of hardware-aware SNN systems.
Wei Sun (Physics)
Wei Sun is a graduate student in Physics at Notre Dame advised by Prof. Grant Mathews, studying dense matter in neutron stars through merger and post-merger observables. Her SAI fellowship project, “Joint Bayesian Inference of Neutron Star Equations of State with Multi-messenger and Laboratory Constraints”, builds a unified Bayesian pipeline that combines GW, NICER, kilonova, and laboratory constraints to derive more self-consistent equation-of-state inferences across neutron-star density regimes.
Parisa Toofani Movaghar (Civil Engineering)
Parisa Toofani Movaghar is a Civil Engineering Ph.D. student at Notre Dame working with Prof. Alex Taflanidis whose work focuses on scientific machine learning, uncertainty quantification, and hazard/risk modeling for coastal and storm-driven systems. Her SAI project, “Graph-based ML Models for Data-driven Storm Surge Hazard Estimation”, develops scalable graph neural network surrogates for large synthetic storm databases to improve spatial storm-surge prediction and support operational coastal hazard assessment workflows.
Ruyu Zhou (Statistics)
Ruyu Zhou is a Statistics Ph.D. student at Notre Dame advised by Dr. Fang Liu, with research in statistical machine learning, Bayesian methods, differential privacy, and deep generative modeling. Her SAI project, “AI Meets Scientific Data with Missing Values: Multiple Imputation via Deep Generative Models”, proposes a two-stage imputation framework combining normalizing flows with autoencoder/VAE methods to improve missing-data handling and downstream inference across scientific domains.
Spring 2025 SAI Graduate Fellows
Delin An
Delin An is a Ph.D. student in Computer Science and Engineering at the University of Notre Dame advised by Chaoli Wang, with research interests in AI methods for medical image processing and visualization. His SAI fellowship project, "CT-Conditional Diffusion Model for Aortic Vessel Surface Reconstruction," developed a conditional diffusion and geometric reconstruction pipeline that generated anatomically realistic 3D aortic vessel meshes from CT data.
Nnamdi Chinomso Chikere
Nnamdi Chinomso Chikere is a Ph.D. student in Electrical Engineering at the University of Notre Dame advised by Prof. Yasemin Ozkan-Aydin, researching bioinspired robotic locomotion across complex terrains. His SAI fellowship project, "AI-Driven Terrain Modeling and Gait Optimization for Bioinspired Robotic Mobility," developed a reinforcement-learning and central-pattern-generator framework in simulation to produce terrain-adaptive gait control.
Jihye Hong
Jihye Hong is a Ph.D. student in Physics and Astronomy at the University of Notre Dame advised by Prof. Evan N. Kirby and Prof. Timothy C. Beers, studying stellar chemical abundances and galactic history from large photometric datasets. Her SAI fellowship project, "Machine Learning-based Estimation of Stellar Chemical Abundances in the M31 Using Photometric Data," applied and compared machine learning models to estimate abundances in M31 using APOGEE-trained workflows.
Hyunsu Jeon
Hyunsu Jeon is a Ph.D. student in Chemical and Biomolecular Engineering at the University of Notre Dame advised by Dr. Yichun Wang, focusing on tissue engineering and high-content analysis for cancer systems. His SAI fellowship project, "Artificial Intelligence (AI)-Assisted 3D Tumor-Bone Ensemble Analysis Tool Development for Studying Prostate Cancer Bone Metastasis," built CNN-assisted workflows for automated ROI recognition and spatiotemporal tracking in 3D tumor-bone models.
Logan Todd Monks
Logan Todd Monks is a Ph.D. student in Biology at the University of Notre Dame advised by Dr. Nathan Swenson, with research centered on ecological remote sensing and leaf spectral variation. His SAI fellowship project, "Synthetic generation of remotely sensed hyperspectral imagery," developed a physics-informed generative workflow combining CNN/GAN methods and spectral libraries to synthesize high-resolution hyperspectral imagery from RGB inputs.
Alexander W. Simmons
Alexander W. Simmons is a Ph.D. student in Biophysics at the University of Notre Dame advised by Prof. Holly Goodson, where he studies microtubule dynamic instability and dimer-scale tip structure. His SAI fellowship project, "Using AI to Characterize the Mechanism of Microtubule Dynamic Instability," applied supervised machine learning and explainable AI methods to classify dynamic-instability phases and identify structural motifs linked to catastrophe, rescue, and stutter behavior.
Jichuan Tang
Jichuan Tang is a Ph.D. student in Civil Engineering at the University of Notre Dame advised by Prof. Patrick Brewick, with a focus on dynamical systems and surrogate modeling under uncertainty. His SAI fellowship project, "Using Deep Operator Networks to Enable Spatial-temporal Surrogate Models of Dynamical Systems under Uncertainty," developed DeepONet-based methods to learn full spatial-temporal response fields while reducing computational burden relative to high-fidelity FE simulations.
Maksym Zarodniuk
Maksym Zarodniuk is a Ph.D. student in Bioengineering at the University of Notre Dame advised by Prof. Meenal Datta, where he studies tumor microenvironment biophysics in glioblastoma. His SAI fellowship project, "AI-driven Single-Cell Spatial Proteomics for the Study of Tumor Microenvironment," implemented deep-learning segmentation workflows for multiplex immunofluorescence imaging to support scalable single-cell spatial proteomics analysis.
Gabija Ziemyte
Gabija Ziemyte is a Ph.D. student in Physics at the University of Notre Dame advised by Prof. Marc Osherson, where she works on reconstruction methods for diphoton events in collider data. Her SAI fellowship project, "Machine Learning for Object Reconstruction of Diphoton Events," redesigned AI-based diphoton identification and mass-reconstruction workflows, including extending the approach to ECAL endcap regions and validating it with CMS simulation and collision data.