People
Meet associate fellows of the AI Hub for Science from the College of Sciences. The hub will be adding collaborators across campus, as well as external institutions and industry.
Biological Sciences
| Faculty Name | AI Research Activities | |
|---|---|---|
| Scott Belcher | [email protected] | ML/Neural networks - used to predict PFAS toxicity. Toxicol Sci. 2025 Jan 1;203(1):67-78. |
| Carlos Goller | [email protected] | Research: Testing ML/Neural networks for pathway prediction/identification in microbial genomes and BED file creation for adaptive sequencing of metagenomes. Education: UNC system Claude.ai test for education and comparing to Gemini. Quality Matters AI-assisted course design aligned with SRSs. |
| Louis-Marie Bobay | [email protected] | ML/Neural networks - Big data and inference of population genetics parameters |
| Bonnie Hurwitz | [email protected] | Virus detection in microbiomes |
| Carter Clinton | [email protected] | ML to identify/predict genetic sequences in degraded/aDNA (human); ML - generate models of pathogen evolution in historical infectious disease outbreaks; ML - Phenotype prediction (random forests, gradient boosting, neural nets) to improve EHR-based phenotype definitions; ML - Bayesian deep learning or variational inference models for ancestry-aware fine-mapping; ML - multi-task learning models to detect pleiotropy, sharing representations across traits |
| Stephanie Mathews | [email protected] | PIT Stop program with NCSU Libraries to develop AI teaching tool; AlphaFold2: Predict phage protein structure in MB/BIT 211; LLM to generate lecture and research focus group transcripts |
| Chris Halweg | [email protected] | LLM to generate course question banks compatible with Moodle bulk import based on learning outcomes and course content |
| Jeff Yoder | [email protected] | Leveraging protein language models to characterize immune receptor families and discover novel protein variants across vertebrate lineages. Uses ESM2 embeddings fine-tuned for deep sequence analysis, combined with ESMfold for domain prediction and structural modeling |
| Amanda Yi-Hui Zhou | [email protected] | Leads research on machine learning approaches to advance biomedical data analysis and discovery." |
Chemistry
| Faculty Name | AI Research Activities | |
|---|---|---|
| Phil Castellano | [email protected] | Used in the CAPs Phase I CCI for photoreaction optimization, selectivity, discovery, and making spectroscopic predictions based on structure/composition |
| Ryan Chiechi | [email protected] | Generative AI for data processing and coding; RAG for a contextual semantic interface to course material for undergraduate chemistry students |
| Raja Ghosh | [email protected] | Integrating Quantum Algorithms with AI-guided automation experiments for accelerating materials design and discovery |
| Milena Jovanovic | [email protected] | Crystal structure prediction |
| Jonathan Lindsey | [email protected] | Leveraging chatbots for fundamental concepts and measurements in photochemistry |
| Thomas Theis | [email protected] | Neural Nets for image processing |
Marine, Earth and Atmospheric Sciences
| Faculty Name | AI Research/Education Activities | |
|---|---|---|
| Del Bohnenstiehl | [email protected] | Use ML/AI involves classification of underwater sounds, marine ecology, and remote sensing. Taught a graduate-level class in ML for Geoscientists in Spring 2024 & 2025 |
| Roy He | [email protected] | Co-Principal Investigator of the NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES). Co-developed OceanNet and OceanAI. Applies AI/ML techniques to oceanography and ocean forecasting, combining physics-informed modeling with deep learning |
| Gary Lackmann | [email protected] | ML for sorting and categorization, exploring predictive methods (e.g., random forests). See papers such as Chase et al. 2022, 2023; Radford and Lackmann 2022a,b |
| Paul Liu | [email protected] | Conducts research on AI-LLM applications in geoscience. Co-developed OceanAI, OceanGPT-autocoding, DeltaGPT, and TradeAI systems. Taught DSC 595-002: Generative AI for Science. Delivered multiple Two-day intensive, hands-on AI-LLM training workshopsAuthor of [How to Build and Fine-Tune a Small Language Model], [Generative AI for Science (coming soon)] |
| Zhen Qu | [email protected] | Applies machine learning to predict air pollutants and greenhouse gases |
| Lian Xie | [email protected] | ML for hurricane-related forecast |
| Sandra Yuter | [email protected] | Machine learning for big data analysis |
| Xiangdong Zhang | [email protected] | Deep learning for reconstructing polar region climate data |
Mathematics
| Faculty Name | AI Research Activities | |
|---|---|---|
| Bojko Bakalov | [email protected] | Quantum Machine Learning |
| Zixuan Cang | [email protected] | Geometric and topological data analysis, with applications in biology |
| Chao Chen | [email protected] | Fast algorithms for training neural networks |
| Patrick Combettes | [email protected] | Non-smooth and convex optimization |
| Mohammad Farazmand | [email protected] | Scientific machine learning and AI for dynamical systems |
| Kevin Flores | [email protected] | Data science for mathematical biology |
| Mikhail Gilman | [email protected] | CNN for classification of radar images |
| Mansoor Haider | [email protected] | FDS, unsupervised learning and applying machine learning to the design of optimized microelectronic circuits and systems |
| Ilse Ipsen | [email protected] | Mathematics underlying LLMs (low-rank approximation, quantization, etc.) |
| Hangjie Ji | [email protected] | Scientific Machine Learning |
| Rachel Levy | [email protected] | Lead Data Science and AI Academy and Campus-wide AI Advisory group. Interest in literacy to expertise workforce development, education, policy |
| Ryan Murray | [email protected] | Develop theory for data science algorithms |
| Yeonjong Shin | [email protected] | Scientific Machine Learning, Fundamental understanding and new developments of AI algorithms. Applications to physical sciences and engineering |
| Jordan Snyder | [email protected] | Data Science Education |
Physics and Astronomy
| Faculty Name | AI Research Activities | |
|---|---|---|
| Harald Ade | [email protected] | Working on automated identification of thermal transition temperatures from in-situ spectroscopy using combined statistical models; high-throughput data analysis of in situ X-ray scattering. Toward the use of supervised machine learning for classification, decision making for applications in conjugated polymer-based thin films. (With Brendan O'Connor) |
| Brendan O'Connor | [email protected] | Working with Harald Ade on automated identification of thermal transition temperatures and supervised machine learning for classification |
| Rongmon Bordoloi | [email protected] | Used deep learning methods to study evolution of the intergalactic medium when the Universe was very young. Applied novel Bayesian deep learning techniques to estimate rigorous model uncertainties |
| Bill Ditto | [email protected] | Physics Informed Neural Networks, Improvement of AI approaches through nonlinear dynamics and adaption. Working on commercialization of Chaos Aware AI (patent issuing soon) and Adaptive and Growing network AI |
| Nathan Ennist | [email protected] | Uses ML-based methods of computational protein design to develop new, genetically-encodable photosynthetic pathways for high-efficiency solar energy conversion |
| Paschalis Gkoupidenis | [email protected] | Emulating and interfacing biological systems with organic neuromorphic electronics for physical and physiological AI |
| Hans Hallen | [email protected] | Used ML to forecast upcoming blockages in wireless communications systems. Address the problem of expensive/insufficient measured data to train AI for real world use |
| Chueng-Ryong Ji | [email protected] | QCD global analysis of meson and nucleon parton distribution functions using ML/DL |
| Sebastian Koenig | [email protected] | Working on the development of novel AI/ML techniques within the STREAMLINE Collaboration. Focus on application of eigenvector continuation to quantum resonance states |
| Xingcheng Lin | [email protected] | Collaborates with UNC-Chapel Hill and Texas A&M to develop AI models that integrate dynamic information from MD simulations for improved predictions of protein function |
| Robert Riehn | [email protected] | DNN-based annotation of ant poses in video data. ML/DNN based identification of motion patterns of ants |
| Vladimir Skokov | [email protected] | Locating the QCD critical point by performing analytical continuation using ML |
| Andrey Tarasov | [email protected] | ML based modelling of Transverse Momentum Dependent distribution functions, which describe the three-dimensional structure of protons and neutrons inside the atom's nucleus |
| #NAME? | [email protected] | Quantum Machine Learning |
Statistics
| Faculty Name | AI Research Activities | |
|---|---|---|
| Rosemary Danaher | [email protected] | For research, uses AI tools for identifying environmental/lifestyle risk factors driving Young Adult Breast Cancer; for teaching, uses Google Notebook to create video and audio summaries of lecture notes |
| Sujit Ghosh | [email protected] | Designs probabilistic approaches for solving challenging optimization problems in high-dimensional spaces. Develops active learning strategies that leverage similarity-based techniques to improve accuracy and efficiency of classification and regression models |
| Subhashis Ghoshal | [email protected] | Theory of deep learning |
| Jessie Jeng | [email protected] | High-dimensional inference and transfer learning, applying AI machine learning grounded in statistical principles to enhance weak signal detection and feature extraction in complex, noisy datasets |
| Jungeum Kim | [email protected] | Develops principled methods for statistical uncertainty quantification in artificial intelligence; applications include generative models, deep learning, and adversarial robustness. Bridges classical statistical theory with AI to create interpretable and reliable methodologies |
| Wenbin Lu | [email protected] | Develops machine learning and reinforcement learning methods for evaluating policies and learning optimal policies; Uses machine learning/LLM tools for risk prediction |
| Brian Reich | [email protected] | Deep learning for large spatial datasets in climate and epidemiology |
| Ana-Maria Staicu | [email protected] | Develops statistical methods for longitudinal and functional data that advance AI applications in biostatistics, brain imaging, social media, environmental science, and animal health |
| Jung-Ying Tzeng | [email protected] | Focuses on developing federated learning and federated meta-analysis methods for structural variant analysis and genetic risk prediction. Develops privacy-preserving, summary statistics-based approaches |
| Jon Williams | [email protected] | Contributes essential tools for uncertainty quantification in artificial intelligence applications, with finite-sample reliability guarantees. Works on unification of uncertainty quantification in statistics and related research communities |
| Shu Yang | [email protected] | Develops AI and machine learning-innovated clinical trial designs for drug discovery and decision-making. Develops causal inference methods leveraging AI's predictive capabilities to enhance treatment effect evaluation in real-world data and evidence |