AIRE Lab - AI for a Resilient Earth

Research Overview

We develop methodologically rigorous, application-driven AI and machine learning methods for science and engineering. Our approach integrates scientific and engineering knowledge, including physical principles, into data-driven learning, with a focus on spatiotemporal modeling and prediction of complex systems.

People

Principal Investigator and Lab Director

Feng Ye

Assistant Professor

Personal Website

Member

Si-Tong Yang

Ph.D. Student
(Spring 2026–now)
Xuanhe Chen

Ph.D. Student
(Fall 2026–now)

Alumni

Cory Petersen — M.S. Student (2024–2025)
Xinxi “Chris” Zhang — M.S. Student (2023–2024)
Prisha Bhamre — Undergraduate Student (2024–2025)
Briana Worrell — Undergraduate Student (2024–2025)
Jeeva Ramasamy — Undergraduate Student (2023–2025)
Andrei Dimitriu — Undergraduate Student (2022–2023)
Althea Miquela — Undergraduate Student (2022–2023)

Publications

Selected publications on spatiotemporal learning and forecasting for weather and energy systems.

Physics-guided flow matching framework integrating physical equations for global total electron content forecasting

Physics-Guided Flow Matching: A Generative AI Framework for Global Total Electron Content Forecasting

S.-T. Yang, F. Ye, X. Lu, D. Lin, and B. C. Martinez

arXiv preprint, arXiv:2610.37159, 2026.

DeepMIDE: A Multi-Output Spatio-Temporal Method for Ultra-Scale Offshore Wind Energy Forecasting

F. Ye, X. Zhang, M. L. Stein, and A. A. Ezzat

Technometrics, vol. 68, no. 3, pp. 452–468, 2026.

First Place, 2024 IISE Annual Meeting QCRE Track Best Student Poster Award

Horizon-dependent ensemble method for probabilistic offshore wind forecasting

A Horizon-Dependent Ensemble Method for Probabilistic Forecasting in Offshore Wind Farms

J. Ji, F. Ye, T. Miles, and A. A. Ezzat

INFORMS Journal on Data Science, accepted.

Animated AIRU-WRF offshore wind forecasts

AIRU-WRF: A Physics-Guided Spatio-Temporal Wind Forecasting Model and Its Application to the U.S. Mid-Atlantic Offshore Wind Energy Areas

F. Ye, J. Brodie, T. Miles, and A. A. Ezzat

Renewable Energy, vol. 223, 119934, 2024.

First Place, 2023 IISE Annual Meeting Energy Systems Track Best Paper Award

First Place, 2022 INFORMS Annual Meeting Sustainability Cluster Best Student Paper Award

Coastal upwelling schematic and sea surface temperature maps for offshore wind forecasting

Improved Spatio-Temporal Offshore Wind Forecasting with Coastal Upwelling Information

F. Ye, T. Miles, and A. A. Ezzat

Applied Energy, vol. 380, 125010, 2025.

Wind turbine icing detection and prediction using sensor data and machine learning

Icing Detection and Prediction for Wind Turbines Using Multivariate Sensor Data and Machine Learning

F. Ye and A. A. Ezzat

Renewable Energy, vol. 231, 120879, 2024.

Offshore wind farm maintenance scheduling and vessel logistics research overview

Accessibility-Aware Stochastic Optimization of Maintenance Scheduling and Vessel Logistics for Offshore Wind Farms

M. C. Sahin, F. Ye, A. A. Ezzat, O. A. Kilic, and M. Yildirim

IEEE Transactions on Reliability, pp. 1–14, 2026.

Animated vessel routes from a data-driven probabilistic simulation of vessel operations

Data-Driven Probabilistic Simulation of Vessel Operations to Support the Blue Economy

C. Petersen, J. Ji, F. Ye, A. A. Ezzat, J. Kohut, D. Saginaw, A. Montanti, and J. Cammarota

Ocean Engineering, vol. 354, 124818, 2026.

Offshore Wind Energy Prediction Using Machine Learning with Multi-Resolution Inputs

F. Ye, T. Miles, and A. A. Ezzat

In Multimodal and Tensor Data Analytics for Industrial Systems Improvement, edited by N. Gaw, M. Reisi, and P. Pardalos. Cham: Springer International Publishing, pp. 167–183, 2024. (Invited chapter.)

Accessibility and serviceability assessment for US East Coast offshore wind operations

Accessibility and Serviceability Assessment to Inform Offshore Wind Energy Development and Operations off the US East Coast

C. Petersen, F. Ye, J. Ji, J. Kohut, A. A. Ezzat, D. Saginaw, A. Montanti, and J. Cammarota

Wind Energy, vol. 29, no. 7, e70131, 2026.

Economic and reliability value of offshore wind forecasting in the New York power grid

Economic and Reliability Value of Improved Offshore Wind Forecasting in Bulk Power Grid Operation: A Case Study of the New York Power Grid

K. B. Walid, F. Ye, J. Ji, A. A. Ezzat, T. Miles, and Y. Jiang

IEEE Access, vol. 14, pp. 148337–148357, 2026.

An Integro-Difference Equation Model for Spatio-Temporal Offshore Wind Forecasting

F. Ye and A. A. Ezzat

2024 IEEE Power & Energy Society General Meeting (PESGM) Proceedings, 2024.

Ultra-short-term probabilistic wind forecasting using numerical weather predictions

Ultra-Short-Term Probabilistic Wind Forecasting: Can Numerical Weather Predictions Help?

F. Ye, J. Brodie, T. Miles, and A. A. Ezzat

2023 IEEE Power & Energy Society General Meeting (PESGM) Proceedings, 2023.

Opening

Ph.D. Student Openings

I am always looking for excellent students with high motivation and strong research potential to join our lab.

Applicants with backgrounds in engineering, statistics, computer science, or related fields and strong coding skills are encouraged to apply. If interested, please email me your CV, transcript, and any additional materials that highlight your qualifications to fengye.recruit@gmail.com. Use “Ph.D. Application – Your Name – Target Term” as the email subject. For more information, please check the Ph.D. programs at Clemson IE.