Mostafa Rezaali

Curriculum Vitae

Personal website

Focus Areas:

• Earth System Science
• Sustainability & Global Environmental Change

Country of Origin: Iran

Degree Program: PhD

Entered Program: Fall 2022

Expected Graduation: Fall 2026

Dissertation Topic: TBD

Research Statement

My research develops generative deep learning frameworks for probabilistic prediction of climate extremes, with a focus on heat waves and flash droughts over the continental United States. I build on two core methods: a Variational Diffusion Model (VDM) that captures spatial uncertainty through ensemble forecasting, and a Conditional Flow Matching (CFM) framework using a physics-informed graph neural network on an icosahedral mesh (MeshFlowNet) that processes global teleconnection fields for regional downscaling. I work with large-scale reanalysis and remote sensing datasets (ERA5, CMIP6, MODIS) and train models on UF's HiPerGator using distributed PyTorch. My broader interests include hydroclimatology, climate change impacts on ecosystems, and bridging physics-based and data-driven modeling.

Adviser: Dr. David Keellings

Educational Background

• M.S. in Civil and Environmental Engineering, Qom University of Technology, 2018
• B.S. in Civil and Environmental Engineering, Islamic Azad University, Khomeini Shahr, 2016

Publications

Rezaali, M., Fouladi-Fard, R., O'Shaughnessy, P., Naddafi, K., & Karimi, A. (2025). Assessment of AERMOD and ADMS for NOx dispersion modeling with a combination of line and point sources. Stochastic Environmental Research and Risk Assessment, 1-15.

Narayanan, A., Rezaali, M., Bunting, E.L., & Keellings, D. (2025). It's getting hot in here: Spatial impact of humidity on heat wave severity in the US. Science of The Total Environment, 963, 178397.

Rezaali, M., Jahangir, M. S., Fouladi-Fard, R., & Keellings, D. (2024). An ensemble deep learning approach to spatiotemporal tropospheric ozone forecasting: A case study of Tehran, Iran. Urban Climate, 55, 101950.

Rezaali, M., Quilty, J., & Karimi, A. (2021). Probabilistic urban water demand forecasting using wavelet-based machine learning models. Journal of Hydrology, 600, 126358.

Rezaali, M., Fouladi-Fard, R., Mojarad, H., Sorooshian, A., Mahdinia, M., et al. (2021). A wavelet-based random forest approach for indoor BTEX spatiotemporal modeling and health risk assessment. Environmental Science and Pollution Research, 28, 22522-22535.