Our group has moved to the University of Chicago.

We study extreme weather, climate change, geophysical turbulence, and scientific machine learning (ML) through the lens of multi-scale nonlinear dynamics. We integrate tools and concepts from nonlinear and climate dynamics, applied and computational math, and ML to gain a deeper theoretical understanding of these phenomena and to develop novel frameworks to predict them across the time and spatial scales. We are also interested in interdisciplinary collaborations that enable direct translation of fundamental advances in AI+science to address critical societal needs, particularly through our involvement with UChicago’s AI for Climate (AICE) Initiative and Human-centered Weather Forecasts (HCF) Initiative.

Recent News:

• May 2025: Check out the paper led by research scientist Dr. Qiang Sun titled “Can AI weather models predict out-of-distribution gray swan tropical cyclones” published at PNAS. The paper presents controlled experiments showing that an AI weather model cannot forecast tropical cyclones stronger than anything they had seen in the training set (i.e., they cannot extrapolate). However, the AI model shows promise in learning from strong storms in one region and forecasting them in another region. The results have important implications for the current AI weather models and climate emulators.
• September 2024: Prof. Hassanzadeh is the director of the new AI for Climate (AICE) Initiative at UChicago’s Data Science Institute. AICE aims at interdisciplinary integration of AI with fundamental domain knowledge to accelerate and transform climate research with a focus on both scientific advances and societal impacts.
• August 2024: Congratulations to PhD student Karan Jakhar for receiving three honors for his work on equation discovery of turbulence closure using ML: AGU Editor’s Highlight for his new paper in JAMES, 2023 AGU Outstanding Student Presentation Award (OSPA), and best presentation award at Schmidt Sicneces Cross-VESRI meeting in Cambridge University.
• October 2023: Check out the recording of the talk titled “Integrating physics, data and scientific machine learning to predict climate variability and extremes“, which was gaving as a part of the APS-GPC seminar series.