Taming AI for Meteorological Research: The Role of Interpretable AI

Abstract: As we enter the AI era, domain scientists face a critical question: What can we do to harness AI effectively for scientific discovery? AI has demonstrated remarkable capabilities, from accelerating simulations to uncovering hidden patterns in complex datasets. While these advancements offer unprecedented opportunities, they also raise concerns—AI models often function as “black boxes,” making it difficult to connect their outputs to established scientific principles. This lack of interpretability can undermine trust and limit adoption, particularly in fields like meteorology where physical understanding is critical.

In this talk, I will explore how interpretable AI can bridge this gap, highlighting its potential to generate explicit, physically meaningful equations rather than opaque neural networks. Through four case studies from my lab, I will showcase how interpretable AI can enhance scientific understanding:

1. Satellite Precipitation Retrieval: Using AI-based approaches to interpret precipitation retrieval algorithms from AMSU data, we identified critical microwave channels (89 and 150 GHz) that directly link to physical processes in the atmosphere.
2. Quantitative Precipitation Estimation (QPE): By applying symbolic regression models to polarimetric radar data, we derived mathematical expressions that outperform traditional Z-R relationships and existing QPE algorithms, offering new insights into rainfall microphysics.
3. Tornado Probability Prediction: Leveraging reinforcement learning-based symbolic deep learning models, we developed interpretable equations that outperform the traditional Significant Tornado Parameter (STP) index, providing a clearer understanding of the relationships between key atmospheric variables and tornado risk.
4. Domain-Aware Symbolic Regression for Scientific Equations: In our latest work, we introduced a symbolic regression framework that incorporates domain-specific symbol priors extracted from thousands of scientific publications. By encoding common mathematical structures—such as the prevalence of trigonometric functions in physics or logarithmic forms in biology—into a tree-structured reinforcement learning model, we improved both the accuracy and interpretability of discovered equations. This approach accelerates convergence, enforces physical plausibility, and reveals new governing relationships in climate and geophysical data.

Through these examples, I hope to spark discussion on the evolving role of domain scientists in the AI era and inspire new ways to integrate AI with physical understanding in atmospheric research.

Bio: Dr. Yixin Berry Wen is an Assistant Professor of the Department of Geography at the University of Florida. Berry received her PhD degree from the School of Meteorology, University of Oklahoma. She further honed her skills during postdoctoral research at the NASA/ Jet Propulsion Laboratory (JPL) before returning to Oklahoma as a research scientist at NOAA. In this role, she was affiliated with Radar Division in National Severe Storms Laboratory.

Berry is the Chair of User Working Group with NASA/Goddard Earth Sciences Data and Information Services Center (GES DISC) as an expert in AI and data fusion. Additionally, she serves as an editor of the AGU’s new journal, JGR: Machine Learning and Computation.

Berry's research areas of focus include radar and satellite remote sensing, machine learning, and interpretable AI. Additionally, she engages in long-term climate data analysis, studying extreme events and water-related natural hazards. Beyond her scientific pursuits, Dr. Wen is committed to working with Indigenous Peoples and Native Nations.

*This seminar will be held in person and online*

Topic: IACS Seminar Speaker: Yixin Wen

Time: Apr 2, 2025 01:30 PM Eastern Time (US and Canada)

Join Zoom Meeting

https://stonybrook.zoom.us/j/97596399106?pwd=0PBvElFLqov3biO6OlQxSWLWudkIuH.1

Meeting ID: 975 9639 9106

Passcode: 096213