Spring 2026 Lecture in Climate Data Science: SAVANNAH FERRETTI

*Please note that in-person space is limited.*

__________________________________________________________________________________

Abstract: Machine learning can improve climate prediction by combining information across horizontal space, height, and time in a “neighborhood” around each prediction point. However, as these neighborhoods grow, the learned relationships can become difficult to interpret and increasingly prone to overfitting.

We introduce data-driven integration kernels, a framework that builds interpretability into this setting by separating information aggregation from local nonlinear prediction. Each predictor field is first summarized by integrating it with learnable weighting functions (“kernels”) over space, height, and/or time, and the prediction model then operates only on these integrated features (plus any optional local inputs).

This structure limits complex nonlinear interactions while making each kernel directly interpretable as a weighting pattern, revealing which horizontal locations, vertical levels, and past timesteps contribute most to the prediction. We demonstrate the approach for South Asian monsoon rainfall, showing that kernel-based models achieve near-baseline performance with far fewer trainable parameters, suggesting that a small number of interpretable integrations can capture much of the relevant spatiotemporal information.

Bio: Savannah is a fifth-year PhD candidate in Earth System Science at the University of California, Irvine, co-advised by Professors Mike Pritchard (now at NVIDIA) and Jane Baldwin. Her research combines statistical modeling and machine learning to understand the drivers of South Asian monsoon rainfall. She is passionate about building reproducible, open-source workflows that bridge atmospheric science and data science, and she is currently exploring opportunities for the next stage of her career after completing her PhD.

Learn More:

SAVANNAH FERRETTI
University of California Irvine

Event Venue & Nearby Stays

Columbia Innovation Hub - Tang Family Hall, 2276 12th Avenue, New York, United States

Concerts, fests, parties, meetups - all the happenings, one place.

Get App