Ana Silva Tavares

Explainable Neural Networks for Subseasonal Atlantic Tropical Cyclone Forecasting

Ana is a DPhil student interested in advancing our understanding of Earth system predictability through the implementation of explainable and/or interpretable machine learning methods. More specifically, during her project, she aims to study different sources of subseasonal tropical cyclone predictability in the Atlantic using explainable neural networks.

Ana has an interdisciplinary background, with a BEng in Aerospace Engineering and an MSc in Applied Data Science and Statistics. She is currently part of the Environmental Research DTP, with her research funded by the Natural Environment Research Council (NERC). Ana is part of the Hydro-Climate Extremes Research Group, led by her supervisor, Professor Louise Slater. She is co-supervisor by Dr Katherine Kowal, a former member of the group, who is now based at the National Oceanic and Atmospheric Administration (NOAA).

Outside of work, Ana spends most of my time either dancing bachata or cooking. While she loves any Afro-Latin dances, the rhythms of the Dominican Republic have truly captured her heart. Ana is passionate about exploring different cultures through dance, music, and cuisine.

• Subseasonal Predictability & Variability
• Subseasonal-to-Seasonal Prediction
• Explainable and Interpretable Machine Learning for Weather and Climate
• Tropical-Extratropical Teleconnections
• Tropical Cyclones
• Windows of Opportunity