Jessica is a PhD student in the Department of Statistics, where her work bridges the gap between advanced machine learning and extreme event prediction, particularly with regards to extreme climate events. Her background spans both technical ML and public policy, with prior experience applying computational methods to humanitarian decision-making, infrastructure investment, and global governance. She is particularly interested in the reliability of generative AI in high-stakes environments, specifically how synthetic weather data can be rigorously validated to ensure it accurately captures extreme tails of a distribution, including rare, extreme events that fall outside the historical record but are critical for long-term risk management.

Her research focuses on the intersection of generative modelling and extreme value theory, with an emphasis on developing formal validation frameworks for synthetic climate data. This involves combining statistical machine learning with spatio-temporal modelling to assess the trustworthiness of AI outputs for applications in energy systems, infrastructure planning, and environmental risk. Her work includes building benchmark datasets, designing controlled evaluation systems, and systematically comparing modelling approaches across different mechanisms of extreme event formation to provide a rigorous foundation for decision-making under uncertainty.