Research
I use artificial intelligence (AI) and machine learning (ML) techniques to analyze the outputs of climate models, focusing on evaluating and intercomparing model performance across key structural aspects such as resolution, coupling strategies, and parameterisation schemes. This work aims to provide innovative, data-driven insights to inform model development and ultimately reduce uncertainties in future climate projections.
I am also interested in leveraging climate model simulations to train ML/AI algorithms, with the goal of applying these models to observational data. This includes enhancing our understanding of the climate system, reconstructing unobserved past climate features, and improving predictive capabilities.
In addition, I collaborate on ML-based paleoclimate reconstruction projects with external partners, combining data-driven approaches with domain knowledge to gain deeper insights into past climate variability.