I am a Ph.D. candidate associated with the Environmental Intelligence CDT, specialising in the intersection of climate science and machine learning. My academic background includes an integrated master’s degree in Natural Science from the university of Exeter, with a focus on Machine Learning and Scientific Computing.

My current doctoral research focuses on addressing the computational challenges inherent in climate and cloud modelling. Specifically, I am developing a machine learning approach for cloud modelling that offers improved efficiency compared to traditional methods. This approach also aims to provide insights into discrepancies within traditional climate models' cloud schemes.

Emphasising open-source principles and modularity, my work is designed to facilitate integration into existing climate modelling practices.

I am interested in Physics-Informed Neural Networks (PINNs), a framework that integrates both physical principles and domain-specific knowledge, extending beyond traditional physical laws to encompass diverse fields such as economics and biology. My interest lies in leveraging PINNs to reconcile data-driven approaches with fundamental principles across various scientific domains.

I welcome opportunities to collaborate on research.

My previous work has involved research on the combination of bioclimatic classification schemes and CMIP6 climate projections.