Bradley is a DPhil student in the Applied Artificial Intelligence Lab at the Oxford Robotics Institute and the Atmospheric Processes Group in the Department of Physics, co-supervised by Professor Ingmar Posner and Professor Hannah Christensen. He is part of the Intelligent Earth CDT, working at the intersection of machine learning and climate science.
His research focuses on developing machine learning methods for complex dynamical climate systems, where non-stationarity and out-of-distribution behaviour are central challenges rather than edge cases. In particular, he is interested in moving beyond physics-informed networks towards “physics-learned” approaches, drawing on scientific discovery, causal representation learning, and compositional generalisation to ground models in the true physics governing the climate.
Before starting his DPhil, Bradley worked as a biomedical engineer developing a surgical simulator for implanting a neuromodulation device. He previously completed an MEng in Electronic and Information Engineering at Imperial College London, focusing on machine learning, computer vision, mobile and human-centred robotics.
