Bio
As Co-Director of the Natural Environment, Turing Research and Innovation Cluster in Digital Twins (TRIC-DT) at The Alan Turing Institute and Science Leader and Head of the AI Lab at the British Antarctic Survey I lead a multidisciplinary team focused on pioneering the application of artificial intelligence and digital twin technologies to environmental forecasting and decision-making. Our work is especially relevant in data-sparse environments like the polar regions, where we develop innovative solutions to integrate diverse data sources, improve predictive modelling, and enhance our understanding of a rapidly changing planet.
Our projects are as diverse as the ecosystems we study. We’re merging data from satellites and ground sensors to create a real-time pulse of our planet, developing new machine learning algorithms to forecast our weather, and developing AI-powered tools to track wildlife populations and monitor environmental change. I’m particularly excited about our Antarctic Digital Twin programme, which aims to provide near-instantaneous insights for informed decision-making in this crucial region.
My journey has been fuelled by incredible collaborations, partnerships, and a dash of recognition along the way. Our research has been featured in Nature Communications, Nvidia, Wired Magazine and our group was acknowledged as an “AI for Good” exemplar by the UK government. But the most rewarding moments are witnessing the impact of our work – informing policies, shaping sustainable practices, and ultimately, giving our planet a voice through the power of AI.
There’s still so much to explore, and I’m excited to continue this journey, one digital twin at a time. If you share my passion for protecting our planet, let’s connect! I’m always eager to collaborate, share knowledge, and inspire others to join the fight for a sustainable future.
P.S. I’m a firm believer in the power of open collaboration. Feel free to join our Slack if you’re interested in joining our mission!
Research interests
- AI and Digital Twinning for the natural environment
- Application of AI for climate risks, and the prediction of high-impact weather events
- Intelligent post-processing of climate data, including bias correction and downscaling
- Simplifying data analysis pipelines for the application of AI
- Probabilistic machine learning, providing robust uncertainty estimates for business and environmental policy decision making
- Combining Little Data and Big Data
- Scalable data science methods for large N-dimensional spatiotemporal datasets
- Flexible approaches for irregularly sampled and fragmented datasets