High Mountain Asia supplies freshwater to over one billion people via Asia's largest rivers. In this area, rain and snowfall are the main drivers of river flow. However, the spatiotemporal distribution of precipitation is still poorly understood due to limited direct measurements from weather stations. Existing tools to fill in missing data or improve the resolution of coarser precipitation products produce biased results. In this talk, I will propose a method to generate more accurate high-resolution precipitation predictions over areas with sparse in situ data, called Multi-Fidelity Gaussian Processes (MFGPs). MFGP can combine multiple precipitation sources to increase the accuracy of precipitation estimates while providing principled uncertainties. This method can also make predictions in ungauged locations, away from the high-fidelity training distribution. Finally, MFGPs are simpler to implement and more applicable to small datasets than state-of-the-art machine learning models.
I am a 3rd year PhD student at the University of Cambridge and a member of the AI for Environmental Risk Programme. My PhD focuses on applying Gaussian Process-based methods to better understand precipitation in High Mountain Asia. I also have experience applying machine learning to other environmental problems such as wildfires, glacier elevation change and cloud identification. I'm also interested in climate policy and bridging the gap between science and decision-making. Before coming to Cambridge, I completed an integrated master's in Physics at Imperial College London.
