About the event
Water security in the Himalayas is threatened by climate change. This is especially the case for the Upper Indus Basin where water resources sustain over 270 million people. Most solid water reserves are expected to disappear by the end of the century and precipitation is set to become the main driver of river flow. Yet future precipitation estimates for this region are uncertain.
This talk will explore the feasibility of using large-scale atmospheric features, better constrained by global climate models, to predict local precipitation and assess the probability of extreme precipitation events in the future. More specifically, Gaussian processes are trained to predict monthly ERA5 precipitation data over a 15-year horizon. Different Gaussian process model designs, contrasting covariance functions built using domain knowledge with a non-stationary covariance function that learns empirical relationships within the data will also be explored.
This event is part of the Environment and Sustainability Seminar Series.