This project will explore the use of supervised and unsupervised statistical learning methods (such as neural networks, random forest, clustering) to understand the impact of climate change on hydrological extremes and/or to simulate downstream impacts on affected sectors, such as agriculture, energy, transport, water resources management.
Tag Archive: hydrological extremes
Research brief: Higher streamflow variability than rainfall creates challenges for hydrologic variability framework.March 9, 2020 2:35 pm Comments Off on Research brief: Higher streamflow variability than rainfall creates challenges for hydrologic variability framework.
New research shows, contrary to expectation, the inter-annual variance in evapotranspiration is much smaller than for precipitation, runoff and soil storage. Accounting for hydrologic covariances explains why it is possible for variability in the principal sink (e.g., streamflow) to exceed variability in the source (precipitation).
The aim of this student project is to investigate the impacts of climate change on hydrological extremes, such as high runoff events, hydrological or agricultural drought. It uses outputs of the AWRA-L hydrological model, which underpins the BoM's Australian Landscape Water Balance website.