Abstract

In the face of impending climate change, the need to understand the impact of extreme weather events is critical; whilst large climate models provide broad detail, such as large scale patterns in surface temperature, they are unsuitable for understanding regional and localised impact and for predicting the potential impact of extreme events. An investigation into machine learning approaches will be undertaken to determine whether or not such approaches are capable of generating credible predictions for extreme scenarios, specifically precipitative events and subsequent catchment run-off/peak flow. There are three aspects to this project: creating more usable output of precipitation data from GCMs, through bias correction and downscaling; an investigation into whether machine learning approaches can deliver more credible results when compared with industry hydrologists (partner: Mott MacDonald); and the analysis of machine learning performance around extreme hydrological events.