Application of machine learning methods for nutrient prediction in urban catchments

The impacts of urbanisation on water quality and long- and short-term water quality changes are of central concern in many estuaries and coastal waters. This thesis demonstrated that machine learning (ML) methods can be successfully used for interpolation and simulation of nutrient and oxygen concentrations, across a range of hydrological systems and hydrological conditions. ML models are an essential tool to fully utilise all available water quality and hydrological data for water quality modelling, to facilitate the exploration of spatial and temporal signals in groundwater and surface water nutrient data, and ultimately the management of receiving waters.