Probabilistic modelling for forecasting of water data time series

The outcome of the thesis is the development of a forecasting methodological approach applied to wastewater quality control and water supply demand analysis. This approach involves the definition of one or more deterministic models, which act as input for the probabilistic component. Consequently, it allows for estimating the complete probability distribution of a target variable, conditioned on the deterministic component forecasts. The adaptability of this methodology to different contexts and objectives is evident, making it applicable to a variety of scenarios.