Using a novel Non-linear AutoRegressive Moving Average with eXogenous inputs (NARMAX) systems identification (an interpretable form of machine learning) approach, that identifies and models linear and non-linear dynamic relationships between a range of variables, this project seeks to extend skilful seasonal forecasting to seasons beyond winter, identify factors that contribute skill to the forecast, develop regional seasonal forecasts for Northwest Europe and assess the benefits of skilful probabilistic seasonal forecasts to potential users such as the agri-food industry.