This dataset provides Northwest European seasonal weather predictions from complex systems modelling for Summer and Winter from 1940 to 2023.

Time series of standardised anomalies with respect to the period 1981-2010 were obtained for each dataset, covering sea ice cover, sea surface temperatures, tropical precipitation, sea level pressure, the stratospheric polar vortex, snow cover, sunspot activity, volcanic activity and carbon dioxide concentrations. In addition, using 500 hPa geopotential height data from the ERA5 reanalysis, time series of jet speed and latitude were derived and the top three principal empirical orthogonal functions of atmospheric circulation variability for the North Atlantic and European sector.

Weather conditions have significant socio-economic impacts and producing seasonal forecasts some months ahead would have significant benefits for society. Dynamical seasonal forecasting systems have led to some recent advances in forecasting skill, particularly in winter. However, there is considerable scope for applying machine-learning techniques to the problem. 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.

The datasets used for generating the predictor datasets for both winter and summer can be found alongside the data in Word documents. These datasets relate to NERC grant: NE/V001787/1.