Meteorological data recorded at high frequency by automatic sensors are often marred by multiple forms of error. Existing validation techniques, in isolation, are sub-optimal for such error-prone data. We propose a new data-standardization procedure for the validation of strongly correlated series which commonly arise in meteorology. We show the procedure to be more comprehensive in the simultaneous detection of solitary spikes, shifts in series means, and irregular diurnal patterns.

Southeasterm Australia, including the Murray–Darling Basin, is a highly productive agricultural region largely dependent on adequate rainfall, providing irrigation water needed for crops.

The Australian Bureau of Meteorology uses linear methods and provides seasonal forecasts expressed as the probability of exceeding median rainfall. I use expanded methods, including more ocean data and deep learning neural networks that provide nonlinear estimates of the rainfall as measured by rain gauges.

We employ hierarchical statistical models to investigate spatiotemporal differences between sea surface temperature, marine air temperature, and their anomalies in the tropical Pacific.

This paper assesses the skill of probabilistic forecasts of solar irradiance in the northern regions of Chile. Raw ensemble forecast are calibrated using a parametric and a novel non-parametric machine-learning-based method. As the reference approach, the ensemble model output statistics are considered. We verify the superiority of the proposed non-parametric neural-network-based ensemble correction, resulting in more than 50 % improvement in prediction performance compared to the raw forecasts.