Modelling Seasonality and Trends in Daily Rainfall Data
Peter M. Williams · Figshare · 1997
This paper presents a new approach to modelling daily rainfall using neural networks. We fist model the conditional distributions of rainfall amounts, in such a way that the model itself determines the order of the process, and the time-dependent shape and scale of the conditional distributions. After integrating over particular weather patterns, we are able to extracxt seasonal variations and long-term trends.