Improving a Stocastic Rainfall Forecasting Model

Abstract

Short-term rainfall forecasting is a major subject of research in the domain of weather prediction. The development of radar imaging since the 50’s and recent advances in data analysis methods such as neural networks made it possible to design radar-based statistical frameworks dedicated to the modelling of rainfall processes. A model of that kind has been developped last year at Aston University’s Neural Research Group. This thesis describes the problems inherent to this model and the modifications attempted to correct them.

Date of Award	2003
Original language	English
Awarding Institution	Aston University