Overview

Alex G. B chner
University of Ulster, UK

J.C.L. Chan
City University of Hong Kong, China

S.L. Hung
City University of Hong Kong, China

John G. Hughes
University of Ulster, UK

10.1 Introduction

Geophysical data is the most important material that meteorologists use to model the behaviour of the earth's atmospheres and oceans. Although most research dedicated to explanation and prediction has been based on the application of a specific statistical or artificial intelligence technique, only a few endeavours have tackled the holistic nature of the subject. One possible way of approaching this target is the application of knowledge-discovery techniques or, as P. Stolorz et al. have put it: 'The important scientific challenge of understanding global climate change is one that clearly requires the application of knowledge discovery and data mining techniques on a massive scale' z[1].

Owing to the highly heterogeneous nature of the data and the vast amount of available domain expertise, traditional data-mining techniques by themselves have proven infeasible. Additionally, owing to the large quantity of available historical data, discovery of knowledge from a virtual data view as created in distributed and heterogeneous databases and presented in B chner et al. and Chan and Stolfo [2 4] supersedes the capacity of up-to-date algorithms and hardware. An alternative approach, which has proven successful in other disciplines such as finance, retail and manufacturing, is the discovery of knowledge from a materialised view, represented in a data warehouse.

We have followed that approach and designed the meteorology and data-mining environment...