The role of knowledge representation in geographic knowledge discovery: A case study

Jeremy Mennis, Donna J. Peuquet

Research output: Contribution to journalArticlepeer-review

13 Scopus citations


With the advent of massive, heterogeneous geographic datasets, data mining and knowledge discovery in databases (KDD) have become important tools in deriving meaningful information from these data. In this paper, we discuss how knowledge representation can be employed to significantly enhance the power of the knowledge discovery process to uncover patterns and relationships. We suggest that geographic data models that support knowledge discovery must represent both observational data and derived knowledge. In addition, knowledge representation in the context of KDD must support the iterative and interactive nature of the knowledge discovery process to enable the analyst to iteratively apply, and revise the parameters of, specific analytical techniques. Our approach to knowledge representation and discovery is demonstrated through a case study that focuses on the identification and analysis of storms and other related climate phenomena embedded within a spatio-temporal data set of meteorological observations.

Original languageEnglish (US)
Pages (from-to)371-391
Number of pages21
JournalTransactions in GIS
Issue number3
StatePublished - Jun 2003

All Science Journal Classification (ASJC) codes

  • General Earth and Planetary Sciences


Dive into the research topics of 'The role of knowledge representation in geographic knowledge discovery: A case study'. Together they form a unique fingerprint.

Cite this