Computational intelligence in earth sciences and environmental applications: Issues and challenges

V. Cherkassky, V. Krasnopolsky, D. P. Solomatine, J. Valdes

Research output: Contribution to journalArticlepeer-review

53 Scopus citations

Abstract

This paper introduces a generic theoretical framework for predictive learning, and relates it to data-driven and learning applications in earth and environmental sciences. The issues of data quality, selection of the error function, incorporation of the predictive learning methods into the existing modeling frameworks, expert knowledge, model uncertainty, and other application-domain specific problems are discussed. A brief overview of the papers in the Special Issue is provided, followed by discussion of open issues and directions for future research.

Original languageEnglish (US)
Pages (from-to)113-121
Number of pages9
JournalNeural Networks
Volume19
Issue number2
DOIs
StatePublished - Mar 2006

Keywords

  • Climate
  • Earth sciences
  • Environment
  • Hydrology
  • Neural networks
  • Predictive learning

Fingerprint

Dive into the research topics of 'Computational intelligence in earth sciences and environmental applications: Issues and challenges'. Together they form a unique fingerprint.

Cite this