Adding constrained discontinuities to Gaussian process models of wind fields

Dan Cornford, Ian T. Nabney, Christopher K. I. Williams, Michael S. Kearns (Editor), Sara A. Solla (Editor), David A. Cohn (Editor)

Research output: Contribution to journalArticle

Abstract

Gaussian Processes provide good prior models for spatial data, but can be too smooth. In many physical situations there are discontinuities along bounding surfaces, for example fronts in near-surface wind fields. We describe a modelling method for such a constrained discontinuity and demonstrate how to infer the model parameters in wind fields with MCMC sampling.
Original languageEnglish
Pages (from-to)861-867
Number of pages7
JournalAdvances in Neural Information Processing Systems
Volume11
Publication statusPublished - 1999
EventAdvances in Neural Information Processing Systems 1999 - Dublin, Ireland
Duration: 3 Aug 19996 Aug 1999

Bibliographical note

Copyright of the Massachusetts Institute of Technology Press (MIT Press) Available also on Google Books

Keywords

  • Gaussian processes
  • spatial data
  • discontinuities
  • near-surface

Fingerprint Dive into the research topics of 'Adding constrained discontinuities to Gaussian process models of wind fields'. Together they form a unique fingerprint.

  • Cite this

    Cornford, D., Nabney, I. T., Williams, C. K. I., Kearns, M. S. (Ed.), Solla, S. A. (Ed.), & Cohn, D. A. (Ed.) (1999). Adding constrained discontinuities to Gaussian process models of wind fields. Advances in Neural Information Processing Systems, 11, 861-867.