Building structure-property predictive models using data assimilation

  • Authors:

  • Hamse Y. Mussa;David J. Lary;Robert C. Glen

  • Affiliations:

  • Unilever Centre for Molecular Sciences Informatics, Department of Chemistry, University of Cambridge, Cambridge, U.K;NASA, Goddard Space Flight Centre, Greenbelt, MD;Unilever Centre for Molecular Sciences Informatics, Department of Chemistry, University of Cambridge, Cambridge, U.K

  • Venue:
  • CompLife'06 Proceedings of the Second international conference on Computational Life Sciences
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In Chemometrics it is often the norm to develop regression methods for analysing non-linear multivariate data by using the observations (measurements) as the sole constraint. This is the case regardless of the nature of the regression method (parametric or non-parametric)[1]. In this article we present the development of a regression model using data assimilation[2] – A technique that takes into account additional available information about the “system” which the model is to represent. The new approach shows substantial improvement over the “conventional” methods[3] against which it has been compared.