Statistical downscaling of rainfall data using sparse variable selection methods

In many statistical downscaling methods, atmospheric variables are chosen by using a combination of expert knowledge with empirical measures such as correlations and partial correlations. In this short communication, we describe the use of a fast, sparse variable selection method, known as RaVE, for...

Full description

Saved in:
Bibliographic Details
Published inEnvironmental modelling & software : with environment data news Vol. 26; no. 11; pp. 1363 - 1371
Main Authors Phatak, A., Bates, B.C., Charles, S.P.
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.11.2011
Subjects
Atmospherics
Computer programs
computer software
Correlation analysis
environmental models
L1-norm
Logistic regression
Markov chain
Mathematical models
meteorological data
rain
Rainfall
Software
Sparse variable selection
Stations
Statistical downscaling
Variable selection
South Australia
Australia, South Australia
L1-norm
Logistic regression
Statistical downscaling
Sparse variable selection
Variable selection
Online AccessGet full text

Cover

More Information
Summary:In many statistical downscaling methods, atmospheric variables are chosen by using a combination of expert knowledge with empirical measures such as correlations and partial correlations. In this short communication, we describe the use of a fast, sparse variable selection method, known as RaVE, for selecting atmospheric predictors, and illustrate its use on rainfall occurrence at stations in South Australia. We show that RaVE generates parsimonious models that are both sensible and interpretable, and whose results compare favourably to those obtained by a non-homogeneous hidden Markov model ( Hughes et al., 1999).
Bibliography:http://dx.doi.org/10.1016/j.envsoft.2011.05.007
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1364-8152
1873-6726
DOI:10.1016/j.envsoft.2011.05.007