Alternative least squares methods for determining the meteoric water line, demonstrated using GNIP data

Simple item page
dc.contributor.authorCrawford, Jen_AU
dc.contributor.authorHughes, CEen_AU
dc.contributor.authorLykoudis, Sen_AU
dc.date.accessioned2016-06-30T05:31:32Zen_AU
dc.date.available2016-06-30T05:31:32Zen_AU
dc.date.issued2014-11-01en_AU
dc.date.statistics2016-06-30en_AU
dc.description.abstractThe relationship between δ2H and δ18O in precipitation at a site, known as the local meteoric water line (LMWL), is normally defined using an ordinary least squares regression (OLSR). However, it has been argued that this form of minimisation is more appropriate when a predictive model is being developed (and there are no measurement errors associated with the independent variable) and that orthogonal regression, also known as major axis regression (MA), or reduced major axis regression (RMA) may be better suited when a relationship is being sought between two variables which are related by underlying physical processes. The slope of the LMWLs for the GNIP data is examined using the three linear regressions, and the corresponding precipitation weighted regressions. The MA and RMA regressions generally produced larger slopes, with the largest differences for oceanic islands and coastal sites. The difference between the various methods was the least for continental sites. In all considered cases, both for the standard and precipitation weighted regressions, the slope produced by RMA was in between those determined by OLSR and MA, with OLSR producing the smaller slope. Further, the results of both RMA and precipitation weighted RMA were less sensitive to the removal of outliers and values with high leverage statistic. The results indicate that when a good linear relationship exists between δ2H and δ18O, all considered regressions result in a close fit. When the values are distributed within circles or ellipses on the δ18O–δ2H bivariate plot, as would appear in coastal and oceanic sites from first stage rainout, care needs to be taken as to which regression is utilised. However, in some of these cases, it appears the precipitation weighted MA (and in some cases MA) produces large slopes. In these cases the average Root Mean Sum of Squared Error (rmSSEav) value of the fit can be used as a guide of the suitability of the MA and PWMA for each site. Where the slope of the PWRMA was significantly different to the slope of the OLSR regression (22% of sites; dominated by coastal, island and Mediterranean locations), we believe PWRMA is more suitable.© 2014 Elsevier B.V.en_AU
dc.identifier.citationCrawford, J., Hughes, C. E., & Lykoudis, S. (2014). Alternative least squares methods for determining the meteoric water line, demonstrated using GNIP data. Journal of Hydrology, 519, 2331-2340. doi:10.1016/j.jhydrol.2014.10.033en_AU
dc.identifier.govdoc6783en_AU
dc.identifier.issn0022-1694en_AU
dc.identifier.journaltitleJournal of Hydrologyen_AU
dc.identifier.pagination2331-2340en_AU
dc.identifier.urihttp://dx.doi.org/10.1016/j.jhydrol.2014.10.033en_AU
dc.identifier.urihttp://apo.ansto.gov.au/dspace/handle/10238/7118en_AU
dc.identifier.volume519en_AU
dc.language.isoenen_AU
dc.publisherElsevieren_AU
dc.subjectDeuteriumen_AU
dc.subjectOxygenen_AU
dc.subjectIsotopesen_AU
dc.subjectPrecipitationen_AU
dc.subjectWateren_AU
dc.subjectSeasen_AU
dc.titleAlternative least squares methods for determining the meteoric water line, demonstrated using GNIP dataen_AU
dc.typeJournal Articleen_AU
Files
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Journal Articles