Articles | Volume 16, issue 6
https://doi.org/10.5194/cp-16-2599-2020
https://doi.org/10.5194/cp-16-2599-2020
Research article
 | 
23 Dec 2020
Research article |  | 23 Dec 2020

OPTiMAL: a new machine learning approach for GDGT-based palaeothermometry

Tom Dunkley Jones, Yvette L. Eley, William Thomson, Sarah E. Greene, Ilya Mandel, Kirsty Edgar, and James A. Bendle

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
ED: Reconsider after major revisions (18 Dec 2019) by Alberto Reyes
AR by Yvette Eley on behalf of the Authors (15 Feb 2020)  Author's response    Manuscript
ED: Referee Nomination & Report Request started (05 Mar 2020) by Alberto Reyes
RR by Anonymous Referee #1 (23 Mar 2020)
RR by Jessica Tierney (20 Apr 2020)
ED: Reconsider after major revisions (23 Apr 2020) by Alberto Reyes
ED: Referee Nomination & Report Request started (02 Oct 2020) by Alberto Reyes
RR by Peter Bijl (23 Oct 2020)
RR by Anonymous Referee #1 (04 Nov 2020)
AR by Svenja Lange on behalf of the Authors (06 Oct 2020)  Author's response    Manuscript
ED: Publish subject to minor revisions (review by editor) (06 Nov 2020) by Alberto Reyes
AR by Tom Dunkley Jones on behalf of the Authors (16 Nov 2020)  Author's response
ED: Publish as is (18 Nov 2020) by Alberto Reyes
Download
Short summary
We explore the utiliity of the composition of fossil lipid biomarkers, which are commonly preserved in ancient marine sediments, in providing estimates of past ocean temperatures. The group of lipids concerned show compositional changes across the modern oceans that are correlated, to some extent, with local surface ocean temperatures. Here we present new machine learning approaches to improve our understanding of this temperature sensitivity and its application to reconstructing past climates.