Journal cover Journal topic
Biogeosciences An interactive open-access journal of the European Geosciences Union
Journal topic
Discussion papers
https://doi.org/10.5194/bg-2018-525
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-2018-525
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 11 Jan 2019

Research article | 11 Jan 2019

Review status
This discussion paper is a preprint. A revision of the manuscript is under review for the journal Biogeosciences (BG).

Global trends in marine nitrate N isotopes from observations and a neural network-based climatology

Patrick A. Rafter1, Aaron Bagnell2, Dario Marconi3, and Timothy DeVries2 Patrick A. Rafter et al.
  • 1University of California, Irvine
  • 2University of California, Santa Barbara
  • 3Princeton University

Abstract. Nitrate is a critical ingredient for life in the ocean because, as the most abundant form of fixed nitrogen in the ocean, it is an essential nutrient for primary production. The availability of marine nitrate is principally determined by biological processes, each having a distinct influence on the N isotopic composition of nitrate (nitrate δ15N) – a property that informs much of our understanding of the marine N cycle as well as marine ecology, fisheries, and past ocean conditions. However, the sparse spatial distribution of nitrate δ15N observations makes it difficult to apply this useful property in global studies, or to facilitate robust model-data comparisons. Here, we use a compilation of published nitrate δ15N measurements (n = 12277) and climatological maps of physical and biogeochemical tracers to create a surface-to-seafloor, 1° resolution map of nitrate δ15N using an Ensemble of Artificial Neural Networks (EANN). The strong correlation (R2 > 0.87) and small mean difference (< 0.05 ‰) between EANN-estimated and observed nitrate δ15N indicates that the EANN provides a good estimate of climatological nitrate δ15N without a significant bias. The magnitude of observation-model residuals is consistent with the magnitude of seasonal-decadal changes in observed nitrate δ15N that are not captured by our climatological model. As such, these observation-constrained results provide a globally-resolved map of mean nitrate δ15N for observational and modeling studies of marine biogeochemistry, paleoceanography, and marine ecology.

Patrick A. Rafter et al.
Interactive discussion
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Patrick A. Rafter et al.
Patrick A. Rafter et al.
Viewed  
Total article views: 396 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
286 105 5 396 1 2
  • HTML: 286
  • PDF: 105
  • XML: 5
  • Total: 396
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 11 Jan 2019)
Cumulative views and downloads (calculated since 11 Jan 2019)
Viewed (geographical distribution)  
Total article views: 196 (including HTML, PDF, and XML) Thereof 196 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 23 Mar 2019
Publications Copernicus
Download
Short summary
The N isotopic composition of nitrate (nitrate δ15N) is a useful tracer of ocean N cycling and many other ocean processes. Here, we use a global compilation of marine nitrate δ15N as an input, training, and validating dataset for an artificial neural network (a.k.a., machine learning) and examine basin-scale trends in marine nitrate δ15N from the surface to the seafloor.
The N isotopic composition of nitrate (nitrate δ15N) is a useful tracer of ocean N cycling and...
Citation