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

Rafter, Patrick A.; Bagnell, Aaron; Marconi, Dario; DeVries, Timothy

doi:https://doi.org/10.5194/bg-16-2617-2019

Articles | Volume 16, issue 13

https://doi.org/10.5194/bg-16-2617-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/bg-16-2617-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 16, issue 13

Research article

|

05 Jul 2019

Research article |

| 05 Jul 2019

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

Patrick A. Rafter, Aaron Bagnell, Dario Marconi, and Timothy DeVries

Data sets

Compiled dataset consisting of published and unpublished global nitrate δ15N measurements from from 1975–2018. Biological and Chemical Oceanography Data Management Office (BCO-DMO) P. Rafter, A. Bagnell, T. DeVries, and D. Marconi https://doi.org/10.1575/1912/bco-dmo.768627.1

Estimated nitrate δ15N modeled using an ensemble of artificial neural networks (EANNs). Biological and Chemical Oceanography Data Management Office (BCO-DMO) P. Rafter, A. Bagnell, T. DeVries, and D. Marconi https://doi.org/10.1575/1912/bco-dmo.768655.1

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.