An Alternative to Static Climatologies: Robust Estimation of Open Ocean CO2 Variables and Nutrient Concentrations From T, S, and O2 Data Using Bayesian Neural Networks

This work presents two new methods to estimate oceanic alkalinity (AT), dissolved inorganic carbon (CT), pH, and pCO2 from temperature, salinity, oxygen, and geolocation data. “CANYON-B” is a Bayesian neural network mapping that accurately reproduces GLODAPv2 bottle data and the biogeochemical relat...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Henry C. Bittig, Tobias Steinhoff, Hervé Claustre, Björn Fiedler, Nancy L. Williams, Raphaëlle Sauzède, Arne Körtzinger, Jean-Pierre Gattuso
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	Frontiers Media S.A. 2018-09-01
Serie:	Frontiers in Marine Science
Ämnen:	carbon cycle GLODAP marine carbonate system surface pCO2 climatology Revelle buffer factor increase machine learning
Länkar:	https://www.frontiersin.org/article/10.3389/fmars.2018.00328/full
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!