Global assessment of marine phytoplankton primary production: Integrating machine learning and environmental accounting models

F. Mattei, E. Buonocore, P.P. Franzese and M. Scardi

Ecological Modelling, 2021, vol. 451, issue C

Abstract: The emergy accounting method has been widely applied to terrestrial and marine ecosystems although there is a lack of emergy studies focusing on phytoplankton primary production. Phytoplankton production is a pivotal process since it is intimately coupled with oceanic food webs, energy fluxes, carbon cycle, and Earth's climate. In this study, we proposed a new methodology to perform a biophysical assessment of the global phytoplankton primary production combining Machine Learning (ML) techniques and an emergy-based accounting model. Firstly, we produced global phytoplankton production estimates using an Artificial Neural Network (ANN) model. Secondly, we assessed the main energy inputs supporting the global phytoplankton production. Finally, we converted these inputs into emergy units and analysed the results from an ecological perspective. Among the energy flows, tides showed the highest maximum emergy contribution to global phytoplankton production highlighting the importance of thise flow in the complex dynamics of marine ecosystems. In addition, an emergy/production ratio was calculated showing different global patterns in terms of emergy convergence into the primary production process. We believe that the proposed emergy-based assessment of phytoplankton production could be extremely valuable to improve our understanding of this key biological process at global scale adopting a systems perspective. This model can also provide a useful benchmark for future assessments of marine ecosystem services at global scale.

Keywords: Phytoplankton primary production; Systems ecology; Artificial neural networks; Machine learning; Emergy accounting (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0304380021001435
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:ecomod:v:451:y:2021:i:c:s0304380021001435

DOI: 10.1016/j.ecolmodel.2021.109578

Access Statistics for this article

Ecological Modelling is currently edited by Brian D. Fath

More articles in Ecological Modelling from Elsevier
Bibliographic data for series maintained by Catherine Liu ().