Enhanced Net Community Production With Sea Ice Loss in the Western Arctic Ocean Uncovered by Machine-Learning-Based Mapping
Date
2024-11-23
Journal Title
Journal ISSN
Volume Title
Publisher
Geophysical Research Letters
Abstract
In the Arctic Ocean (AO), net community production (NCP) has displayed spatially heterogeneous responses to sea ice reduction and associated environmental changes. Using a random forest machine learning model trained with >42,000 in situ measurements and concurrent, collocated environmental predictors, we reconstructed 19 years of 8‐day, 6‐km NCP maps. During 2015–2021, the integrated NCP between late‐May and early‐September (intNCP) over the western AO was 10.95 ± 3.30 Tg C per year, with interannual variations positively tracking open water area. While the relationship between intNCP and open water area was quasi‐linear at high latitudes, strong nonlinearity was detected on the inflow shelf. The nonlinearity highlights that the intNCP increase resulted from area gain could be compounded by sea‐ice loss induced ecosystem adjustments. Additional retrospective analysis for 2003–2014 suggests a potential long‐term increase of export production and efficiency in the western AO with sea ice loss.
Key Points:
• A multiyear, gap‐free net community production (NCP) product was con- structed using a machine learning model for the western Arctic Ocean
• Seasonally and regionally integrated NCP responded to sea ice loss quasi‐ linearly at high latitudes but non- linearly on the inflow shelf
• Compared with the 2010s, carbon export production has increased in recent years, accompanying sea ice loss in the western Arctic Ocean
Plain Language Summary
Net community production (NCP) refers to the portion of phytoplankton production that remains unused by consumers and can be exported to the deeper part of the ocean. In the western Arctic Ocean (AO), NCP patterns are uneven due to complex interactions between the physical environment and the ecosystem. In this study, we developed a machine learning model of NCP in the western AO. The model used publicly available underway measurements and the associated environmental variables to create long‐term, high‐resolution maps of NCP. For the period of 2015–2021, we found that the integrated NCP between late‐ May and early‐September (intNCP) was 10.95 ± 3.30 Tg C per year in the western AO. intNCP varied from year to year and was higher when the open water area was larger. Notably, on the inflow shelf, intNCP increased at a faster rate than a linear relationship would suggest, due to both area expansion and ecosystem adjustments induced by sea ice loss. Our findings indicate that with long‐term sea ice loss, the western AO is likely to export more phytoplankton production to deeper ocean waters.
Description
This article was originally published in Geophysical Research Letters. The version of record is available at: https://doi.org/10.1029/2024GL110931.
© 2024. The Author(s).
This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.
This research was featured in UDaily on 03/19/2025 at: https://www.udel.edu/udaily/2025/march/arctic-ocean-sea-ice-loss-research-cruise/
Keywords
net community production, Arctic ocean, machine learning, O2/Ar, export production, climate action, life below water
Citation
Zhou, T., Li, Y., Ouyang, Z., Cai, W.-J., & Ji, R. (2024). Enhanced net community production with sea ice loss in the western Arctic ocean uncovered by machine-learning-based mapping. Geophysical Research Letters, 51, e2024GL110931. https://doi.org/10.1029/2024GL110931