Journal cover Journal topic
Biogeosciences An interactive open-access journal of the European Geosciences Union
Journal topic
Preprints
https://doi.org/10.5194/bg-2020-262
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-2020-262
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

  22 Jul 2020

22 Jul 2020

Review status
This preprint is currently under review for the journal BG.

Linking intrinsic and apparent relationships between phytoplankton and environmental forcings using machine learning ‐ What are the challenges?

Christopher Holder and Anand Gnanadesikan Christopher Holder and Anand Gnanadesikan
  • Morton K. Blaustein Department of Earth and Planetary Sciences, Johns Hopkins University, Baltimore, MD 21218, United States of America

Abstract. Controls on phytoplankton growth are typically determined in two ways: by varying one driver of growth at a time such as nutrient or light in a controlled laboratory setting (intrinsic relationships) or by observing the emergence of relationships in the environment (apparent relationships). However, challenges remain when trying to take the intrinsic relationships found in a lab and scaling them up to the size of ecosystems (i.e., linking intrinsic relationships in the lab to apparent relationships in large ecosystems). We investigated whether machine learning (ML) techniques could help bridge this gap. ML methods have many benefits, including the ability to accurately predict outcomes in complex systems without prior knowledge. Although previous studies have found that ML can find apparent relationships, there has yet to be a systematic study that has examined when and why these apparent relationships will diverge from the underlying intrinsic relationships. To investigate this question, we created three scenarios: one where the intrinsic and apparent relationships operate on the same time and spatial scale, another model where the intrinsic and apparent relationships have different timescales but the same spatial scale, and finally one in which we apply ML to actual ESM output. Our results demonstrated that when intrinsic and apparent relationships are closely related and operate on the same spatial and temporal timescale, ML is able to extract the intrinsic relationships when only provided information about the apparent relationships. However, when the intrinsic and apparent relationships operated on different timescales (as little separation as hourly to daily), the ML methods underestimated the biomass in the intrinsic relationships. This was largely attributable to the decline in the variation of the measurements; the hourly time series had higher variability than the daily, weekly, and monthly-averaged time series. Although the limitations found by ML were overestimated, they were able to produce more realistic shapes of the actual relationships compared to MLR. Future research may use this type of information to investigate which nutrients affect the biomass most when values of the other nutrients change. From our study, it appears that ML can extract useful information from ESM output and could likely do so for observational datasets as well.

Christopher Holder and Anand Gnanadesikan

Interactive discussion

Status: open (until 02 Sep 2020)
Status: open (until 02 Sep 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Christopher Holder and Anand Gnanadesikan

Data sets

Dataset and scripts for manuscript "Linking intrinsic and apparent relationships between phytoplankton and environmental forcings using machine learning - What are the challenges?" Christopher Holder and Anand Gnanadesikan https://doi.org/10.5281/zenodo.3932388

Model code and software

Dataset and scripts for manuscript "Linking intrinsic and apparent relationships between phytoplankton and environmental forcings using machine learning - What are the challenges?" Christopher Holder and Anand Gnanadesikan https://doi.org/10.5281/zenodo.3932388

Christopher Holder and Anand Gnanadesikan

Viewed

Total article views: 166 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
119 41 6 166 4 3
  • HTML: 119
  • PDF: 41
  • XML: 6
  • Total: 166
  • BibTeX: 4
  • EndNote: 3
Views and downloads (calculated since 22 Jul 2020)
Cumulative views and downloads (calculated since 22 Jul 2020)

Viewed (geographical distribution)

Total article views: 73 (including HTML, PDF, and XML) Thereof 73 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: 05 Aug 2020
Publications Copernicus
Download
Short summary
A frequent challenge for marine ecologists is linking small-scale relationships found in a lab to broader relationships observed on large scales in the environment. We investigated whether machine learning (ML) could help connect these small and large-scale relationships. ML can recover the small-scale relationships when the small and large-scale relationships operate on similar time and spatial scales, but this breaks down when the variability in the observations is lost due to time-averaging.
A frequent challenge for marine ecologists is linking small-scale relationships found in a lab...
Citation