It can be challenging to understand why Earth system models (ESMs) produce specific results because one can arrive at the same result simply by changing the values of the parameters. In our paper, we demonstrate that it is possible to use machine learning to figure out how and why particular components of an ESM (such as biology or ocean circulations) affect the output. This work could be applied to observations to improve the accuracy of the formulations used in ESMs.

A challenge for marine ecologists in studying phytoplankton 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 was able to provide qualitative information about the small-scale processes from large-scale information. This method could help identify important relationships from observations in future research.

This study examines challenges in modeling phytoplankton blooms in Northwestern Arabian Sea and Gulf of Oman. Blooms in the region show strong modulation both by seasons and in the wintertime by eddies. However getting both of these correct is a challenge in a set of state-of-the-art global Earth System models. It is argued that maintaining a sharp pycnocline may be the key for preventing the wintertime bloom from being too strong and for allowing eddies to modulate upward mixing of nutrients.

A methodology is presented for reconstructing past global ocean bathymetry using a plate cooling model for the oceanic lithosphere, the age distribution of the oceanic crust, global oceanic sediment thicknesses, plus shelf-slope-rise structures calibrated at modern active and passive continental margins. The final product is a globally complete ocean bathymetry at arbitrary resolution with an isostatically adjusted, multicomponent sediment layer.

Light absorption by colored detrital material (CDM) was included in a fully coupled Earth system model. Chlorophyll and biomass increased near the surface but decreased at greater depths when CDM was included. Concurrently, total biomass decreased leaving more nutrients in the water. Regional changes were analyzed by comparing the competing factors of diminished light availability and increased nutrient availability on phytoplankton growth.