Identifying drivers and dynamics of phytoplankton in the Black Sea: application of a neural emulator
Smith, P.A.H.; Chauhan, A.; Gregoire, M.; Vandenbulcke, L.; Rodrigues, F.; Christensen, A.; St John, M.A.; Mariani, P. (2026). Identifying drivers and dynamics of phytoplankton in the Black Sea: application of a neural emulator. Front. Mar. Sci. 13: 1760162. https://dx.doi.org/10.3389/fmars.2026.1760162
In: Frontiers in Marine Science. Frontiers Media: Lausanne. ISSN 2296-7745; e-ISSN 2296-7745, meer
|  |
| Author keywords |
biogeochemical modeling;Black Sea;chlorophyll;deep learning;marine ecosystems;model emulation;neural networks;nutrient dynamics;biogeochemical model;data assimilation;global ocean;marine;networks;eutrophication;variability;simulation;oxygen |
| Auteurs | | Top |
- Smith, P.A.H.
- Chauhan, A.
- Gregoire, M.
- Vandenbulcke, L., meer
|
- Rodrigues, F.
- Christensen, A.
- St John, M.A.
- Mariani, P., meer
|
|
| Abstract |
We present a spatiotemporal convolutional U-Net emulator model to forecast phytoplankton chlorophyll concentrations and key nutrient fields (nitrate and ammonium) in the Black Sea, using simulation data from 1950-2014. The emulator achieved substantially higher predictive skill compared to baseline approaches, with a 41% improvement for chlorophyll and 59% for phosphate, while accurately capturing both spatial and temporal variability in biogeochemical dynamics. In addition to forecasting, interpretability of the model was obtained through Sobol sensitivity analysis, complemented by derivative-based global sensitivity measures (DGSM) and elasticity analysis. These revealed pronounced spatial and seasonal variations in the dominant environmental drivers across the basin, enabling exploration of "what-if" scenarios through targeted perturbations of key physical and biogeochemical drivers. Overall, light availability and nutrient concentrations (particularly nitrate, ammonium, and phosphate) emerged as key contributors, with a transition from predominantly light-driven short-term sensitivity toward increasing nutrient influence at longer lead times, modulated by strong regional and seasonal variability. The ability of the model to forecast biogeochemical states and to identify their dominant drivers highlights its potential as an early warning tool for detecting ecosystem changes and supporting adaptive management of the Black Sea. |
|
