Forecasting seasonal global sea surface chlorophyll <i>a</i> with a lightweight data-driven approach

Martinez Balbontin, Gabriela; Jouanno, Julien; Benshila, Rachid; Lamouroux, Julien; Perruche, Coralie; Ciavatta, Stefano

doi:10.5194/bg-23-2601-2026

Articles | Volume 23, issue 7

https://doi.org/10.5194/bg-23-2601-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/bg-23-2601-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 23, issue 7

Research article

|

17 Apr 2026

Research article |

| 17 Apr 2026

Forecasting seasonal global sea surface chlorophyll a with a lightweight data-driven approach

Gabriela Martinez Balbontin, Julien Jouanno, Rachid Benshila, Julien Lamouroux, Coralie Perruche, and Stefano Ciavatta

Data sets

Seasonal monthly ocean data Copernicus Climate Change Service https://doi.org/10.24381/cds.2f9be611

Ocean Colour (GlobColour) L4 (OCEANCOLOUR_GLO_BGC_L4_MY_009_104) Copernicus Marine Environment Monitoring Service https://doi.org/10.48670/moi-00281

Global Ocean Physics Reanalysis (GLOBAL_MULTIYEAR_PHY_001_030) Copernicus Marine Environment Monitoring Service https://doi.org/10.48670/moi-00021

Global Ocean Biogeochemistry Analysis and Forecast (GLOBAL_ANALYSISFORECAST_BGC_001_028) Copernicus Marine Environment Monitoring Service https://doi.org/10.48670/moi-00015

Short summary

This study uses machine learning to predict global sea surface chlorophyll a, which is important for monitoring marine ecosystems and the carbon cycle. Using forecasts of sea surface temperature, salinity, height, and mixed layer depth, we generate global predictions up to six months ahead in just minutes. Our approach matches state-of-the-art numerical methods while being faster and more resource-efficient.