satellIte phytoplaNkton Drivers In the Global Ocean over 1998-2015 (INDIGO Benchmark dataset)

This benchmark dataset contains the physical data used as predictors to reconstruct global chlorophyll-a concentrations (Chl, a proxy of phytoplankton biomass) in Roussillon et al., as well as the reference satellite Chl target fields. The nine physical predictors' data (Short-Wave radiations, Sea Surface Temperature, Sea Level Anomaly, Zonal and meridional surface currents, Zonal and meridional surface wind stress, Bathymetry, Binary continental mask) were extracted from publicly available datasets over [1998-2015] and resampled to the same spatio-temporel resolution as Chl, i.e. monthly on a 1°x1° grid between 50°N and 50°S. Missing values were gap-filled using the heat diffusion equation. Each variable was normalized by substracting its mean from the original values and dividing by its standard deviation over [1998-2015].

This dataset was used to train and validate the Multi-Mode Convolutional Neural network (CNNMM8) introduced in Roussillon et al. ; reconstructed monthly Chl fields over the [2012-2015] test period are also provided here.

We hope this benchmark dataset can help to promote the improvements of methods as well as the emergence of new ideas, as building datasets is sometimes more time-consuming than the implementation of machine learning tools themselves. This would also facilitate the quantitative comparison of models performances' on the exact same datasets.

 
Citation proposal
Roussillon Joana (UMR6523 Laboratoire d'Oceanographie Physique et Spatiale (LOPS), France) - Fablet Ronan (IMT Atlantique, Lab-STICC, UMR CNRS 6285, France) - Gorgues Thomas (UMR6523 Laboratoire d'Oceanographie Physique et Spatiale (LOPS), France) - Drumetz Lucas (IMT Atlantique, Lab-STICC, UMR CNRS 6285, France) - Littaye Jean (UMR6523 Laboratoire d'Oceanographie Physique et Spatiale (LOPS), France) - Martinez Elodie (UMR6523 Laboratoire d'Oceanographie Physique et Spatiale (LOPS), France) (2022) . satellIte phytoplaNkton Drivers In the Global Ocean over 1998-2015 (INDIGO Benchmark dataset). https://services.mspdata.eu:/geonetwork/srv/api/records/seanoe:91910

Simple

Date ( Publication )
2022-11
Date ( Revision )
2023-03-24
Other citation details
Roussillon Joana, Fablet Ronan, Gorgues Thomas, Drumetz Lucas, Littaye Jean, Martinez Elodie (2022). satellIte phytoplaNkton Drivers In the Global Ocean over 1998-2015 (INDIGO Benchmark dataset). SEANOE. https://doi.org/10.17882/91910

  Author

  Author

  Author

  Author

  Author

  Author

  Publisher

Keywords ( Theme )
  • phytoplankton physical drivers , satellite ocean color , time-series regression , global scale , deep learning , benchmark , Biological oceanography , Physical oceanography
ODATIS aggregation parameters and Essential Variable names ( Theme )
  • Phytoplankton , Ocean colour , Pigments
SeaDataNet Parameter Disciplines ( parameter )
  • Biological oceanography , Physical oceanography
Type de jeux de donnée ODATIS ( Theme )
  • Aggregate data
Use constraints
Other restrictions
Other constraints
Date ( Publication )
2023

  Publisher

  Author

  Author

  Author

  Author

  Author

  Author

Association Type
Cross reference
Initiative Type
document
Metadata language
English
Topic category
  • Oceans
N
S
E
W


Distribution format
  • NUMPY ARRAY ( )

OnLine resource
Processed data  

Normalized physical input data over 1998-2015 - 945 MB

OnLine resource
Processed data  

Reference target satellite Chl over 1998-2015 - 105 MB

OnLine resource
Processed data  

Reconstructed Chl over 2012-2015 test period - 23 MB

OnLine resource
DOI of the product  
OnLine resource
Seanoe  
Hierarchy level
Dataset
Statement

Metadata

File identifier
seanoe:91910   XML
Metadata language
English
Character set
UTF8
Hierarchy level
Dataset
Date stamp
2023-03-24
Metadata standard name
ISO 19115:2003/19139
Metadata standard version
1.0

  Point of contact

 
 

  Overviews


Provided by

Access to the portal

Associated resources

Not available