Spatial multi-modality as a way to improve both performance and interpretability of deep learning models to reconstruct phytoplankton time-series in the global ocean - IMT Atlantique
Poster De Conférence Année : 2022

Spatial multi-modality as a way to improve both performance and interpretability of deep learning models to reconstruct phytoplankton time-series in the global ocean

Domaines

Apprentissage [cs.LG] Océan, Atmosphère

Ronan Fablet  : Connectez-vous pour contacter le contributeur

https://imt-atlantique.hal.science/hal-04231217

Soumis le : vendredi 6 octobre 2023-15:01:00

Dernière modification le : mercredi 18 décembre 2024-12:08:02

Fichier non déposé

Dates et versions

hal-04231217 , version 1 (06-10-2023)

Identifiants

  • HAL Id : hal-04231217 , version 1

Citer

Joana Roussillon, Ronan Fablet, Thomas Gorgues, Lucas Drumetz, Elodie Martinez. Spatial multi-modality as a way to improve both performance and interpretability of deep learning models to reconstruct phytoplankton time-series in the global ocean. EGU General Assembly 2022, May 2022, Vienna, Austria. ⟨hal-04231217⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

INSU UNIV-BREST CNRS INRIA IUEM LAB-STICC_UBO ENIB LAB-STICC INRIA2 LOPS UNIV-RENNES IMT-ATLANTIQUE LAB-STICC_OSE LAB-STICC_IAOCEAN INSTITUT-MINES-TELECOM
35 Consultations
0 Téléchargements

Partager

More