Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 18, issue 20
Articles | Volume 18, issue 20
https://doi.org/10.5194/gmd-18-7575-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-18-7575-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 18, issue 20
Development and technical paper
 | 
22 Oct 2025
Development and technical paper |  | 22 Oct 2025

Data-Informed Inversion Model (DIIM): a framework to retrieve marine optical constituents using a three-stream irradiance model

Carlos Enmanuel Soto López, Mirna Gharbi Dit Kacem, Fabio Anselmi, and Paolo Lazzari

Viewed

Total article views: 2,705 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,197 399 109 2,705 104 151
  • HTML: 2,197
  • PDF: 399
  • XML: 109
  • Total: 2,705
  • BibTeX: 104
  • EndNote: 151
Views and downloads (calculated since 20 Nov 2024)
Cumulative views and downloads (calculated since 20 Nov 2024)

Viewed (geographical distribution)

Total article views: 2,705 (including HTML, PDF, and XML) Thereof 2,582 with geography defined and 123 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 11 Jun 2026
Download
Short summary
We used a semi-analytical expression to estimate the concentration of optically active constituents, allowing us to have an interpretable formulation consistent with the laws of physics. We focused on a probabilistic approach, inverting the model with its respective uncertainty. Considering future applications to big data, we explored a neural-network-based method, retrieving computationally efficient estimates with an accuracy comparable to existing state-of-the-art algorithms.
Read more
Share