Generalization performance of neural mapping schemes for the space-time interpolation of satellite-derived ocean colour datasets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Thi Thuy Nga, Dorffer, Clément, Jourdin, Frédéric, Fablet, Ronan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909925976834048
author Nguyen, Thi Thuy Nga
Dorffer, Clément
Jourdin, Frédéric
Fablet, Ronan
author_facet Nguyen, Thi Thuy Nga
Dorffer, Clément
Jourdin, Frédéric
Fablet, Ronan
contents Neural mapping schemes have become appealing approaches to deliver gap-free satellite-derived products for sea surface tracers. The generalization performance of these learning-based approaches naturally arises as a key challenge. This is particularly true for satellite-derived ocean colour products given the variety of bio-optical variables of interest, as well as the diversity of processes and scales involved. Considering region-specific and parameter-specific neural mapping schemes will result in substantial training costs. This study addresses generalization performance of neural mapping schemes to deliver gap-free satellite-derived ocean colour products. We develop a comprehensive experimental framework using real multi-sensor ocean colour datasets for two regions (the Mediterranean Sea and the North Sea) and a representative set of bio-optical parameters (Chlorophyll-a concentration, suspended particulate matter concentration, particulate backscattering coefficient). We consider several neural mapping schemes, and we report excellent generalization performance across regions and bio-optical parameters without any fine-tuning using appropriate dataset-specific normalization procedures. We discuss further how these results provide new insights towards the large-scale deployment of neural schemes for the processing of satellite-derived ocean colour datasets beyond case-study-specific demonstrations.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11588
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalization performance of neural mapping schemes for the space-time interpolation of satellite-derived ocean colour datasets
Nguyen, Thi Thuy Nga
Dorffer, Clément
Jourdin, Frédéric
Fablet, Ronan
Image and Video Processing
I.2.10; I.4.5
Neural mapping schemes have become appealing approaches to deliver gap-free satellite-derived products for sea surface tracers. The generalization performance of these learning-based approaches naturally arises as a key challenge. This is particularly true for satellite-derived ocean colour products given the variety of bio-optical variables of interest, as well as the diversity of processes and scales involved. Considering region-specific and parameter-specific neural mapping schemes will result in substantial training costs. This study addresses generalization performance of neural mapping schemes to deliver gap-free satellite-derived ocean colour products. We develop a comprehensive experimental framework using real multi-sensor ocean colour datasets for two regions (the Mediterranean Sea and the North Sea) and a representative set of bio-optical parameters (Chlorophyll-a concentration, suspended particulate matter concentration, particulate backscattering coefficient). We consider several neural mapping schemes, and we report excellent generalization performance across regions and bio-optical parameters without any fine-tuning using appropriate dataset-specific normalization procedures. We discuss further how these results provide new insights towards the large-scale deployment of neural schemes for the processing of satellite-derived ocean colour datasets beyond case-study-specific demonstrations.
title Generalization performance of neural mapping schemes for the space-time interpolation of satellite-derived ocean colour datasets
topic Image and Video Processing
I.2.10; I.4.5
url https://arxiv.org/abs/2503.11588