paper-with-me

홈 › Papers

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

2025-03-14 · Thi Thuy Nga Nguyen, Clément Dorffer, Frédéric Jourdin, Ronan Fablet

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.

📄 PDF Abstract BibTeX arXiv:2503.11588

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Training neural mapping schemes for satellite altimetry with simulation data

2023-09-19 · Quentin Febvre, Julien Le Sommer, Clément Ubelmann, Ronan Fablet

Satellite altimetry combined with data assimilation and optimal interpolation schemes have deeply renewed our ability to monitor sea surface dynamics. Recently, deep learning (DL) schemes have emerged as appealing soluti…

Benchmarking

Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search

2021-03-02 · Kartik Hegde, Po-An Tsai, Sitao Huang, Vikas Chandra 외

Modern day computing increasingly relies on specialization to satiate growing performance and efficiency requirements. A core challenge in designing such specialized hardware architectures is how to perform mapping space…

DIFFnet: Diffusion parameter mapping network generalized for input diffusion gradient schemes and bvalues

2021-02-04 · Juhung Park, Woojin Jung, Eun-Jung Choi, Se-Hong Oh 외

In MRI, deep neural networks have been proposed to reconstruct diffusion model parameters. However, the inputs of the networks were designed for a specific diffusion gradient scheme (i.e., diffusion gradient directions a…

Design Space Exploration of Dense and Sparse Mapping Schemes for RRAM Architectures

2022-01-18 · Corey Lammie, Jason K. Eshraghian, Chenqi Li, Amirali Amirsoleimani 외

The impact of device and circuit-level effects in mixed-signal Resistive Random Access Memory (RRAM) accelerators typically manifest as performance degradation of Deep Learning (DL) algorithms, but the degree of impact v…

Quantization

Learning Generic Solutions for Multiphase Transport in Porous Media via the Flux Functions Operator

2023-07-03 · Waleed Diab, Omar Chaabi, Shayma Alkobaisi, Abeeb Awotunde 외

Traditional numerical schemes for simulating fluid flow and transport in porous media can be computationally expensive. Advances in machine learning for scientific computing have the potential to help speed up the simula…