English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Accurately reconstructing a three-dimensional ocean sound speed field (3DSSF) is essential for various ocean acoustic applications, but the sparsity anduncertainty of sound speed samples across a vast ocean region make it achallenging task. To tackle this challenge, a large body of reconstructionmethods has been developed, including spline interpolation, matrix/tensor-basedcompletion, and deep neural networks-based reconstruction. However, aprincipled analysis of their effectiveness in 3D SSF reconstruction is stilllacking. This paper performs a thorough analysis of the reconstruction errorand highlights the need for a balanced representation model that integratesboth expressiveness and conciseness. To meet this requirement, a 3DSSF-tailored tensor deep neural network is proposed, which utilizes tensorcomputations and deep neural network architectures to achieve remarkable 3D SSFreconstruction. The proposed model not only includes the previous tensor-basedSSF representation model as a special case, but also has a natural ability toreject noise. The numerical results using the South China Sea 3D SSF datademonstrate that the proposed method outperforms state-of-the-art methods. Thecode is available at https://github.com/OceanSTARLab/Tensor-Neural-Network.

Striking The Right Balance: Three-Dimensional Ocean Sound Speed Field Reconstruction Using Tensor Neural Networks