A Hybrid Dropout Method for High-Precision Seafloor Topography Reconstruction and Uncertainty Quantification

Seafloor topography super-resolution reconstruction is critical for marine resource exploration, geological monitoring, and navigation safety. However, sparse acoustic data frequently result in the loss of high-frequency details, and traditional deep learning models exhibit limitations in uncertaint...

Täydet tiedot

Bibliografiset tiedot

Päätekijät:	Xinye Cui, Houpu Li, Yanting Yu, Shaofeng Bian, Guojun Zhai
Aineistotyyppi:	Artigo
Kieli:	Inglês
Julkaistu:	MDPI AG 2025-05-01
Sarja:	Applied Sciences
Aiheet:	super-resolution reconstruction uncertainty quantification seafloor topography deep learning heteroscedastic noise modeling
Linkit:	https://www.mdpi.com/2076-3417/15/11/6113
Tagit:	Lisää tagi Ei tageja, Lisää ensimmäinen tagi!