Please use this identifier to cite or link to this item:
Title: Deep learning methods applied to digital elevation models: state of the art
Authors: Ruiz-Lendínez, Juan J.
Ariza-López, Francisco J.
Reinoso-Gordo, Juan F.
Ureña-Cámara, Manuel A.
Quesada-Real, Francisco J.
Abstract: Deep Learning (DL) has a wide variety of applications in various thematic domains, including spatial information. Although with limitations, it is also starting to be considered in operations related to Digital Elevation Models (DEMs). This study aims to review the methods of DL applied in the field of altimetric spatial information in general, and DEMs in particular. Void Filling (VF), Super-Resolution (SR), landform classification and hydrography extraction are just some of the operations where traditional methods are being replaced by DL methods. Our review concludes that although these methods have great potential, there are aspects that need to be improved. More appropriate terrain information or algorithm parameterisation are some of the challenges that this methodology still needs to face.
Keywords: deep learning
void filling
landform classification
Issue Date: 2023
metadata.dc.description.sponsorship: This work has been partially founded by the research project ‘Functional Quality of Digital Elevation Models in Engineering’ of the State Agency Research of Spain. PID2019-106195RB-I00/AEI/10.13039/501100011033.
Publisher: Taylor & Francis
Appears in Collections:DICGF-Artículos

Files in This Item:
File Description SizeFormat 
2023_Deep learning methods applied to digital elevation models state of the art.pdf2,41 MBAdobe PDFView/Open

This item is protected by original copyright