Deep learning methods applied to digital elevation models: state of the art
Metadatos
Mostrar el registro completo del ítemEditorial
Taylor&Francis
Materia
Deep learning DEMs Void filling Super-resolution Landform classification
Fecha
2023-09-06Referencia bibliográfica
Juan J. Ruiz-Lendínez, Francisco J. Ariza-López, Juan F. Reinoso-Gordo, Manuel A. Ureña-Cámara & Francisco J. Quesada-Real (2023) Deep learning methods applied to digital elevation models: state of the art, Geocarto International, 38:1, 2252389, [DOI: 10.1080/10106049.2023.2252389]
Patrocinador
Functional Quality of Digital Elevation Models in Engineering’ of the State Agency Research of Spain; PID2019-106195RB- I00/AEI/10.13039/501100011033Resumen
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.