Spatially autocorrelated training and validation samples inflate performance assessment of convolutional neural networks

Spatially autocorrelated training and validation samples inflate performance assessment of convolutional neural networks

Deep learning and particularly Convolutional Neural Networks (CNN) in concert with remote sensing are becoming standard analytical tools in the geosciences. A series of studies has presented the seemingly outstanding performance of CNN for predictive modelling. However, the predictive performance of...

Full description

Bibliographic Details
Main Authors: Teja Kattenborn, Felix Schiefer, Julian Frey, Hannes Feilhauer, Miguel D. Mahecha, Carsten F. Dormann
Format: Article
Language:English
Published: Elsevier 2022-08-01
Series:ISPRS Open Journal of Photogrammetry and Remote Sensing
Subjects:
Spatial autocorrelation
Convolutional neural networks
Deep learning
Machine learning
Mapping
Reference data
Online Access:http://www.sciencedirect.com/science/article/pii/S2667393222000072

Internet

http://www.sciencedirect.com/science/article/pii/S2667393222000072

Similar Items