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...

पूर्ण विवरण

ग्रंथसूची विवरण

मुख्य लेखकों:	Teja Kattenborn, Felix Schiefer, Julian Frey, Hannes Feilhauer, Miguel D. Mahecha, Carsten F. Dormann
स्वरूप:	Artigo
भाषा:	Inglês
प्रकाशित:	Elsevier 2022-08-01
श्रृंखला:	ISPRS Open Journal of Photogrammetry and Remote Sensing
विषय:	Spatial autocorrelation Convolutional neural networks Deep learning Machine learning Mapping Reference data
ऑनलाइन पहुंच:	http://www.sciencedirect.com/science/article/pii/S2667393222000072
टैग:	टैग जोड़ें कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!