Evaluating neural networks and evidence pooling for land cover mapping. / Aitkenhead, M. J.; Flaherty, S.; Cutler, M. E. J.
In: Photogrammetric Engineering and Remote Sensing, Vol. 74, No. 8, 08.2008, p. 1019-1032.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Evaluating neural networks and evidence pooling for land cover mapping
AU - Aitkenhead,M. J.
AU - Flaherty,S.
AU - Cutler,M. E. J.
PY - 2008/8
Y1 - 2008/8
N2 - The diversity of data sources, analysis methodologies, and classification systems has led to a number of new techniques for monitoring land-cover change. However, this wide choice means that it is difficult to know which solution to choose. A system capable of integrating the results of different analyses and applying them to land-cover mapping would therefore be extremely useful. This study investigates the use of evidence pooling and neural networks in land-cover mapping. Neural networks were used to classify land-cover using evidence from spectral (Landsat-7 ETM1), textural, and topographic information. Mapping was performed using combinations of evidence source and evidence pooling techniques. The best performance was achieved using all available information with a method that summed evidence directly instead of categorizing it. While the methodology failed to reach the level of accuracy recommended elsewhere, a comparison of the number of classes used with other methods showed that the system performed better than these approaches. © 2008 American Society for Photogrammetry and Remote Sensing.
AB - The diversity of data sources, analysis methodologies, and classification systems has led to a number of new techniques for monitoring land-cover change. However, this wide choice means that it is difficult to know which solution to choose. A system capable of integrating the results of different analyses and applying them to land-cover mapping would therefore be extremely useful. This study investigates the use of evidence pooling and neural networks in land-cover mapping. Neural networks were used to classify land-cover using evidence from spectral (Landsat-7 ETM1), textural, and topographic information. Mapping was performed using combinations of evidence source and evidence pooling techniques. The best performance was achieved using all available information with a method that summed evidence directly instead of categorizing it. While the methodology failed to reach the level of accuracy recommended elsewhere, a comparison of the number of classes used with other methods showed that the system performed better than these approaches. © 2008 American Society for Photogrammetry and Remote Sensing.
KW - Artificial intelligence
KW - Computer networks
KW - Conformal mapping
KW - Accuracy assessment
KW - Neural networks
KW - Classification
KW - Land cover
KW - Landsat
KW - Topographic mapping
M3 - Article
VL - 74
SP - 1019
EP - 1032
JO - Photogrammetric Engineering and Remote Sensing
T2 - Photogrammetric Engineering and Remote Sensing
JF - Photogrammetric Engineering and Remote Sensing
SN - 0099-1112
IS - 8
ER -