Effects of landscape characteristics on land-cover class accuracy

By Jonathan H. Smith, Stephen V. Stehman, James D. Wickham, Limin Yang. 2003

214 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Some challenges in global land cover mapping : An assessment of agreement and accuracy in existing 1 km datasets (2008, background): “Studies of Moody and Woodcock (1994, 1995), Mayaux and Lambin (1995, 1997), Smith et al. (2002, 2003) and Latifovic and Olthof (2004) have provided empirical evidence for the spatial heterogeneity of landscapes being an important variable determining land cover mapping accuracy in regional studies.”
Driving forces of tropical deforestation: The role of remote sensing and spatial models (2006, background): “…LUCC and landscape ecological research suggest that the relative advantages and drawbacks of pixels versus patches as units of analysis appear to depend upon the chosen mapping/modelling goals, scale of analysis and landscape context (Smith et al. , 2003; Crews-Meyer, 2004; Fleming et al. , 2004).”
Global Land Cover Mapping: A Review and Uncertainty Analysis (2014, unknown): “The definition of mixed type classes should be of great consideration because previous research has proven that mixed pixels greatly decrease the accuracy of the land cover products [22,57].”