Controlling for misclassified land use data: A post-classification latent multinomial logit approach

Raymundo Marcos Martinez, Kenneth A. Baerenklau
2015 Remote Sensing of Environment  
7 Terrain and landscape complexities can limit the accurate discrimination of land use 8 categories with similar spectral signatures, as well as the accurate detection of land use 9 change in temporal analyses of landscape dynamics. Studies based on misclassified land use 10 data can generate biased parameter estimates and standard errors, inaccurate predictions, and 11 incorrect policy recommendations. To address these challenges and improve the accuracy of 12 land use analyses, we implement a
more » ... post-classification strategy to detect misclassified land use 13 observations using a latent multinomial logit model. This strategy is tested using both Monte 14 Carlo simulations and a time series dataset based on supervised classification of remotely 15 sensed data corresponding to land use decisions observed in a Mexican coffee growing region 16 during the period 1984-2006. The results indicate that the strategy is useful for identifying 17 land use observations with a high probability of being wrongly classified, even between 18 categories with low discriminative spectral signatures. Reclassification of the land use data, 19 based on the model results, increases the magnitudes of the marginal effects of the analyzed 20 land use drivers in the theoretically expected directions, and in some cases improves the 21 statistical significance of the parameter estimates. 22
doi:10.1016/j.rse.2015.09.025 fatcat:knqk3t6iyfe3zckuaydhcnncwa