On appropriate modelling strategies for estimating land cover areas from satellite imagery

The mapping of land cover and land use is a key application of remotely sensed data. Studies have suggested the outputs of statistical models that estimate the posterior probability of class membership can be interpreted as subpixel area proportions. This paper examines the correlation between posterior probability of class membership, estimated using neural network and nearest neighbour models, and area proportion. In addition, the paper describes several models, again based on neural networks and nearest neighbour algorithms, that have been developed to estimate the land cover area proportions explicitly. Both types of model were applied to a Landsat TM data set. The results demonstrated that better estimates of the true land cover area were obtained using models that predicted the area proportion directly than were obtained using models that predicted the posterior probability of class membership. Further, it was found that a linear model (single-layer neural network) and a nearest neighbour smoothing model produced higher correlation and lower errors than the other models investigated.