Incorporating spatial variability measures in land-cover classification using random forest

Rodriguez-Galiano, V.F., Abarca-Hernandez, F., Ghimire, B., Chica-Olmo, M., Atkinson, P.M. and Jeganathan, C. (2011) Incorporating spatial variability measures in land-cover classification using random forest. Procedia Environmental Sciences, 3, 44-49. (doi:10.1016/j.proenv.2011.02.009).

Abstract

The spatialvariability of remotely sensed image values provides important information about the arrangement of objects and their spatial relationships within the image. The characterisation of spatialvariability in such images, for example, to measure of texture, is of great utility for the discrimination of landcover classes. To this end, the variogram, a function commonly applied in geostatistics, has been used widely to extract image texture for remotely sensed data classification.

The aim of this study was to assess the increase in accuracy that can be achieved by incorporating univariate and multivariate textural measures of Landsat TM imagery in classification models applied to large heterogeneous landscapes. Such landscapes which difficult to classify due to the large number of landcover categories and low inter-class separability. Madogram, rodogram and direct variogram for the univariate case, and cross- and pseudocross variograms for the multivariate one, together with multi-seasonal spectral information were used in a RandomForest classifier to map landcover types.

The addition of spatialvariability into multi-seasonal RandomForest models leads to an increase in the overall accuracy of 8%, and to an increase in the Kappa index of 9%, respectively. The increase in per categories Kappa for the textural RandomForest model reached 30% for certain categories. This study demonstrates that the use of information on spatialvariability produces a fundamental increase in per class classification accuracy of complex land-cover categories

This record has no associated files available for download.

Contributors

Author: P.M. Atkinson

Download statistics