EVOR-STACK: A label-dependent evolutive stacking on remote sensing data fusion

Land use and land cover (LULC) maps are remote sensing products that are used to classify areas into different landscapes. Data fusion for remote sensing is becoming an important tool to improve classical approaches. In addition, soft computing techniques such as machine learning or evolutive computation are often applied to improve the final LULC classification. In this paper, a method based on an ensemble of multiple classifiers to improve LULC map accuracy is shown. The method works in two processing levels: first, an evolutionary algorithm (EA) for label-dependent feature weighting transforms the feature space by assigning different weights to every attribute depending on the class. Then the second level builds a statistical raster from LIDAR and image data fusion following a pixel-oriented and feature-based strategy that uses a support vector machine (SVM) and a weighted k-NN restricted stacking, taking into account the special characteristics of spatial data. A classical SVM, the original restricted stacking (R-STACK) and the current improved method (EVORSTACK) are compared. The results show that the evolutive approach obtains the best results in the context of the real data from a riparian area in southern Spain. EVOR-STACK: a label-dependent evolutive stacking on remote sensing data fusion Jorge Garcı́a-Gutiérreza,b, Daniel Mateos-Garcı́aa,c, José C. Riquelme-Santosa,d aDepartment of Computing Languages and Systems, Avda. Reina Mercedes S/N, 41012 Seville (Spain) [email protected] [email protected] [email protected]