 The study aims to improve the accuracy of land cover and land use. LCLU, classification using deep neural network ensemble, DNNE, methods, which combines multiple models to enhance generalizability and robustness for different sensing geometries and categories. Experimental results on NWPU, RESISC 45 and A-datasets show that DNNE leads to an increase in classification performance and promotes the use of this technique in remote sensing applications. This article was offered by Buraki Kim and Elif Sertl.