PREPRINT. PAPER PUBLISHED IN PROCEEDINGS OF THE IEEE, DOI: 10.1109/JPROC.2015.2449668 1 Multimodal Classification of Remote Sensing Images: A Review and Future Directions Luis G´ omez-Chova, Senior Member, IEEE, Devis Tuia, Senior Member, IEEE, Gabriele Moser, Senior Member, IEEE, and Gustau Camps-Valls, Senior Member, IEEE Abstract Earth observation through remote sensing images allows the accurate characterization and iden- tification of materials on the surface from space and airborne platforms. Multiple and heterogeneous image sources can be available for the same geographical region: multispectral, hyperspectral, radar, multitemporal and multiangular images can nowadays be acquired over a given scene. These sources can be combined/fused to improve classification of the materials on the surface. Even if this type of systems is generally accurate, the field is about to face new challenges: the upcoming constellations of satellite sensors will acquire large amounts of images of different spatial, spectral, angular and temporal resolutions. In this scenario, multimodal image fusion stands out as the appropriate framework to address these problems. In this paper, we provide a taxonomical view of the field and review the current methodologies for multimodal classification of remote sensing images. We also highlight the most recent advances, which exploit synergies with machine learning and signal processing: sparse methods, kernel-based fusion, Manuscript received November 2014; This work has been partly supported by the Generalitat Valenciana under project GV/2013/079, the Swiss National Science Foundation (grant PP00P2 150593), the spanish Ministry of Economy and Competitiveness (MINECO) under project LIFE- VISION TIN2012-38102-C03-01, and by the Italian Space Agency under projects ID-2181 (COSMO-SkyMed: Announcement of Opportunity) and “OPERA - Civil protection from floods.” LGC and GCV are with the Image Processing Laboratory (IPL), Universitat de Val` encia, C/ Catedr´ atico A. Escardino, 9 - 46980 Paterna, Val` encia (Spain). {chovago,gcamps}@uv.es. DT is with the Department of Geography, University of Z¨ urich. devis.tuia@geo.uzh.ch. GM is with the Department of Electrical, Electronic, Telecommunications Engineering and Naval Architecture (DITEN), University of Genoa, Italy, gabriele.moser@unige.it. Preprint. Paper published in Proceedings of the IEEE, doi: 10.1109/JPROC.2015.2449668 August 19, 2015 DRAFT