Three new papers related to the EnMAP mission...
In Guanter et al. (http://www.mdpi.com/2072-4292/7/7/8830) an overview of the EnMAP mission and preparatory activities is given. Definitely the new base line paper for EnMAP to get latest infos on the mission and also to cite as a general reference.
Suess et al. (http://www.mdpi.com/2072-4292/7/8/10668) describes the quantitative mapping of sparse shrub surfaces. He uses an adapted SVM classification that achieves good quantitative results (based on class probabilites) while even improving the discrete class accuracies. All done on simulated EnMAP data from Portugal. The approach is available in the EnMAP-Box and maybe interesting to all interested in accurate SVM mapping.
The joint overview paper on the EnMap-Box functionality and applications by van der Linden et al. (http://www.mdpi.com/2072-4292/7/9/11249) may be of high interest for everyone using the EnMAP-Box. The paper gives you a good overview, also of applications that were not implemented at HU. More important: the paper uses the imageSVM case for a detailed description of user-friendly machine learning applications for remote sensing and may therefore also be used to cite imageSVM, its concept and functionality. PLEASE USE THIS REFERENCE FOR ALL FUTURE PUBLICATIONS USING IMAGESVM FOR REGRESSION OR CLASSIFICATION!
Special issue of Remote Sensing