“…This way, spectral unmixing [28] is used to estimate the endmembers at different time instants from low resolution images, while using different strategies to mitigate the spectral variability of a single material [30,33,34]. However, abrupt abundance variations (originating from, e.g., land cover changes) are commonly found in multitemporal image streams [35,36,37,38], which may negatively impact the performance of such methods and can be particularly challenging to address when occurring jointly with finer endmember variations [35]. Thus, special care is required when fusing images which are temporally distant from one another [39], motivating the development of strategies using, e.g., spatially adaptive quantification of the reliability of the input images to guide unmixing based image fusion strategies [40].…”