I have 2 land cover maps of an area which were classified by randomForest in R from 2 different sources. I would like to apply the Dempster-Shafer theory to fuse these maps to produce the final land cover map. The basic probability assignment (BPA) function will be constructed by "calculating the probability of each pixel that belongs to each category and the probability of correct classification based on the Random Forest classification" (the same method with this article: https://www.researchgate.net/publication/310386683_Mapping_Urban_Impervious_Surface_by_Fusing_Optical_and_SAR_Data_at_the_Decision_Level)
I have just found some packages in R such as DST, EvCombR, MuViCP. However, I don't know how to use these packages using raster data to produce the map as the method mentioned above.
Can someone guide me on how to do that in R?