Is it possible to stack the training vectors of 2 or 3 different S-2 products into 1?
you can create masks from the vectors in the Mask Manager and then transfer the masks between the products.
Thank you for the quick reply!
I’m trying to run a multi-temporal analysis of an agricultural area by merging S-2 products and then running a RF classification.
Will the overlapping training vector stacks create confusion to the classifier?
I don’t think so because the RF classifier is based on random selection of training pixels anyways. Make sure to select a large number of trees (100) to make full use of this.