Feature Space of XRD Patterns Constructed by an Autoencoder

It would be a natural expectation that only major peaks, not all of them, make an important contribution to the characterization XRD pattern. We developed scheme can identify which peaks are relavant what extent by using auto-encoder technique construct feature space for peak patterns. Individual patterns projected onto single point in two-dimensional constructed method. If is significantly shifted when interest masked, then we say relevant represented on space. In this way, formulate relevancy quantitatively. By scheme, actually found such with significant intensity but low structure. The easily explained physical viewpoint as higher-order from same plane index, being heuristic finding power machine-learning.