This paper introduces a novel post-processing technique for analyzing high dimensional combustion data. In this technique, t-Distributed Stochastic Neighbor Embedding (t-SNE) is used to reduce the dimensionality of the combustion data with no prior knowledge while preserving the similarity of the original data. Multidimensional combustion datasets are from premixed and non-premixed laminar flame simulations and measurements of a series of well documented piloted flames with inhomogeneous inlets. The resulting reduced manifold is visualized by scatter plots to reveal the global and local structure of the data (manual labeling). Unsupervised clustering algorithms are then utilized for post-processing the t-SNE manifold in order to develop an automatic labeling process. (C) 2018 The Combustion Institute. Published by Elsevier Inc. All rights reserved.