Identifying anomalies in chemical processes is highly desirable. Usually, one relies on previous knowledge of normal and faulty samples, excluding anomalies from model training and associating deviations to faults. How reliable is such knowledge, however, is questionable, especially during atypical scenarios. Unsupervised approaches, using no labels, provide an unbiased analysis. A generative topographic mapping (GTM) and graph theory combined approach, then, is proposed for unsupervised fault identification. GTM, given its probabilistic nature, highlights system features, reducing variable dimensionality. With this information, correlation between samples is calculated. Graph theory, then, generates a network, clustering similar samples. Two anomaly cases are analyzed: an artificial dataset and Tennessee Eastman Process. Principal component analysis (PCA) and Dynamic PCA indexes Q and T-2 along GTM and graph theory-independent monitoring methodologies are used for comparison, considering supervised and unsupervised approaches. The proposed method performed similarly to all supervised methodologies, motivating its application and developments. (c) 2015 American Institute of Chemical Engineers AIChE J, 61: 1559-1571, 2015