BACKGROUND AND AIM: Environmental health (EH) researchers often aim to identify sources that drive potentially harmful environmental exposures. We have adapted Principal Component Pursuit (PCP), a robust dimensionality reduction algorithm, to pattern recognition in EH. PCP decomposes the exposure matrix into consistent patterns of chemical exposure while separately isolating unique or infrequent outlying exposure events. We further tailored PCP for EH by adding: (1) a non-negativity constraint to enhance interpretability of identified patterns, (2) procedures to accommodate missingness, and (3) a separate penalty for observations below the limit of detection. METHODS: We began with an exposure mixture of 21 dioxins, furans, and polychlorinated biphenyls (PCBs), collectively referred to as persistent organic pollutants (POPs), measured in 1,000 U.S. adults from the 2001-2002 National Health and Nutrition Examination Survey (NHANES). We applied PCP to this mixture to identify exposure patterns and investigated the association between identified patterns and leukocyte telomere length (LTL), a biomarker associated with chronic disease. We used pattern scores from PCP in linear regression models to evaluate their association with LTL, adjusting for potential confounders. RESULTS:PCP identified four patterns representing the overall exposure matrix: pattern 1 was characterized by dioxins, pattern 2 by furans, pattern 3 by higher-weight PCBs, while pattern 4 was driven by lower-weight PCBs including two mono-ortho PCBs. In adjusted models, we observed no association between patterns 1, 2, or 3 and LTL. We observed on average a 0.017 (95% CI: 0.000, 0.034) unit increase in log-LTL per one standard deviation increase in the exposure profile described by pattern 4. CONCLUSIONS:PCP can serve as a useful and robust technique that can accommodate missing values and values below the limit of detection to identify exposure patterns that are amenable to public health messaging and research. KEYWORDS: Mixtures, Mixtures analysis, Chemical exposures, Environmental epidemiology