In Hubei, China, where the coronavirus disease (COVID-19) epidemic first emerged, the government has enforced strict quarantine and lockdown measures. Longitudinal studies suggest that the impact of adverse events on psychological adjustment is highly heterogenous. To better understand protective and risk factors that predict longitudinal psychopathology and resilience following strict COVID-19 lockdowns, this study used unsupervised machine learning to identify half-year longitudinal trajectories (April, June, August, and October, 2020) of three mental health outcomes (depression, anxiety, and posttraumatic stress disorder [PTSD]) among a sample of Hubei residents (N = 326), assessed a broad range of person- and context-level predictors, and applied least absolute shrinkage and selection operator (LASSO) logistic regression, a supervised machine learning approach, to select best predictors for trajectory memberships of resilience and chronic psychopathology. Across outcomes, most individuals remained resilient. Models with both person- and context-level predictors showed excellent predictive accuracy, except for models predicting chronic anxiety. The person-level models showed either good or excellent predictive accuracy. The context-level models showed good predictive accuracy for depression trajectories but were only fair in predicting trajectories of anxiety and PTSD. Overall, the most critical person-level predictors were worry, optimism, fear of COVID, and coping flexibility, whereas important context-level predictors included features of stressful life events, community satisfaction, and family support. This study identified clinical patterns of response to COVID-19 lockdowns and used a combination of risk and protective factors to accurately differentiate these patterns. These findings have implications for clinical risk identifications and interventions in the context of potential trauma. (PsycInfo Database Record (c) 2022 APA, all rights reserved).