This paper proposes a novel sequence-to-sequence recurrent neural network model to predict re-entry trajectories of uncontrolled space objects. The epoch and altitude information of the objects from two-line element data were interpolated to equally spaced data and were used as inputs to the model. More than 200 datasets from five different objects with already known re-entry times were used as the training set for the model. Test datasets being not used for training, were chosen to validate the model's performance. To assess the performance, the model predictions were compared with the ground-truth data of the test objects and with predictions from the Inter Agency Space Debris Coordination re-entry campaign, in which space agencies from various countries had participated. The results indicate that the proposed approach is highly suitable for re-entry prediction compared to classical dynamics-based approaches, despite the small quantity of training data. (C) 2021 COSPAR. Published by Elsevier B.V. All rights reserved.