Noradrenaline (NA) is a ubiquitous neuromodulator largely produced by locus coeruleus (LC) neurons that impacts multiple cognitive processes. Non-invasive methods are used to track LC-NA activity. For instance, pupillometry is shown to be linked to arousal state, LC-NA, and other neuromodulator activity. However, given that pupillometry is a relatively slow process, the extent by which LC-NA can be predicted by pupil is limited. Since movements are linked with increased LC activity, orofacial movements could potentially be used as an additional psychophysiological marker for arousal and LC-NA activity in mice. Here, we will test with advanced computational methods how non-invasive methods can correctly predict LC activity. To investigate the relationship between NA, pupil dynamics and facial movements of mice, we developed a recurrent neural network (RNN) able to predict NA release by LC neurons. Preliminary results show that the model can predict (40 ± 8) \% of LC neurons activity with only the time series of pupil dilatation and orofacial movements as predictors. Furthermore, the trained model is able to predict LC activity in a mouse not in the training set, which suggests the model is not animal specific and can be universalized. Together, our findings aim to deepen our understanding of the dynamics linking the pupil, the face motion and the LC activity allowing to convert information from a simple face recording (past, present or future) to information on brain states.